2792 lines
430 KiB
Plaintext
2792 lines
430 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"id": "fcdce269",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"2025-04-29 19:42:49.399316: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.\n",
|
|
"2025-04-29 19:42:49.399795: I external/local_xla/xla/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.\n",
|
|
"2025-04-29 19:42:49.402037: I external/local_xla/xla/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.\n",
|
|
"2025-04-29 19:42:49.408084: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:467] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n",
|
|
"WARNING: All log messages before absl::InitializeLog() is called are written to STDERR\n",
|
|
"E0000 00:00:1745930569.418345 277850 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
|
|
"E0000 00:00:1745930569.421510 277850 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
|
|
"W0000 00:00:1745930569.429407 277850 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
|
|
"W0000 00:00:1745930569.429422 277850 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
|
|
"W0000 00:00:1745930569.429424 277850 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
|
|
"W0000 00:00:1745930569.429425 277850 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
|
|
"2025-04-29 19:42:49.432428: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n",
|
|
"To enable the following instructions: AVX2 AVX_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"from keras.models import Model\n",
|
|
"from keras.layers import Input, Embedding, Bidirectional, LSTM, TimeDistributed, Dense\n",
|
|
"from keras.utils import to_categorical\n",
|
|
"from keras.preprocessing.sequence import pad_sequences\n",
|
|
"from sklearn.model_selection import train_test_split\n",
|
|
"from seqeval.metrics import classification_report\n",
|
|
"from sklearn.metrics import confusion_matrix\n",
|
|
"\n",
|
|
"import matplotlib.pyplot as plt\n",
|
|
"import seaborn as sns\n",
|
|
"import numpy as np\n",
|
|
"import matplotlib.pyplot as plt\n",
|
|
"\n",
|
|
"import nltk\n",
|
|
"from nltk.corpus import stopwords\n",
|
|
"from nltk.tokenize import word_tokenize\n",
|
|
"\n",
|
|
"from Sastrawi.Stemmer.StemmerFactory import StemmerFactory\n",
|
|
"\n",
|
|
"from collections import Counter\n",
|
|
"import re\n",
|
|
"import string\n",
|
|
"import pickle\n",
|
|
"import json\n",
|
|
"import numpy as np\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 2,
|
|
"id": "92b6b57f",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"[nltk_data] Downloading package stopwords to /home/akeon/nltk_data...\n",
|
|
"[nltk_data] Package stopwords is already up-to-date!\n",
|
|
"[nltk_data] Downloading package punkt to /home/akeon/nltk_data...\n",
|
|
"[nltk_data] Package punkt is already up-to-date!\n",
|
|
"[nltk_data] Downloading package punkt_tab to /home/akeon/nltk_data...\n",
|
|
"[nltk_data] Package punkt_tab is already up-to-date!\n",
|
|
"[nltk_data] Downloading package wordnet to /home/akeon/nltk_data...\n",
|
|
"[nltk_data] Package wordnet is already up-to-date!\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/plain": [
|
|
"True"
|
|
]
|
|
},
|
|
"execution_count": 2,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"nltk.download(\"stopwords\")\n",
|
|
"nltk.download(\"punkt\")\n",
|
|
"nltk.download(\"punkt_tab\")\n",
|
|
"nltk.download(\"wordnet\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"id": "d568e8f2",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"158 sentences\n",
|
|
"=== NER LABEL COUNTS ===\n",
|
|
"O -> 1495 labels\n",
|
|
"B-LOC -> 100 labels\n",
|
|
"B-MISC -> 6 labels\n",
|
|
"B-TIME -> 46 labels\n",
|
|
"I-TIME -> 37 labels\n",
|
|
"I-LOC -> 19 labels\n",
|
|
"B-QUANT -> 4 labels\n",
|
|
"I-QUANT -> 5 labels\n",
|
|
"B-DATE -> 42 labels\n",
|
|
"B-REL -> 2 labels\n",
|
|
"B-ETH -> 2 labels\n",
|
|
"I-ETH -> 2 labels\n",
|
|
"B-ORG -> 9 labels\n",
|
|
"I-ORG -> 5 labels\n",
|
|
"B-MIN -> 6 labels\n",
|
|
"B-TERM -> 2 labels\n",
|
|
"I-TERM -> 3 labels\n",
|
|
"B-RES -> 8 labels\n",
|
|
"I-RES -> 2 labels\n",
|
|
"B-PER -> 13 labels\n",
|
|
"I-PER -> 16 labels\n",
|
|
"I-DATE -> 34 labels\n",
|
|
"I-MISC -> 4 labels\n",
|
|
"B-EVENT -> 4 labels\n",
|
|
"I-EVENT -> 4 labels\n",
|
|
"\n",
|
|
"=== SRL LABEL COUNTS ===\n",
|
|
"ARG1 -> 421 labels\n",
|
|
"ARGM-LOC -> 65 labels\n",
|
|
"AM-NEG -> 2 labels\n",
|
|
"V -> 196 labels\n",
|
|
"ARGM-SRC -> 13 labels\n",
|
|
"O -> 320 labels\n",
|
|
"AM-QUE -> 5 labels\n",
|
|
"ARGM-BNF -> 6 labels\n",
|
|
"ARG2 -> 184 labels\n",
|
|
"ARGM-MNR -> 9 labels\n",
|
|
"ARG0 -> 129 labels\n",
|
|
"AM-TMP -> 279 labels\n",
|
|
"AM-PRP -> 1 labels\n",
|
|
"AM-MOD -> 5 labels\n",
|
|
"AM-ADV -> 1 labels\n",
|
|
"AM-CAU -> 14 labels\n",
|
|
"AM-EXT -> 6 labels\n",
|
|
"AM-MNR -> 22 labels\n",
|
|
"AM-DIS -> 2 labels\n",
|
|
"AM-FRQ -> 2 labels\n",
|
|
"ARGM-PNC -> 4 labels\n",
|
|
"R-ARG1 -> 3 labels\n",
|
|
"AM-LOC -> 78 labels\n",
|
|
"AM-DIR -> 4 labels\n",
|
|
"ARGM-CAU -> 17 labels\n",
|
|
"ARGM-MOD -> 11 labels\n",
|
|
"ARGM-EXT -> 2 labels\n",
|
|
"ARGM-TMP -> 12 labels\n",
|
|
"ARGM-DIS -> 9 labels\n",
|
|
"ARG3 -> 12 labels\n",
|
|
"ARGM-NEG -> 2 labels\n",
|
|
"ARGM-COM -> 3 labels\n",
|
|
"ARGM-PRP -> 10 labels\n",
|
|
"ARGM-EX -> 4 labels\n",
|
|
"ARGM-PRD -> 4 labels\n",
|
|
"AM-COM -> 9 labels\n",
|
|
"I-AM-LOC -> 1 labels\n",
|
|
"AM-PNC -> 5 labels\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"# === LOAD DATA ===\n",
|
|
"with open(\"../dataset/dataset_ner_srl.json\", \"r\", encoding=\"utf-8\") as f:\n",
|
|
" data = json.load(f)\n",
|
|
"\n",
|
|
"sentences = [[token.lower() for token in item[\"tokens\"]] for item in data]\n",
|
|
"ner_labels = [item[\"labels_ner\"] for item in data]\n",
|
|
"srl_labels = [item[\"labels_srl\"] for item in data]\n",
|
|
"\n",
|
|
"print(len(sentences), \"sentences\")\n",
|
|
"\n",
|
|
"# === COUNTERS ===\n",
|
|
"ner_counter = Counter()\n",
|
|
"srl_counter = Counter()\n",
|
|
"\n",
|
|
"for ner_seq in ner_labels:\n",
|
|
" ner_counter.update(ner_seq)\n",
|
|
"\n",
|
|
"for srl_seq in srl_labels:\n",
|
|
" srl_counter.update(srl_seq)\n",
|
|
"\n",
|
|
"# === PRINT RESULT ===\n",
|
|
"print(\"=== NER LABEL COUNTS ===\")\n",
|
|
"for label, count in ner_counter.items():\n",
|
|
" print(f\"{label} -> {count} labels\")\n",
|
|
"\n",
|
|
"print(\"\\n=== SRL LABEL COUNTS ===\")\n",
|
|
"for label, count in srl_counter.items():\n",
|
|
" print(f\"{label} -> {count} labels\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 4,
|
|
"id": "95f16969",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"old [['keberagaman', 'potensi', 'sumber', 'daya', 'alam', 'indonesia', 'tidak', 'lepas', 'dari', 'proses', 'geografis', 'yang', 'terjadi', '.'], ['bagaimana', 'proses', 'geografis', 'di', 'indonesia', '?'], ['bagaimana', 'pengaruh', 'proses', 'geografis', 'bagi', 'keragaman', 'alam', 'dan', 'keragaman', 'sosial', 'masyarakat', 'indonesia', '?'], ['bagaimana', 'mengoptimalkan', 'peranan', 'sumber', 'daya', 'manusia', 'dalam', 'mengelola', 'sumber', 'daya', 'alam', 'indonesia', '?'], ['apakah', 'sumber', 'daya', 'manusia', 'di', 'indonesia', 'sudah', 'memenuhi', 'syarat', 'untuk', 'mengolah', 'pariwisata', 'yang', 'dimilikinya', '?'], ['bagaimana', 'lembaga', 'sosial', 'yang', 'akan', 'mewadahi', 'untuk', 'mengolah', 'sumber', 'daya', 'alam', 'dan', 'sumber', 'daya', 'manusianya', '?'], ['kalian', 'juga', 'perlu', 'memahami', ',', 'bahwa', 'keragaman', 'sosial', 'dan', 'budaya', 'telah', 'menarik', 'kedatangan', 'bangsa-bangsa', 'asing', 'sejak', 'ribuan', 'tahun', 'yang', 'lalu', '.'], ['perkembangan', 'hindu-buddha', 'di', 'indonesia', 'tidak', 'lepas', 'dari', 'perkembangan', 'perdagangan', 'dan', 'pelayaran', 'pada', 'awal', 'abad', 'masehi', '.'], ['bangsa', 'indonesia', 'patut', 'bersyukur', 'karena', 'proses', 'geografis', 'dan', 'keragaman', 'alam', 'yang', 'dimiliki', '.'], ['indonesia', 'merupakan', 'negara', 'terluas', 'di', 'asia', 'tenggara', '.'], ['luas', 'daratan', 'indonesia', 'sebesar', '1.910.932,37', 'km2', '.'], ['dan', 'lautan', 'indonesia', 'mencapai', '5,8', 'juta', 'km2', '.'], ['letak', 'indonesia', 'sangat', 'menguntungkan', 'bagi', 'kehidupan', 'masyarakat', '.'], ['selain', 'memiliki', 'letak', 'geografis', 'yang', 'sangat', 'menguntungkan', ',', 'indonesia', 'juga', 'memiliki', 'letak', 'geologis', ',', 'iklim', ',', 'dan', 'cuaca', 'yang', 'sangat', 'menguntungkan', '.'], ['kalian', 'tentu', 'sering', 'membincangkan', 'tentang', 'musim', 'dan', 'hubungannya', 'dengan', 'aktivitas', 'sehari-hari', '.'], ['masyarakat', 'memiliki', 'kebiasaan', 'di', 'musim', 'hujan', 'dan', 'musim', 'kemarau', 'baik', 'berhubungan', 'dengan', 'mata', 'pencaharian', 'dan', 'kesenangan', '(', 'hobi', ')', '.'], ['kalian', 'juga', 'sering', 'memperhatikan', 'prakiraan', 'cuaca', 'untuk', 'merancang', 'kegiatan', 'harian', '.'], ['cuaca', 'dan', 'iklim', 'inilah', 'bagian', 'penting', 'yang', 'memengaruhi', 'aktivitas', 'masyarakat', 'indonesia', '.'], ['cuaca', 'adalah', 'kondisi', 'rata-rata', 'udara', 'pada', 'saat', 'tertentu', 'di', 'suatu', 'wilayah', 'yang', 'relatif', 'sempit', 'dan', 'dalam', 'waktu', 'yang', 'singkat', '.'], ['iklim', 'merupakan', 'kondisi', 'cuaca', 'rata-rata', 'tahunan', 'pada', 'suatu', 'wilayah', 'yang', 'luas', '.'], ['indonesia', 'memiliki', 'iklim', 'tropis', 'yang', 'memiliki', 'dua', 'musim', 'yaitu', 'musim', 'hujan', 'dan', 'musim', 'kemarau', '.'], ['musim', 'hujan', 'terjadi', 'pada', 'bulan', 'oktober', '-', 'maret', ',', 'sedangkan', 'musim', 'kemarau', 'terjadi', 'pada', 'bulan', 'april', '-', 'september', '.'], ['semakin', 'ke', 'timur', 'curah', 'hujan', 'semakin', 'sedikit', '.'], ['hal', 'ini', 'karena', 'hujan', 'telah', 'banyak', 'jatuh', 'dan', 'menguap', 'di', 'bagian', 'barat', '.'], ['keadaan', 'iklim', 'dapat', 'diamati', 'dengan', 'memperhatikan', 'unsur-unsur', 'cuaca', 'dan', 'iklim', '.'], ['unsur-unsur', 'tersebut', 'antara', 'lain', ',', 'penyinaran', 'matahari', ',', 'suhu', 'udara', ',', 'kelembaban', 'udara', ',', 'angin', ',', 'dan', 'hujan', '.'], ['tanaman', 'tropis', 'memiliki', 'banyak', 'varietas', 'yang', 'kaya', 'akan', 'hidrat', 'arang', 'terutama', 'tanaman', 'bahan', 'makanan', 'pokok', '.'], ['berikut', 'pengaruh', 'unsur-unsur', 'iklim', 'terhadap', 'tanaman'], ['penyinaran', 'matahari', 'memengaruhi', 'fotosintesis', 'tanaman', ',', 'dapat', 'meningkatkan', 'suhu', 'udara', '.'], ['suhu', 'mengurangi', 'kadar', 'air', 'sehingga', 'cenderung', 'menjadi', 'kering', '.'], ['kelembaban', 'membatasi', 'hilangnya', 'air', '.'], ['angin', 'membantu', 'proses', 'penyerbukan', 'secara', 'alami', ',', 'mengurangi', 'kadar', 'air', '.'], ['hujan', 'meningkatkan', 'kadar', 'air', ',', 'mengikis', 'tanah', '.'], ['kalian', 'menemukan', 'berbagai', 'perbedaan', 'sosial', 'budaya', 'masyarakat', 'di', 'sekitar', 'tempat', 'tinggalmu', '.'], ['apabila', 'kalian', 'tinggal', 'di', 'perkotaan', ',', 'perbedaan', 'sosial', 'budaya', 'akan', 'semakin', 'banyak', '.'], ['perbedaan', 'sosial', 'budaya', 'meliputi', 'perbedaan', 'nilai-nilai', ',', 'norma', ',', 'dan', 'karakteristik', 'dari', 'suatu', 'kelompok', '.'], ['keragaman', 'sosial', 'budaya', 'di', 'masyarakat', 'dapat', 'terjadi', 'saat', 'berbagai', 'jenis', 'suku', 'dan', 'agama', 'yang', 'ada', 'di', 'suatu', 'ruang', 'bertemu', 'dan', 'berinteraksi', 'setiap', 'harinya', '.'], ['ruang', 'tersebut', 'adalah', 'ruang', 'yang', 'ada', 'pada', 'masyarakat', '.'], ['budaya', 'dapat', 'berupa', 'cara', 'hidup', 'masyarakat', ',', 'cara', 'berpakaian', ',', 'adat', 'istiadat', ',', 'jenis', 'mata', 'pecaharian', ',', 'dan', 'tata', 'upacara', 'keagamaan', '.'], ['keragaman', 'budaya', 'juga', 'mencakup', 'barang-barang', 'yang', 'dihasilkan', 'oleh', 'masyarakat', ',', 'seperti', 'senjata', ',', 'alat', 'bajak', 'sawah', ',', 'kitab', 'hukum', 'adat', ',', 'dan', 'tempat', 'tinggal', '.'], ['budaya', 'dapat', 'dianggap', 'sebagai', 'serangkaian', 'rancangan', 'untuk', 'bertahan', 'hidup', 'atau', 'alat', 'dari', 'praktik', ',', 'pengetahuan', ',', 'dan', 'simbol', 'yang', 'diperoleh', 'melalui', 'pembelajaran', ',', 'bukan', 'oleh', 'naluri', ',', 'yang', 'memungkinkan', 'orang', 'untuk', 'hidup', 'dalam', 'masyarakat', '.'], ['masyarakat', 'terdiri', 'dari', 'orang-orang', 'yang', 'berinteraksi', 'dan', 'berbagi', 'budaya', 'yang', 'sama', '.'], ['perbedaan', 'budaya', 'dapat', 'disebabkan', 'oleh', 'berbagai', 'hal', 'seperti', 'sejarah', ',', 'keturunan', ',', 'keyakinan', ',', 'dan', 'faktor', 'geografis', '.'], ['salah', 'satu', 'penyebab', 'perbedaan', 'budaya', 'adalah', 'faktor', 'geografis', '.'], ['faktor', 'geografis', 'yang', 'memengaruhi', 'keragaman', 'budaya', 'yang', 'akan', 'dibahas', 'berikut', 'ini'], ['dari', 'teks', 'tersebut', 'dapat', 'kita', 'pelajari', 'bahwa', 'budaya', 'yang', 'ada', 'di', 'masyarakat', 'dapat', 'dipengaruhi', 'oleh', 'lingkungan', 'yang', 'ada', 'di', 'sekitarnya', ','], ['misalnya', 'suku', 'lawu', 'dan', 'suku', 'bugis', 'yang', 'bermata', 'pencaharian', 'sebagai', 'nelayan', 'dengan', 'kapal', 'pinisinya', ','], ['sehingga', 'menjadi', 'sebuah', 'simbol', 'bahwa', 'indonesia', 'merupakan', 'negara', 'maritim', 'yang', 'kuat', 'dan', 'disegani', 'di', 'lautan', '.'], ['keragaman', 'budaya', 'dipengaruhi', 'oleh', 'lingkungan', 'fisik', '.'], ['manusia', 'sebagai', 'individu', 'adalah', 'kesatuan', 'jiwa', ',', 'raga', 'dan', 'kegiatan', 'atau', 'perilaku', 'pribadi', 'itu', 'sendiri', '.'], ['sebagai', 'individu', ',', 'dalam', 'pribadi', 'manusia', 'terdapat', 'tiga', 'unsur', ',', 'yaitu', 'nafsu', ',', 'semangat', ',', 'dan', 'intelegensi', '.'], ['kombinasi', 'dari', 'unsur', 'tersebut', 'menghasilkan', 'tingkah', 'laku', 'seseorang', 'yang', 'mencerminkan', 'karakter', 'atau', 'budayaanya', '.'], ['kesatuan', 'dari', 'kepribadian-kepribadian', 'seseorang', 'pada', 'suatu', 'daerah', 'yang', 'mempunyai', 'pola', 'yang', 'sama', 'dapat', 'membentuk', 'budaya', 'daerah', 'tersebut', 'yang', 'membedakan', 'dengan', 'tempat', 'lain', '.'], ['indonesia', 'memiliki', 'kebudayaan', 'yang', 'beragam', '.'], ['indonesia', 'memiliki', 'kekayaan', 'yang', 'begitu', 'besar', '.'], ['bukan', 'hanya', 'pemandangan', 'alam', 'budaya', ',', 'jauh', 'di', 'kedalaman', 'tanahnya', 'begitu', 'banyak', 'kandungan', 'mineral', 'berharga', '.'], ['selama', 'puluhan', 'tahun', ',', 'freeport', 'mengelola', 'tambang', 'mineral', 'di', 'tanah', 'papua', ',', 'indonesia', '.'], ['berdasarkan', 'laporan', 'keuangan', 'freeport', 'mcmorran', 'inc', 'periode', '2017', ',', 'freeport', 'indonesia', 'di', 'papua', 'tercatat', 'memiliki', '6', 'tambang', ',', 'yakni', 'grasberg', 'block', 'cave', ',', 'dmlz', ',', 'tambang', 'kucing', 'liar', ',', 'doz', ',', 'big', 'gossan', ',', 'dan', 'grasberg', 'open', 'pit', '.'], ['tambang', 'freeport', 'memiliki', 'beberapa', 'kandungan', 'cadangan', 'mineral', ',', 'yaitu', 'tembaga', ',', 'emas', ',', 'dan', 'perak', '.'], ['sumber', 'daya', 'alam', 'yang', 'terdapat', 'pada', 'pertambangan', 'freeport', 'di', 'atas', 'merupakan', 'salah', 'satu', 'contoh', 'dari', 'berbagai', 'sumber', 'daya', 'yang', 'ada', 'di', 'indonesia', 'yang', 'memiliki', 'beberapa', 'kandungan', 'cadangan', 'mineral', ',', 'seperti', 'tembaga', ',', 'emas', ',', 'dan', 'perak', '.'], ['kemudian', 'apa', 'sih', 'sumber', 'daya', 'alam', 'itu', '?'], ['apakah', 'ada', 'manfaatnya', 'untuk', 'kita', '?'], ['yuk', 'silahkan', 'simak', 'penjelasan', 'di', 'bawah', 'ini', '.'], ['sumber', 'daya', 'alam', 'merupakan', 'segala', 'sesuatu', 'yang', 'ada', 'di', 'permukaan', 'bumi', 'dan', 'dapat', 'dimanfaatkan', 'untuk', 'memenuhi', 'kebutuhan', 'manusia', '.'], ['potensi', 'sumber', 'daya', 'ini', 'mencakup', 'hal', 'yang', 'ada', 'di', 'udara', ',', 'daratan', ',', 'dan', 'perairan', '.'], ['berdasarkan', 'kelestariannya', ',', 'sumber', 'daya', 'alam', 'dapat', 'dibedakan', 'menjadi', 'dua', 'yaitu', 'sumber', 'daya', 'alam', 'yang', 'dapat', 'diperbarui', '(', 'renewable', 'resources', ')', 'dan', 'tidak', 'dapat', 'diperbarui', '(', 'non', 'renewable', 'resource', ')', '.'], ['contoh', 'sumber', 'daya', 'alam', 'yang', 'dapat', 'diperbarui', 'yaitu', 'seperti', 'air', ',', 'tanah', ',', 'dan', 'hutan', '.'], ['sedangkan', 'sumber', 'daya', 'alam', 'yang', 'tidak', 'dapat', 'diperbarui', 'seperti', 'minyak', 'bumi', 'dan', 'batu', 'bara', '.'], ['berikut', 'ini', 'merupakan', 'potensi', 'sumber', 'daya', 'alam', 'di', 'indonesia', 'yang', 'dirinci', 'menjadi', 'tiga', 'yaitu', 'sumber', 'daya', 'alam', 'hutan', ',', 'sumber', 'daya', 'alam', 'tambang', ',', 'dan', 'sumber', 'daya', 'alam', 'kemaritiman', '.'], ['indonesia', 'termasuk', 'negara', 'yang', 'memiliki', 'kekayaan', 'alam', 'yang', 'berlimpah', 'dibandingkan', 'negara-negara', 'yang', 'lain', '.'], ['potensi', 'sumber', 'daya', 'alam', 'indonesia', 'sangat', 'beraneka', 'ragam', '.'], ['bangsa', 'indonesia', 'memiliki', 'modal', 'penting', 'dalam', 'pembangunan', '.'], ['jumlah', 'penduduk', 'indonesia', 'yang', 'lebih', 'dari', '270', 'juta', 'merupakan', 'potensi', 'penting', 'dalam', 'pembangunan', '.'], ['pada', 'tahun', '2016', 'badan', 'pusat', 'statistik', 'mencatat', 'bahwa', 'di', 'indonesia', 'terdapat', 'angkatan', 'kerja', '127,67', 'juta', 'jiwa', '.'], ['di', 'antara', 'negara', 'asean', ',', 'kualitas', 'sdm', 'dan', 'ketenagakerjaan', 'indonesia', 'masih', 'berada', 'di', 'peringkat', 'bawah', '.'], ['kualitas', 'sdm', 'dan', 'ketenagakerjaan', 'indonesia', 'menempati', 'urutan', 'kelima', '.'], ['peringkat', 'ini', 'masih', 'kalah', 'jika', 'dibandingkan', 'singapura', ',', 'brunei', 'darussalam', ',', 'malaysia', ',', 'dan', 'thailand', '.'], ['kualitas', 'sumber', 'daya', 'manusia', 'di', 'indonesia', 'memengaruhi', 'terhadap', 'kemajuan', 'sebuah', 'bangsa', '.'], ['peristiwa', 'itu', 'dilatarbelakangi', 'oleh', 'peristiwa', 'yang', 'jauh', 'dari', 'indonesia', ',', 'misalnya', 'peristiwa', 'jatuhnya', 'konstantinopel', 'di', 'kawasan', 'laut', 'tengah', 'pada', 'tahun', '1453', '.'], ['kehidupan', 'global', 'semakin', 'berkembang', 'dengan', 'maraknya', 'penjelajahan', 'samudera', 'orang-orang', 'eropa', 'ke', 'dunia', 'timur', '.'], ['begitu', 'juga', 'peristiwa', 'kedatangan', 'bangsa', 'eropa', 'ke', 'indonesia', ',', 'telah', 'ikut', 'meningkatkan', 'kehidupan', 'global', '.'], ['pada', 'tahun', '1488', 'karena', 'serangan', 'ombak', 'besar', 'terpaksa', 'bartholomeus', 'diaz', 'mendarat', 'di', 'suatu', 'ujung', 'selatan', 'benua', 'afrika', '.'], ['pada', 'juli', '1497', 'vasco', 'da', 'gama', 'berangkat', 'dari', 'pelabuhan', 'lisabon', 'untuk', 'memulai', 'penjelajahan', 'samudra', '.'], ['berdasarkan', 'pengalaman', 'bartholomeus', 'diaz', 'tersebut', ',', 'vasco', 'da', 'gama', 'juga', 'berlayar', 'mengambil', 'rute', 'yang', 'pernah', 'dilayari', 'bartholomeus', 'diaz', '.'], ['rombongan', 'vasco', 'da', 'gama', 'juga', 'singgah', 'di', 'tanjung', 'harapan', '.'], ['atas', 'petunjuk', 'dari', 'pelaut', 'bangsa', 'moor', 'yang', 'telah', 'disewanya', ',', 'rombongan', 'vasco', 'da', 'gama', 'melanjutkan', 'penjelajahan', ',', 'berlayar', 'menelusuri', 'pantai', 'timur', 'afrika', 'kemudian', 'berbelok', 'ke', 'kanan', 'untuk', 'mengarungi', 'lautan', 'hindia', '(', 'samudra', 'indonesia', ')', '.'], ['pada', 'tahun', '1498', 'rombongan', 'vasco', 'da', 'gama', 'mendarat', 'sampai', 'di', 'kalikut', 'dan', 'juga', 'goa', 'di', 'pantai', 'barat', 'india', '.'], ['pada', 'tahun', '1511', 'armada', 'portugis', 'berhasil', 'menguasai', 'malaka', '.'], ['proklamasi', 'kemerdekaan', 'indonesia', 'terjadi', 'pada', '17', 'agustus', '1945', '.'], ['barack', 'obama', 'lahir', 'pada', '4', 'agustus', '1961', 'di', 'hawaii', '.'], ['reformasi', 'indonesia', 'dimulai', 'tahun', '1998', 'setelah', 'soeharto', 'mundur', '.'], ['perang', 'dunia', 'ii', 'berakhir', 'pada', '2', 'september', '1945', '.'], ['indonesia', 'menjadi', 'anggota', 'pbb', 'sejak', '28', 'september', '1950', '.'], ['banjir', 'bandang', 'terjadi', 'pada', '5', 'januari', '2021', 'di', 'bandung', '.'], ['hari', 'pahlawan', 'diperingati', 'setiap', '10', 'november', '.'], ['pada', 'tahun', '1511', 'portugis', 'menguasai', 'malaka', '.'], ['konferensi', 'asia-afrika', 'diselenggarakan', 'tahun', '1955', 'di', 'bandung', '.'], ['musim', 'kemarau', 'diperkirakan', 'mulai', 'april', '2025', '.'], ['rapat', 'dimulai', 'pukul', '09.00', 'pagi', '.'], ['kereta', 'akan', 'tiba', 'sekitar', 'jam', '3', 'sore', '.'], ['pertandingan', 'akan', 'dimulai', 'pada', 'pukul', '19.30', '.'], ['matahari', 'terbit', 'sekitar', '05.45', 'pagi', 'di', 'jakarta', '.'], ['makan', 'siang', 'biasanya', 'dilakukan', 'sekitar', 'jam', '12', 'siang', '.'], ['penerbangan', 'dijadwalkan', 'lepas', 'landas', 'pukul', '23.15', '.'], ['film', 'tayang', 'mulai', 'jam', '8', 'malam', 'nanti', '.'], ['pesawat', 'mendarat', 'tepat', 'pada', '00.30', 'dinihari', '.'], ['siaran', 'langsung', 'dimulai', 'pukul', '18.00', '.'], ['jam', 'kerja', 'dimulai', 'pukul', '08.00', 'dan', 'berakhir', 'pukul', '17.00', '.'], ['alarm', 'berbunyi', 'pada', 'pukul', '06.00', 'pagi', '.'], ['saya', 'bangun', 'sekitar', 'jam', '5', 'pagi', 'setiap', 'hari', '.'], ['konser', 'dimulai', 'sekitar', '20.00', 'malam', 'di', 'stadion', '.'], ['wawancara', 'dijadwalkan', 'pada', 'jam', '11', 'pagi', '.'], ['kami', 'tiba', 'di', 'bandara', 'sekitar', 'jam', '2', 'dinihari', '.'], ['dia', 'mengajar', 'kelas', 'pada', 'pukul', '13.00', '.'], ['peserta', 'diminta', 'hadir', 'sebelum', 'jam', '7', 'pagi', '.'], ['televisi', 'menayangkan', 'berita', 'malam', 'pada', '22.00', '.'], ['kami', 'akan', 'bertemu', 'jam', '10', 'malam', 'di', 'kafe', '.'], ['toko', 'buka', 'hingga', 'pukul', '21.00', '.'], ['dia', 'biasanya', 'berolahraga', 'pada', 'pagi', 'hari', '.'], ['kami', 'bertemu', 'lagi', 'pada', 'malam', 'hari', 'itu', '.'], ['upacara', 'dilaksanakan', 'pada', 'sore', 'hari', 'di', 'lapangan', '.'], ['ia', 'pulang', 'setiap', 'malam', 'sekitar', 'jam', '9', '.'], ['kami', 'berangkat', 'di', 'pagi', 'hari', 'menggunakan', 'mobil', '.'], ['acara', 'berlangsung', 'hingga', 'malam', 'hari', '.'], ['kami', 'tiba', 'di', 'bandara', 'pada', 'dinihari', '.'], ['pintu', 'gerbang', 'dibuka', 'setiap', 'pagi', '.'], ['ia', 'selalu', 'belajar', 'di', 'malam', '.'], ['waktu', 'bermain', 'dimulai', 'sore', 'hari', '.'], ['pelajaran', 'kedua', 'dimulai', 'sekitar', 'jam', 'tujuh', 'lebih', 'sepuluh', 'menit', '.'], ['bus', 'berangkat', 'kurang', 'lebih', 'jam', 'delapan', 'malam', '.'], ['pertemuan', 'terakhir', 'dilaksanakan', 'sebelum', 'matahari', 'terbenam', '.'], ['kereta', 'berangkat', 'sekitar', 'tengah', 'malam', 'dari', 'stasiun', 'gambir', '.'], ['jadwal', 'sholat', 'dimulai', 'pukul', 'empat', 'lebih', 'lima', 'menit', '.'], ['pemadaman', 'listrik', 'akan', 'dimulai', 'menjelang', 'malam', '.'], ['layanan', 'pelanggan', 'dibuka', 'setiap', 'hari', 'kerja', 'jam', 'sembilan', '.'], ['ia', 'terjaga', 'di', 'tengah', 'malam', 'karena', 'petir', '.'], ['kelas', 'selesai', 'sekitar', 'jam', 'dua', 'kurang', 'seperempat', '.'], ['waktu', 'sarapan', 'dimulai', 'pukul', '6.30', 'hingga', '7.30', '.'], ['proklamasi', 'kemerdekaan', 'terjadi', 'pada', '17', 'agustus', '1945', '.'], ['indonesia', 'merdeka', 'pada', 'tahun', '1945', '.'], ['pemilu', 'diadakan', 'pada', '14', 'februari', '2024', '.'], ['tanggal', '1', 'januari', '2023', 'merupakan', 'hari', 'libur', '.'], ['barack', 'obama', 'lahir', 'pada', '4', 'agustus', '1961', '.'], ['hari', 'bumi', 'diperingati', 'setiap', '22', 'april', '.'], ['musim', 'kemarau', 'terjadi', 'antara', 'bulan', 'april', 'hingga', 'oktober', '.'], ['reformasi', '1998', 'mengubah', 'sistem', 'politik', 'indonesia', '.'], ['konferensi', 'asia-afrika', 'digelar', 'pada', 'tahun', '1955', 'di', 'bandung', '.'], ['perang', 'dunia', 'kedua', 'berakhir', 'tahun', '1945', '.'], ['sumpah', 'pemuda', 'diperingati', 'setiap', '28', 'oktober', '.'], ['habibie', 'dilantik', 'menjadi', 'presiden', 'pada', '21', 'mei', '1998', '.'], ['hari', 'kemerdekaan', 'indonesia', 'dirayakan', 'setiap', '17', 'agustus', '.'], ['pada', 'tahun', '1949', ',', 'belanda', 'mengakui', 'kemerdekaan', 'indonesia', '.'], ['tsunami', 'aceh', 'terjadi', 'pada', '26', 'desember', '2004', '.'], ['bung', 'karno', 'meninggal', 'pada', '21', 'juni', '1970', '.'], ['jakarta', 'ditetapkan', 'sebagai', 'ibu', 'kota', 'negara', 'pada', 'tahun', '1961', '.'], ['pada', '1955', ',', 'indonesia', 'menjadi', 'tuan', 'rumah', 'konferensi', 'asia-afrika', '.'], ['pemerintah', 'mengumumkan', 'kebijakan', 'psbb', 'pada', 'april', '2020', 'di', 'jakarta', '.'], ['undang-undang', 'dasar', '1945', 'disahkan', 'pada', 'tanggal', '18', 'agustus', '1945', '.']]\n",
|
|
"new [['keberagaman', 'potensi', 'sumber', 'daya', 'alam', 'indonesia', 'tidak', 'lepas', 'dari', 'proses', 'geografis', 'yang', 'terjadi', '.'], ['bagaimana', 'proses', 'geografis', 'di', 'indonesia', '?'], ['bagaimana', 'pengaruh', 'proses', 'geografis', 'bagi', 'keragaman', 'alam', 'dan', 'keragaman', 'sosial', 'masyarakat', 'indonesia', '?'], ['bagaimana', 'mengoptimalkan', 'peranan', 'sumber', 'daya', 'manusia', 'dalam', 'mengelola', 'sumber', 'daya', 'alam', 'indonesia', '?'], ['apakah', 'sumber', 'daya', 'manusia', 'di', 'indonesia', 'sudah', 'memenuhi', 'syarat', 'untuk', 'mengolah', 'pariwisata', 'yang', 'dimilikinya', '?'], ['bagaimana', 'lembaga', 'sosial', 'yang', 'akan', 'mewadahi', 'untuk', 'mengolah', 'sumber', 'daya', 'alam', 'dan', 'sumber', 'daya', 'manusianya', '?'], ['kalian', 'juga', 'perlu', 'memahami', ',', 'bahwa', 'keragaman', 'sosial', 'dan', 'budaya', 'telah', 'menarik', 'kedatangan', 'bangsa-bangsa', 'asing', 'sejak', 'ribuan', 'tahun', 'yang', 'lalu', '.'], ['perkembangan', 'hindu-buddha', 'di', 'indonesia', 'tidak', 'lepas', 'dari', 'perkembangan', 'perdagangan', 'dan', 'pelayaran', 'pada', 'awal', 'abad', 'masehi', '.'], ['bangsa', 'indonesia', 'patut', 'bersyukur', 'karena', 'proses', 'geografis', 'dan', 'keragaman', 'alam', 'yang', 'dimiliki', '.'], ['indonesia', 'merupakan', 'negara', 'terluas', 'di', 'asia', 'tenggara', '.'], ['luas', 'daratan', 'indonesia', 'sebesar', '1.910.932,37', 'km2', '.'], ['dan', 'lautan', 'indonesia', 'mencapai', '5,8', 'juta', 'km2', '.'], ['letak', 'indonesia', 'sangat', 'menguntungkan', 'bagi', 'kehidupan', 'masyarakat', '.'], ['selain', 'memiliki', 'letak', 'geografis', 'yang', 'sangat', 'menguntungkan', ',', 'indonesia', 'juga', 'memiliki', 'letak', 'geologis', ',', 'iklim', ',', 'dan', 'cuaca', 'yang', 'sangat', 'menguntungkan', '.'], ['kalian', 'tentu', 'sering', 'membincangkan', 'tentang', 'musim', 'dan', 'hubungannya', 'dengan', 'aktivitas', 'sehari-hari', '.'], ['masyarakat', 'memiliki', 'kebiasaan', 'di', 'musim', 'hujan', 'dan', 'musim', 'kemarau', 'baik', 'berhubungan', 'dengan', 'mata', 'pencaharian', 'dan', 'kesenangan', '(', 'hobi', ')', '.'], ['kalian', 'juga', 'sering', 'memperhatikan', 'prakiraan', 'cuaca', 'untuk', 'merancang', 'kegiatan', 'harian', '.'], ['cuaca', 'dan', 'iklim', 'inilah', 'bagian', 'penting', 'yang', 'memengaruhi', 'aktivitas', 'masyarakat', 'indonesia', '.'], ['cuaca', 'adalah', 'kondisi', 'rata-rata', 'udara', 'pada', 'saat', 'tertentu', 'di', 'suatu', 'wilayah', 'yang', 'relatif', 'sempit', 'dan', 'dalam', 'waktu', 'yang', 'singkat', '.'], ['iklim', 'merupakan', 'kondisi', 'cuaca', 'rata-rata', 'tahunan', 'pada', 'suatu', 'wilayah', 'yang', 'luas', '.'], ['indonesia', 'memiliki', 'iklim', 'tropis', 'yang', 'memiliki', 'dua', 'musim', 'yaitu', 'musim', 'hujan', 'dan', 'musim', 'kemarau', '.'], ['musim', 'hujan', 'terjadi', 'pada', 'bulan', 'oktober', '-', 'maret', ',', 'sedangkan', 'musim', 'kemarau', 'terjadi', 'pada', 'bulan', 'april', '-', 'september', '.'], ['semakin', 'ke', 'timur', 'curah', 'hujan', 'semakin', 'sedikit', '.'], ['hal', 'ini', 'karena', 'hujan', 'telah', 'banyak', 'jatuh', 'dan', 'menguap', 'di', 'bagian', 'barat', '.'], ['keadaan', 'iklim', 'dapat', 'diamati', 'dengan', 'memperhatikan', 'unsur-unsur', 'cuaca', 'dan', 'iklim', '.'], ['unsur-unsur', 'tersebut', 'antara', 'lain', ',', 'penyinaran', 'matahari', ',', 'suhu', 'udara', ',', 'kelembaban', 'udara', ',', 'angin', ',', 'dan', 'hujan', '.'], ['tanaman', 'tropis', 'memiliki', 'banyak', 'varietas', 'yang', 'kaya', 'akan', 'hidrat', 'arang', 'terutama', 'tanaman', 'bahan', 'makanan', 'pokok', '.'], ['berikut', 'pengaruh', 'unsur-unsur', 'iklim', 'terhadap', 'tanaman'], ['penyinaran', 'matahari', 'memengaruhi', 'fotosintesis', 'tanaman', ',', 'dapat', 'meningkatkan', 'suhu', 'udara', '.'], ['suhu', 'mengurangi', 'kadar', 'air', 'sehingga', 'cenderung', 'menjadi', 'kering', '.'], ['kelembaban', 'membatasi', 'hilangnya', 'air', '.'], ['angin', 'membantu', 'proses', 'penyerbukan', 'secara', 'alami', ',', 'mengurangi', 'kadar', 'air', '.'], ['hujan', 'meningkatkan', 'kadar', 'air', ',', 'mengikis', 'tanah', '.'], ['kalian', 'menemukan', 'berbagai', 'perbedaan', 'sosial', 'budaya', 'masyarakat', 'di', 'sekitar', 'tempat', 'tinggalmu', '.'], ['apabila', 'kalian', 'tinggal', 'di', 'perkotaan', ',', 'perbedaan', 'sosial', 'budaya', 'akan', 'semakin', 'banyak', '.'], ['perbedaan', 'sosial', 'budaya', 'meliputi', 'perbedaan', 'nilai-nilai', ',', 'norma', ',', 'dan', 'karakteristik', 'dari', 'suatu', 'kelompok', '.'], ['keragaman', 'sosial', 'budaya', 'di', 'masyarakat', 'dapat', 'terjadi', 'saat', 'berbagai', 'jenis', 'suku', 'dan', 'agama', 'yang', 'ada', 'di', 'suatu', 'ruang', 'bertemu', 'dan', 'berinteraksi', 'setiap', 'harinya', '.'], ['ruang', 'tersebut', 'adalah', 'ruang', 'yang', 'ada', 'pada', 'masyarakat', '.'], ['budaya', 'dapat', 'berupa', 'cara', 'hidup', 'masyarakat', ',', 'cara', 'berpakaian', ',', 'adat', 'istiadat', ',', 'jenis', 'mata', 'pecaharian', ',', 'dan', 'tata', 'upacara', 'keagamaan', '.'], ['keragaman', 'budaya', 'juga', 'mencakup', 'barang-barang', 'yang', 'dihasilkan', 'oleh', 'masyarakat', ',', 'seperti', 'senjata', ',', 'alat', 'bajak', 'sawah', ',', 'kitab', 'hukum', 'adat', ',', 'dan', 'tempat', 'tinggal', '.'], ['budaya', 'dapat', 'dianggap', 'sebagai', 'serangkaian', 'rancangan', 'untuk', 'bertahan', 'hidup', 'atau', 'alat', 'dari', 'praktik', ',', 'pengetahuan', ',', 'dan', 'simbol', 'yang', 'diperoleh', 'melalui', 'pembelajaran', ',', 'bukan', 'oleh', 'naluri', ',', 'yang', 'memungkinkan', 'orang', 'untuk', 'hidup', 'dalam', 'masyarakat', '.'], ['masyarakat', 'terdiri', 'dari', 'orang-orang', 'yang', 'berinteraksi', 'dan', 'berbagi', 'budaya', 'yang', 'sama', '.'], ['perbedaan', 'budaya', 'dapat', 'disebabkan', 'oleh', 'berbagai', 'hal', 'seperti', 'sejarah', ',', 'keturunan', ',', 'keyakinan', ',', 'dan', 'faktor', 'geografis', '.'], ['salah', 'satu', 'penyebab', 'perbedaan', 'budaya', 'adalah', 'faktor', 'geografis', '.'], ['faktor', 'geografis', 'yang', 'memengaruhi', 'keragaman', 'budaya', 'yang', 'akan', 'dibahas', 'berikut', 'ini'], ['dari', 'teks', 'tersebut', 'dapat', 'kita', 'pelajari', 'bahwa', 'budaya', 'yang', 'ada', 'di', 'masyarakat', 'dapat', 'dipengaruhi', 'oleh', 'lingkungan', 'yang', 'ada', 'di', 'sekitarnya', ','], ['misalnya', 'suku', 'lawu', 'dan', 'suku', 'bugis', 'yang', 'bermata', 'pencaharian', 'sebagai', 'nelayan', 'dengan', 'kapal', 'pinisinya', ','], ['sehingga', 'menjadi', 'sebuah', 'simbol', 'bahwa', 'indonesia', 'merupakan', 'negara', 'maritim', 'yang', 'kuat', 'dan', 'disegani', 'di', 'lautan', '.'], ['keragaman', 'budaya', 'dipengaruhi', 'oleh', 'lingkungan', 'fisik', '.'], ['manusia', 'sebagai', 'individu', 'adalah', 'kesatuan', 'jiwa', ',', 'raga', 'dan', 'kegiatan', 'atau', 'perilaku', 'pribadi', 'itu', 'sendiri', '.'], ['sebagai', 'individu', ',', 'dalam', 'pribadi', 'manusia', 'terdapat', 'tiga', 'unsur', ',', 'yaitu', 'nafsu', ',', 'semangat', ',', 'dan', 'intelegensi', '.'], ['kombinasi', 'dari', 'unsur', 'tersebut', 'menghasilkan', 'tingkah', 'laku', 'seseorang', 'yang', 'mencerminkan', 'karakter', 'atau', 'budayaanya', '.'], ['kesatuan', 'dari', 'kepribadian-kepribadian', 'seseorang', 'pada', 'suatu', 'daerah', 'yang', 'mempunyai', 'pola', 'yang', 'sama', 'dapat', 'membentuk', 'budaya', 'daerah', 'tersebut', 'yang', 'membedakan', 'dengan', 'tempat', 'lain', '.'], ['indonesia', 'memiliki', 'kebudayaan', 'yang', 'beragam', '.'], ['indonesia', 'memiliki', 'kekayaan', 'yang', 'begitu', 'besar', '.'], ['bukan', 'hanya', 'pemandangan', 'alam', 'budaya', ',', 'jauh', 'di', 'kedalaman', 'tanahnya', 'begitu', 'banyak', 'kandungan', 'mineral', 'berharga', '.'], ['selama', 'puluhan', 'tahun', ',', 'freeport', 'mengelola', 'tambang', 'mineral', 'di', 'tanah', 'papua', ',', 'indonesia', '.'], ['berdasarkan', 'laporan', 'keuangan', 'freeport', 'mcmorran', 'inc', 'periode', '2017', ',', 'freeport', 'indonesia', 'di', 'papua', 'tercatat', 'memiliki', '6', 'tambang', ',', 'yakni', 'grasberg', 'block', 'cave', ',', 'dmlz', ',', 'tambang', 'kucing', 'liar', ',', 'doz', ',', 'big', 'gossan', ',', 'dan', 'grasberg', 'open', 'pit', '.'], ['tambang', 'freeport', 'memiliki', 'beberapa', 'kandungan', 'cadangan', 'mineral', ',', 'yaitu', 'tembaga', ',', 'emas', ',', 'dan', 'perak', '.'], ['sumber', 'daya', 'alam', 'yang', 'terdapat', 'pada', 'pertambangan', 'freeport', 'di', 'atas', 'merupakan', 'salah', 'satu', 'contoh', 'dari', 'berbagai', 'sumber', 'daya', 'yang', 'ada', 'di', 'indonesia', 'yang', 'memiliki', 'beberapa', 'kandungan', 'cadangan', 'mineral', ',', 'seperti', 'tembaga', ',', 'emas', ',', 'dan', 'perak', '.'], ['kemudian', 'apa', 'sih', 'sumber', 'daya', 'alam', 'itu', '?'], ['apakah', 'ada', 'manfaatnya', 'untuk', 'kita', '?'], ['yuk', 'silahkan', 'simak', 'penjelasan', 'di', 'bawah', 'ini', '.'], ['sumber', 'daya', 'alam', 'merupakan', 'segala', 'sesuatu', 'yang', 'ada', 'di', 'permukaan', 'bumi', 'dan', 'dapat', 'dimanfaatkan', 'untuk', 'memenuhi', 'kebutuhan', 'manusia', '.'], ['potensi', 'sumber', 'daya', 'ini', 'mencakup', 'hal', 'yang', 'ada', 'di', 'udara', ',', 'daratan', ',', 'dan', 'perairan', '.'], ['berdasarkan', 'kelestariannya', ',', 'sumber', 'daya', 'alam', 'dapat', 'dibedakan', 'menjadi', 'dua', 'yaitu', 'sumber', 'daya', 'alam', 'yang', 'dapat', 'diperbarui', '(', 'renewable', 'resources', ')', 'dan', 'tidak', 'dapat', 'diperbarui', '(', 'non', 'renewable', 'resource', ')', '.'], ['contoh', 'sumber', 'daya', 'alam', 'yang', 'dapat', 'diperbarui', 'yaitu', 'seperti', 'air', ',', 'tanah', ',', 'dan', 'hutan', '.'], ['sedangkan', 'sumber', 'daya', 'alam', 'yang', 'tidak', 'dapat', 'diperbarui', 'seperti', 'minyak', 'bumi', 'dan', 'batu', 'bara', '.'], ['berikut', 'ini', 'merupakan', 'potensi', 'sumber', 'daya', 'alam', 'di', 'indonesia', 'yang', 'dirinci', 'menjadi', 'tiga', 'yaitu', 'sumber', 'daya', 'alam', 'hutan', ',', 'sumber', 'daya', 'alam', 'tambang', ',', 'dan', 'sumber', 'daya', 'alam', 'kemaritiman', '.'], ['indonesia', 'termasuk', 'negara', 'yang', 'memiliki', 'kekayaan', 'alam', 'yang', 'berlimpah', 'dibandingkan', 'negara-negara', 'yang', 'lain', '.'], ['potensi', 'sumber', 'daya', 'alam', 'indonesia', 'sangat', 'beraneka', 'ragam', '.'], ['bangsa', 'indonesia', 'memiliki', 'modal', 'penting', 'dalam', 'pembangunan', '.'], ['jumlah', 'penduduk', 'indonesia', 'yang', 'lebih', 'dari', '270', 'juta', 'merupakan', 'potensi', 'penting', 'dalam', 'pembangunan', '.'], ['pada', 'tahun', '2016', 'badan', 'pusat', 'statistik', 'mencatat', 'bahwa', 'di', 'indonesia', 'terdapat', 'angkatan', 'kerja', '127,67', 'juta', 'jiwa', '.'], ['di', 'antara', 'negara', 'asean', ',', 'kualitas', 'sdm', 'dan', 'ketenagakerjaan', 'indonesia', 'masih', 'berada', 'di', 'peringkat', 'bawah', '.'], ['kualitas', 'sdm', 'dan', 'ketenagakerjaan', 'indonesia', 'menempati', 'urutan', 'kelima', '.'], ['peringkat', 'ini', 'masih', 'kalah', 'jika', 'dibandingkan', 'singapura', ',', 'brunei', 'darussalam', ',', 'malaysia', ',', 'dan', 'thailand', '.'], ['kualitas', 'sumber', 'daya', 'manusia', 'di', 'indonesia', 'memengaruhi', 'terhadap', 'kemajuan', 'sebuah', 'bangsa', '.'], ['peristiwa', 'itu', 'dilatarbelakangi', 'oleh', 'peristiwa', 'yang', 'jauh', 'dari', 'indonesia', ',', 'misalnya', 'peristiwa', 'jatuhnya', 'konstantinopel', 'di', 'kawasan', 'laut', 'tengah', 'pada', 'tahun', '1453', '.'], ['kehidupan', 'global', 'semakin', 'berkembang', 'dengan', 'maraknya', 'penjelajahan', 'samudera', 'orang-orang', 'eropa', 'ke', 'dunia', 'timur', '.'], ['begitu', 'juga', 'peristiwa', 'kedatangan', 'bangsa', 'eropa', 'ke', 'indonesia', ',', 'telah', 'ikut', 'meningkatkan', 'kehidupan', 'global', '.'], ['pada', 'tahun', '1488', 'karena', 'serangan', 'ombak', 'besar', 'terpaksa', 'bartholomeus', 'diaz', 'mendarat', 'di', 'suatu', 'ujung', 'selatan', 'benua', 'afrika', '.'], ['pada', 'juli', '1497', 'vasco', 'da', 'gama', 'berangkat', 'dari', 'pelabuhan', 'lisabon', 'untuk', 'memulai', 'penjelajahan', 'samudra', '.'], ['berdasarkan', 'pengalaman', 'bartholomeus', 'diaz', 'tersebut', ',', 'vasco', 'da', 'gama', 'juga', 'berlayar', 'mengambil', 'rute', 'yang', 'pernah', 'dilayari', 'bartholomeus', 'diaz', '.'], ['rombongan', 'vasco', 'da', 'gama', 'juga', 'singgah', 'di', 'tanjung', 'harapan', '.'], ['atas', 'petunjuk', 'dari', 'pelaut', 'bangsa', 'moor', 'yang', 'telah', 'disewanya', ',', 'rombongan', 'vasco', 'da', 'gama', 'melanjutkan', 'penjelajahan', ',', 'berlayar', 'menelusuri', 'pantai', 'timur', 'afrika', 'kemudian', 'berbelok', 'ke', 'kanan', 'untuk', 'mengarungi', 'lautan', 'hindia', '(', 'samudra', 'indonesia', ')', '.'], ['pada', 'tahun', '1498', 'rombongan', 'vasco', 'da', 'gama', 'mendarat', 'sampai', 'di', 'kalikut', 'dan', 'juga', 'goa', 'di', 'pantai', 'barat', 'india', '.'], ['pada', 'tahun', '1511', 'armada', 'portugis', 'berhasil', 'menguasai', 'malaka', '.'], ['proklamasi', 'kemerdekaan', 'indonesia', 'terjadi', 'pada', '17', 'agustus', '1945', '.'], ['barack', 'obama', 'lahir', 'pada', '4', 'agustus', '1961', 'di', 'hawaii', '.'], ['reformasi', 'indonesia', 'dimulai', 'tahun', '1998', 'setelah', 'soeharto', 'mundur', '.'], ['perang', 'dunia', 'ii', 'berakhir', 'pada', '2', 'september', '1945', '.'], ['indonesia', 'menjadi', 'anggota', 'pbb', 'sejak', '28', 'september', '1950', '.'], ['banjir', 'bandang', 'terjadi', 'pada', '5', 'januari', '2021', 'di', 'bandung', '.'], ['hari', 'pahlawan', 'diperingati', 'setiap', '10', 'november', '.'], ['pada', 'tahun', '1511', 'portugis', 'menguasai', 'malaka', '.'], ['konferensi', 'asia-afrika', 'diselenggarakan', 'tahun', '1955', 'di', 'bandung', '.'], ['musim', 'kemarau', 'diperkirakan', 'mulai', 'april', '2025', '.'], ['rapat', 'dimulai', 'pukul', '09.00', 'pagi', '.'], ['kereta', 'akan', 'tiba', 'sekitar', 'jam', '3', 'sore', '.'], ['pertandingan', 'akan', 'dimulai', 'pada', 'pukul', '19.30', '.'], ['matahari', 'terbit', 'sekitar', '05.45', 'pagi', 'di', 'jakarta', '.'], ['makan', 'siang', 'biasanya', 'dilakukan', 'sekitar', 'jam', '12', 'siang', '.'], ['penerbangan', 'dijadwalkan', 'lepas', 'landas', 'pukul', '23.15', '.'], ['film', 'tayang', 'mulai', 'jam', '8', 'malam', 'nanti', '.'], ['pesawat', 'mendarat', 'tepat', 'pada', '00.30', 'dinihari', '.'], ['siaran', 'langsung', 'dimulai', 'pukul', '18.00', '.'], ['jam', 'kerja', 'dimulai', 'pukul', '08.00', 'dan', 'berakhir', 'pukul', '17.00', '.'], ['alarm', 'berbunyi', 'pada', 'pukul', '06.00', 'pagi', '.'], ['saya', 'bangun', 'sekitar', 'jam', '5', 'pagi', 'setiap', 'hari', '.'], ['konser', 'dimulai', 'sekitar', '20.00', 'malam', 'di', 'stadion', '.'], ['wawancara', 'dijadwalkan', 'pada', 'jam', '11', 'pagi', '.'], ['kami', 'tiba', 'di', 'bandara', 'sekitar', 'jam', '2', 'dinihari', '.'], ['dia', 'mengajar', 'kelas', 'pada', 'pukul', '13.00', '.'], ['peserta', 'diminta', 'hadir', 'sebelum', 'jam', '7', 'pagi', '.'], ['televisi', 'menayangkan', 'berita', 'malam', 'pada', '22.00', '.'], ['kami', 'akan', 'bertemu', 'jam', '10', 'malam', 'di', 'kafe', '.'], ['toko', 'buka', 'hingga', 'pukul', '21.00', '.'], ['dia', 'biasanya', 'berolahraga', 'pada', 'pagi', 'hari', '.'], ['kami', 'bertemu', 'lagi', 'pada', 'malam', 'hari', 'itu', '.'], ['upacara', 'dilaksanakan', 'pada', 'sore', 'hari', 'di', 'lapangan', '.'], ['ia', 'pulang', 'setiap', 'malam', 'sekitar', 'jam', '9', '.'], ['kami', 'berangkat', 'di', 'pagi', 'hari', 'menggunakan', 'mobil', '.'], ['acara', 'berlangsung', 'hingga', 'malam', 'hari', '.'], ['kami', 'tiba', 'di', 'bandara', 'pada', 'dinihari', '.'], ['pintu', 'gerbang', 'dibuka', 'setiap', 'pagi', '.'], ['ia', 'selalu', 'belajar', 'di', 'malam', '.'], ['waktu', 'bermain', 'dimulai', 'sore', 'hari', '.'], ['pelajaran', 'kedua', 'dimulai', 'sekitar', 'jam', 'tujuh', 'lebih', 'sepuluh', 'menit', '.'], ['bus', 'berangkat', 'kurang', 'lebih', 'jam', 'delapan', 'malam', '.'], ['pertemuan', 'terakhir', 'dilaksanakan', 'sebelum', 'matahari', 'terbenam', '.'], ['kereta', 'berangkat', 'sekitar', 'tengah', 'malam', 'dari', 'stasiun', 'gambir', '.'], ['jadwal', 'sholat', 'dimulai', 'pukul', 'empat', 'lebih', 'lima', 'menit', '.'], ['pemadaman', 'listrik', 'akan', 'dimulai', 'menjelang', 'malam', '.'], ['layanan', 'pelanggan', 'dibuka', 'setiap', 'hari', 'kerja', 'jam', 'sembilan', '.'], ['ia', 'terjaga', 'di', 'tengah', 'malam', 'karena', 'petir', '.'], ['kelas', 'selesai', 'sekitar', 'jam', 'dua', 'kurang', 'seperempat', '.'], ['waktu', 'sarapan', 'dimulai', 'pukul', '6.30', 'hingga', '7.30', '.'], ['proklamasi', 'kemerdekaan', 'terjadi', 'pada', '17', 'agustus', '1945', '.'], ['indonesia', 'merdeka', 'pada', 'tahun', '1945', '.'], ['pemilu', 'diadakan', 'pada', '14', 'februari', '2024', '.'], ['tanggal', '1', 'januari', '2023', 'merupakan', 'hari', 'libur', '.'], ['barack', 'obama', 'lahir', 'pada', '4', 'agustus', '1961', '.'], ['hari', 'bumi', 'diperingati', 'setiap', '22', 'april', '.'], ['musim', 'kemarau', 'terjadi', 'antara', 'bulan', 'april', 'hingga', 'oktober', '.'], ['reformasi', '1998', 'mengubah', 'sistem', 'politik', 'indonesia', '.'], ['konferensi', 'asia-afrika', 'digelar', 'pada', 'tahun', '1955', 'di', 'bandung', '.'], ['perang', 'dunia', 'kedua', 'berakhir', 'tahun', '1945', '.'], ['sumpah', 'pemuda', 'diperingati', 'setiap', '28', 'oktober', '.'], ['habibie', 'dilantik', 'menjadi', 'presiden', 'pada', '21', 'mei', '1998', '.'], ['hari', 'kemerdekaan', 'indonesia', 'dirayakan', 'setiap', '17', 'agustus', '.'], ['pada', 'tahun', '1949', ',', 'belanda', 'mengakui', 'kemerdekaan', 'indonesia', '.'], ['tsunami', 'aceh', 'terjadi', 'pada', '26', 'desember', '2004', '.'], ['bung', 'karno', 'meninggal', 'pada', '21', 'juni', '1970', '.'], ['jakarta', 'ditetapkan', 'sebagai', 'ibu', 'kota', 'negara', 'pada', 'tahun', '1961', '.'], ['pada', '1955', ',', 'indonesia', 'menjadi', 'tuan', 'rumah', 'konferensi', 'asia-afrika', '.'], ['pemerintah', 'mengumumkan', 'kebijakan', 'psbb', 'pada', 'april', '2020', 'di', 'jakarta', '.'], ['undang-undang', 'dasar', '1945', 'disahkan', 'pada', 'tanggal', '18', 'agustus', '1945', '.']] \n",
|
|
" 158\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"# text preprocessing\n",
|
|
"stop_words = set(stopwords.words(\"indonesian\")) \n",
|
|
"factory = StemmerFactory()\n",
|
|
"stemmer = factory.create_stemmer()\n",
|
|
"\n",
|
|
"with open(\"../normalize_text/normalize.json\", \"r\", encoding=\"utf-8\") as file:\n",
|
|
" normalization_dict = json.load(file)\n",
|
|
" \n",
|
|
"def text_preprocessing(text):\n",
|
|
" \n",
|
|
" # if(text == \"?\" or text == \".\" or text == \"!\"): return text\n",
|
|
" # lowercase\n",
|
|
" text = text.lower()\n",
|
|
" \n",
|
|
" # remove punctuation\n",
|
|
" # text = text.translate(str.maketrans(\"\", \"\", string.punctuation))\n",
|
|
" \n",
|
|
" # remove extra spaces\n",
|
|
" text = re.sub(r\"\\s+\", \" \", text).strip()\n",
|
|
" \n",
|
|
" # tokenize\n",
|
|
" # tokens = word_tokenize(text)\n",
|
|
" \n",
|
|
" # normalization\n",
|
|
" # tokens = normalization_dict.get(text, text) \n",
|
|
" \n",
|
|
" \n",
|
|
" # stemming\n",
|
|
" # tokens = stemmer.stem(tokens)\n",
|
|
" \n",
|
|
" \n",
|
|
" # remove stopwords\n",
|
|
" # tokens = [word for word in tokens if word not in stop_words]\n",
|
|
" \n",
|
|
" # print(f\"Original: {text}\")\n",
|
|
" # print(f\"Normalized: {tokens}\")\n",
|
|
" \n",
|
|
" return text\n",
|
|
"\n",
|
|
"# sentences = [text_preprocessing(\" \".join(sentence)) for sentence in sentences]\n",
|
|
"print(\"old\", sentences)\n",
|
|
"preprocessing_sentences = []\n",
|
|
"\n",
|
|
"for text in sentences:\n",
|
|
" result = []\n",
|
|
" for i in range(len(text)):\n",
|
|
" text[i] = text_preprocessing(text[i])\n",
|
|
" result.append(text[i])\n",
|
|
" preprocessing_sentences.append(result)\n",
|
|
"\n",
|
|
"print(\"new\", preprocessing_sentences, \"\\n\", len(preprocessing_sentences))\n",
|
|
"\n",
|
|
" "
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 5,
|
|
"id": "e9653d99",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"['kebutuhan', 'kalian', 'lapangan', '2', 'upacara', 'membentuk', 'sangat', 'fotosintesis', 'tsunami', 'perdagangan', 'resources', 'adalah', 'tayang', 'gossan', 'sore', 'antara', 'selalu', 'mengubah', 'kepribadian-kepribadian', 'vasco', 'kesenangan', 'alat', 'global', 'bagi', 'jika', 'sebuah', 'toko', 'mata', 'berpakaian', 'berada', 'ini', 'pelanggan', 'tiga', 'berangkat', 'ruang', 'sesuatu', 'empat', 'kuat', 'juta', 'tropis', 'ragam', 'daerah', 'perilaku', 'unsur', 'di', 'reformasi', 'berhubungan', 'presiden', 'modal', 'pengetahuan', 'silahkan', 'kualitas', 'dilaksanakan', 'alarm', 'februari', 'sumpah', 'membincangkan', 'besar', '10', 'kafe', 'digelar', 'kehidupan', 'kelas', '06.00', 'thailand', 'delapan', 'tersebut', 'belajar', 'merdeka', 'hukum', 'proklamasi', 'hujan', 'harian', 'asia', '22.00', 'angkatan', 'disahkan', 'kalikut', 'berita', 'simak', 'yaitu', 'dua', 'banjir', 'suhu', 'lalu', 'satu', 'konstantinopel', 'lain', 'papua', 'pernah', 'belanda', 'dasar', 'tepat', 'hari', 'seperempat', 'menit', 'memperhatikan', 'maret', 'jenis', 'dibuka', 'penting', 'berbagai', 'stadion', 'asing', 'freeport', 'iklim', 'perbedaan', '1945', 'seseorang', 'bertemu', 'karakteristik', 'kebudayaan', 'juga', 'berlayar', 'selesai', '26', 'lautan', 'manusianya', 'kegiatan', 'memenuhi', 'laku', '7.30', 'kawasan', 'tengah', 'minyak', 'bermata', 'alam', 'bangsa', 'pertambangan', '00.30', 'pagi', 'merancang', 'menempati', 'rata-rata', 'karno', 'keyakinan', 'politik', 'kemaritiman', 'samudera', 'ujung', 'kucing', 'meningkatkan', 'tambang', '28', 'jatuhnya', 'sdm', 'india', '20.00', 'kedalaman', 'sempit', '05.45', 'ditetapkan', 'barat', 'beraneka', 'malam', 'laporan', 'cave', 'sebagai', '2024', 'peringkat', 'kebijakan', 'telah', 'bangun', '1453', 'kedua', 'terbenam', 'pemerintah', 'menjadi', 'penyinaran', 'pelabuhan', 'dibedakan', 'ke', 'potensi', 'perang', 'terjaga', 'benua', 'gambir', 'mengakui', 'menguntungkan', 'nilai-nilai', 'berkembang', 'tertentu', 'selama', '6', 'mengambil', 'serangan', 'kelestariannya', 'kemerdekaan', 'tenggara', 'sejarah', 'bangsa-bangsa', 'negara-negara', 'hilangnya', 'musim', 'bawah', 'tahunan', 'kelima', 'hindia', 'puluhan', 'diperingati', 'apabila', '1950', 'penerbangan', 'penyerbukan', 'perkembangan', 'beragam', 'ikut', 'keadaan', '17.00', 'dianggap', 'geologis', 'rapat', 'hanya', 'kandungan', 'tingkah', 'asean', 'sawah', 'seperti', 'sendiri', '7', 'akan', 'resource', 'kering', 'asia-afrika', 'pertandingan', 'buka', 'terbit', 'lingkungan', 'dirayakan', 'bus', 'cuaca', 'gerbang', 'lepas', 'ibu', 'moor', 'statistik', '1.910.932,37', 'hindu-buddha', 'istiadat', 'bumi', 'memungkinkan', '2016', 'ia', '19.30', '1497', 'sepuluh', 'pusat', 'hidup', 'tempat', 'permukaan', 'kami', 'pertemuan', 'dijadwalkan', 'teks', '9', 'patut', 'diperbarui', 'konser', 'peristiwa', 'dalam', '2020', 'sih', 'menggunakan', 'konferensi', 'aktivitas', 'penyebab', '127,67', 'da', 'apakah', 'memiliki', 'naluri', 'hutan', 'relatif', 'maritim', 'bandung', 'serangkaian', 'memulai', 'pelayaran', 'orang-orang', 'sekitarnya', 'saya', 'bandang', 'km2', 'terpaksa', 'jadwal', 'sebesar', 'karakter', 'singgah', 'intelegensi', 'contoh', 'simbol', 'kanan', 'ketenagakerjaan', '18.00', '1', 'pecaharian', 'dinihari', 'petir', 'televisi', 'mendarat', 'cadangan', 'keuangan', 'pencaharian', 'kitab', 'bersyukur', 'november', '6.30', 'bermain', '1970', ')', 'meliputi', 'semakin', 'darussalam', 'dan', 'bahwa', 'cara', 'budayaanya', 'tidak', 'oleh', 'tanaman', 'liar', 'landas', 'bugis', 'grasberg', '21', 'fisik', 'keberagaman', 'pengaruh', 'hingga', 'terdiri', 'misalnya', 'pemuda', 'sembilan', 'disewanya', 'pribadi', 'perlu', '2025', 'masehi', 'menayangkan', '21.00', 'arang', '2023', 'berbelok', '08.00', 'pahlawan', 'terdapat', 'tahun', 'adat', 'barang-barang', 'malaka', 'desember', 'mengajar', 'renewable', 'laut', 'segala', 'meninggal', 'eropa', 'gama', 'rancangan', 'perkotaan', 'kondisi', 'juni', 'pantai', 'biasanya', 'dirinci', 'jam', 'hal', 'membantu', 'melalui', 'masih', 'soeharto', 'portugis', 'agustus', 'berikut', '1511', 'peranan', 'singapura', 'rombongan', 'sumber', 'bukan', 'lima', 'bajak', 'atau', 'makan', 'peserta', 'setiap', 'indonesia', 'kedatangan', 'mencakup', 'emas', 'dimanfaatkan', 'penduduk', 'juli', 'mengarungi', 'bulan', 'jatuh', 'pukul', 'mobil', '1488', 'badan', '1955', 'kekayaan', 'mengoptimalkan', 'letak', 'block', 'terhadap', 'varietas', 'penjelajahan', 'secara', 'urutan', '23.15', 'sebelum', 'batu', 'membedakan', 'langsung', 'perairan', 'inc', 'bagian', 'kesatuan', 'lebih', 'pengalaman', 'setelah', 'suatu', 'lagi', 'libur', 'praktik', 'september', 'merupakan', 'kemudian', 'termasuk', 'memengaruhi', 'melanjutkan', 'dihasilkan', 'tinggal', 'sejak', 'membatasi', 'stasiun', 'alami', 'bung', 'pesawat', 'menelusuri', 'barack', 'makanan', '3', 'jauh', 'orang', 'diamati', 'kebiasaan', 'manusia', 'kapal', 'manfaatnya', 'diselenggarakan', 'semangat', '-', 'mcmorran', 'proses', 'faktor', 'udara', 'hawaii', 'ii', 'pembelajaran', 'acara', 'tanahnya', '12', 'tanjung', 'tujuh', 'untuk', 'dilatarbelakangi', 'tanggal', 'rumah', 'hobi', 'wilayah', 'berdasarkan', 'memahami', 'sedangkan', '5,8', '14', 'mei', 'dengan', 'itu', 'beberapa', 'pinisinya', 'menemukan', 'hidrat', 'april', 'tuan', 'daratan', '2017', '17', 'dia', 'armada', 'angin', 'kombinasi', 'diadakan', '13.00', 'budaya', 'prakiraan', 'kadar', 'siang', 'berbunyi', 'dilayari', 'sehingga', 'penjelasan', '?', 'harapan', 'suku', 'unsur-unsur', 'pbb', 'diperoleh', 'doz', 'pit', 'bagaimana', '.', 'nafsu', 'kelompok', '22', 'perak', 'berolahraga', 'pokok', 'aceh', '1498', 'mengolah', 'bandara', 'berlangsung', '5', 'nelayan', 'kerja', 'afrika', 'keturunan', '18', 'syarat', 'senjata', 'dimilikinya', 'mewadahi', 'mencatat', 'mengelola', 'listrik', 'agama', 'salah', 'jiwa', 'diminta', 'sekitar', 'selatan', 'raga', 'individu', '(', '09.00', 'kaya', 'dimulai', 'dimiliki', 'pelajaran', 'selain', 'kita', 'pemandangan', 'diaz', 'tentang', 'sama', 'sosial', 'lawu', 'mengumumkan', ',', 'bertahan', 'anggota', 'habibie', 'sehari-hari', 'sampai', 'berhasil', 'siaran', 'obama', 'mempunyai', 'dapat', 'berinteraksi', 'rute', 'non', 'dari', 'sering', 'hadir', 'pariwisata', 'bara', 'kemarau', 'brunei', 'film', '2021', 'samudra', 'terutama', 'big', '11', 'mineral', 'bahan', 'pelajari', 'goa', '8', '1998', 'tentu', 'berbagi', 'jakarta', 'dibandingkan', 'menarik', 'oktober', 'tanah', 'jumlah', 'sudah', 'berupa', 'menjelang', 'pintu', 'berharga', 'apa', 'lembaga', 'periode', 'sedikit', 'yang', 'maraknya', 'dilantik', 'negara', 'begitu', 'petunjuk', 'lisabon', 'mengikis', 'malaysia', 'terjadi', '1961', 'keragaman', 'berakhir', 'kota', 'kurang', 'sholat', 'lahir', 'undang-undang', 'ribuan', 'tinggalmu', 'pada', 'air', 'kemajuan', 'kalah', 'sarapan', 'dibahas', 'daya', 'pelaut', 'tiba', 'dilakukan', '2004', 'pulang', 'yuk', 'dipengaruhi', 'tercatat', 'banyak', 'dunia', 'atas', 'disebabkan', 'kelembaban', 'pembangunan', 'norma', 'inilah', 'baik', 'menguap', 'januari', 'singkat', 'luas', 'curah', 'ada', 'open', 'tembaga', 'mencapai', 'yakni', 'berlimpah', '270', 'masyarakat', 'hubungannya', 'waktu', 'menguasai', 'menghasilkan', 'disegani', 'kereta', 'abad', 'layanan', 'bartholomeus', 'pemilu', 'saat', 'karena', 'geografis', 'matahari', 'wawancara', 'sistem', 'pemadaman', 'harinya', 'psbb', 'awal', 'mundur', 'mengurangi', 'tata', 'diperkirakan', 'nanti', '1949', '4', 'dmlz', 'cenderung', 'mulai', 'mencerminkan', 'terakhir', 'pola', 'keagamaan', 'ombak', 'timur', 'terluas']\n",
|
|
"{'kebutuhan': 2, 'kalian': 3, 'lapangan': 4, '2': 5, 'upacara': 6, 'membentuk': 7, 'sangat': 8, 'fotosintesis': 9, 'tsunami': 10, 'perdagangan': 11, 'resources': 12, 'adalah': 13, 'tayang': 14, 'gossan': 15, 'sore': 16, 'antara': 17, 'selalu': 18, 'mengubah': 19, 'kepribadian-kepribadian': 20, 'vasco': 21, 'kesenangan': 22, 'alat': 23, 'global': 24, 'bagi': 25, 'jika': 26, 'sebuah': 27, 'toko': 28, 'mata': 29, 'berpakaian': 30, 'berada': 31, 'ini': 32, 'pelanggan': 33, 'tiga': 34, 'berangkat': 35, 'ruang': 36, 'sesuatu': 37, 'empat': 38, 'kuat': 39, 'juta': 40, 'tropis': 41, 'ragam': 42, 'daerah': 43, 'perilaku': 44, 'unsur': 45, 'di': 46, 'reformasi': 47, 'berhubungan': 48, 'presiden': 49, 'modal': 50, 'pengetahuan': 51, 'silahkan': 52, 'kualitas': 53, 'dilaksanakan': 54, 'alarm': 55, 'februari': 56, 'sumpah': 57, 'membincangkan': 58, 'besar': 59, '10': 60, 'kafe': 61, 'digelar': 62, 'kehidupan': 63, 'kelas': 64, '06.00': 65, 'thailand': 66, 'delapan': 67, 'tersebut': 68, 'belajar': 69, 'merdeka': 70, 'hukum': 71, 'proklamasi': 72, 'hujan': 73, 'harian': 74, 'asia': 75, '22.00': 76, 'angkatan': 77, 'disahkan': 78, 'kalikut': 79, 'berita': 80, 'simak': 81, 'yaitu': 82, 'dua': 83, 'banjir': 84, 'suhu': 85, 'lalu': 86, 'satu': 87, 'konstantinopel': 88, 'lain': 89, 'papua': 90, 'pernah': 91, 'belanda': 92, 'dasar': 93, 'tepat': 94, 'hari': 95, 'seperempat': 96, 'menit': 97, 'memperhatikan': 98, 'maret': 99, 'jenis': 100, 'dibuka': 101, 'penting': 102, 'berbagai': 103, 'stadion': 104, 'asing': 105, 'freeport': 106, 'iklim': 107, 'perbedaan': 108, '1945': 109, 'seseorang': 110, 'bertemu': 111, 'karakteristik': 112, 'kebudayaan': 113, 'juga': 114, 'berlayar': 115, 'selesai': 116, '26': 117, 'lautan': 118, 'manusianya': 119, 'kegiatan': 120, 'memenuhi': 121, 'laku': 122, '7.30': 123, 'kawasan': 124, 'tengah': 125, 'minyak': 126, 'bermata': 127, 'alam': 128, 'bangsa': 129, 'pertambangan': 130, '00.30': 131, 'pagi': 132, 'merancang': 133, 'menempati': 134, 'rata-rata': 135, 'karno': 136, 'keyakinan': 137, 'politik': 138, 'kemaritiman': 139, 'samudera': 140, 'ujung': 141, 'kucing': 142, 'meningkatkan': 143, 'tambang': 144, '28': 145, 'jatuhnya': 146, 'sdm': 147, 'india': 148, '20.00': 149, 'kedalaman': 150, 'sempit': 151, '05.45': 152, 'ditetapkan': 153, 'barat': 154, 'beraneka': 155, 'malam': 156, 'laporan': 157, 'cave': 158, 'sebagai': 159, '2024': 160, 'peringkat': 161, 'kebijakan': 162, 'telah': 163, 'bangun': 164, '1453': 165, 'kedua': 166, 'terbenam': 167, 'pemerintah': 168, 'menjadi': 169, 'penyinaran': 170, 'pelabuhan': 171, 'dibedakan': 172, 'ke': 173, 'potensi': 174, 'perang': 175, 'terjaga': 176, 'benua': 177, 'gambir': 178, 'mengakui': 179, 'menguntungkan': 180, 'nilai-nilai': 181, 'berkembang': 182, 'tertentu': 183, 'selama': 184, '6': 185, 'mengambil': 186, 'serangan': 187, 'kelestariannya': 188, 'kemerdekaan': 189, 'tenggara': 190, 'sejarah': 191, 'bangsa-bangsa': 192, 'negara-negara': 193, 'hilangnya': 194, 'musim': 195, 'bawah': 196, 'tahunan': 197, 'kelima': 198, 'hindia': 199, 'puluhan': 200, 'diperingati': 201, 'apabila': 202, '1950': 203, 'penerbangan': 204, 'penyerbukan': 205, 'perkembangan': 206, 'beragam': 207, 'ikut': 208, 'keadaan': 209, '17.00': 210, 'dianggap': 211, 'geologis': 212, 'rapat': 213, 'hanya': 214, 'kandungan': 215, 'tingkah': 216, 'asean': 217, 'sawah': 218, 'seperti': 219, 'sendiri': 220, '7': 221, 'akan': 222, 'resource': 223, 'kering': 224, 'asia-afrika': 225, 'pertandingan': 226, 'buka': 227, 'terbit': 228, 'lingkungan': 229, 'dirayakan': 230, 'bus': 231, 'cuaca': 232, 'gerbang': 233, 'lepas': 234, 'ibu': 235, 'moor': 236, 'statistik': 237, '1.910.932,37': 238, 'hindu-buddha': 239, 'istiadat': 240, 'bumi': 241, 'memungkinkan': 242, '2016': 243, 'ia': 244, '19.30': 245, '1497': 246, 'sepuluh': 247, 'pusat': 248, 'hidup': 249, 'tempat': 250, 'permukaan': 251, 'kami': 252, 'pertemuan': 253, 'dijadwalkan': 254, 'teks': 255, '9': 256, 'patut': 257, 'diperbarui': 258, 'konser': 259, 'peristiwa': 260, 'dalam': 261, '2020': 262, 'sih': 263, 'menggunakan': 264, 'konferensi': 265, 'aktivitas': 266, 'penyebab': 267, '127,67': 268, 'da': 269, 'apakah': 270, 'memiliki': 271, 'naluri': 272, 'hutan': 273, 'relatif': 274, 'maritim': 275, 'bandung': 276, 'serangkaian': 277, 'memulai': 278, 'pelayaran': 279, 'orang-orang': 280, 'sekitarnya': 281, 'saya': 282, 'bandang': 283, 'km2': 284, 'terpaksa': 285, 'jadwal': 286, 'sebesar': 287, 'karakter': 288, 'singgah': 289, 'intelegensi': 290, 'contoh': 291, 'simbol': 292, 'kanan': 293, 'ketenagakerjaan': 294, '18.00': 295, '1': 296, 'pecaharian': 297, 'dinihari': 298, 'petir': 299, 'televisi': 300, 'mendarat': 301, 'cadangan': 302, 'keuangan': 303, 'pencaharian': 304, 'kitab': 305, 'bersyukur': 306, 'november': 307, '6.30': 308, 'bermain': 309, '1970': 310, ')': 311, 'meliputi': 312, 'semakin': 313, 'darussalam': 314, 'dan': 315, 'bahwa': 316, 'cara': 317, 'budayaanya': 318, 'tidak': 319, 'oleh': 320, 'tanaman': 321, 'liar': 322, 'landas': 323, 'bugis': 324, 'grasberg': 325, '21': 326, 'fisik': 327, 'keberagaman': 328, 'pengaruh': 329, 'hingga': 330, 'terdiri': 331, 'misalnya': 332, 'pemuda': 333, 'sembilan': 334, 'disewanya': 335, 'pribadi': 336, 'perlu': 337, '2025': 338, 'masehi': 339, 'menayangkan': 340, '21.00': 341, 'arang': 342, '2023': 343, 'berbelok': 344, '08.00': 345, 'pahlawan': 346, 'terdapat': 347, 'tahun': 348, 'adat': 349, 'barang-barang': 350, 'malaka': 351, 'desember': 352, 'mengajar': 353, 'renewable': 354, 'laut': 355, 'segala': 356, 'meninggal': 357, 'eropa': 358, 'gama': 359, 'rancangan': 360, 'perkotaan': 361, 'kondisi': 362, 'juni': 363, 'pantai': 364, 'biasanya': 365, 'dirinci': 366, 'jam': 367, 'hal': 368, 'membantu': 369, 'melalui': 370, 'masih': 371, 'soeharto': 372, 'portugis': 373, 'agustus': 374, 'berikut': 375, '1511': 376, 'peranan': 377, 'singapura': 378, 'rombongan': 379, 'sumber': 380, 'bukan': 381, 'lima': 382, 'bajak': 383, 'atau': 384, 'makan': 385, 'peserta': 386, 'setiap': 387, 'indonesia': 388, 'kedatangan': 389, 'mencakup': 390, 'emas': 391, 'dimanfaatkan': 392, 'penduduk': 393, 'juli': 394, 'mengarungi': 395, 'bulan': 396, 'jatuh': 397, 'pukul': 398, 'mobil': 399, '1488': 400, 'badan': 401, '1955': 402, 'kekayaan': 403, 'mengoptimalkan': 404, 'letak': 405, 'block': 406, 'terhadap': 407, 'varietas': 408, 'penjelajahan': 409, 'secara': 410, 'urutan': 411, '23.15': 412, 'sebelum': 413, 'batu': 414, 'membedakan': 415, 'langsung': 416, 'perairan': 417, 'inc': 418, 'bagian': 419, 'kesatuan': 420, 'lebih': 421, 'pengalaman': 422, 'setelah': 423, 'suatu': 424, 'lagi': 425, 'libur': 426, 'praktik': 427, 'september': 428, 'merupakan': 429, 'kemudian': 430, 'termasuk': 431, 'memengaruhi': 432, 'melanjutkan': 433, 'dihasilkan': 434, 'tinggal': 435, 'sejak': 436, 'membatasi': 437, 'stasiun': 438, 'alami': 439, 'bung': 440, 'pesawat': 441, 'menelusuri': 442, 'barack': 443, 'makanan': 444, '3': 445, 'jauh': 446, 'orang': 447, 'diamati': 448, 'kebiasaan': 449, 'manusia': 450, 'kapal': 451, 'manfaatnya': 452, 'diselenggarakan': 453, 'semangat': 454, '-': 455, 'mcmorran': 456, 'proses': 457, 'faktor': 458, 'udara': 459, 'hawaii': 460, 'ii': 461, 'pembelajaran': 462, 'acara': 463, 'tanahnya': 464, '12': 465, 'tanjung': 466, 'tujuh': 467, 'untuk': 468, 'dilatarbelakangi': 469, 'tanggal': 470, 'rumah': 471, 'hobi': 472, 'wilayah': 473, 'berdasarkan': 474, 'memahami': 475, 'sedangkan': 476, '5,8': 477, '14': 478, 'mei': 479, 'dengan': 480, 'itu': 481, 'beberapa': 482, 'pinisinya': 483, 'menemukan': 484, 'hidrat': 485, 'april': 486, 'tuan': 487, 'daratan': 488, '2017': 489, '17': 490, 'dia': 491, 'armada': 492, 'angin': 493, 'kombinasi': 494, 'diadakan': 495, '13.00': 496, 'budaya': 497, 'prakiraan': 498, 'kadar': 499, 'siang': 500, 'berbunyi': 501, 'dilayari': 502, 'sehingga': 503, 'penjelasan': 504, '?': 505, 'harapan': 506, 'suku': 507, 'unsur-unsur': 508, 'pbb': 509, 'diperoleh': 510, 'doz': 511, 'pit': 512, 'bagaimana': 513, '.': 514, 'nafsu': 515, 'kelompok': 516, '22': 517, 'perak': 518, 'berolahraga': 519, 'pokok': 520, 'aceh': 521, '1498': 522, 'mengolah': 523, 'bandara': 524, 'berlangsung': 525, '5': 526, 'nelayan': 527, 'kerja': 528, 'afrika': 529, 'keturunan': 530, '18': 531, 'syarat': 532, 'senjata': 533, 'dimilikinya': 534, 'mewadahi': 535, 'mencatat': 536, 'mengelola': 537, 'listrik': 538, 'agama': 539, 'salah': 540, 'jiwa': 541, 'diminta': 542, 'sekitar': 543, 'selatan': 544, 'raga': 545, 'individu': 546, '(': 547, '09.00': 548, 'kaya': 549, 'dimulai': 550, 'dimiliki': 551, 'pelajaran': 552, 'selain': 553, 'kita': 554, 'pemandangan': 555, 'diaz': 556, 'tentang': 557, 'sama': 558, 'sosial': 559, 'lawu': 560, 'mengumumkan': 561, ',': 562, 'bertahan': 563, 'anggota': 564, 'habibie': 565, 'sehari-hari': 566, 'sampai': 567, 'berhasil': 568, 'siaran': 569, 'obama': 570, 'mempunyai': 571, 'dapat': 572, 'berinteraksi': 573, 'rute': 574, 'non': 575, 'dari': 576, 'sering': 577, 'hadir': 578, 'pariwisata': 579, 'bara': 580, 'kemarau': 581, 'brunei': 582, 'film': 583, '2021': 584, 'samudra': 585, 'terutama': 586, 'big': 587, '11': 588, 'mineral': 589, 'bahan': 590, 'pelajari': 591, 'goa': 592, '8': 593, '1998': 594, 'tentu': 595, 'berbagi': 596, 'jakarta': 597, 'dibandingkan': 598, 'menarik': 599, 'oktober': 600, 'tanah': 601, 'jumlah': 602, 'sudah': 603, 'berupa': 604, 'menjelang': 605, 'pintu': 606, 'berharga': 607, 'apa': 608, 'lembaga': 609, 'periode': 610, 'sedikit': 611, 'yang': 612, 'maraknya': 613, 'dilantik': 614, 'negara': 615, 'begitu': 616, 'petunjuk': 617, 'lisabon': 618, 'mengikis': 619, 'malaysia': 620, 'terjadi': 621, '1961': 622, 'keragaman': 623, 'berakhir': 624, 'kota': 625, 'kurang': 626, 'sholat': 627, 'lahir': 628, 'undang-undang': 629, 'ribuan': 630, 'tinggalmu': 631, 'pada': 632, 'air': 633, 'kemajuan': 634, 'kalah': 635, 'sarapan': 636, 'dibahas': 637, 'daya': 638, 'pelaut': 639, 'tiba': 640, 'dilakukan': 641, '2004': 642, 'pulang': 643, 'yuk': 644, 'dipengaruhi': 645, 'tercatat': 646, 'banyak': 647, 'dunia': 648, 'atas': 649, 'disebabkan': 650, 'kelembaban': 651, 'pembangunan': 652, 'norma': 653, 'inilah': 654, 'baik': 655, 'menguap': 656, 'januari': 657, 'singkat': 658, 'luas': 659, 'curah': 660, 'ada': 661, 'open': 662, 'tembaga': 663, 'mencapai': 664, 'yakni': 665, 'berlimpah': 666, '270': 667, 'masyarakat': 668, 'hubungannya': 669, 'waktu': 670, 'menguasai': 671, 'menghasilkan': 672, 'disegani': 673, 'kereta': 674, 'abad': 675, 'layanan': 676, 'bartholomeus': 677, 'pemilu': 678, 'saat': 679, 'karena': 680, 'geografis': 681, 'matahari': 682, 'wawancara': 683, 'sistem': 684, 'pemadaman': 685, 'harinya': 686, 'psbb': 687, 'awal': 688, 'mundur': 689, 'mengurangi': 690, 'tata': 691, 'diperkirakan': 692, 'nanti': 693, '1949': 694, '4': 695, 'dmlz': 696, 'cenderung': 697, 'mulai': 698, 'mencerminkan': 699, 'terakhir': 700, 'pola': 701, 'keagamaan': 702, 'ombak': 703, 'timur': 704, 'terluas': 705, 'PAD': 0, 'UNK': 1}\n",
|
|
"['B-DATE', 'B-ETH', 'B-EVENT', 'B-LOC', 'B-MIN', 'B-MISC', 'B-ORG', 'B-PER', 'B-QUANT', 'B-REL', 'B-RES', 'B-TERM', 'B-TIME', 'I-DATE', 'I-ETH', 'I-EVENT', 'I-LOC', 'I-MISC', 'I-ORG', 'I-PER', 'I-QUANT', 'I-RES', 'I-TERM', 'I-TIME', 'O']\n",
|
|
"['AM-ADV', 'AM-CAU', 'AM-COM', 'AM-DIR', 'AM-DIS', 'AM-EXT', 'AM-FRQ', 'AM-LOC', 'AM-MNR', 'AM-MOD', 'AM-NEG', 'AM-PNC', 'AM-PRP', 'AM-QUE', 'AM-TMP', 'ARG0', 'ARG1', 'ARG2', 'ARG3', 'ARGM-BNF', 'ARGM-CAU', 'ARGM-COM', 'ARGM-DIS', 'ARGM-EX', 'ARGM-EXT', 'ARGM-LOC', 'ARGM-MNR', 'ARGM-MOD', 'ARGM-NEG', 'ARGM-PNC', 'ARGM-PRD', 'ARGM-PRP', 'ARGM-SRC', 'ARGM-TMP', 'I-AM-LOC', 'O', 'R-ARG1', 'V']\n",
|
|
"{'B-DATE': 0, 'B-ETH': 1, 'B-EVENT': 2, 'B-LOC': 3, 'B-MIN': 4, 'B-MISC': 5, 'B-ORG': 6, 'B-PER': 7, 'B-QUANT': 8, 'B-REL': 9, 'B-RES': 10, 'B-TERM': 11, 'B-TIME': 12, 'I-DATE': 13, 'I-ETH': 14, 'I-EVENT': 15, 'I-LOC': 16, 'I-MISC': 17, 'I-ORG': 18, 'I-PER': 19, 'I-QUANT': 20, 'I-RES': 21, 'I-TERM': 22, 'I-TIME': 23, 'O': 24}\n",
|
|
"{'AM-ADV': 0, 'AM-CAU': 1, 'AM-COM': 2, 'AM-DIR': 3, 'AM-DIS': 4, 'AM-EXT': 5, 'AM-FRQ': 6, 'AM-LOC': 7, 'AM-MNR': 8, 'AM-MOD': 9, 'AM-NEG': 10, 'AM-PNC': 11, 'AM-PRP': 12, 'AM-QUE': 13, 'AM-TMP': 14, 'ARG0': 15, 'ARG1': 16, 'ARG2': 17, 'ARG3': 18, 'ARGM-BNF': 19, 'ARGM-CAU': 20, 'ARGM-COM': 21, 'ARGM-DIS': 22, 'ARGM-EX': 23, 'ARGM-EXT': 24, 'ARGM-LOC': 25, 'ARGM-MNR': 26, 'ARGM-MOD': 27, 'ARGM-NEG': 28, 'ARGM-PNC': 29, 'ARGM-PRD': 30, 'ARGM-PRP': 31, 'ARGM-SRC': 32, 'ARGM-TMP': 33, 'I-AM-LOC': 34, 'O': 35, 'R-ARG1': 36, 'V': 37}\n",
|
|
"{0: 'B-DATE', 1: 'B-ETH', 2: 'B-EVENT', 3: 'B-LOC', 4: 'B-MIN', 5: 'B-MISC', 6: 'B-ORG', 7: 'B-PER', 8: 'B-QUANT', 9: 'B-REL', 10: 'B-RES', 11: 'B-TERM', 12: 'B-TIME', 13: 'I-DATE', 14: 'I-ETH', 15: 'I-EVENT', 16: 'I-LOC', 17: 'I-MISC', 18: 'I-ORG', 19: 'I-PER', 20: 'I-QUANT', 21: 'I-RES', 22: 'I-TERM', 23: 'I-TIME', 24: 'O'}\n",
|
|
"{0: 'AM-ADV', 1: 'AM-CAU', 2: 'AM-COM', 3: 'AM-DIR', 4: 'AM-DIS', 5: 'AM-EXT', 6: 'AM-FRQ', 7: 'AM-LOC', 8: 'AM-MNR', 9: 'AM-MOD', 10: 'AM-NEG', 11: 'AM-PNC', 12: 'AM-PRP', 13: 'AM-QUE', 14: 'AM-TMP', 15: 'ARG0', 16: 'ARG1', 17: 'ARG2', 18: 'ARG3', 19: 'ARGM-BNF', 20: 'ARGM-CAU', 21: 'ARGM-COM', 22: 'ARGM-DIS', 23: 'ARGM-EX', 24: 'ARGM-EXT', 25: 'ARGM-LOC', 26: 'ARGM-MNR', 27: 'ARGM-MOD', 28: 'ARGM-NEG', 29: 'ARGM-PNC', 30: 'ARGM-PRD', 31: 'ARGM-PRP', 32: 'ARGM-SRC', 33: 'ARGM-TMP', 34: 'I-AM-LOC', 35: 'O', 36: 'R-ARG1', 37: 'V'}\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"words = list(set(word for sentence in preprocessing_sentences for word in sentence))\n",
|
|
"word2idx = {word: idx + 2 for idx, word in enumerate(words)}\n",
|
|
"word2idx[\"PAD\"] = 0\n",
|
|
"word2idx[\"UNK\"] = 1\n",
|
|
"\n",
|
|
"all_ner_tags = sorted(set(tag for seq in ner_labels for tag in seq))\n",
|
|
"all_srl_tags = sorted(set(tag for seq in srl_labels for tag in seq))\n",
|
|
"tag2idx_ner = {tag: idx for idx, tag in enumerate(all_ner_tags)}\n",
|
|
"tag2idx_srl = {tag: idx for idx, tag in enumerate(all_srl_tags)}\n",
|
|
"idx2tag_ner = {i: t for t, i in tag2idx_ner.items()}\n",
|
|
"idx2tag_srl = {i: t for t, i in tag2idx_srl.items()}\n",
|
|
"\n",
|
|
"print(words)\n",
|
|
"print(word2idx)\n",
|
|
"print(all_ner_tags)\n",
|
|
"print(all_srl_tags)\n",
|
|
"print(tag2idx_ner)\n",
|
|
"print(tag2idx_srl)\n",
|
|
"print(idx2tag_ner)\n",
|
|
"print(idx2tag_srl)"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 6,
|
|
"id": "9d3a37b3",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"[[328 174 380 ... 0 0 0]\n",
|
|
" [513 457 681 ... 0 0 0]\n",
|
|
" [513 329 457 ... 0 0 0]\n",
|
|
" ...\n",
|
|
" [632 402 562 ... 0 0 0]\n",
|
|
" [168 561 162 ... 0 0 0]\n",
|
|
" [629 93 109 ... 0 0 0]]\n",
|
|
"y_ner \n",
|
|
" \n",
|
|
"[[24 24 24 ... 24 24 24]\n",
|
|
" [24 24 24 ... 24 24 24]\n",
|
|
" [24 24 24 ... 24 24 24]\n",
|
|
" ...\n",
|
|
" [24 0 24 ... 24 24 24]\n",
|
|
" [24 24 24 ... 24 24 24]\n",
|
|
" [24 24 0 ... 24 24 24]]\n",
|
|
"y_srl \n",
|
|
" \n",
|
|
"[[16 16 16 ... 35 35 35]\n",
|
|
" [13 16 16 ... 35 35 35]\n",
|
|
" [13 16 16 ... 35 35 35]\n",
|
|
" ...\n",
|
|
" [14 14 35 ... 35 35 35]\n",
|
|
" [15 37 16 ... 35 35 35]\n",
|
|
" [16 16 14 ... 35 35 35]]\n",
|
|
"y_ner cat \n",
|
|
" \n",
|
|
"[array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 1., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 1., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 1., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [1., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [1., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [1., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [1., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [1., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [1., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 1., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [1., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [1., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 1., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 1., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [1., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [1., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]]), array([[0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [1., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.]])]\n",
|
|
"y_srl cat \n",
|
|
" \n",
|
|
"[array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [1., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 1., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 1., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 1., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 1., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 1.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]]), array([[0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 0., 0., 0.],\n",
|
|
" ...,\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.],\n",
|
|
" [0., 0., 0., ..., 1., 0., 0.]])]\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"\n",
|
|
"# === ENCODING ===\n",
|
|
"X = [[word2idx.get(w, word2idx[\"UNK\"]) for w in s] for s in sentences]\n",
|
|
"y_ner = [[tag2idx_ner[t] for t in ts] for ts in ner_labels]\n",
|
|
"y_srl = [[tag2idx_srl[t] for t in ts] for ts in srl_labels]\n",
|
|
"\n",
|
|
"maxlen = 50\n",
|
|
"\n",
|
|
"X = pad_sequences(X, maxlen=maxlen, padding=\"post\", value=word2idx[\"PAD\"])\n",
|
|
"y_ner = pad_sequences(y_ner, maxlen=maxlen, padding=\"post\", value=tag2idx_ner[\"O\"])\n",
|
|
"y_srl = pad_sequences(y_srl, maxlen=maxlen, padding=\"post\", value=tag2idx_srl[\"O\"])\n",
|
|
"\n",
|
|
"y_ner_cat = [to_categorical(seq, num_classes=len(tag2idx_ner)) for seq in y_ner]\n",
|
|
"y_srl_cat = [to_categorical(seq, num_classes=len(tag2idx_srl)) for seq in y_srl]\n",
|
|
"\n",
|
|
"print(X)\n",
|
|
"print(\"y_ner \\n \")\n",
|
|
"print(y_ner)\n",
|
|
"print(\"y_srl \\n \")\n",
|
|
"print(y_srl)\n",
|
|
"print(\"y_ner cat \\n \")\n",
|
|
"print(y_ner_cat)\n",
|
|
"print(\"y_srl cat \\n \")\n",
|
|
"print(y_srl_cat)\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 7,
|
|
"id": "a5c264df",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# split dataset \n",
|
|
"X_temp, X_test, y_ner_temp, y_ner_test, y_srl_temp, y_srl_test = train_test_split(\n",
|
|
" X, y_ner_cat, y_srl_cat, test_size=0.1, random_state=42\n",
|
|
")\n",
|
|
"X_train, X_val, y_ner_train, y_ner_val, y_srl_train, y_srl_val = train_test_split(\n",
|
|
" X_temp, y_ner_temp, y_srl_temp, test_size=0.1111, random_state=42 # ~10% of total\n",
|
|
")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 8,
|
|
"id": "712c1789",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"2025-04-29 19:42:52.271455: E external/local_xla/xla/stream_executor/cuda/cuda_platform.cc:51] failed call to cuInit: INTERNAL: CUDA error: Failed call to cuInit: UNKNOWN ERROR (303)\n"
|
|
]
|
|
},
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"functional\"</span>\n",
|
|
"</pre>\n"
|
|
],
|
|
"text/plain": [
|
|
"\u001b[1mModel: \"functional\"\u001b[0m\n"
|
|
]
|
|
},
|
|
"metadata": {},
|
|
"output_type": "display_data"
|
|
},
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┓\n",
|
|
"┃<span style=\"font-weight: bold\"> Layer (type) </span>┃<span style=\"font-weight: bold\"> Output Shape </span>┃<span style=\"font-weight: bold\"> Param # </span>┃<span style=\"font-weight: bold\"> Connected to </span>┃\n",
|
|
"┡━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━┩\n",
|
|
"│ input_layer │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">50</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │ - │\n",
|
|
"│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">InputLayer</span>) │ │ │ │\n",
|
|
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
|
"│ embedding │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">50</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">45,184</span> │ input_layer[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>] │\n",
|
|
"│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Embedding</span>) │ │ │ │\n",
|
|
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
|
"│ bidirectional │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">50</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">66,048</span> │ embedding[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>][<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>] │\n",
|
|
"│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Bidirectional</span>) │ │ │ │\n",
|
|
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
|
"│ ner_output │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">50</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">25</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">3,225</span> │ bidirectional[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>]… │\n",
|
|
"│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">TimeDistributed</span>) │ │ │ │\n",
|
|
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
|
"│ srl_output │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">50</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">38</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">4,902</span> │ bidirectional[<span style=\"color: #00af00; text-decoration-color: #00af00\">0</span>]… │\n",
|
|
"│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">TimeDistributed</span>) │ │ │ │\n",
|
|
"└─────────────────────┴───────────────────┴────────────┴───────────────────┘\n",
|
|
"</pre>\n"
|
|
],
|
|
"text/plain": [
|
|
"┏━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━┓\n",
|
|
"┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mConnected to \u001b[0m\u001b[1m \u001b[0m┃\n",
|
|
"┡━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━┩\n",
|
|
"│ input_layer │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m50\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ - │\n",
|
|
"│ (\u001b[38;5;33mInputLayer\u001b[0m) │ │ │ │\n",
|
|
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
|
"│ embedding │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m50\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m45,184\u001b[0m │ input_layer[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
|
|
"│ (\u001b[38;5;33mEmbedding\u001b[0m) │ │ │ │\n",
|
|
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
|
"│ bidirectional │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m50\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m66,048\u001b[0m │ embedding[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
|
|
"│ (\u001b[38;5;33mBidirectional\u001b[0m) │ │ │ │\n",
|
|
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
|
"│ ner_output │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m50\u001b[0m, \u001b[38;5;34m25\u001b[0m) │ \u001b[38;5;34m3,225\u001b[0m │ bidirectional[\u001b[38;5;34m0\u001b[0m]… │\n",
|
|
"│ (\u001b[38;5;33mTimeDistributed\u001b[0m) │ │ │ │\n",
|
|
"├─────────────────────┼───────────────────┼────────────┼───────────────────┤\n",
|
|
"│ srl_output │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m50\u001b[0m, \u001b[38;5;34m38\u001b[0m) │ \u001b[38;5;34m4,902\u001b[0m │ bidirectional[\u001b[38;5;34m0\u001b[0m]… │\n",
|
|
"│ (\u001b[38;5;33mTimeDistributed\u001b[0m) │ │ │ │\n",
|
|
"└─────────────────────┴───────────────────┴────────────┴───────────────────┘\n"
|
|
]
|
|
},
|
|
"metadata": {},
|
|
"output_type": "display_data"
|
|
},
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">119,359</span> (466.25 KB)\n",
|
|
"</pre>\n"
|
|
],
|
|
"text/plain": [
|
|
"\u001b[1m Total params: \u001b[0m\u001b[38;5;34m119,359\u001b[0m (466.25 KB)\n"
|
|
]
|
|
},
|
|
"metadata": {},
|
|
"output_type": "display_data"
|
|
},
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">119,359</span> (466.25 KB)\n",
|
|
"</pre>\n"
|
|
],
|
|
"text/plain": [
|
|
"\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m119,359\u001b[0m (466.25 KB)\n"
|
|
]
|
|
},
|
|
"metadata": {},
|
|
"output_type": "display_data"
|
|
},
|
|
{
|
|
"data": {
|
|
"text/html": [
|
|
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
|
|
"</pre>\n"
|
|
],
|
|
"text/plain": [
|
|
"\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
|
|
]
|
|
},
|
|
"metadata": {},
|
|
"output_type": "display_data"
|
|
}
|
|
],
|
|
"source": [
|
|
"#training model\n",
|
|
"input_layer = Input(shape=(maxlen,))\n",
|
|
"embedding = Embedding(input_dim=len(word2idx), output_dim=64)(input_layer)\n",
|
|
"bilstm = Bidirectional(LSTM(units=64, return_sequences=True))(embedding)\n",
|
|
"out_ner = TimeDistributed(Dense(len(tag2idx_ner), activation=\"softmax\"), name=\"ner_output\")(bilstm)\n",
|
|
"out_srl = TimeDistributed(Dense(len(tag2idx_srl), activation=\"softmax\"), name=\"srl_output\")(bilstm)\n",
|
|
"\n",
|
|
"model = Model(inputs=input_layer, outputs=[out_ner, out_srl])\n",
|
|
"model.compile(\n",
|
|
" optimizer=\"adam\",\n",
|
|
" loss={\"ner_output\": \"categorical_crossentropy\", \"srl_output\": \"categorical_crossentropy\"},\n",
|
|
" metrics={\"ner_output\": \"accuracy\", \"srl_output\": \"accuracy\"}\n",
|
|
")\n",
|
|
"\n",
|
|
"model.summary()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 9,
|
|
"id": "98feee87",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Epoch 1/10\n",
|
|
"\u001b[1m63/63\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 19ms/step - loss: 3.7132 - ner_output_accuracy: 0.8752 - ner_output_loss: 1.6339 - srl_output_accuracy: 0.7399 - srl_output_loss: 2.0793 - val_loss: 0.7544 - val_ner_output_accuracy: 0.9463 - val_ner_output_loss: 0.2714 - val_srl_output_accuracy: 0.8450 - val_srl_output_loss: 0.4830\n",
|
|
"Epoch 2/10\n",
|
|
"\u001b[1m63/63\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 10ms/step - loss: 0.7800 - ner_output_accuracy: 0.9586 - ner_output_loss: 0.2194 - srl_output_accuracy: 0.8145 - srl_output_loss: 0.5605 - val_loss: 0.6925 - val_ner_output_accuracy: 0.9463 - val_ner_output_loss: 0.2589 - val_srl_output_accuracy: 0.8563 - val_srl_output_loss: 0.4336\n",
|
|
"Epoch 3/10\n",
|
|
"\u001b[1m63/63\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 10ms/step - loss: 0.7723 - ner_output_accuracy: 0.9535 - ner_output_loss: 0.2264 - srl_output_accuracy: 0.8309 - srl_output_loss: 0.5460 - val_loss: 0.6375 - val_ner_output_accuracy: 0.9463 - val_ner_output_loss: 0.2429 - val_srl_output_accuracy: 0.8825 - val_srl_output_loss: 0.3945\n",
|
|
"Epoch 4/10\n",
|
|
"\u001b[1m63/63\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 9ms/step - loss: 0.7463 - ner_output_accuracy: 0.9521 - ner_output_loss: 0.2214 - srl_output_accuracy: 0.8501 - srl_output_loss: 0.5249 - val_loss: 0.5878 - val_ner_output_accuracy: 0.9463 - val_ner_output_loss: 0.2284 - val_srl_output_accuracy: 0.8950 - val_srl_output_loss: 0.3594\n",
|
|
"Epoch 5/10\n",
|
|
"\u001b[1m63/63\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 9ms/step - loss: 0.7682 - ner_output_accuracy: 0.9441 - ner_output_loss: 0.2412 - srl_output_accuracy: 0.8410 - srl_output_loss: 0.5270 - val_loss: 0.5590 - val_ner_output_accuracy: 0.9463 - val_ner_output_loss: 0.2182 - val_srl_output_accuracy: 0.9037 - val_srl_output_loss: 0.3408\n",
|
|
"Epoch 6/10\n",
|
|
"\u001b[1m63/63\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 10ms/step - loss: 0.6489 - ner_output_accuracy: 0.9487 - ner_output_loss: 0.2089 - srl_output_accuracy: 0.8736 - srl_output_loss: 0.4399 - val_loss: 0.5293 - val_ner_output_accuracy: 0.9463 - val_ner_output_loss: 0.2094 - val_srl_output_accuracy: 0.9012 - val_srl_output_loss: 0.3199\n",
|
|
"Epoch 7/10\n",
|
|
"\u001b[1m63/63\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 9ms/step - loss: 0.6142 - ner_output_accuracy: 0.9540 - ner_output_loss: 0.1842 - srl_output_accuracy: 0.8802 - srl_output_loss: 0.4300 - val_loss: 0.5180 - val_ner_output_accuracy: 0.9475 - val_ner_output_loss: 0.2047 - val_srl_output_accuracy: 0.9025 - val_srl_output_loss: 0.3134\n",
|
|
"Epoch 8/10\n",
|
|
"\u001b[1m13/63\u001b[0m \u001b[32m━━━━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m0s\u001b[0m 8ms/step - loss: 0.5499 - ner_output_accuracy: 0.9632 - ner_output_loss: 0.1377 - srl_output_accuracy: 0.8832 - srl_output_loss: 0.4122"
|
|
]
|
|
},
|
|
{
|
|
"ename": "KeyboardInterrupt",
|
|
"evalue": "",
|
|
"output_type": "error",
|
|
"traceback": [
|
|
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
|
|
"\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
|
|
"Cell \u001b[0;32mIn[9], line 2\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[38;5;66;03m# === TRAINING ===\u001b[39;00m\n\u001b[0;32m----> 2\u001b[0m history \u001b[38;5;241m=\u001b[39m \u001b[43mmodel\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfit\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 3\u001b[0m \u001b[43m \u001b[49m\u001b[43mX_train\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 4\u001b[0m \u001b[43m \u001b[49m\u001b[43m{\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mner_output\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mnp\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43marray\u001b[49m\u001b[43m(\u001b[49m\u001b[43my_ner_train\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43msrl_output\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mnp\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43marray\u001b[49m\u001b[43m(\u001b[49m\u001b[43my_srl_train\u001b[49m\u001b[43m)\u001b[49m\u001b[43m}\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 5\u001b[0m \u001b[43m \u001b[49m\u001b[43mvalidation_data\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43mX_val\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m{\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mner_output\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mnp\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43marray\u001b[49m\u001b[43m(\u001b[49m\u001b[43my_ner_val\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43msrl_output\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m:\u001b[49m\u001b[43m \u001b[49m\u001b[43mnp\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43marray\u001b[49m\u001b[43m(\u001b[49m\u001b[43my_srl_val\u001b[49m\u001b[43m)\u001b[49m\u001b[43m}\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 6\u001b[0m \u001b[43m \u001b[49m\u001b[43mbatch_size\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m2\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 7\u001b[0m \u001b[43m \u001b[49m\u001b[43mepochs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m10\u001b[39;49m\n\u001b[1;32m 8\u001b[0m \u001b[43m)\u001b[49m\n\u001b[1;32m 10\u001b[0m \u001b[38;5;66;03m# === SAVE ===\u001b[39;00m\n\u001b[1;32m 11\u001b[0m model\u001b[38;5;241m.\u001b[39msave(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmulti_task_bilstm_model.keras\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
|
|
"File \u001b[0;32m/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/keras/src/utils/traceback_utils.py:117\u001b[0m, in \u001b[0;36mfilter_traceback.<locals>.error_handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 115\u001b[0m filtered_tb \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 116\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 117\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 118\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 119\u001b[0m filtered_tb \u001b[38;5;241m=\u001b[39m _process_traceback_frames(e\u001b[38;5;241m.\u001b[39m__traceback__)\n",
|
|
"File \u001b[0;32m/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/keras/src/backend/tensorflow/trainer.py:371\u001b[0m, in \u001b[0;36mTensorFlowTrainer.fit\u001b[0;34m(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq)\u001b[0m\n\u001b[1;32m 369\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m step, iterator \u001b[38;5;129;01min\u001b[39;00m epoch_iterator:\n\u001b[1;32m 370\u001b[0m callbacks\u001b[38;5;241m.\u001b[39mon_train_batch_begin(step)\n\u001b[0;32m--> 371\u001b[0m logs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtrain_function\u001b[49m\u001b[43m(\u001b[49m\u001b[43miterator\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 372\u001b[0m callbacks\u001b[38;5;241m.\u001b[39mon_train_batch_end(step, logs)\n\u001b[1;32m 373\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mstop_training:\n",
|
|
"File \u001b[0;32m/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/keras/src/backend/tensorflow/trainer.py:219\u001b[0m, in \u001b[0;36mTensorFlowTrainer._make_function.<locals>.function\u001b[0;34m(iterator)\u001b[0m\n\u001b[1;32m 215\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21mfunction\u001b[39m(iterator):\n\u001b[1;32m 216\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(\n\u001b[1;32m 217\u001b[0m iterator, (tf\u001b[38;5;241m.\u001b[39mdata\u001b[38;5;241m.\u001b[39mIterator, tf\u001b[38;5;241m.\u001b[39mdistribute\u001b[38;5;241m.\u001b[39mDistributedIterator)\n\u001b[1;32m 218\u001b[0m ):\n\u001b[0;32m--> 219\u001b[0m opt_outputs \u001b[38;5;241m=\u001b[39m \u001b[43mmulti_step_on_iterator\u001b[49m\u001b[43m(\u001b[49m\u001b[43miterator\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 220\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m opt_outputs\u001b[38;5;241m.\u001b[39mhas_value():\n\u001b[1;32m 221\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mStopIteration\u001b[39;00m\n",
|
|
"File \u001b[0;32m/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/tensorflow/python/util/traceback_utils.py:150\u001b[0m, in \u001b[0;36mfilter_traceback.<locals>.error_handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 148\u001b[0m filtered_tb \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 149\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 150\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 151\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 152\u001b[0m filtered_tb \u001b[38;5;241m=\u001b[39m _process_traceback_frames(e\u001b[38;5;241m.\u001b[39m__traceback__)\n",
|
|
"File \u001b[0;32m/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/tensorflow/python/eager/polymorphic_function/polymorphic_function.py:833\u001b[0m, in \u001b[0;36mFunction.__call__\u001b[0;34m(self, *args, **kwds)\u001b[0m\n\u001b[1;32m 830\u001b[0m compiler \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mxla\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_jit_compile \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mnonXla\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 832\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m OptionalXlaContext(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_jit_compile):\n\u001b[0;32m--> 833\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwds\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 835\u001b[0m new_tracing_count \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mexperimental_get_tracing_count()\n\u001b[1;32m 836\u001b[0m without_tracing \u001b[38;5;241m=\u001b[39m (tracing_count \u001b[38;5;241m==\u001b[39m new_tracing_count)\n",
|
|
"File \u001b[0;32m/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/tensorflow/python/eager/polymorphic_function/polymorphic_function.py:878\u001b[0m, in \u001b[0;36mFunction._call\u001b[0;34m(self, *args, **kwds)\u001b[0m\n\u001b[1;32m 875\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_lock\u001b[38;5;241m.\u001b[39mrelease()\n\u001b[1;32m 876\u001b[0m \u001b[38;5;66;03m# In this case we have not created variables on the first call. So we can\u001b[39;00m\n\u001b[1;32m 877\u001b[0m \u001b[38;5;66;03m# run the first trace but we should fail if variables are created.\u001b[39;00m\n\u001b[0;32m--> 878\u001b[0m results \u001b[38;5;241m=\u001b[39m \u001b[43mtracing_compilation\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcall_function\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 879\u001b[0m \u001b[43m \u001b[49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkwds\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_variable_creation_config\u001b[49m\n\u001b[1;32m 880\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 881\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_created_variables:\n\u001b[1;32m 882\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mCreating variables on a non-first call to a function\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 883\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m decorated with tf.function.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
|
|
"File \u001b[0;32m/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/tensorflow/python/eager/polymorphic_function/tracing_compilation.py:139\u001b[0m, in \u001b[0;36mcall_function\u001b[0;34m(args, kwargs, tracing_options)\u001b[0m\n\u001b[1;32m 137\u001b[0m bound_args \u001b[38;5;241m=\u001b[39m function\u001b[38;5;241m.\u001b[39mfunction_type\u001b[38;5;241m.\u001b[39mbind(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 138\u001b[0m flat_inputs \u001b[38;5;241m=\u001b[39m function\u001b[38;5;241m.\u001b[39mfunction_type\u001b[38;5;241m.\u001b[39munpack_inputs(bound_args)\n\u001b[0;32m--> 139\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunction\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_flat\u001b[49m\u001b[43m(\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;66;43;03m# pylint: disable=protected-access\u001b[39;49;00m\n\u001b[1;32m 140\u001b[0m \u001b[43m \u001b[49m\u001b[43mflat_inputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcaptured_inputs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfunction\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcaptured_inputs\u001b[49m\n\u001b[1;32m 141\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n",
|
|
"File \u001b[0;32m/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/tensorflow/python/eager/polymorphic_function/concrete_function.py:1322\u001b[0m, in \u001b[0;36mConcreteFunction._call_flat\u001b[0;34m(self, tensor_inputs, captured_inputs)\u001b[0m\n\u001b[1;32m 1318\u001b[0m possible_gradient_type \u001b[38;5;241m=\u001b[39m gradients_util\u001b[38;5;241m.\u001b[39mPossibleTapeGradientTypes(args)\n\u001b[1;32m 1319\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m (possible_gradient_type \u001b[38;5;241m==\u001b[39m gradients_util\u001b[38;5;241m.\u001b[39mPOSSIBLE_GRADIENT_TYPES_NONE\n\u001b[1;32m 1320\u001b[0m \u001b[38;5;129;01mand\u001b[39;00m executing_eagerly):\n\u001b[1;32m 1321\u001b[0m \u001b[38;5;66;03m# No tape is watching; skip to running the function.\u001b[39;00m\n\u001b[0;32m-> 1322\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_inference_function\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcall_preflattened\u001b[49m\u001b[43m(\u001b[49m\u001b[43margs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1323\u001b[0m forward_backward \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_select_forward_and_backward_functions(\n\u001b[1;32m 1324\u001b[0m args,\n\u001b[1;32m 1325\u001b[0m possible_gradient_type,\n\u001b[1;32m 1326\u001b[0m executing_eagerly)\n\u001b[1;32m 1327\u001b[0m forward_function, args_with_tangents \u001b[38;5;241m=\u001b[39m forward_backward\u001b[38;5;241m.\u001b[39mforward()\n",
|
|
"File \u001b[0;32m/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/tensorflow/python/eager/polymorphic_function/atomic_function.py:216\u001b[0m, in \u001b[0;36mAtomicFunction.call_preflattened\u001b[0;34m(self, args)\u001b[0m\n\u001b[1;32m 214\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21mcall_preflattened\u001b[39m(\u001b[38;5;28mself\u001b[39m, args: Sequence[core\u001b[38;5;241m.\u001b[39mTensor]) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Any:\n\u001b[1;32m 215\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"Calls with flattened tensor inputs and returns the structured output.\"\"\"\u001b[39;00m\n\u001b[0;32m--> 216\u001b[0m flat_outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcall_flat\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 217\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfunction_type\u001b[38;5;241m.\u001b[39mpack_output(flat_outputs)\n",
|
|
"File \u001b[0;32m/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/tensorflow/python/eager/polymorphic_function/atomic_function.py:251\u001b[0m, in \u001b[0;36mAtomicFunction.call_flat\u001b[0;34m(self, *args)\u001b[0m\n\u001b[1;32m 249\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m record\u001b[38;5;241m.\u001b[39mstop_recording():\n\u001b[1;32m 250\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_bound_context\u001b[38;5;241m.\u001b[39mexecuting_eagerly():\n\u001b[0;32m--> 251\u001b[0m outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_bound_context\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcall_function\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 252\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mname\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 253\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43mlist\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43margs\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 254\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43mlen\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfunction_type\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mflat_outputs\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 255\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 256\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 257\u001b[0m outputs \u001b[38;5;241m=\u001b[39m make_call_op_in_graph(\n\u001b[1;32m 258\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 259\u001b[0m \u001b[38;5;28mlist\u001b[39m(args),\n\u001b[1;32m 260\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_bound_context\u001b[38;5;241m.\u001b[39mfunction_call_options\u001b[38;5;241m.\u001b[39mas_attrs(),\n\u001b[1;32m 261\u001b[0m )\n",
|
|
"File \u001b[0;32m/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/tensorflow/python/eager/context.py:1688\u001b[0m, in \u001b[0;36mContext.call_function\u001b[0;34m(self, name, tensor_inputs, num_outputs)\u001b[0m\n\u001b[1;32m 1686\u001b[0m cancellation_context \u001b[38;5;241m=\u001b[39m cancellation\u001b[38;5;241m.\u001b[39mcontext()\n\u001b[1;32m 1687\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m cancellation_context \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m-> 1688\u001b[0m outputs \u001b[38;5;241m=\u001b[39m \u001b[43mexecute\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mexecute\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1689\u001b[0m \u001b[43m \u001b[49m\u001b[43mname\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdecode\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mutf-8\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1690\u001b[0m \u001b[43m \u001b[49m\u001b[43mnum_outputs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mnum_outputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1691\u001b[0m \u001b[43m \u001b[49m\u001b[43minputs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtensor_inputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1692\u001b[0m \u001b[43m \u001b[49m\u001b[43mattrs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mattrs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1693\u001b[0m \u001b[43m \u001b[49m\u001b[43mctx\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1694\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1695\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 1696\u001b[0m outputs \u001b[38;5;241m=\u001b[39m execute\u001b[38;5;241m.\u001b[39mexecute_with_cancellation(\n\u001b[1;32m 1697\u001b[0m name\u001b[38;5;241m.\u001b[39mdecode(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mutf-8\u001b[39m\u001b[38;5;124m\"\u001b[39m),\n\u001b[1;32m 1698\u001b[0m num_outputs\u001b[38;5;241m=\u001b[39mnum_outputs,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1702\u001b[0m cancellation_manager\u001b[38;5;241m=\u001b[39mcancellation_context,\n\u001b[1;32m 1703\u001b[0m )\n",
|
|
"File \u001b[0;32m/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/tensorflow/python/eager/execute.py:53\u001b[0m, in \u001b[0;36mquick_execute\u001b[0;34m(op_name, num_outputs, inputs, attrs, ctx, name)\u001b[0m\n\u001b[1;32m 51\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 52\u001b[0m ctx\u001b[38;5;241m.\u001b[39mensure_initialized()\n\u001b[0;32m---> 53\u001b[0m tensors \u001b[38;5;241m=\u001b[39m \u001b[43mpywrap_tfe\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mTFE_Py_Execute\u001b[49m\u001b[43m(\u001b[49m\u001b[43mctx\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_handle\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdevice_name\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mop_name\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 54\u001b[0m \u001b[43m \u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mattrs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mnum_outputs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 55\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m core\u001b[38;5;241m.\u001b[39m_NotOkStatusException \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 56\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m name \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n",
|
|
"\u001b[0;31mKeyboardInterrupt\u001b[0m: "
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"\n",
|
|
"# === TRAINING ===\n",
|
|
"history = model.fit(\n",
|
|
" X_train,\n",
|
|
" {\"ner_output\": np.array(y_ner_train), \"srl_output\": np.array(y_srl_train)},\n",
|
|
" validation_data=(X_val, {\"ner_output\": np.array(y_ner_val), \"srl_output\": np.array(y_srl_val)}),\n",
|
|
" batch_size=2,\n",
|
|
" epochs=10\n",
|
|
")\n",
|
|
"\n",
|
|
"# === SAVE ===\n",
|
|
"model.save(\"multi_task_bilstm_model.keras\")\n",
|
|
"with open(\"word2idx.pkl\", \"wb\") as f:\n",
|
|
" pickle.dump(word2idx, f)\n",
|
|
"with open(\"tag2idx_ner.pkl\", \"wb\") as f:\n",
|
|
" pickle.dump(tag2idx_ner, f)\n",
|
|
"with open(\"tag2idx_srl.pkl\", \"wb\") as f:\n",
|
|
" pickle.dump(tag2idx_srl, f)\n",
|
|
" \n",
|
|
" \n",
|
|
"history_dict = history.history\n",
|
|
"\n",
|
|
"# === LOSS ===\n",
|
|
"plt.figure(figsize=(12, 6))\n",
|
|
"\n",
|
|
"plt.plot(history_dict[\"loss\"], label=\"Total Loss (train)\")\n",
|
|
"plt.plot(history_dict[\"val_loss\"], label=\"Total Loss (val)\")\n",
|
|
"plt.plot(history_dict[\"ner_output_loss\"], label=\"NER Loss (train)\")\n",
|
|
"plt.plot(history_dict[\"val_ner_output_loss\"], label=\"NER Loss (val)\")\n",
|
|
"plt.plot(history_dict[\"srl_output_loss\"], label=\"SRL Loss (train)\")\n",
|
|
"plt.plot(history_dict[\"val_srl_output_loss\"], label=\"SRL Loss (val)\")\n",
|
|
"\n",
|
|
"plt.title(\"Model Loss per Epoch\")\n",
|
|
"plt.xlabel(\"Epoch\")\n",
|
|
"plt.ylabel(\"Loss\")\n",
|
|
"plt.legend()\n",
|
|
"plt.grid(True)\n",
|
|
"plt.tight_layout()\n",
|
|
"plt.show()\n",
|
|
"\n",
|
|
"\n",
|
|
"# === ACCURACY ===\n",
|
|
"plt.figure(figsize=(12, 6))\n",
|
|
"\n",
|
|
"plt.plot(history_dict[\"ner_output_accuracy\"], label=\"NER Accuracy (train)\")\n",
|
|
"plt.plot(history_dict[\"val_ner_output_accuracy\"], label=\"NER Accuracy (val)\")\n",
|
|
"plt.plot(history_dict[\"srl_output_accuracy\"], label=\"SRL Accuracy (train)\")\n",
|
|
"plt.plot(history_dict[\"val_srl_output_accuracy\"], label=\"SRL Accuracy (val)\")\n",
|
|
"\n",
|
|
"plt.title(\"Model Accuracy per Epoch\")\n",
|
|
"plt.xlabel(\"Epoch\")\n",
|
|
"plt.ylabel(\"Accuracy\")\n",
|
|
"plt.legend()\n",
|
|
"plt.grid(True)\n",
|
|
"plt.tight_layout()\n",
|
|
"plt.show()\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "aeef32c1",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"WARNING:tensorflow:5 out of the last 5 calls to <function TensorFlowTrainer.make_predict_function.<locals>.one_step_on_data_distributed at 0x7f8ec792f520> triggered tf.function retracing. Tracing is expensive and the excessive number of tracings could be due to (1) creating @tf.function repeatedly in a loop, (2) passing tensors with different shapes, (3) passing Python objects instead of tensors. For (1), please define your @tf.function outside of the loop. For (2), @tf.function has reduce_retracing=True option that can avoid unnecessary retracing. For (3), please refer to https://www.tensorflow.org/guide/function#controlling_retracing and https://www.tensorflow.org/api_docs/python/tf/function for more details.\n",
|
|
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 475ms/step\n",
|
|
"\n",
|
|
"📊 [NER] Test Set Classification Report:\n",
|
|
" precision recall f1-score support\n",
|
|
"\n",
|
|
" LOC 0.00 0.00 0.00 6\n",
|
|
" QUANT 0.00 0.00 0.00 1\n",
|
|
"\n",
|
|
" micro avg 0.00 0.00 0.00 7\n",
|
|
" macro avg 0.00 0.00 0.00 7\n",
|
|
"weighted avg 0.00 0.00 0.00 7\n",
|
|
"\n",
|
|
"\n",
|
|
"📊 [SRL] Test Set Classification Report:\n",
|
|
" precision recall f1-score support\n",
|
|
"\n",
|
|
" BNF 0.00 0.00 0.00 1\n",
|
|
" EXT 0.00 0.00 0.00 2\n",
|
|
" LOC 0.00 0.00 0.00 4\n",
|
|
" MNR 0.00 0.00 0.00 1\n",
|
|
" MOD 0.00 0.00 0.00 1\n",
|
|
" NEG 0.00 0.00 0.00 1\n",
|
|
" PRP 0.00 0.00 0.00 1\n",
|
|
" QUE 0.00 0.00 0.00 1\n",
|
|
" RG0 0.00 0.00 0.00 5\n",
|
|
" RG1 0.00 0.00 0.00 8\n",
|
|
" RG2 0.00 0.00 0.00 2\n",
|
|
" SRC 0.00 0.00 0.00 1\n",
|
|
" TMP 0.00 0.00 0.00 1\n",
|
|
" _ 0.00 0.00 0.00 6\n",
|
|
"\n",
|
|
" micro avg 0.00 0.00 0.00 35\n",
|
|
" macro avg 0.00 0.00 0.00 35\n",
|
|
"weighted avg 0.00 0.00 0.00 35\n",
|
|
"\n"
|
|
]
|
|
},
|
|
{
|
|
"name": "stderr",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/seqeval/metrics/v1.py:57: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples. Use `zero_division` parameter to control this behavior.\n",
|
|
" _warn_prf(average, modifier, msg_start, len(result))\n",
|
|
"/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/seqeval/metrics/v1.py:57: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 due to no predicted samples. Use `zero_division` parameter to control this behavior.\n",
|
|
" _warn_prf(average, modifier, msg_start, len(result))\n",
|
|
"/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: ARG0 seems not to be NE tag.\n",
|
|
" warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
|
|
"/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: V seems not to be NE tag.\n",
|
|
" warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
|
|
"/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: ARG1 seems not to be NE tag.\n",
|
|
" warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
|
|
"/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: ARGM-LOC seems not to be NE tag.\n",
|
|
" warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
|
|
"/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: AM-NEG seems not to be NE tag.\n",
|
|
" warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
|
|
"/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: ARGM-SRC seems not to be NE tag.\n",
|
|
" warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
|
|
"/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: ARGM-MOD seems not to be NE tag.\n",
|
|
" warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
|
|
"/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: ARGM-EXT seems not to be NE tag.\n",
|
|
" warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
|
|
"/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: AM-MNR seems not to be NE tag.\n",
|
|
" warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
|
|
"/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: ARGM-BNF seems not to be NE tag.\n",
|
|
" warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
|
|
"/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: AM-EXT seems not to be NE tag.\n",
|
|
" warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
|
|
"/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: AM-QUE seems not to be NE tag.\n",
|
|
" warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
|
|
"/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: AM-TMP seems not to be NE tag.\n",
|
|
" warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
|
|
"/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: AM-PRP seems not to be NE tag.\n",
|
|
" warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
|
|
"/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: ARG2 seems not to be NE tag.\n",
|
|
" warnings.warn('{} seems not to be NE tag.'.format(chunk))\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"# evaluation\n",
|
|
"y_pred_ner, y_pred_srl = model.predict(X_test)\n",
|
|
"\n",
|
|
"y_true_ner = [[idx2tag_ner[np.argmax(tok)] for tok in seq] for seq in y_ner_test]\n",
|
|
"y_pred_ner = [[idx2tag_ner[np.argmax(tok)] for tok in seq] for seq in y_pred_ner]\n",
|
|
"\n",
|
|
"y_true_srl = [[idx2tag_srl[np.argmax(tok)] for tok in seq] for seq in y_srl_test]\n",
|
|
"y_pred_srl = [[idx2tag_srl[np.argmax(tok)] for tok in seq] for seq in y_pred_srl]\n",
|
|
"\n",
|
|
"print(\"\\n📊 [NER] Test Set Classification Report:\")\n",
|
|
"print(classification_report(y_true_ner, y_pred_ner))\n",
|
|
"\n",
|
|
"print(\"\\n📊 [SRL] Test Set Classification Report:\")\n",
|
|
"print(classification_report(y_true_srl, y_pred_srl))\n",
|
|
"\n",
|
|
"\n",
|
|
"# import numpy as np\n",
|
|
"\n",
|
|
"# # Prediksi model (output = probabilitas)\n",
|
|
"# y_pred_ner = model.predict(X_test)[0]\n",
|
|
"# y_pred_ner_idx = np.argmax(y_pred_ner, axis=-1)\n",
|
|
"# y_true_ner_idx = np.argmax(y_ner_test, axis=-1)\n",
|
|
"\n",
|
|
"# # Mapping ke string\n",
|
|
"# y_pred_ner_str = []\n",
|
|
"# y_true_ner_str = []\n",
|
|
"\n",
|
|
"# for y_true_seq, y_pred_seq in zip(y_true_ner_idx, y_pred_ner_idx):\n",
|
|
"# true_seq = []\n",
|
|
"# pred_seq = []\n",
|
|
"# for t, p in zip(y_true_seq, y_pred_seq):\n",
|
|
"# if idx2tag_ner[t] != \"PAD\":\n",
|
|
"# true_seq.append(idx2tag_ner[t])\n",
|
|
"# pred_seq.append(idx2tag_ner[p])\n",
|
|
"# y_true_ner_str.append(true_seq)\n",
|
|
"# y_pred_ner_str.append(pred_seq)\n",
|
|
"\n",
|
|
"# from seqeval.metrics import classification_report\n",
|
|
"# print(\"\\n📊 [NER] Test Set Classification Report:\")\n",
|
|
"# print(classification_report(y_true_ner_str, y_pred_ner_str))\n",
|
|
"\n",
|
|
"\n",
|
|
"# from collections import Counter\n",
|
|
"\n",
|
|
"# flat_preds = [tag for seq in y_pred_ner_str for tag in seq]\n",
|
|
"# print(Counter(flat_preds))\n",
|
|
"\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "5a18da05",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"\n",
|
|
"def plot_confusion_matrix(y_true_flat, y_pred_flat, labels, title=\"Confusion Matrix\"):\n",
|
|
" cm = confusion_matrix(y_true_flat, y_pred_flat, labels=labels)\n",
|
|
" plt.figure(figsize=(10, 8))\n",
|
|
" sns.heatmap(cm, annot=True, fmt='d', cmap='Blues',\n",
|
|
" xticklabels=labels, yticklabels=labels)\n",
|
|
" plt.title(title)\n",
|
|
" plt.xlabel(\"Predicted\")\n",
|
|
" plt.ylabel(\"Actual\")\n",
|
|
" plt.xticks(rotation=45)\n",
|
|
" plt.yticks(rotation=0)\n",
|
|
" plt.tight_layout()\n",
|
|
" plt.show()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "cee30988",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"image/png": "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",
|
|
"text/plain": [
|
|
"<Figure size 1000x800 with 2 Axes>"
|
|
]
|
|
},
|
|
"metadata": {},
|
|
"output_type": "display_data"
|
|
}
|
|
],
|
|
"source": [
|
|
"\n",
|
|
"# Flatten label\n",
|
|
"y_true_flat_ner = [tag for seq in y_true_ner for tag in seq]\n",
|
|
"y_pred_flat_ner = [tag for seq in y_pred_ner for tag in seq]\n",
|
|
"\n",
|
|
"# Buat plot\n",
|
|
"plot_confusion_matrix(\n",
|
|
" y_true_flat_ner, \n",
|
|
" y_pred_flat_ner, \n",
|
|
" labels=list(tag2idx_ner.keys()), \n",
|
|
" title=\"NER Confusion Matrix\"\n",
|
|
")\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "4ba2b85c",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"data": {
|
|
"image/png": "iVBORw0KGgoAAAANSUhEUgAAA6EAAAMWCAYAAAAAlIDnAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjEsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvc2/+5QAAAAlwSFlzAAAPYQAAD2EBqD+naQABAABJREFUeJzs3XtcFPXiPvBn2YVFXQVdLwTlLXQXAc3Ma1qeQoVIU1GRXEVBMy+UZcbBvJdSpHYzLY/LzbscozoetKxEIxGsBM0LdpE8KaTgAl4QWJjfH1/dX9MCAiLMDs/79ZrX9zDzmWeewfM99fEzO6sQBEEAERERERERUQOwa+wCRERERERE1HRwEkpEREREREQNhpNQIiIiIiIiajCchBIREREREVGD4SSUiIiIiIiIGgwnoURERERERNRgOAklIiIiIiKiBsNJKBERERERETUYTkKJiIiIiIiowXASSkRETcrmzZuh1+thb28PZ2fnes9ftmwZFApFvefaquzsbCgUCsTGxjZ2FSIikghOQomIZOzEiRMYN24cOnXqBEdHR7i5uWHYsGH44IMPROM6d+4MhUJh2Vq0aIF+/fohPj7eKjM5ORkKhQL//ve/69wrMTERfn5+aNu2LRwcHODq6ooJEybgm2++qXNmTZw5cwZTp07Fgw8+iH/961/YuHHjPb1eQ7v95zd9+vRKj7/22muWMXl5ebXOT0pKwrJly+qhKRERNWUKQRCExi5BRET17/Dhw/jHP/6Bjh07Ijg4GC4uLvjf//6HI0eO4Ndff8Uvv/xiGdu5c2e0bt0a8+fPBwDk5ORg06ZNOHv2LDZu3IgZM2ZYxiYnJ+Mf//gHEhISMG7cuFp1EgQBISEhiI2NRe/evTFu3Di4uLggJycHiYmJ+OGHH/Ddd99h0KBB9fib+P8++ugjzJo1Cz///DPc3d3vyTXMZjPMZjMcHR3vSX51FAoFHB0d4ejoiD///BMODg6i4127dkVOTg5u3ryJy5cvo23btrXKnzt3Lj788EPU5l8dBEFASUkJ7O3toVQqa3U9IiKSJ1VjFyAiontj5cqVcHJywtGjR60eO7106ZLVeDc3NxgMBsvPU6dORdeuXfHOO++IJqF3Y82aNYiNjcW8efOwdu1a0WOrr732GjZv3gyV6t79o+n2fd+Lx3BvU6lU9/Qe7sTX1xeff/459u7di2eeecay//Dhwzh37hwCAgKwe/fue97DbDajoqICDg4OjTIhJyIi6eLjuEREMvXrr7/C09Oz0glX+/bt73h+u3btoNfr8euvv9ZLn+LiYkRGRkKv12P16tWVfm5y8uTJ6Nevn+Xn3377DePHj0ebNm3QvHlzDBgwAP/9739F59x+PHjXrl1YuXIl7r//fjg6OuLJJ5+0Wu1dunSp5d4UCoXl0dK//ue/6ty5M6ZOnWr5uaysDMuXL0e3bt3g6OgIrVaLwYMHY//+/ZYxlX0m1Gw24/XXX8eDDz4ItVqNzp07Y+HChSgpKbG63tNPP42UlBT069cPjo6O6Nq1a6WPRVfFzc0Njz32GLZt2ybav3XrVnh7e8PLy8vqnG+//Rbjx49Hx44doVar8cADD+Cll15CcXGxZczUqVPx4YcfWn5ftzf85XOfq1evxrvvvmu5z1OnTll9JvTSpUto164dhg4dKlpR/eWXX9CiRQsEBgbW+F6JiMg2cSWUiEimOnXqhNTUVPz000+VTjzuxGw2448//kDr1q3rpU9KSgquXLmCefPm1eixzD///BODBg3CjRs38MILL0Cr1SIuLg6jRo3Cv//9b4wZM0Y0/s0334SdnR1eeeUVFBYWIioqCpMmTUJaWhoA4N1330V8fDwSExOxYcMGaDQa9OzZs1b3sGzZMkRGRmL69Ono168fioqK8P333+PHH3/EsGHDqjxv+vTpiIuLw7hx4zB//nykpaUhMjISp0+fRmJiomjsL7/8gnHjxiE0NBTBwcGIjo7G1KlT0adPH3h6etao57PPPosXX3wR165dg0ajgdlsRkJCAl5++WXcvHnTanxCQgJu3LiBWbNmQavVIj09HR988AH++OMPJCQkAABmzpyJixcvYv/+/di8eXOl142JicHNmzfx3HPPQa1Wo02bNqioqBCNad++PTZs2IDx48fjgw8+wAsvvICKigpMnToVLVu2xPr162t0j0REZMMEIiKSpS+//FJQKpWCUqkUBg4cKLz66qvCF198IZSWllqN7dSpkzB8+HDh8uXLwuXLl4UTJ04IkydPFgAIc+bMEY09cOCAAEBISEioVZ/33ntPACAkJibWaPy8efMEAMK3335r2Xf16lWhS5cuQufOnYXy8nJRHw8PD6GkpMTqeidOnLDsW7p0qQBAuHz5suhaAISlS5dadejUqZMQHBxs+blXr16Cv79/tb1vX+O2jIwMAYAwffp00bhXXnlFACB88803ousBEA4dOmTZd+nSJUGtVgvz58+v9rq372POnDnClStXBAcHB2Hz5s2CIAjCf//7X0GhUAjZ2dmV/g5u3LhhlRUZGSkoFArh999/t+ybM2eOUNm/Opw7d04AILRq1Uq4dOlSpcdiYmJE+4OCgoTmzZsLZ8+eFd5++20BgPDpp5/e8R6JiMj28XFcIiKZGjZsGFJTUzFq1ChkZmYiKioKI0aMgJubGz7//HOr8V9++SXatWuHdu3awdvbG5s3b8a0adPw9ttv10ufoqIiAEDLli1rND4pKQn9+vXD4MGDLfs0Gg2ee+45ZGdn49SpU6Lx06ZNE72IZ8iQIcCtR3rri7OzM06ePImff/65xuckJSUBAF5++WXR/tsvgfr748U9evSwdMetR4d1Ol2t7qN169bw9fXF9u3bAQDbtm3DoEGD0KlTp0rHN2vWzPKfr1+/jry8PAwaNAiCIODYsWM1vm5AQADatWtXo7Hr1q2Dk5MTxo0bh8WLF2Py5Mmiz7ASEZF8cRJKRCRjffv2xSeffAKTyYT09HRERETg6tWrGDdunNUkrn///ti/fz/27duH1atXw9nZGSaTyeoNq3XVqlUrAMDVq1drNP7333+HTqez2u/h4WE5/lcdO3YU/Xz7MWKTyVTnzn+3YsUKFBQUoHv37vD29saCBQtw/Pjxas/5/fffYWdnZ/U2XhcXFzg7O9/xPnDrXmp7H88++yz279+P8+fP49NPP8Wzzz5b5djz589j6tSpaNOmDTQaDdq1a4fHH38cAFBYWFjja3bp0qXGY9u0aYP3338fx48fh5OTE95///0an0tERLaNk1AioibAwcEBffv2xapVq7BhwwaUlZVZPut3W9u2beHj44MRI0Zg/vz52LJlCz799FO899579dJBr9cDt7679F6o6nOmd/NNZOXl5aKfH3vsMfz666+Ijo6Gl5cXNm3ahIcffhibNm26Y1ZlL2KqTH3dx6hRo6BWqxEcHIySkhJMmDCh0nHl5eUYNmwY/vvf/yI8PByffvop9u/fb3mR0N8/01mdv66o1sQXX3wB3PqLgj/++KNW5xIRke3iJJSIqIl55JFHgFvfBVodf39/PP7441i1ahWuX79+19cdPHgwWrduje3bt1tN7irTqVMnZGVlWe0/c+aM5Xh9ad26NQoKCkT7SktLK/0dtWnTBtOmTcP27dvxv//9Dz179qz0zbq3derUCRUVFVaP8P75558oKCio1/v4q2bNmmH06NFITk7GsGHDqvxO0BMnTuDs2bNYs2YNwsPD8cwzz8DHxweurq5WY2s6ka6Jffv2YdOmTXj11VfRrl07BAcHw2w211s+ERFJFyehREQydeDAgUpXz25/RrGyR13/Ljw8HPn5+fjXv/51132aN2+O8PBwnD59GuHh4ZV227JlC9LT0wEATz31FNLT05Gammo5fv36dWzcuBGdO3dGjx497rrTbQ8++CAOHTok2rdx40aryXJ+fr7oZ41GA3d3d6uvWvmrp556Crj1dt6/Wrt2LXBrsn+vvPLKK1i6dCkWL15c5ZjbK69//fMQBKHSFfAWLVoAgNWEvbYKCgosbxhetWoVNm3ahB9//BGrVq26q1wiIrIN/IoWIiKZCgsLw40bNzBmzBjo9XqUlpbi8OHD2LlzJzp37oxp06bdMcPPzw9eXl5Yu3Yt5syZA3t7e8ux3bt3W1Yl/yo4OBgPPPBApXkLFizAyZMnsWbNGhw4cADjxo2Di4sLcnNz8emnnyI9PR2HDx8GAPzzn//E9u3b4efnhxdeeAFt2rRBXFwczp07h927d8POrv7+HnX69Ol4/vnnERAQgGHDhiEzMxNffPGF1ephjx49MHToUPTp0wdt2rTB999/j3//+9+YO3duldm9evVCcHAwNm7ciIKCAjz++ONIT09HXFwcRo8ejX/84x/1dh+VXbtXr17VjtHr9XjwwQfxyiuv4MKFC2jVqhV2795d6WdQ+/TpAwB44YUXMGLECCiVSkycOLHWvV588UXk5+fjq6++glKphK+vL6ZPn4433ngDzzzzzB07ExGRbeMklIhIplavXo2EhAQkJSVh48aNKC0tRceOHTF79mwsWrQIzs7ONcp55ZVXMHXqVGzduhVTp0617N+xY0el44cOHVrlJNTOzg7x8fF45plnsHHjRqxevRpFRUVo164dHnvsMURFRWHgwIEAgA4dOuDw4cMIDw/HBx98gJs3b6Jnz574z3/+U++rhzNmzMC5c+dgNBqxb98+DBkyBPv378eTTz4pGvfCCy/g888/x5dffomSkhJ06tQJb7zxBhYsWFBt/qZNm9C1a1fExsYiMTERLi4uiIiIwNKlS+v1PurC3t4e//nPf/DCCy8gMjISjo6OGDNmDObOnWs1GRw7dizCwsKwY8cObNmyBYIg1HoS+vnnnyM+Ph5r1qyxfE4Yt1aG9+/fj+DgYBw9elT0Fx5ERCQvCuFu3thAREREREREVAv8TCgRERERERE1GE5CiYiIiIiIqMFwEkpEREREREQNhpNQIiIiIiIiajCchBIREREREVGD4SSUiIiIiIiIGgwnoURERERERNRgVI1dgO6tm+bGbkBEREREVHOONjRDadZ7bmNXQPGxdY1doda4EkpEREREREQNhpNQIiIiIiIiajBNYhKampoKpVIJf39/0f7s7GwoFAoolUpcuHBBdCwnJwcqlQoKhQLZ2dl3vMYff/wBBwcHeHl5VXpcoVBYthYtWqBbt26YOnUqfvjhB8uYsLAweHh4VHr++fPnoVQq8fnnn9fwrmtmx7at8Bv2BPr29sakieNx4vhxZjXxLCl3YxazbKkbs+SRJeVuzJJHlpS7STVLUhR2jb/ZINtsXUtGoxFhYWE4dOgQLl68aHXczc0N8fHxon1xcXFwc3Or8TViY2MxYcIEFBUVIS0trdIxMTExyMnJwcmTJ/Hhhx/i2rVr6N+/v+XaoaGhOHPmDA4fPlxpfvv27fHUU0/VuNOd7NubhNVRkZg5ew52JCRCp9Nj1sxQ5OfnM6uJZkm5G7OYZUvdmCWPLCl3Y5Y8sqTcTapZJBOCzF29elXQaDTCmTNnhMDAQGHlypWWY+fOnRMACIsWLRK6desmOq979+7C4sWLBQDCuXPnqr1GRUWF0LVrV2Hfvn1CeHi4MGPGDKsxAITExESr/VOmTBFatmwpXLlyRRAEQXj44YeF0NBQq/wuXboI4eHhtb7/4rKqt7EB44TFS5dbfr5eUi48OniwsG79x9Wexyz5Zkm5G7OYZUvdmCWPLCl3Y5Y8sqTcrTGzbInjwy80+maLZL8SumvXLuj1euh0OhgMBkRHR+P/5oT/36hRo2AymZCSkgIASElJgclkwsiRI2t0jQMHDuDGjRvw8fGBwWDAjh07cP369Rqd+9JLL+Hq1avYv38/cGs1dNeuXaLzk5OTce7cOYSEhNTizqtXVlqK06dOYsDAQZZ9dnZ2GDBgEI5nHmNWE8yScjdmMcuWujFLHllS7sYseWRJuZtUs0g+ZD8JNRqNMBgMAABfX18UFhbi4MGDojH29vaWCSoAREdHw2AwwN7evsbXmDhxIpRKJby8vNC1a1ckJCTU6Fy9Xg/c+nwqADz77LMoKysTnR8TE4PBgweje/fuNbzrOzMVmFBeXg6tVivar9VqkZeXx6wmmCXlbsxili11Y5Y8sqTcjVnyyJJyN6lmkXzIehKalZWF9PR0BAUFAQBUKhUCAwNhNBqtxoaEhCAhIQG5ublISEiodNXR09MTGo0GGo0Gfn5+AICCggJ88sknlokuABgMhkqvUZnbq7IKhQIA4OzsjLFjx1omxEVFRdi9ezdCQ0PvmFVSUoKioiLRVlJSUqMeRERERERUS439UiIbfTGRDX0VbO0ZjUaYzWa4urpa9gmCALVajXXrxF/q6u3tDb1ej6CgIHh4eMDLywsZGRmiMUlJSSgrKwMANGvWDACwbds23Lx5E/379xddo6KiAmfPnr3j6uXp06cBAF26dLHsCw0NxZNPPolffvkFBw4cgFKpxPjx4+94v5GRkVi+fLlo32uLl2LRkmVWY1s7t4ZSqbT6QHh+fj7atm17x2sxS35ZUu7GLGbZUjdmySNLyt2YJY8sKXeTahbJh21OnWvAbDYjPj4ea9asQUZGhmXLzMyEq6srtm/fbnVOSEgIkpOTq/zsZadOneDu7g53d3fLm3ONRiPmz59vdY0hQ4ZYVjOr8+6776JVq1bw8fGx7PvHP/6BLl26ICYmBjExMZg4cSJatGhxx6yIiAgUFhaKtgXhEZWOtXdwgEcPT6QdSbXsq6ioQFpaKnr26n3HazFLfllS7sYsZtlSN2bJI0vK3Zgljywpd5NqFsmHbFdC9+zZA5PJhNDQUDg5OYmOBQQEwGg0wtfXV7R/xowZGD9+PJydnWt0jYyMDPz444/YunWr5bOdtwUFBWHFihV44403oFL936+5oKAAubm5KCkpwdmzZ/Hxxx/j008/RXx8vOiaCoUCISEhWLt2LUwmE955550a9VGr1VCr1aJ9N81Vj58cPA2LF4bD09MLXt49sWVzHIqLizF6zNgaXY9Z8suScjdmMcuWujFLHllS7sYseWRJuZtUsyTn1kfqqHZkOwk1Go3w8fGxmoDi1iQ0KioKRUVFov0qlapWjwUYjUb06NHDagIKAGPGjMHcuXORlJSEUaNGAQCmTZsGAHB0dISbmxsGDx6M9PR0PPzww1bnT506FUuXLoWnp6foUd/65Ov3FExXrmD9uveRl3cZOr0H1n+8Cdo6PBrBLHlkSbkbs5hlS92YJY8sKXdjljyypNxNqlkkDwrh799XQrJS3UooEREREZHUONrQMlmzfq80dgUUp69u7Aq1JtvPhBIREREREZH0cBJKREREREREDcaGFruJiIiIiIgkhC8mqhOuhBIREREREVGD4UooERERERFRXSi4plcX/K0RERERERFRg+EklIiIiIiIiBpMk5iEpqamQqlUwt/fX7Q/OzsbCoUCSqUSFy5cEB3LycmBSqWCQqFAdnZ2tfmCIGDjxo3o378/NBoNnJ2d8cgjj+Ddd9/FjRs3RGP/+OMPODg4wMvLyyrndp+MjAyrY0OHDsW8efNqeed3tmPbVvgNewJ9e3tj0sTxOHH8OLOaeJaUuzGLWbbUjVnyyJJyN2bJI0vK3aSaJSkKReNvNqhJTEKNRiPCwsJw6NAhXLx40eq4m5sb4uPjRfvi4uLg5uZWo/zJkydj3rx5eOaZZ3DgwAFkZGRg8eLF+Oyzz/Dll1+KxsbGxmLChAkoKipCWlraXd7Z3dm3NwmroyIxc/Yc7EhIhE6nx6yZocjPz2dWE82ScjdmMcuWujFLHllS7sYseWRJuZtUs0gmBJm7evWqoNFohDNnzgiBgYHCypUrLcfOnTsnABAWLVokdOvWTXRe9+7dhcWLFwsAhHPnzlWZv3PnTgGA8Omnn1odq6ioEAoKCkQ/d+3aVdi3b58QHh4uzJgxQzT+dp9jx45ZZT3++OPCiy++WOv7Ly6rehsbME5YvHS55efrJeXCo4MHC+vWf1ztecySb5aUuzGLWbbUjVnyyJJyN2bJI0vK3Rozy5Y4Doxo9M0WyX4ldNeuXdDr9dDpdDAYDIiOjoYgCKIxo0aNgslkQkpKCgAgJSUFJpMJI0eOvGP+1q1bodPp8Mwzz1gdUygUcHJysvx84MAB3LhxAz4+PjAYDNixYweuX79eL/dZW2WlpTh96iQGDBxk2WdnZ4cBAwbheOYxZjXBLCl3YxazbKkbs+SRJeVuzJJHlpS7STWL5EP2k1Cj0QiDwQAA8PX1RWFhIQ4ePCgaY29vb5mgAkB0dDQMBgPs7e3vmP/zzz9Dp9PVuMvEiROhVCrh5eWFrl27IiEhoU73dbdMBSaUl5dDq9WK9mu1WuTl5TGrCWZJuRuzmGVL3Zgljywpd2OWPLKk3E2qWSQfsp6EZmVlIT09HUFBQQAAlUqFwMBAGI1Gq7EhISFISEhAbm4uEhISEBISYjXG09MTGo0GGo0Gfn5+wK2XEtVEQUEBPvnkE8uEGAAMBkOlXeqqpKQERUVFoq2kpKTe8omIiIiI6C8a+6VENvpiIlVjF7iXjEYjzGYzXF1dLfsEQYBarca6detEY729vaHX6xEUFAQPDw94eXlZvaU2KSkJZWVlAIBmzZoBALp3744zZ87cscu2bdtw8+ZN9O/fX9SloqICZ8+eRffu3dGqVSsAQGFhodX5BQUFokd7KxMZGYnly5eL9r22eCkWLVlmNba1c2solUqrD4Tn5+ejbdu2d7wfZskvS8rdmMUsW+rGLHlkSbkbs+SRJeVuUs0i+ZDtSqjZbEZ8fDzWrFmDjIwMy5aZmQlXV1ds377d6pyQkBAkJydXugoKAJ06dYK7uzvc3d0tb8599tlncfbsWXz22WdW4wVBsEwojUYj5s+fb9VlyJAhlseA27Rpg7Zt2+KHH34Q5RQVFeGXX35B9+7dq73niIgIFBYWirYF4RGVjrV3cIBHD0+kHUm17KuoqEBaWip69upd7XWYJc8sKXdjFrNsqRuz5JEl5W7MkkeWlLtJNUuSFHaNv9kg2a6E7tmzByaTCaGhoVYriAEBATAajfD19RXtnzFjBsaPHw9nZ+caX2fChAlITExEUFAQFi1ahOHDh6Ndu3Y4ceIE3nnnHYSFhaFz58748ccfsXXrVuj1etH5QUFBWLFiBd544w2oVCq8/PLLWLVqFTp06IABAwYgPz8fr7/+Otq1a4exY8dW20WtVkOtVov23TRXPX5y8DQsXhgOT08veHn3xJbNcSguLsboMdVfh1nyzZJyN2Yxy5a6MUseWVLuxix5ZEm5m1SzSB5kOwk1Go3w8fGp9BHWgIAAREVFoaioSLRfpVLV+rEAhUKBbdu2YePGjYiOjsbKlSuhUqnQrVs3TJkyBSNGjMCrr76KHj16WE1AAWDMmDGYO3cukpKSMGrUKLz66qvQaDR466238Ouvv6JNmzZ49NFHceDAAcsjwPXF1+8pmK5cwfp17yMv7zJ0eg+s/3gTtHV4NIJZ8siScjdmMcuWujFLHllS7sYseWRJuZtUs0geFEJN36xDNqm6lVAiIiIiIqlxtKFlsmZDljR2BRR/u6KxK9SabT5ETERERERERDbJhv6egYiIiIiISEJs9MVAjY2/NSIiIiIiImownIQSERERERFRg+HjuERERERERHXBx3HrhL81IiIiIiIiajCchBIREREREVGD4eO4REREREREdWGnaOwGNkm2K6GpqalQKpXw9/cX7c/OzoZCoYBSqcSFCxdEx3JycqBSqaBQKJCdnV1tviAI2LhxI/r37w+NRgNnZ2c88sgjePfdd3Hjxg3LuCtXrmDevHno1KkTHBwc4OrqipCQEJw/f16UN3XqVCgUCjz//PNW15ozZw4UCgWmTp1ax99G1XZs2wq/YU+gb29vTJo4HieOH2dWE8+ScjdmMcuWujFLHllS7sYseWRJuZtUs8j2yXYSajQaERYWhkOHDuHixYtWx93c3BAfHy/aFxcXBzc3txrlT548GfPmzcMzzzyDAwcOICMjA4sXL8Znn32GL7/8Erg1AR0wYAC++uorfPTRR/jll1+wY8cO/PLLL+jbty9+++03UeYDDzyAHTt2oLi42LLv5s2b2LZtGzp27FjH30TV9u1NwuqoSMycPQc7EhKh0+kxa2Yo8vPzmdVEs6TcjVnMsqVuzJJHlpS7MUseWVLuJtUsyVHYNf5miwQZunr1qqDRaIQzZ84IgYGBwsqVKy3Hzp07JwAQFi1aJHTr1k10Xvfu3YXFixcLAIRz585Vmb9z504BgPDpp59aHauoqBAKCgoEQRCE559/XmjRooWQk5MjGnPjxg3Bzc1N8PX1tewLDg4WnnnmGcHLy0vYsmWLZf/WrVuFnj17Cs8884wQHBxc699FcVnV29iAccLipcstP18vKRceHTxYWLf+42rPY5Z8s6TcjVnMsqVuzJJHlpS7MUseWVLu1phZtsTxH280+lZT69evF7y9vYWWLVsKLVu2FAYMGCAkJSVZjhcXFwuzZ88W2rRpI7Ro0UIYO3askJubK8r4/fffhaeeekpo1qyZ0K5dO+GVV14Ryspq/4dmo1Pn6u3atQt6vR46nQ4GgwHR0dEQBEE0ZtSoUTCZTEhJSQEApKSkwGQyYeTIkXfM37p1K3Q6HZ555hmrYwqFAk5OTqioqMCOHTswadIkuLi4iMY0a9YMs2fPxhdffIErV66IjoWEhCAmJsbyc3R0NKZNm1br38GdlJWW4vSpkxgwcJBln52dHQYMGITjmceY1QSzpNyNWcyypW7MkkeWlLsxSx5ZUu4m1Sy6O/fffz/efPNN/PDDD/j+++/xxBNP4JlnnsHJkycBAC+99BL+85//ICEhAQcPHsTFixcxduxYy/nl5eXw9/dHaWkpDh8+jLi4OMTGxmLJkiW17iLLSajRaITBYAAA+Pr6orCwEAcPHhSNsbe3t0xQcWuyZzAYYG9vf8f8n3/+GTqdrtoxly9fRkFBATw8PCo97uHhAUEQ8Msvv4j2GwwGpKSk4Pfff8fvv/+O7777znIv9clUYEJ5eTm0Wq1ov1arRV5eHrOaYJaUuzGLWbbUjVnyyJJyN2bJI0vK3aSaJUkKReNvNTRy5Eg89dRT6NatG7p3746VK1dCo9HgyJEjKCwshNFoxNq1a/HEE0+gT58+iImJweHDh3HkyBEAwJdffolTp05hy5YteOihh+Dn54fXX38dH374IUpLS2v1a5PdJDQrKwvp6ekICgoCAKhUKgQGBsJoNFqNDQkJQUJCAnJzc5GQkICQkBCrMZ6entBoNNBoNPDz8wNuvZSopmozFgDatWsHf39/xMbGIiYmBv7+/mjbtm2Nzi0pKUFRUZFoKykpqdX1iYiIiIhI3srLy7Fjxw5cv34dAwcOxA8//ICysjL4+PhYxuj1enTs2BGpqanArRe/ent7o0OHDpYxI0aMQFFRkWU1taZk9xUtRqMRZrMZrq6uln2CIECtVmPdunWisd7e3tDr9QgKCoKHhwe8vLyQkZEhGpOUlISysjLg1mO0ANC9e3ecOXOm2h7t2rWDs7MzTp8+Xenx06dPQ6FQwN3d3epYSEgI5s6dCwD48MMPa3zvkZGRWL58uWjfa4uXYtGSZVZjWzu3hlKptPpAeH5+fo0nvcySV5aUuzGLWbbUjVnyyJJyN2bJI0vK3aSaJUkSeDFQSUmJ1cKTWq2GWq22GnvixAkMHDgQN2/ehEajQWJiInr06IGMjAw4ODjA2dlZNL5Dhw7Izc0FAOTm5oomoLeP3z5WG43/W6tHZrMZ8fHxWLNmDTIyMixbZmYmXF1dsX37dqtzQkJCkJycXOkqKAB06tQJ7u7ucHd3t7w599lnn8XZs2fx2WefWY0XBAGFhYWws7PDhAkTsG3bNqs/lOLiYqxfvx4jRoxAmzZtrDJ8fX1RWlqKsrIyjBgxosb3HxERgcLCQtG2IDyi0rH2Dg7w6OGJtCOpln0VFRVIS0tFz169a3xNZsknS8rdmMUsW+rGLHlkSbkbs+SRJeVuUs2iykVGRsLJyUm0RUZGVjpWp9MhIyMDaWlpmDVrFoKDg3Hq1KkG7yyrldA9e/bAZDIhNDQUTk5OomMBAQEwGo3w9fUV7Z8xYwbGjx9vNeuvzoQJE5CYmIigoCAsWrQIw4cPR7t27XDixAm88847CAsLw+jRo7Fq1Sp8/fXXGDZsGKKiouDl5YVz585h0aJFKCsrq3KVU6lUWlZQlUpljXtV9jceN81Vj58cPA2LF4bD09MLXt49sWVzHIqLizF6zNiqT2KWrLOk3I1ZzLKlbsySR5aUuzFLHllS7ibVLLIWERGBl19+WbSvslVQAHBwcLA8idmnTx8cPXoU7733HgIDA1FaWoqCggLRvOjPP/+0vGTVxcUF6enporw///zTcqw2ZDUJNRqN8PHxsZqA4tYkNCoqCkVFRaL9KpWq1o8CKBQKbNu2DRs3bkR0dDRWrlwJlUqFbt26YcqUKZbVS61WiyNHjmDFihWYOXMmcnNz0aZNG/j5+WHLli3Vfvdnq1atatWpLnz9noLpyhWsX/c+8vIuQ6f3wPqPN0Fbh0cjmCWPLCl3YxazbKkbs+SRJeVuzJJHlpS7STVLcmrxYqB7papHb2uioqICJSUl6NOnD+zt7fH1118jICAAuPWunfPnz2PgwIEAgIEDB2LlypW4dOkS2rdvDwDYv38/WrVqhR49etTqugqhtm/OIZtS3UooEREREZHUONrQMlmzYW81dgUU7w+v0biIiAj4+fmhY8eOuHr1KrZt24a33noLX3zxBYYNG4ZZs2YhKSkJsbGxaNWqFcLCwgAAhw8fBm69zOihhx6Cq6sroqKikJubi8mTJ2P69OlYtWpVrTrb0B8xERERERGRhEjgxUQ1denSJUyZMgU5OTlwcnJCz549LRNQAHjnnXdgZ2eHgIAAlJSUYMSIEVi/fr3lfKVSiT179mDWrFkYOHAgWrRogeDgYKxYsaLWXbgSKnNcCSUiIiIiW2JTK6HD327sCij+ckFjV6g125m6ExERERERkc2zob9nICIiIiIikhAJvJjIFnEllIiIiIiIiBoMV0KJiIiIiIjqwoZeTCQl/K0RERERERFRg2myk9DU1FQolUr4+/uL9mdnZ0OhUECpVOLChQuiYzk5OVCpVFAoFMjOzq4yOzk5GQqFAgqFAnZ2dnByckLv3r3x6quvIicnRzR22bJleOihh0Q/3z5XqVTigQcewHPPPYcrV67U273/1Y5tW+E37An07e2NSRPH48Tx48xq4llS7sYsZtlSN2bJI0vK3Zgljywpd5NqFtm+JjsJNRqNCAsLw6FDh3Dx4kWr425uboiPjxfti4uLg5ubW42vkZWVhYsXL+Lo0aMIDw/HV199BS8vL5w4caLa8zw9PZGTk4Pz588jJiYG+/btw6xZs2pxdzWzb28SVkdFYubsOdiRkAidTo9ZM0ORn5/PrCaaJeVuzGKWLXVjljyypNyNWfLIknI3qWZJjkLR+JsNapKT0GvXrmHnzp2YNWsW/P39ERsbazUmODgYMTExon0xMTEIDg6u8XXat28PFxcXdO/eHRMnTsR3332Hdu3a3XFCqVKp4OLiAjc3N/j4+GD8+PHYv39/Le6wZjbHxWDsuAkYPSYAD7q7Y9HS5XB0dMSnn+xmVhPNknI3ZjHLlroxSx5ZUu7GLHlkSbmbVLNIHprkJHTXrl3Q6/XQ6XQwGAyIjo6GIAiiMaNGjYLJZEJKSgoAICUlBSaTCSNHjqzzdZs1a4bnn38e3333HS5dulSjc7Kzs/HFF1/AwcGhztetTFlpKU6fOokBAwdZ9tnZ2WHAgEE4nnmMWU0wS8rdmMUsW+rGLHlkSbkbs+SRJeVuUs2SJIVd4282yDZb3yWj0QiDwQAA8PX1RWFhIQ4ePCgaY29vb5mgAkB0dDQMBgPs7e3v6tp6vR64NbmsyokTJ6DRaNCsWTN06dIFJ0+eRHh4+F1d9+9MBSaUl5dDq9WK9mu1WuTl5TGrCWZJuRuzmGVL3Zgljywpd2OWPLKk3E2qWSQfTW4SmpWVhfT0dAQFBQG3Hn0NDAyE0Wi0GhsSEoKEhATk5uYiISEBISEhVmM8PT2h0Wig0Wjg5+d3x+vfXnFVVPP8tk6nQ0ZGhuWzpCNGjEBYWNgds0tKSlBUVCTaSkpK7ngeERERERFRQ2lyk1Cj0Qiz2QxXV1eoVCqoVCps2LABu3fvRmFhoWist7c39Ho9goKC4OHhAS8vL6u8pKQkZGRkICMjA5s2bbrj9U+fPg0A6Ny5c5VjHBwc4O7uDi8vL7z55ptQKpVYvnz5HbMjIyPh5OQk2t5+K7LSsa2dW0OpVFp9IDw/Px9t27a947WYJb8sKXdjFrNsqRuz5JEl5W7MkkeWlLtJNUuSGvulRHwxkfSZzWbEx8djzZo1loljRkYGMjMz4erqiu3bt1udExISguTk5EpXQQGgU6dOcHd3h7u7+x3fnFtcXIyNGzfiscceQ7t27Wrce9GiRVi9enWlb/H9q4iICBQWFoq2BeERlY61d3CARw9PpB1JteyrqKhAWloqevbqXeNuzJJPlpS7MYtZttSNWfLIknI3ZskjS8rdpJpF8qFq7AINac+ePTCZTAgNDYWTk5PoWEBAAIxGI3x9fUX7Z8yYgfHjx8PZ2bnW17t06RJu3ryJq1ev4ocffkBUVBTy8vLwySef1Cpn4MCB6NmzJ1atWoV169ZVOU6tVkOtVov23TRXnTs5eBoWLwyHp6cXvLx7YsvmOBQXF2P0mLG16scs+WRJuRuzmGVL3Zgljywpd2OWPLKk3E2qWSQPTWoSajQa4ePjYzUBxa1JaFRUFIqKikT7VSpVnR8V0Ol0UCgU0Gg06Nq1K4YPH46XX34ZLi4utc566aWXMHXqVISHh+OBBx6oU5+/8/V7CqYrV7B+3fvIy7sMnd4D6z/eBG0d7pdZ8siScjdmMcuWujFLHllS7sYseWRJuZtUsyTHRt9O29gUwt+/m4RkpbqVUCIiIiIiqXG0oWWyZk9X/ZRiQyneM7exK9SaDf0RExERERERSQhXQuuEvzUiIiIiIiJqMJyEEhERERERUYPh47hERERERER1YaPf09nYuBJKREREREREDYYroURERERERHXBFxPVCX9rRERERERE1GCa9CQ0NTUVSqUS/v7+ov3Z2dlQKBRQKpW4cOGC6FhOTg5UKhUUCgWys7OrzE5OToZCoYBCoYCdnR2cnJzQu3dvvPrqq8jJyRGNXbZsGR566CHLzzdu3EBERAQefPBBODo6ol27dnj88cfx2Wef1du937Zj21b4DXsCfXt7Y9LE8Thx/DizmniWlLsxi1m21I1Z8siScjdmySNLyt2kmkW2r0lPQo1GI8LCwnDo0CFcvHjR6ribmxvi4+NF++Li4uDm5lbja2RlZeHixYs4evQowsPD8dVXX8HLywsnTpyo8pznn38en3zyCT744AOcOXMG+/btw7hx45Cfn1/LO6zevr1JWB0ViZmz52BHQiJ0Oj1mzQyt03WYJY8sKXdjFrNsqRuz5JEl5W7MkkeWlLtJNUtyFIrG32yR0ERdvXpV0Gg0wpkzZ4TAwEBh5cqVlmPnzp0TAAiLFi0SunXrJjqve/fuwuLFiwUAwrlz56rMP3DggABAMJlMov03btwQdDqd8Oijj1r2LV26VOjVq5flZycnJyE2NrZe7rO4rOptbMA4YfHS5Zafr5eUC48OHiysW/9xtecxS75ZUu7GLGbZUjdmySNLyt2YJY8sKXdrzCxb4vjMx42+2aImuxK6a9cu6PV66HQ6GAwGREdHQxAE0ZhRo0bBZDIhJSUFAJCSkgKTyYSRI0fW+brNmjXD888/j++++w6XLl2qdIyLiwuSkpJw9erVOl/nTspKS3H61EkMGDjIss/Ozg4DBgzC8cxjzGqCWVLuxixm2VI3ZskjS8rdmCWPLCl3k2qWJCnsGn+zQbbZuh4YjUYYDAYAgK+vLwoLC3Hw4EHRGHt7e8sEFQCio6NhMBhgb29/V9fW6/XArc+eVmbjxo04fPgwtFot+vbti5deegnffffdXV3z70wFJpSXl0Or1Yr2a7Va5OXlMasJZkm5G7OYZUvdmCWPLCl3Y5Y8sqTcTapZJB9NchKalZWF9PR0BAUFAQBUKhUCAwNhNBqtxoaEhCAhIQG5ublISEhASEiI1RhPT09oNBpoNBr4+fnd8fq3V1wVVTzD/dhjj+G3337D119/jXHjxuHkyZMYMmQIXn/99WpzS0pKUFRUJNpKSkru2IeIiIiIiKihNMlJqNFohNlshqurK1QqFVQqFTZs2IDdu3ejsLBQNNbb2xt6vR5BQUHw8PCAl5eXVV5SUhIyMjKQkZGBTZs23fH6p0+fBgB07ty5yjH29vYYMmQIwsPD8eWXX2LFihV4/fXXUVpaWuU5kZGRcHJyEm1vvxVZ6djWzq2hVCqtPhCen5+Ptm3b3vEemCW/LCl3YxazbKkbs+SRJeVuzJJHlpS7STVLkhr7pUQ2+mKiJjcJNZvNiI+Px5o1aywTx4yMDGRmZsLV1RXbt2+3OickJATJycmVroICQKdOneDu7g53d/c7vjm3uLgYGzduxGOPPYZ27drVuHePHj1gNptx8+bNKsdERESgsLBQtC0Ij6h0rL2DAzx6eCLtSKplX0VFBdLSUtGzV+8a92KWfLKk3I1ZzLKlbsySR5aUuzFLHllS7ibVLJIPVWMXaGh79uyByWRCaGgonJycRMcCAgJgNBrh6+sr2j9jxgyMHz8ezs7Otb7epUuXcPPmTVy9ehU//PADoqKikJeXh08++aTKc4YOHYqgoCA88sgj0Gq1OHXqFBYuXIh//OMfaNWqVZXnqdVqqNVq0b6b5qq7TQ6ehsULw+Hp6QUv757YsjkOxcXFGD1mbK3vk1nyyJJyN2Yxy5a6MUseWVLuxix5ZEm5m1SzpKaqj9dR9ZrcJNRoNMLHx8dqAopbk9CoqCgUFRWJ9qtUqjo/LqDT6aBQKKDRaNC1a1cMHz4cL7/8MlxcXKo8Z8SIEYiLi8PChQtx48YNuLq64umnn8aSJUvq1KEqvn5PwXTlCtavex95eZeh03tg/ceboK3DvTJLHllS7sYsZtlSN2bJI0vK3Zgljywpd5NqFsmDQvj795KQrFS3EkpEREREJDWONrRM1jwgurEr4Mbuyj8yKGU29EdMREREREQkHXwct26a3IuJiIiIiIiIqPFwJZSIiIiIiKguuBBaJ1wJJSIiIiIiogbDlVAiIqpXFfX8vjs7ft6GiIhIVjgJJSIiIiIiqgO+mKhu+DguERERERERNZgmNwlNTU2FUqmEv7+/aH92djYUCgWUSiUuXLggOpaTkwOVSgWFQoHs7Owqs5OTk6FQKCrdcnNzAQCBgYHo168fysvLLeeVlZWhT58+mDRpEqZOnVplhkKhQOfOnev197Fj21b4DXsCfXt7Y9LE8Thx/DizmniWlLsxy/azdu3YjgljRmFw/z4Y3L8PpkwKRMq3h+rcqz67MYtZttaNWfLIknI3qWaR7Wtyk1Cj0YiwsDAcOnQIFy9etDru5uaG+Ph40b64uDi4ubnV+BpZWVnIyckRbe3btwcArF+/HufPn8ebb75pGf/6668jJycH69atw3vvvSc6DwBiYmIsPx89evQu7l5s394krI6KxMzZc7AjIRE6nR6zZoYiPz+fWU00S8rdmCWPrA4uHRD20nxs3bUbW3f+G/36DcBLYXPw6y8/1zqrvrsxi1m21I1Z8siScjepZklNdYtHDbXZJKEJuXr1qqDRaIQzZ84IgYGBwsqVKy3Hzp07JwAQFi1aJHTr1k10Xvfu3YXFixcLAIRz585VmX/gwAEBgGAymart8dlnnwkODg5CZmamcPToUUGlUgn//e9/Kx0LQEhMTKz1vd5WXFb1NjZgnLB46XLLz9dLyoVHBw8W1q3/uNrzmCXfLCl3Y5btZF0vrajV9sgjfYUt23dVeVyq98ks+WdJuRuz5JEl5W6NmWVLNBNiG32zRU1qJXTXrl3Q6/XQ6XQwGAyIjo6G8Le3OI4aNQomkwkpKSkAgJSUFJhMJowcObLeeowaNQoTJ07ElClTEBwcjODgYDz11FP1ll8TZaWlOH3qJAYMHGTZZ2dnhwEDBuF45jFmNcEsKXdjljyy/q68vBz7kv6L4uIb6PnQQ7U+X6r3ySx5ZEm5G7PkkSXlblLNkqLGXgW11ZXQJjUJNRqNMBgMAABfX18UFhbi4MGDojH29vaWCSoAREdHw2AwwN7evsbXuf/++6HRaCybp6en1Zh3330XZ8+eRX5+PtauXXvX91ZbpgITysvLodVqRfu1Wi3y8vKY1QSzpNyNWfLIuu3ns1kY1Pdh9H+4J1a+vgxr3luHBx90r3WOVO+TWfLIknI3ZskjS8rdpJpF8tFkvqIlKysL6enpSExMBACoVCoEBgbCaDRi6NChorEhISEYNGgQVq1ahYSEBKSmpsJsNovGeHp64vfffwcADBkyBHv37rUc+/bbb9GyZUvLz5VNYLdv3w6FQoG8vDycOXMG/fr1u+t7LCkpQUlJiWifoFRDrVbfdTYRUX3p3KULduxOxLWrV/HVl19gyWv/xKbYzXWaiBIREZHtaTKTUKPRCLPZDFdXV8s+QRCgVquxbt060Vhvb2/o9XoEBQXBw8MDXl5eyMjIEI1JSkpCWVkZAKBZs2aiY126dIGzs3OVXX777Te8+uqr2LBhAw4cOICpU6fi2LFjdz1ZjIyMxPLly0X7Xlu8FIuWLLMa29q5NZRKpdUHwvPz89G2bdtaXZdZ8siScjdmySPrNnt7B3Ts2AkA0MPTCydP/oTtW+KxaOmKRuvGLGbZUjdmySNLyt2kmiVFtvo4bGNrEo/jms1mxMfHY82aNcjIyLBsmZmZcHV1xfbt263OCQkJQXJyMkJCQirN7NSpE9zd3eHu7l6rN+dWVFRg6tSpePLJJzFlyhS8++67uHr1KpYsWXJX9wgAERERKCwsFG0LwiMqHWvv4ACPHp5IO5Iq6paWloqevXrX6rrMkkeWlLsxSx5ZVREqKlBaWlrr86R6n8ySR5aUuzFLHllS7ibVLJKPJrESumfPHphMJoSGhsLJyUl0LCAgAEajEb6+vqL9M2bMwPjx46td0azKpUuXcPPmTdE+rVYLe3t7vPfeezh58iROnjwJAHBycsKmTZvw9NNPIyAg4K4ey1WrrR+9vWmucjgmB0/D4oXh8PT0gpd3T2zZHIfi4mKMHjO21tdmljyypNyNWfLIev+dNXh0yGO47777cP36dez97x58fzQd6z/eVOus+u7GLGbZUjdmySNLyt2kmiU5XAitkyYxCTUajfDx8bGagOLWJDQqKgpFRUWi/SqVqs6PCOh0Oqt9qampaNOmDV577TVs2rQJLi4ulmMjRozAtGnT6u2x3Jry9XsKpitXsH7d+8jLuwyd3gPrP94EbR3um1nyyJJyN2bJI+vKlStYvDAceZcvQ9OyJbp112H9x5swYNCjtc6q727MYpYtdWOWPLKk3E2qWSQPCuHv31FCslLdSigR0b1QUc//WLHj522IiJoURxtaJnN6dnNjV0DhtsmNXaHWbOiPmIiIiIiISDr4YqK6aRIvJiIiIiIiIiJp4EooERERERFRHXAltG64EkpEREREREQNhiuhRERUr/giISIiIqoOJ6FERERERER1wMdx64aP4xIREREREVGDaTKT0NTUVCiVSvj7+4v2Z2dnQ6FQQKlU4sKFC6JjOTk5UKlUUCgUyM7OrjI7OTkZCoXCalu0aFGlx9u1a4ennnoKJ06csMr63//+h5CQELi6usLBwQGdOnXCiy++iPz8/Hr7XfzVjm1b4TfsCfTt7Y1JE8fjxPHjzGriWVLuxixm2VI3ZskjS8rdmCWPLCl3k2qWlFQ2B2jozRY1mUmo0WhEWFgYDh06hIsXL1odd3NzQ3x8vGhfXFwc3NzcanyNrKws5OTkWLZ//vOflR7/4osvUFJSAn9/f5SWllqO//bbb3jkkUfw888/Y/v27fjll1/w0Ucf4euvv8bAgQNx5cqVOt17VfbtTcLqqEjMnD0HOxISodPpMWtmaJ0mvMySR5aUuzGLWbbUjVnyyJJyN2bJI0vK3aSaRfLQJCah165dw86dOzFr1iz4+/sjNjbWakxwcDBiYmJE+2JiYhAcHFzj67Rv3x4uLi6WTaPRVHr84Ycfxrx58/C///0PZ86csRyfM2cOHBwc8OWXX+Lxxx9Hx44d4efnh6+++goXLlzAa6+9Vqf7r8rmuBiMHTcBo8cE4EF3dyxauhyOjo749JPdzGqiWVLuxixm2VI3ZskjS8rdmCWPLCl3k2oWyUOTmITu2rULer0eOp0OBoMB0dHREARBNGbUqFEwmUxISUkBAKSkpMBkMmHkyJH13qewsBA7duwAADg4OAAArly5gi+++AKzZ89Gs2bNRONdXFwwadIk7Ny506p3XZWVluL0qZMYMHCQZZ+dnR0GDBiE45nHmNUEs6TcjVnMsqVuzJJHlpS7MUseWVLuJtUsSVJIYLNBTWISajQaYTAYAAC+vr4oLCzEwYMHRWPs7e0tE1QAiI6OhsFggL29fY2vc//990Oj0Vi2vz9icPu4s7Mztm3bhlGjRkGv1wMAfv75ZwiCAA8Pj0qzPTw8YDKZcPny5Vrff2VMBSaUl5dDq9WK9mu1WuTl5TGrCWZJuRuzmGVL3Zgljywpd2OWPLKk3E2qWSQfsv+KlqysLKSnpyMxMREAoFKpEBgYCKPRiKFDh4rGhoSEYNCgQVi1ahUSEhKQmpoKs9ksGuPp6Ynff/8dADBkyBDs3bvXcuzbb79Fy5YtLT+3bt1adO63336L5s2b48iRI1i1ahU++ugjq753Wum8vXJamZKSEpSUlIjzlGqo1epqM4mIiIiIqPZs9cVAjU32k1Cj0Qiz2QxXV1fLPkEQoFarsW7dOtFYb29v6PV6BAUFwcPDA15eXsjIyBCNSUpKQllZGQBYPTbbpUsXODs7V9nl9nGdTodLly4hMDAQhw4dAgC4u7tDoVDg9OnTGDNmjNW5p0+fRrt27arNj4yMxPLly0X7Xlu8FIuWLLMa29q5NZRKpdVqbX5+Ptq2bVvlNSrDLHlkSbkbs5hlS92YJY8sKXdjljyypNxNqlkkH7J+HNdsNiM+Ph5r1qxBRkaGZcvMzISrqyu2b99udU5ISAiSk5MREhJSaWanTp3g7u4Od3f3Wr059+/mzJmDn376ybJCq9VqMWzYMKxfvx7FxcWisbm5udi6dSumTp1abWZERAQKCwtF24LwiErH2js4wKOHJ9KOpFr2VVRUIC0tFT179a7VvTBLHllS7sYsZtlSN2bJI0vK3Zgljywpd5NqFsmHrFdC9+zZA5PJhNDQUDg5OYmOBQQEwGg0wtfXV7R/xowZGD9+fLUrjvWhefPmmDFjBpYuXYrRo0dDoVBg3bp1GDRoEEaMGIE33ngDXbp0wcmTJ7FgwQJ0794dS5YsqTZTrbZ+9PamucrhmBw8DYsXhsPT0wte3j2xZXMciouLMXrM2FrfD7PkkSXlbsxili11Y5Y8sqTcjVnyyJJyN6lmSQ0fx60bWU9CjUYjfHx8rCaguDUJjYqKQlFRkWi/SqVqsEcD5s6di7Vr1yIhIQETJkxAt27dcPToUSxbtgwTJkzApUuXIAgCxo4di82bN6N58+b1en1fv6dgunIF69e9j7y8y9DpPbD+403Q1uH+mSWPLCl3YxazbKkbs+SRJeVuzJJHlpS7STWL5EEh1Nd3ftA9sXTpUqxduxb79+/HgAEDan1+dSuhRERERERS42hDy2Ttpu1s7Aq4HBPY2BVqzYb+iJum5cuXo3Pnzjhy5Aj69esHOztZf4yXiIiIiMhm8HHcuuEk1AZMmzatsSsQERERERHVC05CiYiIiIiI6oILoXXCZzuJiIiIiIiowXASSkRERERERA2Gj+MSERERERHVAV9MVDdcCSUiIiIiIqIG06QmoampqVAqlfD39xftz87OhkKhgFKpxIULF0THcnJyoFKpoFAokJ2dXWV2cnIyFAoFCgoKqhyzZ88ePP7442jZsiWaN2+Ovn37IjY2ttKxu3fvxtChQ+Hk5ASNRoOePXtixYoVuHLlSq3vuzo7tm2F37An0Le3NyZNHI8Tx48zq4lnSbkbs5hlS92YJY8sKXdjljyypNxNqllSolAoGn2zRU1qEmo0GhEWFoZDhw7h4sWLVsfd3NwQHx8v2hcXFwc3N7e7vvYHH3yAZ555Bo8++ijS0tJw/PhxTJw4Ec8//zxeeeUV0djXXnsNgYGB6Nu3L/bu3YuffvoJa9asQWZmJjZv3nzXXW7btzcJq6MiMXP2HOxISIROp8esmaHIz89nVhPNknI3ZjHLlroxSx5ZUu7GLHlkSbmbVLNIJoQm4urVq4JGoxHOnDkjBAYGCitXrrQcO3funABAWLRokdCtWzfRed27dxcWL14sABDOnTtXZf6BAwcEAILJZLI6dv78ecHe3l54+eWXrY69//77AgDhyJEjgiAIQlpamgBAePfddyu9TmX51Skuq3obGzBOWLx0ueXn6yXlwqODBwvr1n9c7XnMkm+WlLsxi1m21I1Z8siScjdmySNLyt0aM8uWdJie0OibLWoyK6G7du2CXq+HTqeDwWBAdHQ0BEEQjRk1ahRMJhNSUlIAACkpKTCZTBg5cuRdXfvf//43ysrKrFY8AWDmzJnQaDTYvn07AGDr1q3QaDSYPXt2pVnOzs531eW2stJSnD51EgMGDrLss7Ozw4ABg3A88xizmmCWlLsxi1m21I1Z8siScjdmySNLyt2kmiVFjf0oLh/HlTij0QiDwQAA8PX1RWFhIQ4ePCgaY29vb5mgAkB0dDQMBgPs7e3v6tpnz56Fk5MT7rvvPqtjDg4O6Nq1K86ePQsA+Pnnn9G1a9e7vuadmApMKC8vh1arFe3XarXIy8tjVhPMknI3ZjHLlroxSx5ZUu7GLHlkSbmbVLNIPprEJDQrKwvp6ekICgoCAKhUKgQGBsJoNFqNDQkJQUJCAnJzc5GQkICQkBCrMZ6entBoNNBoNPDz86vXrn9fna2NkpISFBUVibaSkpJ67UdERERERP+nsVdBuRIqYUajEWazGa6urlCpVFCpVNiwYQN2796NwsJC0Vhvb2/o9XoEBQXBw8MDXl5eVnlJSUnIyMhARkYGNm3adMfrd+/eHYWFhZW+DKm0tBS//vorunfvbhn722+/oaysrNb3GRkZCScnJ9H29luRlY5t7dwaSqXS6gPh+fn5aNu2ba2uyyx5ZEm5G7OYZUvdmCWPLCl3Y5Y8sqTcTapZJB+yn4SazWbEx8djzZo1loljRkYGMjMz4erqavks5l+FhIQgOTm50lVQAOjUqRPc3d3h7u5eozfnBgQEwN7eHmvWrLE69tFHH+H69euWVdpnn30W165dw/r16yvNqu4rYCIiIlBYWCjaFoRHVDrW3sEBHj08kXYk1bKvoqICaWmp6Nmr9x3viVnyy5JyN2Yxy5a6MUseWVLuxix5ZEm5m1SzSD5UjV3gXtuzZw9MJhNCQ0Ph5OQkOhYQEACj0QhfX1/R/hkzZmD8+PF1egnQiRMn0LJlS8vPCoUCvXr1QlRUFObPnw9HR0dMnjwZ9vb2+Oyzz7Bw4ULMnz8f/fv3BwD0798fr776KubPn48LFy5gzJgxcHV1xS+//IKPPvoIgwcPxosvvljptdVqNdRqtWjfTXPVXScHT8PiheHw9PSCl3dPbNkch+LiYoweM7bW980seWRJuRuzmGVL3Zgljywpd2OWPLKk3E2qWZJjm0/DNjrZT0KNRiN8fHysJqC4NQmNiopCUVGRaL9Kparz4wGPPfaY6GelUgmz2Yx58+aha9euWL16Nd577z2Ul5fD09MTGzZswLRp00TnvPXWW+jTpw8+/PBDfPTRR6ioqMCDDz6IcePGITg4uE69KuPr9xRMV65g/br3kZd3GTq9B9Z/vAnaOtw7s+SRJeVuzGKWLXVjljyypNyNWfLIknI3qWaRPCiEu3kTDkledSuhRERERERS42hDy2RusxIbuwIubBjT2BVqTfafCSUiIiIiIiLp4CSUiIiIiIiIGgwnoURERERERHXQ2N8RWpvvCY2MjETfvn3RsmVLtG/fHqNHj0ZWVpZozNChQ63yn3/+edGY8+fPw9/fH82bN0f79u2xYMECmM21+wygDT1xTURERERERHVx8OBBzJkzB3379oXZbMbChQsxfPhwnDp1Ci1atLCMmzFjBlasWGH5uXnz5pb/XF5eDn9/f7i4uODw4cPIycnBlClTYG9vj1WrVtW4CyehREREREREdVCblcjGtm/fPtHPsbGxaN++PX744QfRN3w0b94cLi4ulWZ8+eWXOHXqFL766it06NABDz30EF5//XWEh4dj2bJlcHBwqFEXPo5LRERERETUxBQWFgIA2rRpI9q/detWtG3bFl5eXoiIiMCNGzcsx1JTU+Ht7Y0OHTpY9o0YMQJFRUU4efJkja/NlVAiIiIiIiIbVVJSgpKSEtE+tVoNtVpd5TkVFRWYN28eHn30UXh5eVn2P/vss+jUqRNcXV1x/PhxhIeHIysrC5988gkAIDc3VzQBBWD5OTc3t8adZb0SmpqaCqVSCX9/f9H+7OxsKBQKKJVKXLhwQXQsJycHKpUKCoUC2dnZVWYnJydDoVCgdevWuHnzpujY0aNHrT4ofHu8p6cnysvLReOdnZ0RGxtr+blz586W85s3bw5vb29s2rSpzr+H6uzYthV+w55A397emDRxPE4cP86sJp4l5W7Msv2sH74/irDZz8Nn6GD08tThm6+/qnOn+u7GLGbZWjdmySNLyt2kmiUpisbfIiMj4eTkJNoiIyOrrT1nzhz89NNP2LFjh2j/c889hxEjRsDb2xuTJk1CfHw8EhMT8euvv9brr03Wk1Cj0YiwsDAcOnQIFy9etDru5uaG+Ph40b64uDi4ubnV+BotW7ZEYqL4S2qNRiM6duxY6fjffvvN6pqVWbFiBXJycvDTTz/BYDBgxowZ2Lt3b4171cS+vUlYHRWJmbPnYEdCInQ6PWbNDEV+fj6zmmiWlLsxSx5ZxcU3oNPpELFoaa3PvdfdmMUsW+rGLHlkSbmbVLPIWkREBAoLC0VbRERElePnzp2LPXv24MCBA7j//vurze7fvz8A4JdffgEAuLi44M8//xSNuf1zVZ8jrYxsJ6HXrl3Dzp07MWvWLPj7+4tWGm8LDg5GTEyMaF9MTAyCg4NrfJ3g4GBER0dbfi4uLsaOHTuqzAgLC8PSpUutlsz/rmXLlnBxcUHXrl0RHh6ONm3aYP/+/TXuVROb42IwdtwEjB4TgAfd3bFo6XI4Ojri0092M6uJZkm5G7PkkTV4yOOY++JLeNJnWK3PvdfdmMUsW+rGLHlkSbmbVLPImlqtRqtWrURbZY/iCoKAuXPnIjExEd988w26dOlyx+yMjAwAwH333QcAGDhwIE6cOIFLly5Zxuzfvx+tWrVCjx49atxZtpPQXbt2Qa/XQ6fTwWAwIDo6GoIgiMaMGjUKJpMJKSkpAICUlBSYTCaMHDmyxteZPHkyvv32W5w/fx4AsHv3bnTu3BkPP/xwpePnzZsHs9mMDz74oEb5FRUV2L17N0wmU43fNlUTZaWlOH3qJAYMHGTZZ2dnhwEDBuF45jFmNcEsKXdjljyy6ptU75NZ8siScjdmySNLyt2kmiVFjf0dobV5O++cOXOwZcsWbNu2DS1btkRubi5yc3NRXFwMAPj111/x+uuv44cffkB2djY+//xzTJkyBY899hh69uwJABg+fDh69OiByZMnIzMzE1988QUWLVqEOXPmVPsZ1L+T7STUaDTCYDAAAHx9fVFYWIiDBw+Kxtjb21smqAAQHR0Ng8EAe3v7Gl+nffv28PPzs6y0RkdHIyQkpMrxzZs3x9KlSxEZGWl5I1VlwsPDodFooFarMW7cOLRu3RrTp0+vca87MRWYUF5eDq1WK9qv1WqRl5fHrCaYJeVuzJJHVn2T6n0ySx5ZUu7GLHlkSbmbVLPo7mzYsAGFhYUYOnQo7rvvPsu2c+dOAICDgwO++uorDB8+HHq9HvPnz0dAQAD+85//WDKUSiX27NkDpVKJgQMHwmAwYMqUKaLvFa0JWU5Cs7KykJ6ejqCgIACASqVCYGAgjEaj1diQkBAkJCQgNzcXCQkJlU4gPT09odFooNFo4OfnV2lGbGwsfvvtN6SmpmLSpEnV9gsNDYVWq8Vbb71V5ZgFCxYgIyMD33zzDfr374933nkH7u7u1eaWlJSgqKhItN3psV8iIiIiIqqbxl4Frc1KqCAIlW5Tp04FADzwwAM4ePAg8vPzcfPmTfz888+IiopCq1atRDmdOnVCUlISbty4gcuXL2P16tVQqWr3pSuynIQajUaYzWa4urpCpVJBpVJhw4YN2L17t9Xqo7e3N/R6PYKCguDh4SF6RfFtSUlJyMjIQEZGRqVvqfXz80NxcTFCQ0MxcuRIq7/p+TuVSoWVK1fivffeq/SFSQDQtm1buLu7Y8iQIUhISMALL7yAU6dOVZtb2Zux3n6r8jdjtXZuDaVSafWB8Pz8fLRt27ba6zBLnllS7sYseWTVN6neJ7PkkSXlbsySR5aUu0k1i+RDdpNQs9mM+Ph4rFmzxjJxzMjIQGZmJlxdXbF9+3arc0JCQpCcnFzlY7SdOnWCu7s73N3dK31zrkqlwpQpU6rN+Lvx48fD09MTy5cvv+PYBx54AIGBgdW+5QpVvBlrQXjl59g7OMCjhyfSjqRa9lVUVCAtLRU9e/Wu0T0wS15ZUu7GLHlk1Tep3iez5JEl5W7MkkeWlLtJNYvko3brpjZgz549MJlMCA0NhZOTk+hYQEAAjEYjfH19RftnzJiB8ePHw9nZuc7Xff3117FgwYI7roL+1ZtvvokRI0bUaOyLL74ILy8vfP/993jkkUcqHVPZl9LeNFedOTl4GhYvDIenpxe8vHtiy+Y4FBcXY/SYsTW+B2bJK0vK3Zglj6wb169bXuQGABf++ANnTp+Gk5MT7nN1bdRuzGKWLXVjljyypNxNqllSU5vHYen/k90k1Gg0wsfHx2oCiluT0KioKBQVFYn2q1Squ34cwMHBodYZTzzxBJ544gl8+eWXdxzbo0cPDB8+HEuWLEFSUtJdNP3/fP2egunKFaxf9z7y8i5Dp/fA+o83QVuH3wWz5JEl5W7MkkfWyZM/Yfq0KZafV0f930cGRj0zBq+verNRuzGLWbbUjVnyyJJyN6lmkTwohL9/bwnJSnUroUREREREUuNoQ8tkXeb9t7Er4Ny7/o1dodZk95lQIiIiIiIiki5OQomIiIiIiKjB2NBiNxERERERkYTwvUR1wpVQIiIiIiIiajBcCSUiIiIiIqoDfkVL3XAllIiIiIiIiBoMJ6FERERERETUYGQ5CU1NTYVSqYS/v/g7c7Kzs6FQKKBUKnHhwgXRsZycHKhUKigUCmRnZ1eZnZycDIVCgdatW+PmzZuiY0ePHoVCobBali8vL8c777wDb29vODo6onXr1vDz88N3330nGhcbG2s5X6lUonXr1ujfvz9WrFiBwsLCu/iNVG3Htq3wG/YE+vb2xqSJ43Hi+HFmNfEsKXdjFrNsqRuz5JEl5W7MkkeWlLtJNUtKbv+7e2NutkiWk1Cj0YiwsDAcOnQIFy9etDru5uaG+Ph40b64uDi4ubnV+BotW7ZEYmKi1XU7duwo2icIAiZOnIgVK1bgxRdfxOnTp5GcnIwHHngAQ4cOxaeffioa36pVK+Tk5OCPP/7A4cOH8dxzzyE+Ph4PPfRQpfdyN/btTcLqqEjMnD0HOxISodPpMWtmKPLz85nVRLOk3I1ZzLKlbsySR5aUuzFLHllS7ibVLJIH2U1Cr127hp07d2LWrFnw9/dHbGys1Zjg4GDExMSI9sXExCA4OLjG1wkODkZ0dLTl5+LiYuzYscMqY9euXfj3v/+N+Ph4TJ8+HV26dEGvXr2wceNGjBo1CtOnT8f169ct4xUKBVxcXHDffffBw8MDoaGhOHz4MK5du4ZXX321lr+N6m2Oi8HYcRMwekwAHnR3x6Kly+Ho6IhPP9nNrCaaJeVuzGKWLXVjljyypNyNWfLIknI3qWZJjULR+Jstkt0kdNeuXdDr9dDpdDAYDIiOjoYgCKIxo0aNgslkQkpKCgAgJSUFJpMJI0eOrPF1Jk+ejG+//Rbnz58HAOzevRudO3fGww8/LBq3bds2dO/evdLs+fPnIz8/H/v376/2Wu3bt8ekSZPw+eefo7y8vMYdq1NWWorTp05iwMBBln12dnYYMGAQjmceY1YTzJJyN2Yxy5a6MUseWVLuxix5ZEm5m1SzSD5kNwk1Go0wGAwAAF9fXxQWFuLgwYOiMfb29pYJKgBER0fDYDDA3t6+xtdp3749/Pz8LCut0dHRCAkJsRp39uxZeHh4VJpxe//Zs2fveD29Xo+rV6/W22MLpgITysvLodVqRfu1Wi3y8vKY1QSzpNyNWcyypW7MkkeWlLsxSx5ZUu4m1SySD1lNQrOyspCeno6goCAAgEqlQmBgIIxGo9XYkJAQJCQkIDc3FwkJCZVOID09PaHRaKDRaODn51dpRmxsLH777TekpqZi0qRJlfb6+0psXdzOqO7DxyUlJSgqKhJtJSUld31tIiIiIiKy1tgvJeKLiSTAaDTCbDbD1dUVKpUKKpUKGzZswO7du63eLuvt7Q29Xo+goCB4eHjAy8vLKi8pKQkZGRnIyMjApk2brI77+fmhuLgYoaGhGDlypNXf8ABA9+7dcfr06Ur73t7fvXv3O97b6dOn0apVq0qvcVtkZCScnJxE29tvRVY6trVzayiVSquV1fz8fLRt2/aOfZglvywpd2MWs2ypG7PkkSXlbsySR5aUu0k1i+RDNpNQs9mM+Ph4rFmzxjJxzMjIQGZmJlxdXbF9+3arc0JCQpCcnFzpKigAdOrUCe7u7nB3d6/0zbkqlQpTpkypNmPixIn4+eef8Z///Mfq2Jo1a6DVajFs2LBq7+3SpUvYtm0bRo8eDTu7qv/IIiIiUFhYKNoWhEdUOtbewQEePTyRdiTVsq+iogJpaano2at3tX2YJc8sKXdjFrNsqRuz5JEl5W7MkkeWlLtJNUuKGvulRDa6EApVYxeoL3v27IHJZEJoaCicnJxExwICAmA0GuHr6yvaP2PGDIwfPx7Ozs51vu7rr7+OBQsWVLlCOXHiRCQkJCA4OBhvv/02nnzySRQVFeHDDz/E559/joSEBLRo0cIyXhAE5ObmQhAEFBQUIDU1FatWrYKTkxPefPPNaruo1Wqo1WrRvpvmqsdPDp6GxQvD4enpBS/vntiyOQ7FxcUYPWZsbX8NzJJJlpS7MYtZttSNWfLIknI3ZskjS8rdpJpF8iCbSajRaISPj4/VBBS3JqFRUVEoKioS7VepVHf9GICDg0O1GQqFArt27cK7776Ld955B7Nnz4ajoyMGDhyI5ORkPProo6LxRUVFuO+++6BQKNCqVSvodDoEBwfjxRdfRKtWre6q69/5+j0F05UrWL/ufeTlXYZO74H1H2+Ctg6/E2bJI0vK3ZjFLFvqxix5ZEm5G7PkkSXlblLNInlQCPXx1hySrOpWQomIiIiIpMbRhpbJdOFfNHYFZL01orEr1JpsPhNKRERERERE0sdJKBERERERETUYG1rsJiIiIiIikg5bfTttY+NKKBERERERETUYroQSERERERHVgZ0dl0LrgiuhRERERERE1GA4CSUiIiIiIqIG0yQmoampqVAqlfD39xftz87OhkKhgFKpxIULF0THcnJyoFKpoFAokJ2dXWV2cnIyFAoFPD09UV5eLjrm7OyM2NhYy8+dO3eGQqGw2t58803Rebt378YTTzyB1q1bo1mzZtDpdAgJCcGxY8fu8jdhbce2rfAb9gT69vbGpInjceL4cWY18Swpd2OW7Wf98P1RhM1+Hj5DB6OXpw7ffP1VnTvVdzdmMcvWujFLHllS7ibVLClRKBp/s0VNYhJqNBoRFhaGQ4cO4eLFi1bH3dzcEB8fL9oXFxcHNze3Gl/jt99+s8qozIoVK5CTkyPawsLCLMfDw8MRGBiIhx56CJ9//jmysrKwbds2dO3aFRERETXuUxP79iZhdVQkZs6egx0JidDp9Jg1MxT5+fnMaqJZUu7GLHlkFRffgE6nQ8SipbU+9153YxazbKkbs+SRJeVuUs0ieZD9JPTatWvYuXMnZs2aBX9/f9HK5G3BwcGIiYkR7YuJiUFwcHCNrxMWFoalS5eipKSk2nEtW7aEi4uLaGvRogUA4MiRI4iKisLatWuxdu1aDBkyBB07dkSfPn2waNEi7N27t8Z9amJzXAzGjpuA0WMC8KC7OxYtXQ5HR0d8+sluZjXRLCl3Y5Y8sgYPeRxzX3wJT/oMq/W597obs5hlS92YJY8sKXeTapbUVPaUY0Nvtkj2k9Bdu3ZBr9dDp9PBYDAgOjoagiCIxowaNQomkwkpKSkAgJSUFJhMJowcObLG15k3bx7MZjM++OCDOnfdvn07NBoNZs+eXenx+vwvWVlpKU6fOokBAwdZ9tnZ2WHAgEE4nlm7x36ZJY8sKXdjljyy6ptU75NZ8siScjdmySNLyt2kmkXyIftJqNFohMFgAAD4+vqisLAQBw8eFI2xt7e3TFABIDo6GgaDAfb29jW+TvPmzbF06VJERkaisLCwynHh4eHQaDSi7dtvvwUAnD17Fl27doVK9f+/OWft2rWisdVl14apwITy8nJotVrRfq1Wi7y8PGY1wSwpd2OWPLLqm1Tvk1nyyJJyN2bJI0vK3aSaRfIh60loVlYW0tPTERQUBABQqVQIDAyE0Wi0GhsSEoKEhATk5uYiISEBISEhVmM8PT0tk0E/Pz+r46GhodBqtXjrrbeq7LRgwQJkZGSItkceeaTK8SEhIcjIyMDHH3+M69evW63i/lVJSQmKiopE250eDyYiIiIiorpp7JcS2ejTuFDVYIzNMhqNMJvNcHV1tewTBAFqtRrr1q0TjfX29oZer0dQUBA8PDzg5eWFjIwM0ZikpCSUlZUBAJo1a2Z1PZVKhZUrV2Lq1KmYO3dupZ3atm0Ld3f3So9169YNKSkpKCsrs6zCOjs7w9nZGX/88ccd7zcyMhLLly8X7Xtt8VIsWrLMamxr59ZQKpVWHwjPz89H27Zt73gtZskvS8rdmCWPrPom1ftkljyypNyNWfLIknI3qWaRfMh2JdRsNiM+Ph5r1qwRrTpmZmbC1dUV27dvtzonJCQEycnJla6CAkCnTp3g7u4Od3f3Kt+cO378eHh6elpNBmsiKCgI165dw/r162t9LgBERESgsLBQtC0Ir/yNuvYODvDo4Ym0I6mWfRUVFUhLS0XPXr1rdV1mySNLyt2YJY+s+ibV+2SWPLKk3I1Z8siScjepZklRY7+UyFZfTCTbldA9e/bAZDIhNDQUTk5OomMBAQEwGo3w9fUV7Z8xYwbGjx8PZ2fnu7r2m2++iREjRlR67OrVq8jNzRXta968OVq1aoWBAwdi/vz5mD9/Pn7//XeMHTsWDzzwAHJycmA0GqFQKGBnV/XfG6jVaqjVatG+m+aqe04OnobFC8Ph6ekFL++e2LI5DsXFxRg9Zmxtb5lZMsmScjdmySPrxvXrOH/+vOXnC3/8gTOnT8PJyQn3/eWplcboxixm2VI3ZskjS8rdpJpF8iDbSajRaISPj4/VBBS3JqFRUVEoKioS7VepVPXyWMATTzyBJ554Al9++aXVsSVLlmDJkiWifTNnzsRHH30EAFi9ejX69euHDRs2IDo6Gjdu3ECHDh3w2GOPITU1Fa1atbrrfrf5+j0F05UrWL/ufeTlXYZO74H1H2+Ctg6/A2bJI0vK3Zglj6yTJ3/C9GlTLD+vjooEAIx6ZgxeX/Vmo3ZjFrNsqRuz5JEl5W5SzSJ5UAjVvemGbF51K6FERERERFLjaEPLZL2Wft3YFZC5/MnGrlBrsv1MKBEREREREUmPDf09AxERERERkXTY6HuBGh1XQomIiIiIiKjBcBJKREREREREDYaP4xIREREREdWBrX5PZ2PjSigRERERERE1GK6EEhERERER1QEXQuuGK6FERERERETUYJrcJDQ1NRVKpRL+/v6i/dnZ2VAoFFAqlbhw4YLoWE5ODlQqFRQKBbKzs6vMTk5OhkKhsGwdOnRAQEAAfvvtN8uYzp07W443b94c3t7e2LRpU61z6suObVvhN+wJ9O3tjUkTx+PE8ePMauJZUu7GLNvP+uH7owib/Tx8hg5GL08dvvn6qzp3qu9uzGKWrXVjljyypNxNqllk+5rcJNRoNCIsLAyHDh3CxYsXrY67ubkhPj5etC8uLg5ubm41vkZWVhYuXryIhIQEnDx5EiNHjkR5ebnl+IoVK5CTk4OffvoJBoMBM2bMwN69e2udc7f27U3C6qhIzJw9BzsSEqHT6TFrZijy8/OZ1USzpNyNWfLIKi6+AZ1Oh4hFS2t97r3uxixm2VI3ZskjS8rdpJolNX9dOGqszRY1qUnotWvXsHPnTsyaNQv+/v6IjY21GhMcHIyYmBjRvpiYGAQHB9f4Ou3bt8d9992Hxx57DEuWLMGpU6fwyy+/WI63bNkSLi4u6Nq1K8LDw9GmTRvs37+/1jl3a3NcDMaOm4DRYwLwoLs7Fi1dDkdHR3z6yW5mNdEsKXdjljyyBg95HHNffAlP+gyr9bn3uhuzmGVL3Zgljywpd5NqFslDk5qE7tq1C3q9HjqdDgaDAdHR0RAEQTRm1KhRMJlMSElJAQCkpKTAZDJh5MiRdbpms2bNAAClpaVWxyoqKrB7926YTCY4ODjUOacuykpLcfrUSQwYOMiyz87ODgMGDMLxzGPMaoJZUu7GLHlk1Tep3iez5JEl5W7MkkeWlLtJNYvko0lNQo1GIwwGAwDA19cXhYWFOHjwoGiMvb29ZYIKANHR0TAYDLC3t6/19XJycrB69Wq4ublBp9NZ9oeHh0Oj0UCtVmPcuHFo3bo1pk+fXuucu2EqMKG8vBxarVa0X6vVIi8vj1lNMEvK3Zglj6z6JtX7ZJY8sqTcjVnyyJJyN6lmSZFC0fibLWoyk9CsrCykp6cjKCgIAKBSqRAYGAij0Wg1NiQkBAkJCcjNzUVCQgJCQkKsxnh6ekKj0UCj0cDPz0907P7770eLFi3g6uqK69evY/fu3aKVzgULFiAjIwPffPMN+vfvj3feeQfu7u5W17hTzt+VlJSgqKhItJWUlNT6d0VERERERHSvNJnvCTUajTCbzXB1dbXsEwQBarUa69atE4319vaGXq9HUFAQPDw84OXlhYyMDNGYpKQklJWVAX95VPa2b7/9Fq1atUL79u3RsmVLqy5t27aFu7s73N3dkZCQAG9vbzzyyCPo0aNHrXL+LjIyEsuXLxfte23xUixassxqbGvn1lAqlVYfCM/Pz0fbtm3veC1myS9Lyt2YJY+s+ibV+2SWPLKk3I1Z8siScjepZkmRrb4YqLE1iZVQs9mM+Ph4rFmzBhkZGZYtMzMTrq6u2L59u9U5ISEhSE5OrnQVFAA6depkmUj+/c25Xbp0wYMPPlijieMDDzyAwMBAREREWB2rTQ4AREREoLCwULQtCLfOBQB7Bwd49PBE2pFUy76KigqkpaWiZ6/eNboes+SVJeVuzJJHVn2T6n0ySx5ZUu7GLHlkSbmbVLNIPprESuiePXtgMpkQGhoKJycn0bGAgAAYjUb4+vqK9s+YMQPjx4+Hs7PzPe/34osvwsvLC99//z0eeeSROueo1Wqo1WrRvpvmqsdPDp6GxQvD4enpBS/vntiyOQ7FxcUYPWZsra/NLHlkSbkbs+SRdeP6dZw/f97y84U//sCZ06fh5OSE+/7ypEpjdGMWs2ypG7PkkSXlblLNInloEpNQo9EIHx8fqwkobk1Co6KiUFRUJNqvUqka7BGBHj16YPjw4ViyZAmSkpIa5JoA4Ov3FExXrmD9uveRl3cZOr0H1n+8Cdo63Dez5JEl5W7MkkfWyZM/Yfq0KZafV0dFAgBGPTMGr696s1G7MYtZttSNWfLIknI3qWZJDZ/GrRuF8PfvKCFZqW4llIiIiIhIahxtaJms36rkxq6A9IVDG7tCrdnQHzEREREREZF08MVEddMkXkxERERERERE0sBJKBERERERETUYPo5LRERERERUB3wat264EkpEREREREQNhiuhREREREREdcAXE9UNV0KJiIiIiIiowch+EpqamgqlUgl/f3/R/uzsbCgUCiiVSly4cEF0LCcnByqVCgqFAtnZ2Xe8xsmTJzFhwgS0a9cOarUa3bt3x5IlS3Djxg3ROIVCgU8//dTq/KlTp2L06NGWn4cOHQqFQmG1Pf/883X4DVRvx7at8Bv2BPr29sakieNx4vhxZjXxLCl3Y5btZ/3w/VGEzX4ePkMHo5enDt98/VWdO9V3N2Yxy9a6MUseWVLuJtUssn2yn4QajUaEhYXh0KFDuHjxotVxNzc3xMfHi/bFxcXBzc2tRvlHjhxB//79UVpaiv/+9784e/YsVq5cidjYWAwbNgylpaV16j1jxgzk5OSItqioqDplVWXf3iSsjorEzNlzsCMhETqdHrNmhiI/P59ZTTRLyt2YJY+s4uIb0Ol0iFi0tNbn3utuzGKWLXVjljyypNxNqllSo1A0/maLZD0JvXbtGnbu3IlZs2bB398fsbGxVmOCg4MRExMj2hcTE4Pg4OA75guCgNDQUHh4eOCTTz5Bv3790KlTJ4wfPx7/+c9/kJqainfeeadO3Zs3bw4XFxfR1qpVqzplVWVzXAzGjpuA0WMC8KC7OxYtXQ5HR0d8+sluZjXRLCl3Y5Y8sgYPeRxzX3wJT/oMq/W597obs5hlS92YJY8sKXeTahbJg6wnobt27YJer4dOp4PBYEB0dDQEQRCNGTVqFEwmE1JSUgAAKSkpMJlMGDly5B3zMzIycOrUKbz88suwsxP/Knv16gUfHx9s3769nu+qfpSVluL0qZMYMHCQZZ+dnR0GDBiE45nHmNUEs6TcjVnyyKpvUr1PZskjS8rdmCWPLCl3k2qWFFX2EbqG3myRrCehRqMRBoMBAODr64vCwkIcPHhQNMbe3t4yQQWA6OhoGAwG2Nvb3zH/7NmzAAAPD49Kj3t4eFjG1Nb69euh0WhE29atW+uUVRlTgQnl5eXQarWi/VqtFnl5ecxqgllS7sYseWTVN6neJ7PkkSXlbsySR5aUu0k1i+RDtl/RkpWVhfT0dCQmJgIAVCoVAgMDYTQaMXToUNHYkJAQDBo0CKtWrUJCQgJSU1NhNptFYzw9PfH7778DAIYMGYK9e/dajv19dfWvHBwc6tR/0qRJeO2110T7OnToUO05JSUlKCkpEe0TlGqo1eo6dSAiIiIiIqpvsp2EGo1GmM1muLq6WvYJggC1Wo1169aJxnp7e0Ov1yMoKAgeHh7w8vJCRkaGaExSUhLKysoAAM2aNQMAdOvWDQBw+vRp9O7d26rD6dOn0b17d8vPLVu2RGFhodW4goICODk5ifY5OTnB3d29VvccGRmJ5cuXi/a9tngpFi1ZZjW2tXNrKJVKqw+E5+fno23btrW6LrPkkSXlbsySR1Z9k+p9MkseWVLuxix5ZEm5m1SzpMhGn4ZtdLJ8HNdsNiM+Ph5r1qxBRkaGZcvMzISrq2uln9MMCQlBcnIyQkJCKs3s1KkT3N3d4e7ubnlzbu/evaHX6/HOO++goqJCND4zMxNfffUVpk6datmn0+nwww8/iMaVl5cjMzNTNFmtq4iICBQWFoq2BeERlY61d3CARw9PpB1JteyrqKhAWloqevaynlBXh1nyyJJyN2bJI6u+SfU+mSWPLCl3Y5Y8sqTcTapZJB+yXAnds2cPTCYTQkNDrVYYAwICYDQa4evrK9o/Y8YMjB8/Hs7OzjW+jkKhwKZNmzB8+HAEBAQgIiICLi4uSEtLw/z58zFixAjMnDnTMv7ll19GaGgo9Ho9hg0bhuvXr+ODDz6AyWTC9OnTRdk3btxAbm6uaJ9arUbr1q2r7KNWWz96e9Nc5XBMDp6GxQvD4enpBS/vntiyOQ7FxcUYPWZsjX8HzJJXlpS7MUseWTeuX8f58+ctP1/44w+cOX0aTk5OuO8vT640RjdmMcuWujFLHllS7ibVLKmx1RcDNTZZTkKNRiN8fHysJqC4NQmNiopCUVGRaL9KparTIwGPPvoojhw5guXLl8PPzw9XrlwBAMydOxfvvPMOlEqlZWxQUBAEQcDatWvxz3/+E82bN0efPn1w6NAhq897/utf/8K//vUv0b4RI0Zg3759te5YFV+/p2C6cgXr172PvLzL0Ok9sP7jTdDW4ffALHlkSbkbs+SRdfLkT5g+bYrl59VRkQCAUc+Mweur3mzUbsxili11Y5Y8sqTcTapZJA8Kobq36lCtVVRUIDQ0FF988QUOHjxo+dxoY6luJZSIiIiISGocbWiZbMialMaugG/nD27sCrVmQ3/EtsHOzg5GoxEffPABvv3220afhBIRERER0b3Bx3HrhpPQe8DOzg4vvvhiY9cgIiIiIiKSHFm+HZeIiIiIiIikiSuhREREREREdcCnceuGK6FERERERETUYLgSSkREREREVAd8MVHdcCWUiIiIiIiIGkyTmoSmpqZCqVTC399ftD87OxsKhQJKpRIXLlwQHcvJyYFKpYJCoUB2drZVZufOnaFQKKrcpk6dCtz6WxKFQoEjR46Izi8pKYFWq4VCoUBycrJl/18znJyc8Oijj+Kbb76p598IsGPbVvgNewJ9e3tj0sTxOHH8OLOaeJaUuzHL9rN++P4owmY/D5+hg9HLU4dvvv6qzp3quxuzmGVr3Zgljywpd5NqFtm+JjUJNRqNCAsLw6FDh3Dx4kWr425uboiPjxfti4uLg5ubW5WZR48eRU5ODnJycrB7924AQFZWlmXfe++9Zxn7wAMPICYmRnR+YmIiNBpNpdkxMTHIycnBd999h7Zt2+Lpp5/Gb7/9Vuv7rsq+vUlYHRWJmbPnYEdCInQ6PWbNDEV+fj6zmmiWlLsxSx5ZxcU3oNPpELFoaa3PvdfdmMUsW+rGLHlkSbmbVLOkRqFo/M0WNZlJ6LVr17Bz507MmjUL/v7+iI2NtRoTHBxsNUmMiYlBcHBwlbnt2rWDi4sLXFxc0KZNGwBA+/btLfucnJxE+Tt27EBxcbFlX3R0dJX5zs7OcHFxgZeXFzZs2IDi4mLs37+/Tvdfmc1xMRg7bgJGjwnAg+7uWLR0ORwdHfHpJ7uZ1USzpNyNWfLIGjzkccx98SU86TOs1ufe627MYpYtdWOWPLKk3E2qWSQPTWYSumvXLuj1euh0OhgMBkRHR0MQBNGYUaNGwWQyISUlBQCQkpICk8mEkSNH1kuHPn36oHPnzpYV0/Pnz+PQoUOYPHnyHc9t1qwZAKC0tLReupSVluL0qZMYMHCQZZ+dnR0GDBiE45nHmNUEs6TcjVnyyKpvUr1PZskjS8rdmCWPLCl3k2qWFFX3sbyG2mxRk5mEGo1GGAwGAICvry8KCwtx8OBB0Rh7e3vLBBW3VikNBgPs7e3rrUdISIglPzY2Fk899RTatWtX7Tk3btzAokWLoFQq8fjjj9dLD1OBCeXl5dBqtaL9Wq0WeXl5zGqCWVLuxix5ZNU3qd4ns+SRJeVuzJJHlpS7STWL5KNJTEKzsrKQnp6OoKAgAIBKpUJgYCCMRqPV2JCQECQkJCA3NxcJCQkICQmxGuPp6QmNRgONRgM/P79adTEYDEhNTcVvv/2G2NjYSvNvCwoKgkajQcuWLbF7924YjUb07NmzyvElJSUoKioSbSUlJbXqR0RERERE8hMZGYm+ffuiZcuWaN++PUaPHo2srCzRmJs3b2LOnDnQarXQaDQICAjAn3/+KRpz/vx5+Pv7o3nz5mjfvj0WLFgAs9lcqy5NYhJqNBphNpvh6uoKlUoFlUqFDRs2YPfu3SgsLBSN9fb2hl6vR1BQEDw8PODl5WWVl5SUhIyMDGRkZGDTpk216qLVavH0008jNDQUN2/erHYS+8477yAjIwO5ubnIzc2t9rOpuPVfLCcnJ9H29luRlY5t7dwaSqXS6gPh+fn5aNu2ba3uiVnyyJJyN2bJI6u+SfU+mSWPLCl3Y5Y8sqTcTapZUtTYLyWqzdO4Bw8exJw5c3DkyBHs378fZWVlGD58OK5fv24Z89JLL+E///kPEhIScPDgQVy8eBFjx461HC8vL4e/vz9KS0tx+PBhxMXFITY2FkuWLKnV7032k1Cz2Yz4+HisWbPGMnHMyMhAZmYmXF1dsX37dqtzQkJCkJycXOUqZadOneDu7g53d/dq35xbldv5U6ZMgVKprHKci4sL3N3d7/i47m0REREoLCwUbQvCIyoda+/gAI8enkg7kmrZV1FRgbS0VPTs1btW98MseWRJuRuz5JFV36R6n8ySR5aUuzFLHllS7ibVLLo7+/btw9SpU+Hp6YlevXohNjYW58+fxw8//AAAKCwshNFoxNq1a/HEE0+gT58+iImJweHDhy1fM/nll1/i1KlT2LJlCx566CH4+fnh9ddfx4cfflird9eo7tldSsSePXtgMpkQGhoqelMtAAQEBMBoNMLX11e0f8aMGRg/fjycnZ3vSSdfX19cvnwZrVq1qtdctVoNtVot2nezmpXxycHTsHhhODw9veDl3RNbNsehuLgYo8eMrfokZsk6S8rdmCWPrBvXr+P8+fOWny/88QfOnD4NJycn3Ofq2qjdmMUsW+rGLHlkSbmbVLOkxk4CLwYqKSmx+gheZfOCv7v9ROjtb/j44YcfUFZWBh8fH8sYvV6Pjh07IjU1FQMGDEBqaiq8vb3RoUMHy5gRI0Zg1qxZOHnyJHr3rtlfLMh+Emo0GuHj42M1AcWtSWhUVBSKiopE+1Uq1T19PEChUEji8QNfv6dgunIF69e9j7y8y9DpPbD+403Q1qEbs+SRJeVuzJJH1smTP2H6tCmWn1dH/d9HBkY9Mwavr3qzUbsxi1m21I1Z8siScjepZpG1yMhILF++XLRv6dKlWLZsWZXnVFRUYN68eXj00UctHz/Mzc2Fg4OD1UJchw4dkJubaxnz1wno7eO3j9WUQvj795SQrFS3EkpEREREJDWONrRMNmzdkcaugD0zetd6JXTWrFnYu3cvUlJScP/99wMAtm3bhmnTplll9evXD//4xz/w1ltv4bnnnsPvv/+OL774wnL8xo0baNGiBZKSkmr80lYb+iMmIiIiIiKSDgk8jVujR2//au7cudizZw8OHTpkmYDi1vtoSktLUVBQIFoN/fPPP+Hi4mIZk56eLsq7/fbc22NqQvYvJiIiIiIiImrqBEHA3LlzkZiYiG+++QZdunQRHe/Tpw/s7e3x9ddfW/ZlZWXh/PnzGDhwIABg4MCBOHHiBC5dumQZs3//frRq1Qo9evSocReuhBIREREREdWBQgpLoTU0Z84cbNu2DZ999hlatmxp+Qynk5MTmjVrBicnJ4SGhuLll19GmzZt0KpVK4SFhWHgwIEYMGAAAGD48OHo0aMHJk+ejKioKOTm5mLRokWYM2dOrVZj+ZlQmeNnQomIiIjIltjSZ0JHrE9r7Ar4Ynb/Go2rasIcExODqVOnAgBu3ryJ+fPnY/v27SgpKcGIESOwfv160aO2v//+O2bNmoXk5GS0aNECwcHBePPNN6FS1fwPjpNQmeMklIgaWklZRb3mqe35yREioqaEk9DaqekkVEps6I+YiIiIiIhIOuxs52lcSeFfLxMREREREVGD4SS0hlJTU6FUKuHv7y/an52dDYVCYdnatGmDxx9/HN9++61VRlFRERYvXgxPT080a9YMWq0Wffv2RVRUFEwmk2WcIAhYsmQJ7rvvPjRr1gw+Pj74+eef78l97di2FX7DnkDf3t6YNHE8Thw/zqwmniXlbsyyvawffziKl1+YhaeGPYZ+D3kg+ZuvLMfMZWX44N3VCBo3Co8NeBhPDXsMSxeF4/Jf3rh3L7sxi1m23o1Z8siScjepZknJX+cBjbXZIk5Ca8hoNCIsLAyHDh3CxYsXrY5/9dVXyMnJwaFDh+Dq6oqnn37a8p05AHDlyhUMGDAAMTExeOWVV5CWloYff/wRK1euxLFjx7Bt2zbL2KioKLz//vv46KOPkJaWhhYtWmDEiBG4efNmvd7Tvr1JWB0ViZmz52BHQiJ0Oj1mzQxFfn4+s5polpS7Mcs2s24WF6Nbdx0WRCy2PnbzJrJOn0LIjFnYvGM33lrzPs5nZ2P+vNk2d5/MkmeWlLsxSx5ZUu4m1SySCYHu6OrVq4JGoxHOnDkjBAYGCitXrrQcO3funABAOHbsmGXf8ePHBQDCZ599Ztk3c+ZMoUWLFsKFCxcqvUZFRYXl/7q4uAhvv/225VhBQYGgVquF7du317p7cVnV29iAccLipcstP18vKRceHTxYWLf+42rPY5Z8s6TcjVm2k1Vwo7zSrXv37sKne76o8njBjXLhcHqG0L17d+HMr/+z7JPqfTJL/llS7sYseWRJuVtjZtkSvw1pjb7ZIq6E1sCuXbug1+uh0+lgMBgQHR2Nql4qXFxcjPj4eACAg4MDAKCiogI7d+6EwWCAq6trpefdXko/d+4ccnNz4ePjYznm5OSE/v37IzU1td7uqay0FKdPncSAgYMs++zs7DBgwCAczzzGrCaYJeVuzJJHVk1cu3YVCoUCmpatGrQbs5hlS92YJY8sKXeTapYUKRSNv9kiTkJrwGg0wmAwAAB8fX1RWFiIgwcPisYMGjQIGo0GLVq0wOrVq9GnTx88+eSTAIDLly+joKAAOp1OdE6fPn2g0Wig0WgQFBQEAJYvje3QoYNobIcOHSzH6oOpwITy8nJotVrRfq1Wi7y8PGY1wSwpd2OWPLLupKSkBOveW4Phvv7QaDQN2o1ZzLKlbsySR5aUu0k1i+SDk9A7yMrKQnp6umWSqFKpEBgYCKPRKBq3c+dOHDt2DLt374a7uztiY2Nhb29fbXZiYiIyMjIwYsQIFBcX33XXkpISFBUVibaSkpK7ziUiutfMZWVY+OpLEAQB4a8tbew6REREdA/xe0LvwGg0wmw2ix6jFQQBarUa69ats+x74IEH0K1bN3Tr1g1msxljxozBTz/9BLVajXbt2sHZ2RlZWVmi7I4dOwIAWrZsiYKCAgCAi4sLAODPP//EfffdZxn7559/4qGHHqq2a2RkJJYvXy7a99ripVi0ZJnV2NbOraFUKq0+EJ6fn4+2bdvW6HfDLHllSbkbs+SRVRVzWRkiXn0JOTkXsX5jTI1WQeu7G7OYZUvdmCWPLCl3k2qWFClgo8/DNjKuhFbDbDYjPj4ea9asQUZGhmXLzMyEq6srtm/fXul548aNg0qlwvr164Fbz71PmDABW7ZsqfTNun/VpUsXuLi44Ouvv7bsKyoqQlpaGgYOHFjtuRERESgsLBRtC8IjKh1r7+AAjx6eSDvy/z9nWlFRgbS0VPTs1bva6zBLnllS7sYseWRV5vYE9H/nf8eHH0XD2bl1o3RjFrNsqRuz5JEl5W5SzSL54EpoNfbs2QOTyYTQ0FA4OTmJjgUEBMBoNMLX19fqPIVCgRdeeAHLli3DzJkz0bx5c6xatQrJycno168fVqxYgUceeQQtWrTA8ePHkZqaCi8vL8u58+bNwxtvvIFu3bqhS5cuWLx4MVxdXTF69Ohq+6rVaqjVatG+m+aqx08OnobFC8Ph6ekFL++e2LI5DsXFxRg9ZmztflHMkk2WlLsxyzazbty4jj/On7f8fPHCHzh75jRaOTmhbdt2+OeCeThz+hTWvr8B5RXlyMu7DNx6IZu9vYPN3Cez5Jkl5W7MkkeWlLtJNUtq7LgQWiechFbDaDTCx8fHagKKW5PQqKgoFBUVVXpucHAwXnvtNaxbtw6vvvoqtFot0tPT8dZbb+Htt9/GuXPnYGdnh27duiEwMBDz5s2znPvqq6/i+vXreO6551BQUIDBgwdj3759cHR0rNf78/V7CqYrV7B+3fvIy7sMnd4D6z/eBG0dHo1gljyypNyNWbaZdfrkScyaEWz5+d01bwEA/EeOxozn5+JQ8jcAAEPgGNF5G/4Vhz59+9nMfTJLnllS7sYseWRJuZtUs0geFEJV3zVCslDdSigR0b1QUlZRr3lqe35yhIioKXG0oWWyURuPNnYFfP5c38auUGs29EdMREREREQkHQpb/aLORsa/XiYiIiIiIqIGw5VQIiIiIiKiOuBCaN1wJZSIiIiIiIgaDFdCiYioXpWW88VERET3SkU9vlPUjst41Eg4CSUiIiIiIqoDTuTrhn+9TERERERERA2Gk9AaSk1NhVKphL+/v2h/dnY2FAqFZWvTpg0ef/xxfPvtt1YZRUVFWLx4MTw9PdGsWTNotVr07dsXUVFRMJlMlnGffPIJhg8fDq1WC4VCgYyMjHt2Xzu2bYXfsCfQt7c3Jk0cjxPHjzOriWdJuRuzbCtrc/S/MH3yBAwb0hdP+wxBxMthOJ99TjTms092Ye5zUzH8sX4Y3McTV68WNUg3ZjFLDt2YJY+s+srbtWM7JowZhcH9+2Bw/z6YMikQKd8eavRe9yJLShSKxt9sESehNWQ0GhEWFoZDhw7h4sWLVse/+uor5OTk4NChQ3B1dcXTTz+NP//803L8ypUrGDBgAGJiYvDKK68gLS0NP/74I1auXIljx45h27ZtlrHXr1/H4MGD8dZbb93Te9q3NwmroyIxc/Yc7EhIhE6nx6yZocjPz2dWE82Scjdm2V7WsR+PYuz4IHwcux3vrP8XzGYzXpozA8XFNyxjSm7eRP+Bj2LytBm17iWV+2SWfLOk3I1Z8siqz7wOLh0Q9tJ8bN21G1t3/hv9+g3AS2Fz8OsvPzdqr/rOInlQCEI9frpZpq5du4b77rsP33//PZYuXYqePXti4cKFwK2V0C5duuDYsWN46KGHAAAnTpxAz5498dlnn2HUqFEAgOeffx5btmzB2bNn4erqanUNQRCsvuy2suzaummu+tikiePh6eWNhYuWAAAqKiow/MnHEfTsZITOeK5W12GWPLKk3I1ZtpN1tYr/4TGZrmCkzxCs+1ccHnr4EdGxH79Pxwszp2FvcipatmwlOtbSserXF8jld8YsaWZJuRuz5JFVl7zavJjo8UH9MW/+AowJGFfp8eo+z9iYv7Nq/mdfcgKif2jsCtgd0qexK9QaV0JrYNeuXdDr9dDpdDAYDIiOjkZVc/fi4mLEx8cDABwcHIBb/4+2c+dOGAyGSiegAKwmoPdaWWkpTp86iQEDB1n22dnZYcCAQTieeYxZTTBLyt2YJY+s69euAgBatXKq1XkN0Y1ZzLKlbsySR9a9yLutvLwc+5L+i+LiG+hZh4UMKf/OpOavH8trrM0WcRJaA0ajEQaDAQDg6+uLwsJCHDx4UDRm0KBB0Gg0aNGiBVavXo0+ffrgySefBABcvnwZBQUF0Ol0onP69OkDjUYDjUaDoKCgBrwjwFRgQnl5ObRarWi/VqtFXl4es5pglpS7Mcv2syoqKvD+6rfg3as3urp3q1WHe92NWcyytW7MkkfWvcj7+WwWBvV9GP0f7omVry/DmvfW4cEH3Ru1V33fI8kDJ6F3kJWVhfT0dMskUaVSITAwEEajUTRu586dOHbsGHbv3g13d3fExsbC3t6+2uzExERkZGRgxIgRKC4uvuuuJSUlKCoqEm0lJSV3nUtEdLfWvvkGfvv1ZyyPXN3YVYiIZKtzly7YsTsR8dt2YvyEiVjy2j/x66+/NHYtWWvslxLZ6EIovyf0ToxGI8xms+gxWkEQoFarsW7dOsu+Bx54AN26dUO3bt1gNpsxZswY/PTTT1Cr1WjXrh2cnZ2RlZUlyu7YsSMAoGXLligoKLjrrpGRkVi+fLlo32uLl2LRkmVWY1s7t4ZSqbT6QHh+fj7atm1bq+sySx5ZUu7GLNvOWvvWGzicchDr/hWH9h1canX9e92NWcyyxW7MkkfWvcizt3dAx46dAAA9PL1w8uRP2L4lHouWrmi0XvV9jyQPXAmthtlsRnx8PNasWYOMjAzLlpmZCVdXV2zfvr3S88aNGweVSoX169cDt557nzBhArZs2VLpm3XrS0REBAoLC0XbgvCISsfaOzjAo4cn0o6kWvZVVFQgLS0VPXv1rtV1mSWPLCl3Y5ZtZgmCgLVvvYFDB77Gex9Fw9Xt/lpd+152YxazbLkbs+SRdS/y/k6oqEBpaWmj9rrX90i2iSuh1dizZw9MJhNCQ0Ph5CR+kUZAQACMRiN8fX2tzlMoFHjhhRewbNkyzJw5E82bN8eqVauQnJyMfv36YcWKFXjkkUfQokULHD9+HKmpqfDy8rKcf+XKFZw/f94yYb29guri4gIXl6pXEdRqNdRqtWhfdW/HnRw8DYsXhsPT0wte3j2xZXMciouLMXrM2Jr/kpglqywpd2OW7WWtefN1fLUvCZFrP0Dz5s2Rn3cZAKDRtITa0REAkJ93GVfy83Dhf+cBAL/98jOaN2+ODi73oZWTs03cJ7PkmyXlbsySR1Z95r3/zho8OuQx3Hfffbh+/Tr2/ncPvj+ajvUfb2rUXvWdJTXVvWGYqsZJaDWMRiN8fHysJqC4NQmNiopCUVHlX6weHByM1157DevWrcOrr74KrVaL9PR0vPXWW3j77bdx7tw52NnZoVu3bggMDMS8efMs537++eeYNm2a5eeJEycCAJYuXYply6wfra0rX7+nYLpyBevXvY+8vMvQ6T2w/uNN0Nbh0QhmySNLyt2YZXtZn/57JwAg7Lmpov0Ll76Bp0aN+b8xu3chZuN6y7E506dYjZH6fTJLvllS7sYseWTVZ96VK1eweGE48i5fhqZlS3TrrsP6jzdhwKBHG7VXfWeRPPB7QmWuupVQIqJ7oarvCa2r6r4nlIioqanN94TeiVRX8Wzpf/YnxjX+18zsCLa9x5r5mVAiIiIiIiJqMJyEEhERERERUYOxocVuIiIiIiIi6VBI9JFmqeNKKBERERERETUYroQSEVG90qj5jxYiontFqi8TIqoN/psCERERERFRHdjx7wTqhI/jEhERERERUYPhJLSGUlNToVQq4e/vL9qfnZ0NhUJh2dq0aYPHH38c3377rVVGUVERFi9eDE9PTzRr1gxarRZ9+/ZFVFQUTCYTAKCsrAzh4eHw9vZGixYt4OrqiilTpuDixYv35L52bNsKv2FPoG9vb0yaOB4njh9nVhPPknI3Ztl+lvFfH+PZwAAM6tcb/3hsIOa9MBvZ536rc6/67MYsZtlaN2bJI0vK3aSaJSV/nQc01maLOAmtIaPRiLCwMBw6dKjSCeFXX32FnJwcHDp0CK6urnj66afx559/Wo5fuXIFAwYMQExMDF555RWkpaXhxx9/xMqVK3Hs2DFs27YNAHDjxg38+OOPWLx4MX788Ud88sknyMrKwqhRo+r9nvbtTcLqqEjMnD0HOxISodPpMWtmKPLz85nVRLOk3I1Z8sj64ft0BAZNQvy2XfhoYwzMZWbMei4UxTdu1Dqrvrsxi1m21I1Z8siScjepZpE8KARBEBq7hNRdu3YN9913H77//nssXboUPXv2xMKFC4FbK6FdunTBsWPH8NBDDwEATpw4gZ49e+Kzzz6zTB6ff/55bNmyBWfPnoWrq6vVNQRBqPJvMo4ePYp+/frh999/R8eOHWvV/aa56mOTJo6Hp5c3Fi5aAgCoqKjA8CcfR9CzkxE647laXYdZ8siScjdm2U5Wbf6pcuXKFTzx2EAYY7egzyN9Kx1T3V/yyuV3xixpZkm5G7PkkSXlbo2Z5WhDb60xbMls7ArYYujV2BVqjSuhNbBr1y7o9XrodDoYDAZER0ejqrl7cXEx4uPjAQAODg7Arf9H27lzJwwGQ6UTUNzhO4YKCwuhUCjg7OxcL/cDAGWlpTh96iQGDBxk2WdnZ4cBAwbheOYxZjXBLCl3Y5Y8sipz7dpVAICTk1Otz5XqfTJLHllS7sYseWRJuZtUs6RIoWj8zRZxEloDRqMRBoMBAODr64vCwkIcPHhQNGbQoEHQaDRo0aIFVq9ejT59+uDJJ58EAFy+fBkFBQXQ6XSic/r06QONRgONRoOgoKBKr33z5k2Eh4cjKCgIrVq1qrd7MhWYUF5eDq1WK9qv1WqRl5fHrCaYJeVuzJJH1t9VVFTg7TdX4aHeD8O9W/dany/V+2SWPLKk3I1Z8siScjepZpF82NBid+PIyspCeno6EhMTAQAqlQqBgYEwGo0YOnSoZdzOnTuh1+vx008/4dVXX0VsbCzs7e2rzU5MTERpaSnCw8NRXFxsdbysrAwTJkyAIAjYsGHDHbuWlJSgpKREtE9QqqFWq2txx0REDSPyjeX45ZefERu/rbGrEBER1YmtvhiosXESegdGoxFms1n0GK0gCFCr1Vi3bp1l3wMPPIBu3bqhW7duMJvNGDNmDH766Seo1Wq0a9cOzs7OyMrKEmXf/nxny5YtUVBQIDp2ewL6+++/45tvvqnRKmhkZCSWL18u2vfa4qVYtGSZ1djWzq2hVCqtPhCen5+Ptm3b3vFazJJflpS7MUseWX8VuXIFDh1MRnTcFnRwcalThlTvk1nyyJJyN2bJI0vK3aSaRfLBx3GrYTabER8fjzVr1iAjI8OyZWZmwtXVFdu3b6/0vHHjxkGlUmH9+vXArefeJ0yYgC1bttToq1ZuT0B//vlnfPXVV1aPL1QlIiIChYWFom1BeESlY+0dHODRwxNpR1It+yoqKpCWloqevXrX6HrMkleWlLsxSx5ZuPWXeJErV+Cbr/djY3Qc3O5/oNYZ96Ibs5hlS92YJY8sKXeTahbJB1dCq7Fnzx6YTCaEhoZavTQjICAARqMRvr6+VucpFAq88MILWLZsGWbOnInmzZtj1apVSE5ORr9+/bBixQo88sgjaNGiBY4fP47U1FR4eXkBtyag48aNw48//og9e/agvLwcubm5AIA2bdpYXnZUGbXa+tHb6t6OOzl4GhYvDIenpxe8vHtiy+Y4FBcXY/SYsbX9VTFLJllS7sYseWStemM59ibtwbvvr0eLFi2Ql3cZAKDRtISjo2OjdmMWs2ypG7PkkSXlblLNkho7Po1bJ5yEVsNoNMLHx6fStzYGBAQgKioKRUVFlZ4bHByM1157DevWrcOrr74KrVaL9PR0vPXWW3j77bdx7tw52NnZoVu3bggMDMS8efMAABcuXMDnn38OAJavfLntwIEDos+h3i1fv6dgunIF69e9j7y8y9DpPbD+403Q1uHRCGbJI0vK3Zglj6yEnf/3BMn0aZNF+5e/EYlnRtf+X0akep/MkkeWlLsxSx5ZUu4m1SySB35PqMxVtxJKRHQv1Pc/VfjOByKipsWWvid02o4TjV0BMRO9G7tCrfEzoURERERERNRgOAklIiIiIiKiBmNDi91ERERERETSwU+M1E2NJqG3X5RTE6NGjbqbPkRERERERCRjNZqEjh49ukZhCoUC5eXld9uJiIhsGF8kRERETYUd/6FXJzWahFZUVNz7JkRERERERCR7fDERERERERERNZg6TUKvX7+OpKQkfPTRR3j//ff/H3vnHhdlmff/z8DAKDPKYTR1dvGwMQ4KyhoekNwHU0sMLBEFFYzCLaRWc0slUgTZAEVcWxcpdx1A8gTpw7prZZvuKroRVHLyRLWLayEaxxmlCTlcvz+evH/dzoCAJtfcft+9rteLuQ7v+3OPre2X65p7RE2qFBYWwtbWFgEBAaL+S5cuQSaTCc3FxQV+fn44deqUmcNoNCIuLg4eHh7o378/1Go1Jk2ahNTUVDQ2NgrzEhIS4O7uDqVSCWdnZ8yaNQtFRUU/yX0d2LcXcx6fgUkTxiFs0UJUlJeT6wF38ZyNXOSypmzkkoaL52zkkoaL52y8unhCJuv7Zo30uAgtKSmBm5sbFi9ejN/85jd44403sGrVKrz++ut48803f5qUHKDX67FixQoUFBTgypUrZuPHjh1DTU0NCgoKoNFoEBgYiGvXrgnjDQ0N8PHxQVZWFlavXo2ioiKcOXMGSUlJKCkpwb59+4S5o0ePRnp6OioqKnD69GmMHDkSTzzxBGpra+/pPR394H2kpaYg6sWXcODdfOh07oiOWob6+npyPaAunrORi1zWlI1c0nDxnI1c0nDxnI1XFyERWA/x8/Njzz//PGtvb2cqlYr9+9//ZpcvX2b/8z//ww4dOtRTnVVw/fp1plKp2MWLF1loaChLSkoSxqqqqhgAVlJSIvSVl5czAOzw4cNCX1RUFFMqlay6utriNTo6Ojq9vsFgYADYsWPHepzd1Np5mx+8gMXFbxReN7e0s0enTWPpGTu7XEcu6bp4zkYucllTNnJJw8VzNnJJw8Vztr50WRPP553t82aN9HgntLS0FK+++ipsbGxga2uLlpYWuLq6IjU1Fa+//vpPUyn3MXl5eXB3d4dOp0N4eDgyMzPBGLM412QyIScnBwBgb28P/PBgp9zcXISHh0Oj0VhcJ+tkL/3mzZv405/+BEdHR3h5ed2ze2q9eRMXzp+Dz1Rfoc/GxgY+Pr4oLysh1wPo4jkbuchlTdnIJQ0Xz9nIJQ0Xz9l4dRHSocdFqJ2dHWxs/m/ZQw89hMuXLwMAHB0d8fXXX9/7hByg1+sRHh4OAPD394fBYMDJkydFc3x9faFSqaBUKpGWlgZvb2/MnDkTAFBbW4umpibodDrRGm9vb6hUKqhUKixevFg0duTIEahUKvTr1w/btm3DRx99hEGDBt2ze2psakR7ezvUarWoX61Wo66ujlwPoIvnbOQilzVlI5c0XDxnI5c0XDxn49VFSIceF6ETJkzAp59+CgDw8/PDhg0bsHfvXqxatQqenp4/RcY+pbKyEsXFxUKRKJfLERoaCr1eL5qXm5uLkpISHDp0CG5ubsjOzoadnV2X7vz8fJSWlmL27NkwmUyiscceewylpaX4+OOP4e/vj5CQEHz77bdd+lpaWmA0GkWtpaWl1/dOEARBEARBEETn9PVDiR6YBxMlJydj2LBhAICkpCQ4OzsjOjoatbW1+NOf/vRTZOxT9Ho92traoNFoIJfLIZfL8dZbb+HQoUMwGAzCPFdXV2i1WgQFBSE5ORlBQUFCATh48GA4OTmhsrJS5B4+fDjc3NwwYMAAs+sqlUq4ubnBx8cHer0ecrncrPC9nZSUFDg6Oorals0pFuc6OznD1tbW7APh9fX1Pd5xJZc0XDxnIxe5rCkbuaTh4jkbuaTh4jkbry5COvS4CJ04cSIee+wx4IfjuEePHoXRaMTnn39+Tz+zyANtbW3IycnB1q1bUVpaKrSysjJoNBrs37/f4roFCxZALpcjIyMD+OHce0hICPbs2WPxybrdoaOj4467mrGxsTAYDKK2JibW4lw7e3uMGeuBok8KRdcoKirEeK8JPcpGLmm4eM5GLnJZUzZyScPFczZyScPFczZeXYR0kPd1AJ45cuQIGhsbsWzZMjg6OorGgoODodfr4e/vb7ZOJpNh5cqVSEhIQFRUFBwcHJCcnIwTJ05g8uTJSExMxMSJE6FUKlFeXo7CwkLhKHNzczOSkpLw1FNPYdiwYairq8OOHTtQXV2NhQsXdplXoVBAoVCI+r5v63z+0ojnEPd6DDw8POE5bjz2vLMbJpMJ84Lm9+yNIpdkXDxnIxe5rCkbuaTh4jkbuaTh4jkbry7esLHW87B9TI+L0FGjRnX6JFcA+M9//nO3mbhBr9dj1qxZZgUofihCU1NTYTQaLa6NiIjAunXrkJ6ejrVr10KtVqO4uBibN2/Gli1bUFVVBRsbG2i1WoSGhmLVqlUAAFtbW1y8eBG7d+9GXV0d1Go1Jk2ahFOnTsHDw+Oe3p//nCfR2NCAjPTtqKurhc59DDJ27oK6F0cjyCUNF8/ZyEUua8pGLmm4eM5GLmm4eM7Gq4uQBjLW2XeNdMIf/vAH0evW1laUlJTg6NGjWLNmDV577bV7nZG4C7raCSUIgiAIgiAI3uhnRWc1X/zf830dARnzx/Z1hB7T4z/il19+2WL/jh078Nlnn92LTARBEARBEARBEIRE6fGDiTpjzpw5OHTo0L3SEQRBEARBEARBEBLknm12Hzx4EC4uLvdKRxAEQRAEQRAEwTVdPSuH6JweF6ETJkwQvdmMMVy9ehW1tbXCV5IQBEEQBEEQBEEQhCV6XIQ+/fTToiLUxsYGgwcPxvTp0+Hu7n6v8xEEQRBWRkfPnnd3R+jx9wRBEASv3LPPNj5g9LgITUhI+GmSEARBEARBEARBEJKnx8W7ra0tvv32W7P++vp62Nra3qtcBEEQBEEQBEEQhATpcRHa2deKtrS0wN7e/l5kEigsLIStrS0CAgJE/ZcuXYJMJhOai4sL/Pz8cOrUKTOH0WhEXFwcPDw80L9/f6jVakyaNAmpqalobGwU5k2fPh0ymQybNm0ycwQEBEAmk3W5C5ydnS3KpFKp4O3tjf/93/8Vzbt1nQMHDoj633zzTYwcObJT3622a9eubr573ePAvr2Y8/gMTJowDmGLFqKivJxcD7iL52zksn5X3oH9CAl6CtOmeGPaFG88ExaK06cKep3rXmYjF7msLRu5pOHiORuvLp6w9P/X73ezRrpdhG7fvh3bt28XCqFbr7dv345t27bhpZdeuuefCdXr9VixYgUKCgpw5coVs/Fjx46hpqYGBQUF0Gg0CAwMxLVr14TxhoYG+Pj4ICsrC6tXr0ZRURHOnDmDpKQklJSUYN++fSKfq6srsrOzRX3V1dU4fvw4hg0bdse8AwcORE1NDWpqalBSUoLZs2cjJCQElZWVonn9+vXD+vXr0dra2m3frRYWFnbHHN3l6AfvIy01BVEvvoQD7+ZDp3NHdNQy1NfXk+sBdfGcjVzScA0ZOgQrfvsq9uYdwt7cg5g82Qe/XfES/v3Vlz123ets5CKXNWUjlzRcPGfj1UVIg24Xodu2bcO2bdvAGMPbb78tvN62bRvefvttfPfdd3j77bfvWbAbN24gNzcX0dHRCAgIMCsOAUCtVmPo0KHw9PTE66+/DqPRiKKiImH89ddfx+XLl1FcXIznnnsO48ePx4gRI/DEE09g//79ePHFF0W+wMBA1NXV4V//+pfQt3v3bjzxxBN46KGH7phZJpNh6NChGDp0KLRaLd544w3Y2Nig/Lbf9CxevBhNTU3485//3G3frda/f/875ugu7+zOwvwFIZgXFIyH3dywPn4j+vXrh7/8b8+/75Vc0nDxnI1c0nD5TZ+BX/2PH0aMGIkRI0fhNy//Fg4ODigvK+ux615nIxe5rCkbuaTh4jkbry7esJH1fbNGul2EVlVVoaqqCn5+figrKxNeV1VVobKyEh9++CGmTJlyz4Ll5eXB3d0dOp0O4eHhyMzM7PQosMlkQk5ODgAIR4I7OjqQm5uL8PBwaDQai+tu3762t7dHWFgYsrKyhL7s7GxERkb2OH97ezt2794NAHjkkUdEYwMHDsS6deuQmJiI5ubmHrvvBa03b+LC+XPwmeor9NnY2MDHxxflZSXkegBdPGcjlzRct9Pe3o6j778Hk+k7jP/lL3u8ntf7JJc0XDxnI5c0XDxn49VFSIcefyb0n//8J5ydnX+aND9Cr9cjPDwcAODv7w+DwYCTJ0+K5vj6+kKlUkGpVCItLQ3e3t6YOXMmAKC2thZNTU3Q6XSiNd7e3lCpVFCpVFi8eLHZdSMjI5GXl4fm5mYUFBTAYDAgMDCwW5kNBoPgtre3R3R0NP70pz/h4YcfNpv74osvol+/fvj973/fLZ9KpcLQoUO7laM7NDY1or29HWq1WtSvVqtRV1dHrgfQxXM2cknDdYsvv6iE76RHMOWR8Uj6XQK2/iEdDz/s1mMPr/dJLmm4eM5GLmm4eM7Gq4uQDj0uQoODg7F582az/tTUVCxcuPCehKqsrERxcbFQJMrlcoSGhkKv14vm5ebmoqSkBIcOHYKbmxuys7NhZ2fXpTs/Px+lpaWYPXs2TCaT2biXlxe0Wi0OHjyIzMxMLF26FHK5+JtskpOTRcXh5cuXAQADBgxAaWkpSktLUVJSguTkZCxfvhx/+9vfzK6jUCiQmJiItLS0Tv8H+GNfaWkpPv744y7vraWlBUajUdRaWlq6XEMQBHG/GTlqFA4cykfOvlwsDFmEDetew7///VVfxyIIgiCIHtPXR3Gt9Thuj78ntKCgwOJTYufMmYOtW7fek1B6vR5tbW2iY7SMMSgUCqSnpwt9rq6u0Gq10Gq1aGtrQ1BQEM6ePQuFQoHBgwfDycnJ7KFAw4cPB34o8JqamixePzIyEjt27MD58+dRXFxsNr58+XKEhIQIr2/ltLGxgZvb//9t/vjx4/H3v/8dmzdvxty5c8084eHhSEtLwxtvvCF6Mu4tbvfdiZSUFGzcuFHUty4uHus3mP95OTs5w9bW1uwD4fX19Rg0aFC3r0ku6bh4zkYuabhuYWdnj+HDRwAAxnp44ty5s9i/Jwfr4xP7LBu5yGVN2cglDRfP2Xh1EdKhxzuhN27csPhVLHZ2djAajXcdqK2tDTk5Odi6datoF7CsrAwajQb79++3uG7BggWQy+XIyMgAfijgQkJCsGfPHotP1u2KJUuWoKKiAp6enhg7dqzZuIuLC9zc3IR2+07pj7G1tbW443orY0pKCt566y1cunSpRxktERsbC4PBIGprYmItzrWzt8eYsR4o+qRQ6Ovo6EBRUSHGe03o0XXJJQ0Xz9nIJQ1XZ7CODty8ebPH63i9T3JJw8VzNnJJw8VzNl5dPNLXX89irV/R0uOd0HHjxiE3NxcbNmwQ9R84cMBiwdZTjhw5gsbGRixbtgyOjo6iseDgYOj1evj7+5utk8lkWLlyJRISEhAVFQUHBwckJyfjxIkTmDx5MhITEzFx4kQolUqUl5ejsLAQnp6eFjM4Ozujpqbmjkd7b4cxhqtXrwI/PCzpo48+wocffmj2Xv2YgIAATJkyBTt37sSQIUN6dL3bUSgUUCgUor7v2zqfvzTiOcS9HgMPD094jhuPPe/shslkwryg+T2+Nrmk4eI5G7mk4dq+bSse/dX/YNiwYWhubsYH7x3BZ58WI2Nn774Dmdf7JJc0XDxnI5c0XDxn49VFSIMeF6FxcXGYP38+/v3vf2PGjBkAgOPHj2Pfvn04ePDgXQfS6/WYNWuWWQGKH4rQ1NTUTndcIyIisG7dOqSnp2Pt2rVQq9UoLi7G5s2bsWXLFlRVVcHGxgZarRahoaFYtWpVpzmcnJx6nN1oNArfJ6pQKDBixAgkJiYiJiamy3WbN2+Gr69vl3N+CvznPInGhgZkpG9HXV0tdO5jkLFzF9S9OBpBLmm4eM5GLmm4GhoaEPd6DOpqa6EaMADa0Tpk7NwFH99He+y619nIRS5rykYuabh4zsari5AGMtbZ9550wXvvvYfk5GSUlpaif//+8PLyQnx8PFxcXDrdXST6hq52QgmCIH4KOnr+n5UusbHSo0YEQRBE7+jX422yvmPNkcpuzPpp2RKo68YsvuhVEfpjjEYj9u/fD71ej88//xzt7e33Lh1x11ARShDE/YaKUIIgCOJuoCK0Z1hjEdrjBxPdoqCgABEREdBoNNi6dStmzJiBTz755N6mIwiCIAiCIAiC4BSZrO+bNdKj3zNcvXoV2dnZ0Ov1MBqNCAkJQUtLC/7yl7/ck4cSEQRBEARBEARBENKm2zuhc+fOhU6nQ3l5Od58801cuXIFf/zjH3/adARBEARBEARBEISk6PZO6AcffICVK1ciOjoaWq32p01FEARBWC30GU6CIAjiQYH+m9c7ur0Tevr0aVy/fh3e3t6YMmUK0tPTUVdX99OmIwiCIAiCIAiCIO4JBQUFmDt3LjQaDWQyGf7yl7+Ixp999lnIZDJR8/f3F81paGhAWFgYBg4cCCcnJyxbtgw3btzoUY5uF6E+Pj7485//jJqaGkRFReHAgQPQaDTo6OjARx99hOvXr/fowgRBEARBEARBEMT9o7m5GV5eXtixY0enc/z9/VFTUyO0/fv3i8bDwsJw7tw5fPTRRzhy5AgKCgrwwgsv9ChHj5+Oq1QqERkZidOnT6OiogKvvvoqNm3ahIceeghPPfVUT3UWKSwshK2tLQICAkT9ly5dElXlLi4u8PPzw6lTp8wcRqMRcXFx8PDwQP/+/aFWqzFp0iSkpqaisbFRmDd9+nTIZDJs2rTJzBEQEACZTIaEhIQ7Zi4pKcHChQsxZMgQ9OvXD1qtFs8//zy++OILs7mzZ8+Gra0tPv30U7Ox6dOnY9WqVWb92dnZcHJyumOOnnJg317MeXwGJk0Yh7BFC1FRXk6uB9zFczZykcuaspFLGi6es5FLGi6es/Hq4gkbDlpPmDNnDt544w0EBQV1OkehUGDo0KFCc3Z2FsYuXLiAo0ePYteuXZgyZQqmTZuGP/7xjzhw4ACuXLnSo/et1+h0OqSmpuKbb74xq5DvBr1ejxUrVqCgoMDizRw7dgw1NTUoKCiARqNBYGAgrl27Jow3NDTAx8cHWVlZWL16NYqKinDmzBkkJSWhpKQE+/btE/lcXV2RnZ0t6quursbx48cxbNiwO+Y9cuQIfHx80NLSgr179+LChQvYs2cPHB0dERcXJ5p7+fJlfPzxx/jNb36DzMzMXrw7946jH7yPtNQURL34Eg68mw+dzh3RUctQX19PrgfUxXM2cpHLmrKRSxounrORSxounrPx6iLMaWlpgdFoFLWWlpZe+06cOIGHHnoIOp0O0dHRoj+nwsJCODk5YeLEiULfrFmzYGNjg6Kiom5f466K0FvY2tpi3rx5+Otf/3rXrhs3biA3NxfR0dEICAgwKw4BQK1WY+jQofD09MTrr78Oo9EouunXX38dly9fRnFxMZ577jmMHz8eI0aMwBNPPIH9+/fjxRdfFPkCAwNRV1eHf/3rX0Lf7t278cQTT+Chhx7qMu93332H5557Dk8++ST++te/YtasWRg1ahSmTJmCtLQ07Ny5UzQ/KysLgYGBiI6Oxv79+2Eyme7i3bo73tmdhfkLQjAvKBgPu7lhffxG9OvXD3/530PkekBdPGcjF7msKRu5pOHiORu5pOHiORuvLt7o6+8IlcmAlJQUODo6ilpKSkqv7sff3x85OTk4fvw4Nm/ejJMnT2LOnDlob28HfvjKztvrI7lcDhcXF1y9erXb17knRei9JC8vD+7u7tDpdAgPD0dmZiYYYxbnmkwm5OTkAADs7e0BAB0dHcjNzUV4eDg0Go3FdbLbnmJlb2+PsLAwZGVlCX3Z2dmIjIy8Y94PP/wQdXV1WLt2rcXxHx+hZYwhKysL4eHhcHd3h5ubGw4ePHjHa/wUtN68iQvnz8Fnqq/QZ2NjAx8fX5SXlZDrAXTxnI1c5LKmbOSShovnbOSShovnbLy6CMvExsbCYDCIWmxsbK9cixYtwlNPPYVx48Zh3rx5OHLkCD799FOcOHHinmbmrgjV6/UIDw8HfqjEDQYDTp48KZrj6+sLlUoFpVKJtLQ0eHt7Y+bMmQCA2tpaNDU1QafTidZ4e3tDpVJBpVJh8eLFZteNjIxEXl4empubUVBQAIPBgMDAwDvm/fLLLwEA7u7ud5x77NgxfPfdd5g9ezYAIDw8HHq9/o7rfgoamxrR3t4OtVot6ler1T1+6jG5pOHiORu5yGVN2cglDRfP2cglDRfP2Xh1EZZRKBQYOHCgqCkUinvi/sUvfoFBgwbhq6++AgAMHToU3377rWhOW1sbGhoaMHTo0G57uSpCKysrUVxcLBSJcrkcoaGhZoVabm4uSkpKcOjQIbi5uSE7Oxt2dnZduvPz81FaWorZs2dbPALr5eUFrVaLgwcPIjMzE0uXLoVcLv4a1eTkZKGQValUuHz5cqe7tJbIzMxEaGio4F28eDH+9a9/4d///ne3HV1xr8+DEwRBEARBEATROTYyWZ+3n5JvvvkG9fX1wnNypk6diqamJnz++efCnH/84x/o6OjAlClTuu2Vd2POfUOv16OtrU10jJYxBoVCgfT0dKHP1dUVWq0WWq0WbW1tCAoKwtmzZ6FQKDB48GA4OTmhsrJS5B4+fDgAYMCAAWhqarJ4/cjISOzYsQPnz59HcXGx2fjy5csREhIivNZoNBg9ejQA4OLFi5g6dWqn99bQ0ID8/Hy0trbirbfeEvrb29uRmZmJpKQkAMDAgQNhMBjM1jc1NcHR0bFTP/B/58E3btwo6lsXF4/1G8yf7uvs5AxbW1uzD4TX19dj0KBBXV6HXNJ08ZyNXOSypmzkkoaL52zkkoaL52y8uoi758aNG8KuJgBUVVWhtLQULi4ucHFxwcaNGxEcHIyhQ4fi3//+N9auXQs3NzfhJOeYMWPg7++P559/Hm+//TZaW1vxm9/8BosWLer0o5CW4GYntK2tDTk5Odi6dStKS0uFVlZWBo1G0+nTdxcsWAC5XI6MjAzghzPmISEh2LNnT48eEwwAS5YsQUVFBTw9PTF27FizcRcXF7i5uQlNLpfjiSeewKBBg5CammrReavg3bt3L37+85+jrKxMdH9bt25Fdna28GFfnU6HM2fOmHnOnDkjFLydYek8+JoYy+fB7eztMWasB4o+KRT6Ojo6UFRUiPFeE+7wTpFLii6es5GLXNaUjVzScPGcjVzScPGcjVcXj/T1Q4l6uhH62WefYcKECZgw4f/e+1deeQUTJkzAhg0bYGtri/Lycjz11FMYPXo0li1bBm9vb5w6dUp0vHfv3r1wd3fHzJkz8eSTT2LatGn405/+1KMc3OyEHjlyBI2NjVi2bJnZjl9wcDD0ej38/f3N1slkMqxcuRIJCQmIioqCg4MDkpOTceLECUyePBmJiYmYOHEilEolysvLUVhYCE9PT4sZnJ2dUVNTc8ejvT9GqVRi165dWLhwIZ566imsXLkSbm5uqKurQ15eHi5fvowDBw5Ar9djwYIFZtd2dXVFbGwsjh49ioCAAERHRyM9PR0rV67Er3/9aygUCrz33nvYv38//va3v3WZRaFQmJ3//r6t8/lLI55D3Osx8PDwhOe48djzzm6YTCbMC5rf7fsnl7RcPGcjF7msKRu5pOHiORu5pOHiORuvLuLumD59epcfJ/zwww/v6HBxcTH7ysuewk0RqtfrMWvWLItHToODg5Gamgqj0WhxbUREBNatW4f09HSsXbsWarUaxcXF2Lx5M7Zs2YKqqirY2NhAq9UiNDQUq1at6jTHj59m212efvppfPzxx0hJScGSJUtgNBrh6uqKGTNm4I033sDnn3+OsrIy/PnPfzZb6+joiJkzZ0Kv1yMgIAC/+MUvUFBQgHXr1mHWrFm4efMm3N3d8e6771oswu8G/zlPorGhARnp21FXVwud+xhk7NwFdS+ORpBLGi6es5GLXNaUjVzScPGcjVzScPGcjVcXIQ1krCdP1iGsjq52QgmCIAiCIAiCN/pxs012ZxL+/mVfR0DCE9q+jtBjuPlMKEEQBEEQBEEQBCF9rOj3DARBEARBEARBEPzwU39FilShnVCCIAiCIAiCIAjivkFFKEEQBEEQBEEQBHHfoOO4BEEQBEEQBEEQvYBO4/YO2gklCIIgCIIgCIIg7hu0E0oQBEEQBEEQBNELbGgntFdwsxNaWFgIW1tbBAQEiPovXboEmUwmNBcXF/j5+eHUqVNmDqPRiLi4OHh4eKB///5Qq9WYNGkSUlNT0djYKMybPn06ZDIZNm3aZOYICAiATCZDQkLCHTOXlJRg4cKFGDJkCPr16wetVovnn38eX3zxhWje7t27MWnSJDg4OGDAgAHw8/PDkSNHRHNOnDgBmUwGZ2dnfP/996KxTz/9VLj/e82BfXsx5/EZmDRhHMIWLURFeTm5HnAXz9nIRS5rykYuabh4zkYuabh4zsari7B+uClC9Xo9VqxYgYKCAly5csVs/NixY6ipqUFBQQE0Gg0CAwNx7do1YbyhoQE+Pj7IysrC6tWrUVRUhDNnziApKQklJSXYt2+fyOfq6ors7GxRX3V1NY4fP45hw4bdMe+RI0fg4+ODlpYW7N27FxcuXMCePXvg6OiIuLg4Yd7q1asRFRWF0NBQlJeXo7i4GNOmTcPTTz+N9PR0M++AAQOQn59v9t4MHz78jpl6ytEP3kdaagqiXnwJB97Nh07njuioZaivryfXA+riORu5yGVN2cglDRfP2cglDRfP2Xh1ERKBccD169eZSqViFy9eZKGhoSwpKUkYq6qqYgBYSUmJ0FdeXs4AsMOHDwt9UVFRTKlUsurqaovX6OjoEH728/Nj0dHRTK1Ws9OnTwv9SUlJbO7cuczLy4vFx8d3mre5uZkNGjSIzZs3z+J4Y2MjY4yxwsJCBoBt377dbM4rr7zC7Ozs2OXLlxljjP3zn/9kANj69evZrFmzhHnfffcdc3R0ZHFxcaw3f1ym1s7b/OAFLC5+o/C6uaWdPTptGkvP2NnlOnJJ18VzNnKRy5qykUsaLp6zkUsaLp6z9aXLmkg69lWfN2uEi53QvLw8uLu7Q6fTITw8HJmZmWCMWZxrMpmQk5MDALC3twcAdHR0IDc3F+Hh4dBoNBbX3X6U1d7eHmFhYcjKyhL6srOzERkZece8H374Ierq6rB27VqL405OTgCA/fv3Q6VSISoqymzOq6++itbWVhw6dEjUv3TpUpw6dQqXL18GABw6dAgjR47EI488csdcPaH15k1cOH8OPlN9hT4bGxv4+PiivKyEXA+gi+ds5CKXNWUjlzRcPGcjlzRcPGfj1UVIBy6KUL1ej/DwcACAv78/DAYDTp48KZrj6+sLlUoFpVKJtLQ0eHt7Y+bMmQCA2tpaNDU1QafTidZ4e3tDpVJBpVJh8eLFZteNjIxEXl4empubUVBQAIPBgMDAwDvm/fLLLwEA7u7uXc774osv8PDDDwvF8o/RaDQYOHCg2edHH3roIcyZM0c4KpyZmdmtwrinNDY1or29HWq1WtSvVqtRV1dHrgfQxXM2cpHLmrKRSxounrORSxounrPx6uIRG1nfN2ukz4vQyspKFBcXC0WiXC5HaGgo9Hq9aF5ubi5KSkpw6NAhuLm5ITs7G3Z2dl268/PzUVpaitmzZ8NkMpmNe3l5QavV4uDBg8jMzMTSpUshl4sfGJycnCwUsiqVCpcvX+50l9YSPZl7i8jISGRnZ+M///kPCgsLERYW1q11LS0tMBqNotbS0tLj6xMEQRAEQRAEQfxU9HkRqtfr0dbWBo1GA7lcDrlcjrfeeguHDh2CwWAQ5rm6ukKr1SIoKAjJyckICgoSCqzBgwfDyckJlZWVIvfw4cPh5uaGAQMGdHr9yMhI7NixAwcPHrS447h8+XKUlpYKTaPRYPTo0QCAixcvdnlvo0ePxn/+8x/cvHnTbOzKlSswGo2C68fMmTMHJpMJy5Ytw9y5c81+c9QZKSkpcHR0FLUtm1MsznV2coatra3ZB8Lr6+sxaNCgbl2PXNJy8ZyNXOSypmzkkoaL52zkkoaL52y8ugjp0KdFaFtbG3JycrB161ZRoVdWVgaNRoP9+/dbXLdgwQLI5XJkZGQAP5wrDwkJwZ49eyw+WbcrlixZgoqKCnh6emLs2LFm4y4uLnBzcxOaXC7HE088gUGDBiE1NdWis6mpCQCwaNEi3LhxAzt37jSbk5aWBjs7OwQHB5uNyeVyPPPMMzhx4kSPjuLGxsbCYDCI2pqYWItz7eztMWasB4o+KRT6Ojo6UFRUiPFeE7p9TXJJx8VzNnKRy5qykUsaLp6zkUsaLp6z8erikb4+imutx3Hl3Zjzk3HkyBE0NjZi2bJlcHR0FI0FBwdDr9fD39/fbJ1MJsPKlSuRkJCAqKgoODg4IDk5GSdOnMDkyZORmJiIiRMnQqlUory8HIWFhfD09LSYwdnZGTU1NXc82vtjlEoldu3ahYULF+Kpp57CypUr4ebmhrq6OuTl5eHy5cs4cOAApk6dipdffhlr1qzBzZs3MW/ePLS2tmLPnj34wx/+gDfffBOurq4Wr/G73/0Oa9as6fYuKAAoFAooFApR3/dtnc9fGvEc4l6PgYeHJzzHjceed3bDZDJhXtD8bl+TXNJy8ZyNXOSypmzkkoaL52zkkoaL52y8ughp0KdFqF6vx6xZs8wKUPxQhKampsJoNFpcGxERgXXr1iE9PR1r166FWq1GcXExNm/ejC1btqCqqgo2NjbQarUIDQ3FqlWrOs1x62m2PeHpp5/Gxx9/jJSUFCxZsgRGoxGurq6YMWMG3njjDWHem2++ifHjxyMjIwPr16+Hra0tHnnkEfzlL3/B3LlzO/Xb29v/5EcU/Oc8icaGBmSkb0ddXS107mOQsXMX1L24Lrmk4eI5G7nIZU3ZyCUNF8/ZyCUNF8/ZeHUR0kDGevPkHMJq6GonlCAIgiAIgiB4o1+fbpP1jC0n/tPXEbBm+i/6OkKP6fMHExEEQRAEQRAEQRAPDlb0ewaCIAiCIAiCIAh+sNYHA/U1tBNKEARBEARBEARB3DeoCCUIgiAIgiAIgiDuG3QclyAIgiAIgiAIohfI6Dhur6CdUIIgCIIgCIIgCOK+QTuhBEEQBEEQBEEQvcCGtkJ7Be2EEgRBEARBEARBEPcNqypCCwsLYWtri4CAAFH/pUuXIJPJhObi4gI/Pz+cOnXKzGE0GhEXFwcPDw/0798farUakyZNQmpqKhobG4V506dPh0wmw6ZNm8wcAQEBkMlkSEhI6DLvyJEjhUz9+/fHyJEjERISgn/84x8W85eWlgp9+fn58PHxgaOjIwYMGAAPDw+sWrWqR+9Xdziwby/mPD4DkyaMQ9iihagoLyfXA+7iORu5yGVN2cglDRfP2cglDRfP2Xh1EdaPVRWher0eK1asQEFBAa5cuWI2fuzYMdTU1KCgoAAajQaBgYG4du2aMN7Q0AAfHx9kZWVh9erVKCoqwpkzZ5CUlISSkhLs27dP5HN1dUV2draor7q6GsePH8ewYcO6lTkxMRE1NTWorKxETk4OnJycMGvWLCQlJXW65vjx4wgNDUVwcDCKi4vx+eefIykpCa2trd26Znc5+sH7SEtNQdSLL+HAu/nQ6dwRHbUM9fX15HpAXTxnIxe5rCkbuaTh4jkbuaTh4jkbry7esJH1fbNKmJVw/fp1plKp2MWLF1loaChLSkoSxqqqqhgAVlJSIvSVl5czAOzw4cNCX1RUFFMqlay6utriNTo6OoSf/fz8WHR0NFOr1ez06dNCf1JSEps7dy7z8vJi8fHxXWYeMWIE27Ztm1n/hg0bmI2NDbt48aLF/C+//DKbPn16N9+ZrjG1dt7mBy9gcfEbhdfNLe3s0WnTWHrGzi7XkUu6Lp6zkYtc1pSNXNJw8ZyNXNJw8ZytL13WxB9O/afPmzViNTuheXl5cHd3h06nQ3h4ODIzM8EYszjXZDIhJycHAGBvbw8A6OjoQG5uLsLDw6HRaCyuk932wWJ7e3uEhYUhKytL6MvOzkZkZORd3cvLL78MxhgOHz5scXzo0KE4d+4czp49e1fX6YrWmzdx4fw5+Ez1FfpsbGzg4+OL8rIScj2ALp6zkYtc1pSNXNJw8ZyNXNJw8ZyNVxePyGR936wRqylC9Xo9wsPDAQD+/v4wGAw4efKkaI6vry9UKhWUSiXS0tLg7e2NmTNnAgBqa2vR1NQEnU4nWuPt7Q2VSgWVSoXFixebXTcyMhJ5eXlobm5GQUEBDAYDAgMD7+peXFxc8NBDD+HSpUsWx1esWIFJkyZh3LhxGDlyJBYtWoTMzEy0tLTc1XV/TGNTI9rb26FWq0X9arUadXV15HoAXTxnIxe5rCkbuaTh4jkbuaTh4jkbry5COlhFEVpZWYni4mKhSJTL5QgNDYVerxfNy83NRUlJCQ4dOgQ3NzdkZ2fDzs6uS3d+fj5KS0sxe/ZsmEwms3EvLy9otVocPHgQmZmZWLp0KeRy8TfbJCcnC4WsSqXC5cuX73hPjDGznddbKJVKvPfee/jqq6+wfv16qFQqvPrqq5g8eTK+++67Tp0tLS0wGo2idi8LV4IgCIIgCIIgiLvFKr4nVK/Xo62tTXSMljEGhUKB9PR0oc/V1RVarRZarRZtbW0ICgrC2bNnoVAoMHjwYDg5OaGyslLkHj58OABgwIABaGpqsnj9yMhI7NixA+fPn0dxcbHZ+PLlyxESEiK87uy47y3q6+tRW1uLUaNGdTnv4YcfxsMPP4xf//rXWLduHUaPHo3c3Fw899xzFuenpKRg48aNor51cfFYv8H8Kb7OTs6wtbU1+0B4fX09Bg0a1GUucknTxXM2cpHLmrKRSxounrORSxounrPx6uIRG1jpedg+hvud0La2NuTk5GDr1q0oLS0VWllZGTQaDfbv329x3YIFCyCXy5GRkQH8cPY8JCQEe/bssfhk3a5YsmQJKioq4OnpibFjx5qNu7i4wM3NTWi375Tezh/+8AfY2Nhg3rx53c4wcuRIODg4oLm5udM5sbGxMBgMorYmJtbiXDt7e4wZ64GiTwqFvo6ODhQVFWK814Ru5yKXdFw8ZyMXuawpG7mk4eI5G7mk4eI5G68uQjpwvxN65MgRNDY2YtmyZXB0dBSNBQcHQ6/Xw9/f32ydTCbDypUrkZCQgKioKDg4OCA5ORknTpzA5MmTkZiYiIkTJ0KpVKK8vByFhYXw9PS0mMHZ2Rk1NTV3PNprievXr+Pq1atobW1FVVUV9uzZg127diElJQVubm4W1yQkJOC7777Dk08+iREjRqCpqQnbt29Ha2srHn/88U6vpVAooFAoRH3ft3WebWnEc4h7PQYeHp7wHDcee97ZDZPJhHlB83t8n+SShovnbOQilzVlI5c0XDxnI5c0XDxn49XFG9b6YKC+hvsiVK/XY9asWWYFKH4oQlNTU2E0Gi2ujYiIwLp165Ceno61a9dCrVajuLgYmzdvxpYtW1BVVQUbGxtotVqEhoZi1apVneZwcnLqVf4NGzZgw4YNsLe3x9ChQ+Hj44Pjx4/jscce63SNn58fduzYgWeeeQbXrl2Ds7MzJkyYgL///e9mD1a6G/znPInGhgZkpG9HXV0tdO5jkLFzF9S9OBpBLmm4eM5GLnJZUzZyScPFczZyScPFczZeXYQ0kLHOvueEkARd7YQSBEEQBEEQBG/0436b7P+T8bHlb7u4n7zoO7KvI/QYK/ojJgiCIAiCIAiC4AcbOo7bK7h/MBFBEARBEARBEAQhHWgnlCAIgiAIgiAIohfY0JOJegXthBIEQRAEQRAEQRD3DSpCCYIgCIIgCIIgiPsGHcclCIIgCIIgCILoBXQat3fQTihBEARBEARBEARx37D6IrSwsBC2trYICAgQ9V+6dAkymUxoLi4u8PPzw6lTp8wcRqMRcXFx8PDwQP/+/aFWqzFp0iSkpqaisbFRmDd9+nTIZDJs2rTJzBEQEACZTIaEhIQu844cOVKU61a75Xz//fdhb2+PM2fOiNZt3boVgwYNwtWrV3v8HnXFgX17MefxGZg0YRzCFi1ERXk5uR5wF8/ZyEUua8pGLmm4eM5GLmm4eM7Gq4uwfqy+CNXr9VixYgUKCgpw5coVs/Fjx46hpqYGBQUF0Gg0CAwMxLVr14TxhoYG+Pj4ICsrC6tXr0ZRURHOnDmDpKQklJSUYN++fSKfq6srsrOzRX3V1dU4fvw4hg0b1q3MiYmJqKmpEbUVK1YAAJ588kk888wzeOaZZ9DS0gIAOH/+PNavX48dO3Zg6NChvXqfLHH0g/eRlpqCqBdfwoF386HTuSM6ahnq6+vJ9YC6eM5GLnJZUzZyScPFczZyScPFczZeXbxhI5P1ebNKmBVz/fp1plKp2MWLF1loaChLSkoSxqqqqhgAVlJSIvSVl5czAOzw4cNCX1RUFFMqlay6utriNTo6OoSf/fz8WHR0NFOr1ez06dNCf1JSEps7dy7z8vJi8fHxXWYeMWIE27ZtW5dzjEYjGzFiBIuJiWGtra1s4sSJbOHChXd4Nyxjau28zQ9ewOLiNwqvm1va2aPTprH0jJ1driOXdF08ZyMXuawpG7mk4eI5G7mk4eI5W1+6rIldRf/t82aNWPVOaF5eHtzd3aHT6RAeHo7MzEwwxizONZlMyMnJAQDY29sDADo6OpCbm4vw8HBoNBqL62S3/XbB3t4eYWFhyMrKEvqys7MRGRl5z+5rwIAByMzMxNatWxEWFoavv/4ab7311j3zA0DrzZu4cP4cfKb6Cn02Njbw8fFFeVkJuR5AF8/ZyEUua8pGLmm4eM5GLmm4eM7Gq4tHZLK+b9aIVReher0e4eHhAAB/f38YDAacPHlSNMfX1xcqlQpKpRJpaWnw9vbGzJkzAQC1tbVoamqCTqcTrfH29oZKpYJKpcLixYvNrhsZGYm8vDw0NzejoKAABoMBgYGB3c4dExMj+G+12z+rOmPGDCxYsAB5eXnYvn071Gp1j96bO9HY1Ij29nYzr1qtRl1dHbkeQBfP2chFLmvKRi5puHjORi5puHjOxquLkA5WW4RWVlaiuLhYKBLlcjlCQ0Oh1+tF83Jzc1FSUoJDhw7Bzc0N2dnZsLOz69Kdn5+P0tJSzJ49GyaTyWzcy8sLWq0WBw8eRGZmJpYuXQq5XPxtN8nJyaIi8/Lly8LYmjVrUFpaKmoTJ04Ura+ursbRo0fh4OBg8WFKlmhpaYHRaBS1W58rJQiCIAiCIAiC4AGr/Z5QvV6PtrY20TFaxhgUCgXS09OFPldXV2i1Wmi1WrS1tSEoKAhnz56FQqHA4MGD4eTkhMrKSpF7+PDhwA/HYpuamixePzIyEjt27MD58+dRXFxsNr58+XKEhIQIr3+cc9CgQXBzc+vy/p5//nl4e3tj3bp1ePzxx7FgwQL4+fl1uSYlJQUbN24U9a2Li8f6DeZP7HV2coatra3ZB8Lr6+sxaNCgLq9DLmm6eM5GLnJZUzZyScPFczZyScPFczZeXTxitTt6fYxVvm9tbW3IycnB1q1bRbuJZWVl0Gg02L9/v8V1CxYsgFwuR0ZGBvDDefSQkBDs2bPH4pN1u2LJkiWoqKiAp6cnxo4dazbu4uICNzc3od2+U9oVu3btwunTp6HX6/HYY48hOjoakZGRaG5u7nJdbGwsDAaDqK2JibU4187eHmPGeqDok0Khr6OjA0VFhRjvNaHbWcklHRfP2chFLmvKRi5puHjORi5puHjOxquLkA5WuRN65MgRNDY2YtmyZXB0dBSNBQcHQ6/Xw9/f32ydTCbDypUrkZCQgKioKDg4OCA5ORknTpzA5MmTkZiYiIkTJ0KpVKK8vByFhYXw9PS0mMHZ2Rk1NTV3PNprievXr5t936eDgwMGDhyI//73v3jllVeQlpaGESNGAAA2b96MDz74AK+99hr++Mc/dupVKBRQKBSivu/bOs+xNOI5xL0eAw8PT3iOG4897+yGyWTCvKD5Pb4ncknDxXM2cpHLmrKRSxounrORSxounrPx6uKN2x9iSnQPqyxC9Xo9Zs2aZVaA4ociNDU1FUaj0eLaiIgIrFu3Dunp6Vi7di3UajWKi4uxefNmbNmyBVVVVbCxsYFWq0VoaChWrVrVaQ4nJ6de5d+wYQM2bNgg6ouKisJbb72FZcuWYerUqXjhhReEMQcHB2RnZ2P69OndOpbbXfznPInGhgZkpG9HXV0tdO5jkLFzF9S9OBpBLmm4eM5GLnJZUzZyScPFczZyScPFczZeXYQ0kLHOvtOEkARd7YQSBEEQBEEQBG/0s6Jtst2ffd3XERAx0bWvI/QYK/ojJgiCIAiCIAiC4Ac6jNs7rPLBRARBEARBEARBEIR1QjuhBEEQBEEQBEEQvcCGHkzUK2gnlCAIgiAIgiAIgrhvUBFKEARBEARBEARB3DfoOC5BEARBEARBEEQvoMO4vYN2QgmCIAiCIAiCIIj7BvdFaGFhIWxtbREQECDqv3TpEmQymdBcXFzg5+eHU6dOmTmMRiPi4uLg4eGB/v37Q61WY9KkSUhNTUVjY6Mwb/r06ZDJZNi0aZOZIyAgADKZDAkJCV3mHTlypCjXrXbL+f7778Pe3h5nzpwRrdu6dSsGDRqEAwcOWFz/43bixIkev4+dcWDfXsx5fAYmTRiHsEULUVFeTq4H3MVzNnKR68d8/tmnWPHicsyaPg1eHjr84/ixXme619nIJR0Xz9nIJQ0Xz9l4dfGETNb3zRrhvgjV6/VYsWIFCgoKcOXKFbPxY8eOoaamBgUFBdBoNAgMDMS1a9eE8YaGBvj4+CArKwurV69GUVERzpw5g6SkJJSUlGDfvn0in6urK7Kzs0V91dXVOH78OIYNG9atzImJiaipqRG1FStWAACefPJJPPPMM3jmmWfQ0tICADh//jzWr1+PHTt2YP78+aJ1ISEh8Pf3F/X5+vr26r28naMfvI+01BREvfgSDrybD53OHdFRy1BfX0+uB9TFczZyket2TKbvoNPpELs+vsdrf+ps5JKGi+ds5JKGi+dsvLoIicA45vr160ylUrGLFy+y0NBQlpSUJIxVVVUxAKykpEToKy8vZwDY4cOHhb6oqCimVCpZdXW1xWt0dHQIP/v5+bHo6GimVqvZ6dOnhf6kpCQ2d+5c5uXlxeLj47vMPGLECLZt27Yu5xiNRjZixAgWExPDWltb2cSJE9nChQstzo2IiGBPP/10l76uMLV23uYHL2Bx8RuF180t7ezRadNYesbOLteRS7ounrORi1xdtdGjR7P3jn50Vw5e75NcffvvGK/ZyCUNF8/Z+tJlTez9/Os+b9YI1zuheXl5cHd3h06nQ3h4ODIzM8EYszjXZDIhJycHAGBvbw8A6OjoQG5uLsLDw6HRaCyuk922h21vb4+wsDBkZWUJfdnZ2YiMjLxn9zVgwABkZmZi69atCAsLw9dff4233nrrnvm7Q+vNm7hw/hx8pv7/XVUbGxv4+PiivKyEXA+gi+ds5CLXTw2v90ku+juRXNJ18ZyNVxeP3OljdPejWSNcF6F6vR7h4eEAAH9/fxgMBpw8eVI0x9fXFyqVCkqlEmlpafD29sbMmTMBALW1tWhqaoJOpxOt8fb2hkqlgkqlwuLFi82uGxkZiby8PDQ3N6OgoAAGgwGBgYHdzh0TEyP4b7XbP6s6Y8YMLFiwAHl5edi+fTvUanWP3pu7pbGpEe3t7WbXVavVqKurI9cD6OI5G7nI9VPD632Si/5OJJd0XTxn49VFSAdui9DKykoUFxcLRaJcLkdoaCj0er1oXm5uLkpKSnDo0CG4ubkhOzsbdnZ2Xbrz8/NRWlqK2bNnw2QymY17eXlBq9Xi4MGDyMzMxNKlSyGXi7/NJjk5WVRkXr58WRhbs2YNSktLRW3ixImi9dXV1Th69CgcHBwsPkypN7S0tMBoNIrarc+dEgRBEARBEARxb7HhoFkj3H5PqF6vR1tbm+gYLWMMCoUC6enpQp+rqyu0Wi20Wi3a2toQFBSEs2fPQqFQYPDgwXByckJlZaXIPXz4cOCHY7FNTU0Wrx8ZGYkdO3bg/PnzKC4uNhtfvnw5QkJChNc/zjlo0CC4ubl1eX/PP/88vL29sW7dOjz++ONYsGAB/Pz8uvXedEZKSgo2btwo6lsXF4/1G8yf6Ovs5AxbW1uzD4TX19dj0KBBPbouuaTh4jkbucj1U8PrfZKL/k4kl3RdPGfj1UVIBy6L57a2NuTk5GDr1q2i3cSysjJoNBrs37/f4roFCxZALpcjIyMD+OG8eUhICPbs2WPxybpdsWTJElRUVMDT0xNjx441G3dxcYGbm5vQbt8p7Ypdu3bh9OnT0Ov1eOyxxxAdHY3IyEg0Nzf3KOPtxMbGwmAwiNqamFiLc+3s7TFmrAeKPikU+jo6OlBUVIjxXhN6dF1yScPFczZykeunhtf7JBf9nUgu6bp4zsari5AOXO6EHjlyBI2NjVi2bBkcHR1FY8HBwdDr9fD39zdbJ5PJsHLlSiQkJCAqKgoODg5ITk7GiRMnMHnyZCQmJmLixIlQKpUoLy9HYWEhPD09LWZwdnZGTU3NHY/2WuL69eu4evWqqM/BwQEDBw7Ef//7X7zyyitIS0vDiBEjAACbN2/GBx98gNdeew1//OMfe3y9WygUCigUClHf922dz18a8RziXo+Bh4cnPMeNx553dsNkMmFe0PweX5tc0nDxnI1c5Lqd75qbRR+FqP7mG1y8cAGOjo4Y1snD6O5XNnJJw8VzNnJJw8VzNl5dvGGtDwbqa7gsQvV6PWbNmmVWgOKHIjQ1NRVGo9Hi2oiICKxbtw7p6elYu3Yt1Go1iouLsXnzZmzZsgVVVVWwsbGBVqtFaGgoVq1a1WkOJyenXuXfsGEDNmzYIOqLiorCW2+9hWXLlmHq1Kl44YUXhDEHBwdkZ2dj+vTp9+RYbnfxn/MkGhsakJG+HXV1tdC5j0HGzl1Q9+JoBLmk4eI5G7nIdTvnzp3Fr597RnidlpoCAHjq6SD8LnlTn2YjlzRcPGcjlzRcPGfj1UVIAxnr7DtPCEnQ1U4oQRAEQRAEQfBGPy63ySyTV9qzj/z9FIT8suenf/oaK/ojJgiCIAiCIAiC4Ac6jNs7uHwwEUEQBEEQBEEQBCFNaCeUIAiCIAiCIAiiF9CDiXoH7YQSBEEQBEEQBEEQ9w3aCSUIgiDuKW3t9/Z5d3Jb+i0zQRAEQUgJKkIJgiAIgiAIgiB6AR0r7R30vhEEQRAEQRAEQRD3DW6L0MLCQtja2iIgIEDUf+nSJchkMqG5uLjAz88Pp06dMnMYjUbExcXBw8MD/fv3h1qtxqRJk5CamorGxkZh3vTp0yGTybBpk/mXmwcEBEAmkyEhIaHLvCNHjsSbb77Z6fjXX3+NyMhIaDQa2NvbY8SIEXj55ZdRX19vNverr77Cc889h5///OdQKBQYNWoUFi9ejM8++6zLDL3hwL69mPP4DEyaMA5hixaiorycXA+4i+ds5LJ+V6D/DHiPdzdrm5IS+zwbuchlbdnIJQ0Xz9l4dfHEj+uSvmrWCLdFqF6vx4oVK1BQUIArV8y/BPbYsWOoqalBQUEBNBoNAgMDce3aNWG8oaEBPj4+yMrKwurVq1FUVIQzZ84gKSkJJSUl2Ldvn8jn6uqK7OxsUV91dTWOHz+OYcOG3dW9/Oc//8HEiRPx5ZdfYv/+/fjqq6/w9ttv4/jx45g6dSoaGhqEuZ999hm8vb3xxRdfYOfOnTh//jzy8/Ph7u6OV1999a5y3M7RD95HWmoKol58CQfezYdO547oqGUWC2NyPRgunrORSxqud/YdxIf/OCW0jD9lAgBmPTG7x657nY1c5LKmbOSShovnbLy6CInAOOT69etMpVKxixcvstDQUJaUlCSMVVVVMQCspKRE6CsvL2cA2OHDh4W+qKgoplQqWXV1tcVrdHR0CD/7+fmx6Ohoplar2enTp4X+pKQkNnfuXObl5cXi4+O7zDxixAi2bds2i2P+/v7s5z//Ofvuu+9E/TU1NczBwYEtX75cyOTh4cG8vb1Ze3u7maexsbHLDJYwtXbe5gcvYHHxG4XXzS3t7NFp01h6xs4u15FLui6es5HLelzXv+/odovf+AabMXMWM5raO53D632SS/ounrORSxounrP1pcua+N+ymj5v1giXO6F5eXlwd3eHTqdDeHg4MjMzwZjlpy2aTCbk5OQAAOzt7QEAHR0dyM3NRXh4ODQajcV1t29d29vbIywsDFlZWUJfdnY2IiMj7+peGhoa8OGHH+LFF19E//79RWNDhw5FWFgYcnNzwRhDaWkpzp07h1dffRU2NuZ/NE5OTneV5ce03ryJC+fPwWeqr9BnY2MDHx9flJeVkOsBdPGcjVzScJm5W2/i/ff+iqfnze/VcSJe75Nc0nDxnI1c0nDxnI1XF4/IOGjWCJdFqF6vR3h4OADA398fBoMBJ0+eFM3x9fWFSqWCUqlEWloavL29MXPmTABAbW0tmpqaoNPpRGu8vb2hUqmgUqmwePFis+tGRkYiLy8Pzc3NKCgogMFgQGBg4F3dy5dffgnGGMaMGWNxfMyYMWhsbERtbS2+/PJLAIC7u/tdXbM7NDY1or29HWq1WtSvVqtRV1dHrgfQxXM2cknDdTv//Mdx3Lh+HXOfDurVel7vk1zScPGcjVzScPGcjVcXIR24K0IrKytRXFwsFIlyuRyhoaHQ6/Wiebm5uSgpKcGhQ4fg5uaG7Oxs2NnZdenOz89HaWkpZs+eDZPJZDbu5eUFrVaLgwcPIjMzE0uXLoVcLv4Wm+TkZKGQValUuHz5crfuq7Od3J7O6YqWlhYYjUZRa2lpuSsnQRDET8Xh/IPwffRXGPzQkL6OQhAEQRC9Qibr+2aNcPc9oXq9Hm1tbaJjtIwxKBQKpKenC32urq7QarXQarVoa2tDUFAQzp49C4VCgcGDB8PJyQmVlZUi9/DhwwEAAwYMQFNTk8XrR0ZGYseOHTh//jyKi4vNxpcvX46QkBDhdWfHfW/h5uYGmUyGCxcuICjI/Lf9Fy5cgLOzMwYPHozRo0cDAC5evIgJEyZ06bVESkoKNm7cKOpbFxeP9RvMn+zr7OQMW1tbsw+E19fXY9CgQT26Lrmk4eI5G7mk4foxNVeqUfxJIbZs+2OvHbzeJ7mk4eI5G7mk4eI5G68uQjpwtRPa1taGnJwcbN26FaWlpUIrKyuDRqPB/v37La5bsGAB5HI5MjIygB/OmYeEhGDPnj0Wn6zbFUuWLEFFRQU8PT0xduxYs3EXFxe4ubkJ7fad0ttRq9V4/PHHkZGRYbb7evXqVezduxehoaGQyWT45S9/ibFjx2Lr1q3o6Ogwc3VWON8iNjYWBoNB1NbExFqca2dvjzFjPVD0SaHQ19HRgaKiQoz36lkBTC5puHjORi5puH7MX//yv3B2UWPar/x67eD1PsklDRfP2cglDRfP2Xh1EdKBq53QI0eOoLGxEcuWLYOjo6NoLDg4GHq9Hv7+/mbrZDIZVq5ciYSEBERFRcHBwQHJyck4ceIEJk+ejMTEREycOBFKpRLl5eUoLCyEp6enxQzOzs6oqam549FeS1RXV6O0tFTUN2LECKSnp8PX1xezZ8/GG2+8gVGjRuHcuXNYs2YNfvaznyEpKUm4j6ysLMyaNQu/+tWvsG7dOri7u+PGjRv429/+hr///e9mn439MQqFAgqFQtT3fVvneZdGPIe412Pg4eEJz3Hjseed3TCZTJgXNL/H904uabh4zkYuabjww//5+OvhfAQ+Ne+Ov8i7n9nIRS5rykYuabh4zsarizdsrOzRQAUFBdiyZQs+//xz1NTUID8/H/PmzRPGGWOIj4/Hn//8ZzQ1NeHRRx/FW2+9Ba1WK8xpaGjAihUr8Le//Q02NjYIDg7GH/7wB6hUqm7n4KoI1ev1mDVrllkBih+K0NTUVBiNRotrIyIisG7dOqSnp2Pt2rVQq9UoLi7G5s2bsWXLFlRVVcHGxgZarRahoaFYtWpVpzl6+xTatLQ0pKWlifreeecdhIeH47PPPkN8fDxCQkLQ0NCAoUOHYt68eYiPj4eLi4swf/Lkyfjss8+QlJSE559/HnV1dRg2bBh8fX3x5ptv9ipXZ/jPeRKNDQ3ISN+Ourpa6NzHIGPnLqh7cTSCXNJw8ZyNXNJwAUDRJx/jas0VPD3v7v/PB6/3SS5puHjORi5puHjOxquLuDuam5vh5eWFyMhIzJ9v/t/h1NRUbN++Hbt378aoUaMQFxeH2bNn4/z58+jXrx8AICwsDDU1Nfjoo4/Q2tqK5557Di+88AL27dvX7RwydrdPwyG4pqudUIIgiJ+CtvZ7+58Vua11/ZaZIAiCuDv6cbVN1jVHzl7r6wgI9OzdA/5kMploJ5QxBo1Gg1dffRWrV68GABgMBgwZMgTZ2dlYtGgRLly4gLFjx+LTTz/FxIkTAQBHjx7Fk08+iW+++eaOz8u5BVefCSUIgiAIgiAIgiC6z736hoyqqipcvXoVs2bNEvocHR0xZcoUFBb+32d6CwsL4eTkJBSgADBr1izY2NigqKio29eiIpQgCIIgCIIgCMJKSUlJgaOjo6ilpKT02HP16lUAwJAh4p3VIUOGCGNXr17FQw89JBqXy+VwcXER5nQHK9rsJgiCIAiCIAiC4AcZBw8mio2NxSuvvCLqu/1hpbxBRShBEARBEARBEISVYukbMnrD0KFDAQDXrl3DsGHDhP5r167hl7/8pTDn22+/Fa1ra2sTHrzaXeg4LkEQBHFPkdvK7mkjCIIgCF6Ryfq+3StGjRqFoUOH4vjx40Kf0WhEUVERpk6dCgCYOnUqmpqa8Pnnnwtz/vGPf6CjowNTpkzp9rVoJ5QgCIIgCIIgCOIB4MaNG/jqq6+E11VVVSgtLYWLiwuGDx+OVatW4Y033oBWqxW+okWj0QhP0B0zZgz8/f3x/PPP4+2330Zrayt+85vfYNGiRd1+Mi6oCCUIgiAIgiAIgngw+Oyzz/DYY48Jr299ljQiIgLZ2dlYu3Ytmpub8cILL6CpqQnTpk3D0aNHhe8IBYC9e/fiN7/5DWbOnAkbGxsEBwdj+/btPcrBzXHcwsJC2NraIiAgQNR/6dIlyGQyobm4uMDPzw+nTp0ycxiNRsTFxcHDwwP9+/eHWq3GpEmTkJqaisbGRmHe9OnTIZPJsGnTJjNHQEAAZDIZEhISusw7cuRIyGQyHDhwwGzMw8MDMpkM2dnZZvM/+eQT0dxVq1Zh+vTpwuuEhAThXm1tbeHq6ooXXngBDQ0NXebpLQf27cWcx2dg0oRxCFu0EBXl5eR6wF08ZyMXuawpG7mk4eI5G7mk4eI5G68unrCBrM9bT5g+fToYY2btVt0ik8mQmJiIq1ev4vvvv8exY8cwevRokcPFxQX79u3D9evXYTAYkJmZCZVK1cP3jRP0ej1WrFiBgoICXLlyxWz82LFjqKmpQUFBATQaDQIDA3Ht2v//ctiGhgb4+PggKysLq1evRlFREc6cOYOkpCSUlJRg3759Ip+rq6uoSASA6upqHD9+XPRB3K5wdXVFVlaWqO+TTz7B1atXoVQqzeb369cPMTExd/R6eHigpqYGly9fRlZWFo4ePYro6OhuZeoJRz94H2mpKYh68SUceDcfOp07oqOWob6+nlwPqIvnbOQilzVlI5c0XDxnI5c0XDxn49VFSATGAdevX2cqlYpdvHiRhYaGsqSkJGGsqqqKAWAlJSVCX3l5OQPADh8+LPRFRUUxpVLJqqurLV6jo6ND+NnPz49FR0cztVrNTp8+LfQnJSWxuXPnMi8vLxYfH99l5hEjRrDXXnuNKRQKdvnyZaH/+eefZytWrGCOjo4sKytLNH/lypXM3t6evffee0L/yy+/zPz8/ITX8fHxzMvLS3StV155hTk7O3eZpzNMrZ23+cELWFz8RuF1c0s7e3TaNJaesbPLdeSSrovnbOQilzVlI5c0XDxnI5c0XDxn60uXNfHB2W/7vFkjXOyE5uXlwd3dHTqdDuHh4cjMzARjzOJck8mEnJwcAIC9vT0AoKOjA7m5uQgPD+/0A7Gy2x4dZW9vj7CwMNFOZnZ2NiIjI7ude8iQIZg9ezZ2794NAPjuu++Qm5vbqWPUqFFYvnw5YmNj0dHR0a1rXLp0CR9++KFwr/eK1ps3ceH8OfhM9RX6bGxs4OPji/KyEnI9gC6es5GLXNaUjVzScPGcjVzScPGcjVcXj/T1k3Hv5dNx7ydcFKF6vR7h4eEAAH9/fxgMBpw8eVI0x9fXFyqVCkqlEmlpafD29sbMmTMBALW1tWhqaoJOpxOt8fb2hkqlgkqlwuLFi82uGxkZiby8PDQ3N6OgoAAGgwGBgYE9yh4ZGYns7GwwxnDw4EE8/PDDwvfoWGL9+vWoqqrC3r17O51TUVEBlUqF/v37Y9SoUTh37ly3jvH2hMamRrS3t0OtVov61Wo16urqyPUAunjORi5yWVM2cknDxXM2cknDxXM2Xl2EdOjzIrSyshLFxcVCkSiXyxEaGgq9Xi+al5ubi5KSEhw6dAhubm7Izs6GnZ1dl+78/HyUlpZi9uzZMJlMZuNeXl7QarU4ePAgMjMzsXTpUsjl4gcGJycnC4WsSqXC5cuXReMBAQG4ceMGCgoKkJmZeced1MGDB2P16tXYsGEDbt68aXGOTqdDaWkpPv30U8TExGD27NlYsWJFl14AaGlpgdFoFLWWlpY7riMIgiAIgiAIouf09S4o7YT2Er1ej7a2Nmg0Gsjlcsjlcrz11ls4dOgQDAaDMM/V1RVarRZBQUFITk5GUFCQUGANHjwYTk5OqKysFLmHDx8ONzc3DBgwoNPrR0ZGYseOHTh48KDFAnL58uUoLS0V2u3HfeVyOZYuXYr4+HgUFRUhLCzsjvf8yiuvwGQyISMjw+K4vb093Nzc4OnpiU2bNsHW1hYbN268ozclJQWOjo6itmVzisW5zk7OsLW1NftAeH19PQYNGnTHa5FLei6es5GLXNaUjVzScPGcjVzScPGcjVcXIR36tAhta2tDTk4Otm7dKir0ysrKoNFosH//fovrFixYALlcLhRxNjY2CAkJwZ49eyw+WbcrlixZgoqKCnh6emLs2LFm4y4uLnBzcxPa7Tul+KGQPXnyJJ5++mk4Ozvf8ZoqlQpxcXFISkrC9evX7zh//fr1SEtLu+O9xcbGwmAwiNqamFiLc+3s7TFmrAeKPikU+jo6OlBUVIjxXhPumIlc0nPxnI1c5LKmbOSShovnbOSShovnbLy6COlgXlHdR44cOYLGxkYsW7YMjo6OorHg4GDo9Xr4+/ubrZPJZFi5ciUSEhIQFRUFBwcHJCcn48SJE5g8eTISExMxceJEKJVKlJeXo7CwEJ6enhYzODs7o6am5o5He7tizJgxqKurg4ODQ7fXvPDCC9i2bRv27duHKVOmdDl36tSpGD9+PJKTk5Gent7pPIVCAYVCIer7vq1z79KI5xD3egw8PDzhOW489ryzGyaTCfOC5nf7PsglLRfP2chFLmvKRi5puHjORi5puHjOxquLN2Q9/J5O4v/o0yJUr9dj1qxZZgUofihCU1NTYTQaLa6NiIjAunXrkJ6ejrVr10KtVqO4uBibN2/Gli1bUFVVBRsbG2i1WoSGhmLVqlWd5nBycrrre7n9w9Z3ws7ODr/73e+wZMmSbs3/7W9/i2effRYxMTFwdXXtZUox/nOeRGNDAzLSt6OurhY69zHI2LkL6l4cjSCXNFw8ZyMXuawpG7mk4eI5G7mk4eI5G68uQhrIWGffhUJIgq52QgmCIAiCIAiCN/r16TZZzzh+se+f8DvT3fqK+T5/MBFBEARBEARBEATx4EBFKEEQBEEQBEEQBHHfsKLNboIgCIIgCIIgCH6gBxP1DtoJJQiCIAiCIAiCIO4btBNKEARBEARBEATRC2S0EdoraCeUIAiCIAiCIAiCuG9QEUoQBEEQBEEQBEHcN7goQgsLC2Fra4uAgABR/6VLlyCTyYTm4uICPz8/nDp1ysxhNBoRFxcHDw8P9O/fH2q1GpMmTUJqaioaGxuFedOnT4dMJsOmTZvMHAEBAZDJZEhISOgy78iRIyGTyXDgwAGzMQ8PD8hkMmRnZ4v6P/74Yzz55JNwdnZGv379MG7cOPz+979He3u7aN6P71epVEKr1eLZZ5/F559/3mWm3nJg317MeXwGJk0Yh7BFC1FRXk6uB9zFczZykevHfP7Zp1jx4nLMmj4NXh46/OP4sV5nutfZyCUdF8/ZyCUNF8/ZeHXxhIyDf6wRLopQvV6PFStWoKCgAFeuXDEbP3bsGGpqalBQUACNRoPAwEBcu3ZNGG9oaICPjw+ysrKwevVqFBUV4cyZM0hKSkJJSQn27dsn8rm6upoVidXV1Th+/DiGDRvWrcyurq7IysoS9X3yySe4evUqlEqlqD8/Px9+fn74+c9/jn/+85+4ePEiXn75ZbzxxhtYtGgRGGOi+VlZWaipqcG5c+ewY8cO3LhxA1OmTEFOTk63snWXox+8j7TUFES9+BIOvJsPnc4d0VHLUF9fT64H1MVzNnKR63ZMpu+g0+kQuz6+x2t/6mzkkoaL52zkkoaL52y8ugiJwPqY69evM5VKxS5evMhCQ0NZUlKSMFZVVcUAsJKSEqGvvLycAWCHDx8W+qKiophSqWTV1dUWr9HR0SH87Ofnx6Kjo5larWanT58W+pOSktjcuXOZl5cXi4+P7zLziBEj2GuvvcYUCgW7fPmy0P/888+zFStWMEdHR5aVlcUYY+zGjRtMrVaz+fPnm3n++te/MgDswIEDQh8Alp+fbzb3mWeeYQMGDGANDQ1dZrsdU2vnbX7wAhYXv1F43dzSzh6dNo2lZ+zsch25pOviORu5yNVVGz16NHvv6Ed35eD1PsnVt/+O8ZqNXNJw8ZytL13WxMnK+j5v1kif74Tm5eXB3d0dOp0O4eHhyMzMNNsZvIXJZBJ2A+3t7QEAHR0dyM3NRXh4ODQajcV1stseW2Vvb4+wsDDRTmZ2djYiIyO7nXvIkCGYPXs2du/eDQD47rvvkJuba+b4+9//jvr6eqxevdrMMXfuXIwePRr79++/4/V++9vf4vr16/joo4+6nbErWm/exIXz5+Az1Vfos7GxgY+PL8rLSsj1ALp4zkYucv3U8Hqf5KK/E8klXRfP2Xh1EdKhz4tQvV6P8PBwAIC/vz8MBgNOnjwpmuPr6wuVSgWlUom0tDR4e3tj5syZAIDa2lo0NTVBp9OJ1nh7e0OlUkGlUmHx4sVm142MjEReXh6am5tRUFAAg8GAwMDAHmWPjIxEdnY2GGM4ePAgHn74Yfzyl78Uzfniiy8AAGPGjLHocHd3F+Z0hbu7O/DD52TvBY1NjWhvb4darRb1q9Vq1NXVkesBdPGcjVzk+qnh9T7JRX8nkku6Lp6z8eoipEOfFqGVlZUoLi4WikS5XI7Q0FDo9XrRvNzcXJSUlODQoUNwc3NDdnY27OzsunTn5+ejtLQUs2fPhslkMhv38vKCVqvFwYMHkZmZiaVLl0IuF39tanJyslDIqlQqXL58WTQeEBCAGzduoKCgAJmZmV3upHa2u9tdbq2/fVf3x7S0tMBoNIpaS0vLXV2XIAiCIAiCIAjL9PVDiaz1wUTybsz5ydDr9WhraxMdo2WMQaFQID09XehzdXWFVquFVqtFW1sbgoKCcPbsWSgUCgwePBhOTk6orKwUuYcPHw4AGDBgAJqamixePzIyEjt27MD58+dRXFxsNr58+XKEhIQIr28/7iuXy7F06VLEx8ejqKgI+fn5Zo7Ro0cDAC5cuABfX1+z8QsXLmDs2LFdvk+35gHAqFGjOp2TkpKCjRs3ivrWxcVj/Qbzp/06OznD1tbW7APh9fX1GDRo0B3zkEt6Lp6zkYtcPzW83ie56O9EcknXxXM2Xl2EdOizndC2tjbk5ORg69atKC0tFVpZWRk0Gk2nn5NcsGAB5HI5MjIygB/OlIeEhGDPnj0Wn6zbFUuWLEFFRQU8PT0tFoIuLi5wc3MT2u07pfihkD158iSefvppODs7m40/8cQTcHFxwdatW83G/vrXv+LLL7+0eFz4dt58800MHDgQs2bN6nRObGwsDAaDqK2JibU4187eHmPGeqDok0Khr6OjA0VFhRjvNeGOecglPRfP2chFrp8aXu+TXPR3Irmk6+I5G68uHpHJ+r5ZI322E3rkyBE0NjZi2bJlcHR0FI0FBwdDr9fD39/fbJ1MJsPKlSuRkJCAqKgoODg4IDk5GSdOnMDkyZORmJiIiRMnQqlUory8HIWFhfD09LSYwdnZGTU1NXc82tsVY8aMQV1dHRwcHCyOK5VK7Ny5E4sWLcILL7yA3/zmNxg4cCCOHz+ONWvWYMGCBaLdVgBoamrC1atX0dLSgi+++AI7d+7EX/7yF+Tk5MDJyanTLAqFAgqFQtT3fVvn2ZdGPIe412Pg4eEJz3Hjseed3TCZTJgXNL+nbwO5JOLiORu5yHU73zU3iz4mUf3NN7h44QIcHR0xrJMH1d2vbOSShovnbOSShovnbLy6CGnQZ0WoXq/HrFmzzApQ/FCEpqamwmg0WlwbERGBdevWIT09HWvXroVarUZxcTE2b96MLVu2oKqqCjY2NtBqtQgNDcWqVas6zdFVUdddbv+g9e0sWLAA//znP5GUlIRf/epX+P7776HVarFu3TqsWrXK7HOezz33HACgX79++NnPfoZp06ahuLgYjzzyyF1n/TH+c55EY0MDMtK3o66uFjr3McjYuQvqXhyNIJc0XDxnIxe5bufcubP49XPPCK/TUlMAAE89HYTfJW/q02zkkoaL52zkkoaL52y8ughpIGN3+8Qcgmu62gklCIIgCIIgCN7o16dPrekZ//qysa8j4FGt+UcCeafPv6KFIAiCIAiCIAiCeHCgIpQgCIIgCIIgCIK4b1jRZjdBEARBEARBEAQ/2Fjr42n7GNoJJQiCIAiCIAiCIO4btBNKEARBEARBEATRC2gftHfQTihBEARBEARBEARx36AilCAIgiAIgiAIgrhvcFeEFhYWwtbWFgEBAaL+S5cuQSaTCc3FxQV+fn44deqUmcNoNCIuLg4eHh7o378/1Go1Jk2ahNTUVDQ2/v/v8pk+fTpkMhk2bTL/UvOAgADIZDIkJCR0mXfkyJGQyWT45JNPRP2rVq3C9OnThdcJCQmi/Leau7u7aN1XX32FyMhIDB8+HAqFAj/72c8wc+ZM7N27F21t9/5LPw/s24s5j8/ApAnjELZoISrKy8n1gLt4zkYucllTNnJJw8VzNnJJw8VzNl5dXCHjoFkh3BWher0eK1asQEFBAa5cuWI2fuzYMdTU1KCgoAAajQaBgYG4du2aMN7Q0AAfHx9kZWVh9erVKCoqwpkzZ5CUlISSkhLs27dP5HN1dUV2draor7q6GsePH8ewYcO6lblfv36IiYm54zwPDw/U1NSI2unTp4Xx4uJiPPLII7hw4QJ27NiBs2fP4sSJE/j1r3+Nt956C+fOnetWnu5y9IP3kZaagqgXX8KBd/Oh07kjOmoZ6uvryfWAunjORi5yWVM2cknDxXM2cknDxXM2Xl2ERGAccf36daZSqdjFixdZaGgoS0pKEsaqqqoYAFZSUiL0lZeXMwDs8OHDQl9UVBRTKpWsurra4jU6OjqEn/38/Fh0dDRTq9Xs9OnTQn9SUhKbO3cu8/LyYvHx8V1mHjFiBFu5ciWzt7dn7733ntD/8ssvMz8/P+F1fHw88/Ly6tTT0dHBxowZw7y9vVl7e/sds3cXU2vnbX7wAhYXv1F43dzSzh6dNo2lZ+zsch25pOviORu5yGVN2cglDRfP2cglDRfP2frSZU188lVTnzdrhKud0Ly8PLi7u0On0yE8PByZmZlgjFmcazKZkJOTAwCwt7cHAHR0dCA3Nxfh4eHQaDQW18lu+y4fe3t7hIWFISsrS+jLzs5GZGRkt3OPGjUKy5cvR2xsLDo6Orq97seUlpbiwoULWL16NWxsLP+x3J79bmi9eRMXzp+Dz1Rfoc/GxgY+Pr4oLysh1wPo4jkbuchlTdnIJQ0Xz9nIJQ0Xz9l4dRHSgasiVK/XIzw8HADg7+8Pg8GAkydPiub4+vpCpVJBqVQiLS0N3t7emDlzJgCgtrYWTU1N0Ol0ojXe3t5QqVRQqVRYvHix2XUjIyORl5eH5uZmFBQUwGAwIDAwsEfZ169fj6qqKuzdu7fTORUVFUKOW2358uUAgC+++AIARNm//fZb0dyMjIweZeqKxqZGtLe3Q61Wi/rVajXq6urI9QC6eM5GLnJZUzZyScPFczZyScPFczZeXYR04OZ7QisrK1FcXIz8/HwAgFwuR2hoKPR6vegBP7m5uXB3d8fZs2exdu1aZGdnw87Orkt3fn4+bt68iZiYGJhMJrNxLy8vaLVaHDx4EP/85z+xdOlSyOXityY5ORnJycnC6/Pnz2P48OHC68GDB2P16tXYsGEDQkNDLebQ6XT461//KuobOHBgp7nVajVKS0uBHx6idPPmzS7vs6WlBS0tLaI+ZquAQqHoch1BEARBEARBED3nHh5UfKDgpgjV6/Voa2sTHaNljEGhUCA9PV3oc3V1hVarhVarRVtbG4KCgnD27FkoFAoMHjwYTk5OqKysFLlvFYsDBgxAU1OTxetHRkZix44dOH/+PIqLi83Gly9fjpCQEOG1peO+r7zyCjIyMjrdsbS3t4ebm5vFMa1WC/xQjE+YMAEAYGtrK8y/vSi2REpKCjZu3CjqWxcXj/UbzJ/w6+zkDFtbW7MPhNfX12PQoEF3vBa5pOfiORu5yGVN2cglDRfP2cglDRfP2Xh1EdKBi+O4bW1tyMnJwdatW1FaWiq0srIyaDQa7N+/3+K6BQsWQC6XC0WfjY0NQkJCsGfPHotP1u2KJUuWoKKiAp6enhg7dqzZuIuLC9zc3IRmqShUqVSIi4tDUlISrl+/3qPrT5gwAe7u7khLS+v150pjY2NhMBhEbU1MrMW5dvb2GDPWA0WfFAp9HR0dKCoqxHivCT26Lrmk4eI5G7nIZU3ZyCUNF8/ZyCUNF8/ZeHXxSF9/O4u1bsRysRN65MgRNDY2YtmyZXB0dBSNBQcHQ6/Xw9/f32ydTCbDypUrkZCQgKioKDg4OCA5ORknTpzA5MmTkZiYiIkTJ0KpVKK8vByFhYXw9PS0mMHZ2Rk1NTV3PNp7J1544QVs27YN+/btw5QpU0RjbW1tuHr1qtk9DBkyBDKZDFlZWXj88cfx6KOPIjY2FmPGjEFraysKCgpQW1sLW1vbLq+tUJgfvf2+i68WXRrxHOJej4GHhyc8x43Hnnd2w2QyYV7Q/B7fN7mk4eI5G7nIZU3ZyCUNF8/ZyCUNF8/ZeHUR0oCLIlSv12PWrFlmBSh+KEJTU1NhNBotro2IiMC6deuQnp6OtWvXQq1Wo7i4GJs3b8aWLVtQVVUFGxsbaLVahIaGYtWqVZ3mcHJyuut7sbOzw+9+9zssWbLEbOzcuXNm3z2qUCjw/fffAwB8fHzw+eefIzk5GS+99BKuXr0KpVIJLy8vbNu2rUdP7O0O/nOeRGNDAzLSt6OurhY69zHI2LkL6l4cjSCXNFw8ZyMXuawpG7mk4eI5G7mk4eI5G68uQhrIWGffgUJIgq52QgmCIAiCIAiCN/pxsU3WPT6tMvR1BEwaZb6RxztcfCaUIAiCIAiCIAiCeDCwot8zEARBEARBEARB8IPMah8N1LfQTihBEARBEARBEARx36AilCAIgiAIgiAIgrhv0HFcgiAIgiAIgiCIXiCj07i9gnZCCYIgCIIgCIIgiPsG7YQSBEEQBEEQBEH0AtoI7R3c7oQWFhbC1tYWAQEBov5Lly5BJpMJzcXFBX5+fjh16pSZw2g0Ii4uDh4eHujfvz/UajUmTZqE1NRUNDY2CvOmT58OmUyGTZs2mTkCAgIgk8mQkJDQZd6RI0cKmZRKJR555BG8++67wnhCQgJkMhmWL18uWldaWgqZTIZLly6J+g8dOoTp06fD0dERKpUK48ePR2JiIhoaGrrx7nWfA/v2Ys7jMzBpwjiELVqIivJycj3gLp6zkYtc1pSNXNJw8ZyNXNJw8ZyNVxdh/XBbhOr1eqxYsQIFBQW4cuWK2fixY8dQU1ODgoICaDQaBAYG4tq1a8J4Q0MDfHx8kJWVhdWrV6OoqAhnzpxBUlISSkpKsG/fPpHP1dUV2dnZor7q6mocP34cw4YN61bmxMRE1NTUoKSkBJMmTUJoaCg+/vhjYbxfv37Q6/X48ssvu/SsW7cOoaGhmDRpEj744AOcPXsWW7duRVlZGd55551uZekORz94H2mpKYh68SUceDcfOp07oqOWob6+nlwPqIvnbOQilzVlI5c0XDxnI5c0XDxn49VFSATGIdevX2cqlYpdvHiRhYaGsqSkJGGsqqqKAWAlJSVCX3l5OQPADh8+LPRFRUUxpVLJqqurLV6jo6ND+NnPz49FR0cztVrNTp8+LfQnJSWxuXPnMi8vLxYfH99l5hEjRrBt27YJr1tbW5mDgwN77bXXGGOMxcfHMy8vL/b444+zhQsXCvNKSkoYAFZVVcUYY6yoqIgBYG+++abF6zQ2NnaZ43ZMrZ23+cELWFz8RuF1c0s7e3TaNJaesbPLdeSSrovnbOQilzVlI5c0XDxnI5c0XDxn60uXNfH5JUOfN2uEy53QvLw8uLu7Q6fTITw8HJmZmWCMWZxrMpmQk5MDALC3twcAdHR0IDc3F+Hh4dBoNBbXyW57lJW9vT3CwsKQlZUl9GVnZyMyMrJX9yCXy2FnZ4ebN2+K+jdt2oRDhw7hs88+s7hu7969UKlUePHFFy2OOzk59SrP7bTevIkL58/BZ6qv0GdjYwMfH1+Ul5WQ6wF08ZyNXOSypmzkkoaL52zkkoaL52y8ugjpwGURqtfrER4eDgDw9/eHwWDAyZMnRXN8fX2hUqmgVCqRlpYGb29vzJw5EwBQW1uLpqYm6HQ60Rpvb2+oVCqoVCosXrzY7LqRkZHIy8tDc3MzCgoKYDAYEBgY2OP8N2/eREpKCgwGA2bMmCEae+SRRxASEoKYmBiLa7/88kv84he/gJ2dXY+v2xMamxrR3t4OtVot6ler1airqyPXA+jiORu5yGVN2cglDRfP2cglDRfP2Xh1EdKBuyK0srISxcXFQpEol8sRGhoKvV4vmpebm4uSkhIcOnQIbm5uyM7OvmPhlp+fj9LSUsyePRsmk8ls3MvLC1qtFgcPHkRmZiaWLl0KuVz8AOHk5GShkFWpVLh8+bIwFhMTA5VKBQcHB2zevBmbNm0ye7ASALzxxhs4deoU/v73v5uNdbbj2x1aWlpgNBpFraWlpdc+giAIgiAIgiA6R8bBP9YId1/Rotfr0dbWJjpGyxiDQqFAenq60Ofq6gqtVgutVou2tjYEBQXh7NmzUCgUGDx4MJycnFBZWSlyDx8+HAAwYMAANDU1Wbx+ZGQkduzYgfPnz6O4uNhsfPny5QgJCRFe/zjnmjVr8Oyzz0KlUmHIkCFmR35v8fDDD+P555/Ha6+9ZlZcjx49GqdPn0Zra2uPd0NTUlKwceNGUd+6uHis32D+ZF9nJ2fY2tqafSC8vr4egwYN6tF1ySUNF8/ZyEUua8pGLmm4eM5GLmm4eM7Gq4uQDlzthLa1tSEnJwdbt25FaWmp0MrKyqDRaLB//36L6xYsWAC5XI6MjAzgh3PmISEh2LNnj8Un63bFkiVLUFFRAU9PT4wdO9Zs3MXFBW5ubkL78U7poEGD4ObmhqFDh3ZagN5iw4YN+OKLL3DgwAGz69+4cUO4l9vprHgGgNjYWBgMBlFbExNrca6dvT3GjPVA0SeFQl9HRweKigox3mtCl9nJJU0Xz9nIRS5rykYuabh4zkYuabh4zsari0dksr5v1ghXO6FHjhxBY2Mjli1bBkdHR9FYcHAw9Ho9/P39zdbJZDKsXLkSCQkJiIqKgoODA5KTk3HixAlMnjwZiYmJmDhxIpRKJcrLy1FYWAhPT0+LGZydnVFTU/OTfyZzyJAheOWVV7BlyxZR/5QpU7B27Vq8+uqrqK6uRlBQEDQaDb766iu8/fbbmDZtGl5++WWLToVCAYVCIer7vq3zDEsjnkPc6zHw8PCE57jx2PPObphMJswLmt/j+yGXNFw8ZyMXuawpG7mk4eI5G7mk4eI5G68uQhpwVYTq9XrMmjXLrADFD0VoamoqjEajxbURERFYt24d0tPTsXbtWqjVahQXF2Pz5s3YsmULqqqqYGNjA61Wi9DQUKxatarTHPfqCbR3YvXq1Xjrrbfw/fffi/o3b94Mb29v7NixA2+//TY6Ojrw8MMPY8GCBYiIiLhn1/ef8yQaGxqQkb4ddXW10LmPQcbOXVD34mgEuaTh4jkbuchlTdnIJQ0Xz9nIJQ0Xz9l4dRHSQMbu5kk4BPd0tRNKEARBEARBELzRj6ttsq4pu3y9ryPAa/iAvo7QY7j6TChBEARBEARBEAQhbazo9wwEQRAEQRAEQRAcYaUPBupraCeUIAiCIAiCIAiCuG9QEUoQBEEQBEEQBEHcN+g4LkEQBEEQBEEQRC+Q0XncXkE7oQRBEARBEARBEMR9g3ZCCYIgCIIgCIIgeoGMNkJ7Bbc7oYWFhbC1tUVAQICo/9KlS5DJZEJzcXGBn58fTp06ZeYwGo2Ii4uDh4cH+vfvD7VajUmTJiE1NRWNjY3CvOnTp0Mmk2HTpk1mjoCAAMhkMiQkJHSZd+TIkUImpVKJRx55BO+++64wnpCQIIzb2trC1dUVL7zwAhoaGjr19O/fHyNHjkRISAj+8Y9/9Oj96y4H9u3FnMdnYNKEcQhbtBAV5eXkesBdPGcjF7msKRu5pOHiORu5pOHiORuvLsL64bYI1ev1WLFiBQoKCnDlyhWz8WPHjqGmpgYFBQXQaDQIDAzEtWvXhPGGhgb4+PggKysLq1evRlFREc6cOYOkpCSUlJRg3759Ip+rqyuys7NFfdXV1Th+/DiGDRvWrcyJiYmoqalBSUkJJk2ahNDQUHz88cfCuIeHB2pqanD58mVkZWXh6NGjiI6O7tRTWVmJnJwcODk5YdasWUhKSupWju5y9IP3kZaagqgXX8KBd/Oh07kjOmoZ6uvryfWAunjORi5yWVM2cknDxXM2cknDxXM2Xl2ERGAccv36daZSqdjFixdZaGgoS0pKEsaqqqoYAFZSUiL0lZeXMwDs8OHDQl9UVBRTKpWsurra4jU6OjqEn/38/Fh0dDRTq9Xs9OnTQn9SUhKbO3cu8/LyYvHx8V1mHjFiBNu2bZvwurW1lTk4OLDXXnuNMcZYfHw88/LyEq155ZVXmLOzc5eeW2zYsIHZ2Niwixcvdpnjdkytnbf5wQtYXPxG4XVzSzt7dNo0lp6xs8t15JKui+ds5CKXNWUjlzRcPGcjlzRcPGfrS5c1UfH19T5v1giXO6F5eXlwd3eHTqdDeHg4MjMzwRizONdkMiEnJwcAYG9vDwDo6OhAbm4uwsPDodFoLK6T3XaA297eHmFhYcjKyhL6srOzERkZ2at7kMvlsLOzw82bNy2OX7p0CR9++KGQ+U68/PLLYIzh8OHDvcpzO603b+LC+XPwmeor9NnY2MDHxxflZSXkegBdPGcjF7msKRu5pOHiORu5pOHiORuvLkI6cFmE6vV6hIeHAwD8/f1hMBhw8uRJ0RxfX1+oVCoolUqkpaXB29sbM2fOBADU1taiqakJOp1OtMbb2xsqlQoqlQqLFy82u25kZCTy8vLQ3NyMgoICGAwGBAYG9jj/zZs3kZKSAoPBgBkzZgj9FRUVUKlU6N+/P0aNGoVz584hJiamW04XFxc89NBDuHTpUo/zWKKxqRHt7e1Qq9WifrVajbq6OnI9gC6es5GLXNaUjVzScPGcjVzScPGcjVcXl8g4aFYId0VoZWUliouLhSJRLpcjNDQUer1eNC83NxclJSU4dOgQ3NzckJ2dDTs7uy7d+fn5KC0txezZs2EymczGvby8oNVqcfDgQWRmZmLp0qWQy8UPEE5OThYKWZVKhcuXLwtjMTExUKlUcHBwwObNm7Fp0ybRg5V0Oh1KS0vx6aefIiYmBrNnz8aKFSu6/d4wxsx2cH9MS0sLjEajqLW0tHTbTxAEQRAEQRAE8VPD3Ve06PV6tLW1iY7RMsagUCiQnp4u9Lm6ukKr1UKr1aKtrQ1BQUE4e/YsFAoFBg8eDCcnJ1RWVorcw4cPBwAMGDAATU1NFq8fGRmJHTt24Pz58yguLjYbX758OUJCQoTXP865Zs0aPPvss1CpVBgyZIjFI79ubm4AIBSoGzduxO9+97s7vi/19fWora3FqFGjOp2TkpKCjRs3ivrWxcVj/QbzJ/s6OznD1tbW7APh9fX1GDRo0B3zkEt6Lp6zkYtc1pSNXNJw8ZyNXNJw8ZyNVxchHbjaCW1ra0NOTg62bt2K0tJSoZWVlUGj0WD//v0W1y1YsAByuRwZGRnAD+fMQ0JCsGfPHotP1u2KJUuWoKKiAp6enhg7dqzZuIuLC9zc3IT2453SQYMGwc3NDUOHDu1yx/IW69evR1paWrcy/uEPf4CNjQ3mzZvX6ZzY2FgYDAZRWxMTa3Gunb09xoz1QNEnhUJfR0cHiooKMd5rwh3zkEt6Lp6zkYtc1pSNXNJw8ZyNXNJw8ZyNVxePyDj4xxrhaif0yJEjaGxsxLJly+Do6CgaCw4Ohl6vh7+/v9k6mUyGlStXIiEhAVFRUXBwcEBycjJOnDiByZMnIzExERMnToRSqUR5eTkKCwvh6elpMYOzszNqamrueLT3XjB16lSMHz8eycnJol3e69ev4+rVq2htbUVVVRX27NmDXbt2ISUlRdhJtYRCoYBCoRD1fd/W+fWXRjyHuNdj4OHhCc9x47Hnnd0wmUyYFzS/x/dCLmm4eM5GLnJZUzZyScPFczZyScPFczZeXYQ04KoI1ev1mDVrllkBih+K0NTUVBiNRotrIyIisG7dOqSnp2Pt2rVQq9UoLi7G5s2bsWXLFlRVVcHGxgZarRahoaFYtWpVpzmcnJzu6X11xW9/+1s8++yziImJgaurKwBgw4YN2LBhA+zt7TF06FD4+Pjg+PHjeOyxx+7ptf3nPInGhgZkpG9HXV0tdO5jkLFzF9S9OBpBLmm4eM5GLnJZUzZyScPFczZyScPFczZeXbzRjcOPhAVkrLPvPiEkQVc7oQRBEARBEATBG/242ibrmvNXmvs6AsZqlH0docdw9ZlQgiAIgiAIgiAIQtpY0e8ZCIIgCIIgCIIg+IFO4/YO2gklCIIgCIIgCIIg7htUhBIEQRAEQRAEQRD3DTqOSxAEQRAEQRAE0RvoPG6voJ1QgiAIgiAIgiAI4r5BO6EEQRAEQRAEQRC9QEZbob2C+53QwsJC2NraIiAgQNR/6dIlyGQyobm4uMDPzw+nTp0ycxiNRsTFxcHDwwP9+/eHWq3GpEmTkJqaisbGRmHe9OnTIZPJsGnTJjNHQEAAZDIZEhISusw7cuRIIZNSqcQjjzyCd999VxhPSEgQxm1tbeHq6ooXXngBDQ0NPfLcKw7s24s5j8/ApAnjELZoISrKy8n1gLt4zkYucllTNnJJw8VzNnJJw8VzNl5dhARgnLNs2TL28ssvM5VKxaqrq4X+qqoqBoAdO3aM1dTUsIqKCrZo0SI2cOBAdvXqVWFefX09GzNmDPvZz37GMjMzWVlZGbt06RL78MMP2aJFi1h6erow18/Pj7m6ujKdTifK8GTaG8UAAJ0CSURBVM033zCFQsGGDRvG4uPju8w7YsQIlpiYyGpqalhlZSV74YUXmEwmY//6178YY4zFx8czDw8PVlNTw7755hv20UcfMVdXVxYSEtIjT3cxtXbe8v/6HvPw8GD78w6ysxe+ZLGvr2feEyeyb67WdbmOXNJ18ZyNXOSypmzkkoaL52zkkoaL52x96bImLlxp7vPWXeLj4xkAUftx3WMymdiLL77IXFxcmFKpZPPnzxfVVfcSrovQ69evM5VKxS5evMhCQ0NZUlKSMHarCC0pKRH6ysvLGQB2+PBhoS8qKooplUpRAftjOjo6hJ/9/PxYdHQ0U6vV7PTp00J/UlISmzt3LvPy8upWEbpt2zbhdWtrK3NwcGCvvfYaYz/84Xt5eYnWvPLKK8zZ2blHnu7S1V8I84MXsLj4jcLr5pZ29ui0aSw9Y2eP/3IhlzRcPGcjF7msKRu5pOHiORu5pOHiOVtfuqyJizXNfd66y483w2612tpaYXz58uXM1dWVHT9+nH322WfMx8eH+fr6/iTvG9fHcfPy8uDu7g6dTofw8HBkZmaCMWZxrslkQk5ODgDA3t4eANDR0YHc3FyEh4dDo9FYXCeTic9x29vbIywsDFlZWUJfdnY2IiMje3UPcrkcdnZ2uHnzpsXxS5cu4cMPPxQy99bTU1pv3sSF8+fgM9VX6LOxsYGPjy/Ky0rI9QC6eM5GLnJZUzZyScPFczZyScPFczZeXcTdI5fLMXToUKENGjQIAGAwGKDX6/H73/8eM2bMgLe3N7KysvDxxx/jk08+uec5uC5C9Xo9wsPDAQD+/v4wGAw4efKkaI6vry9UKhWUSiXS0tLg7e2NmTNnAgBqa2vR1NQEnU4nWuPt7Q2VSgWVSoXFixebXTcyMhJ5eXlobm5GQUEBDAYDAgMDe5z/5s2bSElJgcFgwIwZM4T+iooKqFQq9O/fH6NGjcK5c+cQExPTY8/d0NjUiPb2dqjValG/Wq1GXV0duR5AF8/ZyEUua8pGLmm4eM5GLmm4eM7Gq4tHZBy0lpYWGI1GUWtpabGY98svv4RGo8EvfvELhIWF4fLlywCAzz//HK2trZg1a5Yw193dHcOHD0dhYeE9f9+4LUIrKytRXFwsFIlyuRyhoaHQ6/Wiebm5uSgpKcGhQ4fg5uaG7Oxs2NnZdenOz89HaWkpZs+eDZPJZDbu5eUFrVaLgwcPIjMzE0uXLoVcLn6QcHJyslDIqlQq4Q8QAGJiYqBSqeDg4IDNmzdj06ZNogcr6XQ6lJaW4tNPP0VMTAxmz56NFStWmOW4k+d2evIvIEEQBEEQBEEQ1k9KSgocHR1FLSUlxWzelClTkJ2djaNHj+Ktt95CVVUVfvWrX+H69eu4evUq7O3t4eTkJFozZMgQXL169Z5n5vYrWvR6Pdra2kTHaBljUCgUSE9PF/pcXV2h1Wqh1WrR1taGoKAgnD17FgqFAoMHD4aTkxMqKytF7uHDhwMABgwYgKamJovXj4yMxI4dO3D+/HkUFxebjS9fvhwhISHC6x/nXLNmDZ599lmoVCoMGTLE4pFfNzc3ABAKy40bN+J3v/udaN6dPLeTkpKCjRs3ivrWxcVj/QbzJ/o6OznD1tYW9fX1ov76+nphW767kEsaLp6zkYtc1pSNXNJw8ZyNXNJw8ZyNVxdhmdjYWLzyyiuiPoVCYTZvzpw5ws/jx4/HlClTMGLECOTl5aF///73JestuNwJbWtrQ05ODrZu3YrS0lKhlZWVQaPRYP/+/RbXLViwAHK5HBkZGcAP581DQkKwZ88eXLlypUcZlixZgoqKCnh6emLs2LFm4y4uLnBzcxPaj3dKBw0aBDc3NwwdOvSOhSMArF+/HmlpaWYZe+qJjY2FwWAQtTUxsRbn2tnbY8xYDxR98v+31zs6OlBUVIjxXhPueC1ySc/FczZykcuaspFLGi6es5FLGi6es/Hq4pK+Posr+7+Cc+DAgaJmqQi9HScnJ4wePRpfffUVhg4dips3b5pt0F27dg1Dhw69528blzuhR44cQWNjI5YtWwZHR0fRWHBwMPR6Pfz9/c3WyWQyrFy5EgkJCYiKioKDgwOSk5Nx4sQJTJ48GYmJiZg4cSKUSiXKy8tRWFgIT09PixmcnZ1RU1Nzx6O994KpU6di/PjxSE5OFu3y9hSFQmH2L9z3bZ3PXxrxHOJej4GHhyc8x43Hnnd2w2QyYV7Q/B5fm1zScPGcjVzksqZs5JKGi+ds5JKGi+dsvLqIe8eNGzfw73//G0uXLoW3tzfs7Oxw/PhxBAcHAz98PPLy5cuYOnXqPb82l0WoXq/HrFmzzApQ/FCEpqamwmg0WlwbERGBdevWIT09HWvXroVarUZxcTE2b96MLVu2oKqqCjY2NtBqtQgNDcWqVas6zXH7meifkt/+9rd49tlnERMTA1dX1/tyTf85T6KxoQEZ6dtRV1cLnfsYZOzcBXUvjkaQSxounrORi1zWlI1c0nDxnI1c0nDxnI1XF2/IcOfTirywevVqzJ07FyNGjMCVK1cQHx8PW1tbLF68GI6Ojli2bBleeeUVuLi4YODAgVixYgWmTp0KHx+fe55Fxjr7zhNCEnS1E0oQBEEQBEEQvNGPy20yy3x5zfwhp/cb7ZDufZ5z0aJFKCgoQH19PQYPHoxp06YhKSkJDz/8MADg+++/x6uvvor9+/ejpaUFs2fPRkZGxk9yHJeKUIlDRShBEARBEARhTVAR2jO6W4TyhBX9ERMEQRAEQRAEQfBDN54dSliAy6fjEgRBEARBEARBENKEdkIJgiAIgiAIgiB6AW2E9g4qQgmCIIh7SkfHvX3UgI0N/SeeIAiCIKQEHcclCIIgCIIgCIIg7hu0E0oQBEEQBEEQBNEb6LBOr6CdUIIgCIIgCIIgCOK+wXURWlhYCFtbWwQEBIj6L126BJlMJjQXFxf4+fnh1KlTZg6j0Yi4uDh4eHigf//+UKvVmDRpElJTU9HY2CjMmz59OmQyGTZt2mTmCAgIgEwmQ0JCQpd5y8rK8NRTT+Ghhx5Cv379MHLkSISGhuLbb7/tUW7GGP70pz9hypQpUKlUcHJywsSJE/Hmm2/iu+++6/H72BUH9u3FnMdnYNKEcQhbtBAV5eXkesBdPGcjl/W73s74IyaMcxe1oLlzep3rXmYjF7msLRu5pOHiORuvLp6QcfCPVcI4ZtmyZezll19mKpWKVVdXC/1VVVUMADt27BirqalhFRUVbNGiRWzgwIHs6tWrwrz6+no2ZswY9rOf/YxlZmaysrIydunSJfbhhx+yRYsWsfT0dGGun58fc3V1ZTqdTpThm2++YQqFgg0bNozFx8d3mvXbb79larWaRUREsDNnzrD//Oc/7B//+AdbtWoV+89//tOj3GFhYax///4sKSmJFRcXs6qqKvaXv/yFTZ8+neXn5/foPTS1dt7y//oe8/DwYPvzDrKzF75ksa+vZ94TJ7JvrtZ1uY5c0nXxnI1c1uNqbunotG3d9gc258kA9t/qa0L75mp9l2t4vU9ySd/FczZyScPFc7a+dFkT//7W1OfNGuG2CL1+/TpTqVTs4sWLLDQ0lCUlJQljt4q5kpISoa+8vJwBYIcPHxb6oqKimFKpFBWwP6ajo0P42c/Pj0VHRzO1Ws1Onz4t9CclJbG5c+cyLy+vLovQ/Px8JpfLWWtr5//L6U7u3NxcBoD95S9/sZi3qampU78luvoLYX7wAhYXv1F43dzSzh6dNo2lZ+zs8V8u5JKGi+ds5LIe152K0MC5T3U5pydFqFTeM3Lx6eI5G7mk4eI5W1+6rIm+LkCttQjl9jhuXl4e3N3dodPpEB4ejszMTDBm+bH/JpMJOTk5AAB7e3sAQEdHB3JzcxEeHg6NRmNxnUwm3r62t7dHWFgYsrKyhL7s7GxERkbeMe/QoUPR1taG/Pz8TnN2J/fevXuh0+nw9NNPW8zr6OjYLfedaL15ExfOn4PPVF+hz8bGBj4+vigvKyHXA+jiORu5pOG6xeXL/8XjM36FQP9ZeD1mNWpqrvTKw+t9kksaLp6zkUsaLp6z8eriEZms75s1wm0RqtfrER4eDgDw9/eHwWDAyZMnRXN8fX2hUqmgVCqRlpYGb29vzJw5EwBQW1uLpqYm6HQ60Rpvb2+oVCqoVCosXrzY7LqRkZHIy8tDc3MzCgoKYDAYEBgYeMe8Pj4+eP3117FkyRIMGjQIc+bMwZYtW3Dt2jWzuV3l/vLLL80y/xQ0NjWivb0darVa1K9Wq1FXV0euB9DFczZyScMFAJ7jvJD4uxTseGsXXo+LR3X1N4iMCEdz840eu3i9T3JJw8VzNnJJw8VzNl5dhHTgsgitrKxEcXGxUCTK5XKEhoZCr9eL5uXm5qKkpASHDh2Cm5sbsrOzYWdn16U7Pz8fpaWlmD17Nkwmk9m4l5cXtFotDh48iMzMTCxduhRyufibbJKTk4VCVqVS4fLlywCApKQkXL16FW+//TY8PDzw9ttvw93dHRUVFd3O3d1dVEu0tLTAaDSKWktLS699BEEQ95ppv/ofPD7bH6N1Ovg++iukZ/wJN64b8fcPj/Z1NIIgCIIg7hNcfk+oXq9HW1ub6BgtYwwKhQLp6elCn6urK7RaLbRaLdra2hAUFISzZ89CoVBg8ODBcHJyQmVlpcg9fPhwAMCAAQPQ1NRk8fqRkZHYsWMHzp8/j+LiYrPx5cuXIyQkRHj945xqtRoLFy7EwoULkZycjAkTJiAtLQ27d+/uVu7Ro0fj4sWLvXrfUlJSsHHjRlHfurh4rN9g/lRfZydn2Nraor6+XtRfX1+PQYMG9ei65JKGi+ds5JKGyxIDBg7E8BEj8fXl//Z4La/3SS5puHjORi5puHjOxquLR6z0NGyfw91OaFtbG3JycrB161aUlpYKraysDBqNBvv377e4bsGCBZDL5cjIyAB+OGseEhKCPXv24MqVnn3eaMmSJaioqICnpyfGjh1rNu7i4gI3Nzeh3b5Tegt7e3s8/PDDaG5u7vRat+desmQJvvjiCxw+fNhsLmMMBoOhU1dsbCwMBoOorYmJtTjXzt4eY8Z6oOiTQqGvo6MDRUWFGO81odNrkEu6Lp6zkUsaLkt8910zvvn6awwaPLjHa3m9T3JJw8VzNnJJw8VzNl5dhHTgbif0yJEjaGxsxLJly8wewhMcHAy9Xg9/f3+zdTKZDCtXrkRCQgKioqLg4OCA5ORknDhxApMnT0ZiYiImTpwIpVKJ8vJyFBYWwtPT02IGZ2dn1NTU3PFo7+25Dxw4gEWLFmH06NFgjOFvf/sb3n//fdGDju6UOyQkBPn5+Vi8eDHWr1+PJ554AoMHD0ZFRQW2bduGFStWYN68eRZdCoUCCoVC1Pd9W+eZl0Y8h7jXY+Dh4QnPceOx553dMJlMmBc0v9v3TS5puXjORi5puH6fthn/4/cYNBoNvq39Fm/vSIeNrQ3859z5s/c/dTZykcuaspFLGi6es/Hq4g7aCu0V3BWher0es2bNsvgU2ODgYKSmpsJoNFpcGxERgXXr1iE9PR1r166FWq1GcXExNm/ejC1btqCqqgo2NjbQarUIDQ3FqlWrOs3h5OTUo9xjx46Fg4MDXn31VXz99ddQKBTQarXYtWsXli5d2uXa23Pv27cPf/rTn5CZmYmkpCTI5XJotVo888wzmD17do9ydYX/nCfR2NCAjPTtqKurhc59DDJ27oK6F0cjyCUNF8/ZyCUN17Vr1xAb8yoMTU1wdnbBLx/xRs7eXLi4uPTYda+zkYtc1pSNXNJw8ZyNVxchDWTsbp6EQ3BPVzuhBEEQPwUdHff2Pys2NvRrZoIgiAeJftxtk3XOpfrv+zoCRqr79XWEHmNFf8QEQRAEQRAEQRD8IKPzuL2CuwcTEQRBEARBEARBENKFdkIJgiAIgiAIgiB6gYw2QnsF7YQSBEEQBEEQBEEQ9w3aCSUIgiDuKfQgIYIgCIIguoKKUIIgCIIgCIIgiF5Av3btHXQclyAIgiAIgiAIgrhvcF2EFhYWwtbWFgEBAaL+S5cuQSaTCc3FxQV+fn44deqUmcNoNCIuLg4eHh7o378/1Go1Jk2ahNTUVDQ2Ngrzpk+fDplMhk2bNpk5AgICIJPJkJCQYDaWkJAgymKpAcCzzz4LmUyG5cuXmzleeuklyGQyPPvss0LfrfkymQz29vZwc3NDYmIi2tru7Rd/Hti3F3Men4FJE8YhbNFCVJSXk+sBd/GcjVzksqZs5JKGi+ds5JKGi+dsvLp4Qibr+2aVMI5ZtmwZe/nll5lKpWLV1dVCf1VVFQPAjh07xmpqalhFRQVbtGgRGzhwILt69aowr76+no0ZM4b97Gc/Y5mZmaysrIxdunSJffjhh2zRokUsPT1dmOvn58dcXV2ZTqcTZfjmm2+YQqFgw4YNY/Hx8WYZr1+/zmpqaoT285//nCUmJor6GGMsIiKCubq6MkdHR/bdd98J600mE3NycmLDhw9nERERQn9ERATz9/dnNTU17NKlSywjI4PJZDKWnJzco/fQ1Np5y//re8zDw4PtzzvIzl74ksW+vp55T5zIvrla1+U6cknXxXM2cpHLmrKRSxounrORSxounrP1pcua+Lrh+z5v1gi3Rej169eZSqViFy9eZKGhoSwpKUkYu1WElpSUCH3l5eUMADt8+LDQFxUVxZRKpaiA/TEdHR3Cz35+fiw6Opqp1Wp2+vRpoT8pKYnNnTuXeXl5WSxCb2fEiBFs27ZtZv0RERHs6aefZp6enmzPnj1C/969e9n48ePZ008/bVaEPv300yLH448/znx8fO6Y4cd09RfC/OAFLC5+o/C6uaWdPTptGkvP2Nnjv1zIJQ0Xz9nIRS5rykYuabh4zkYuabh4ztaXLmuirwtQay1CuT2Om5eXB3d3d+h0OoSHhyMzMxOMMYtzTSYTcnJyAAD29vYAgI6ODuTm5iI8PBwajcbiOtlt+9f29vYICwtDVlaW0JednY3IyMh7dl+RkZEif2ZmJp577rlure3fvz9u3rx5T3K03ryJC+fPwWeqr9BnY2MDHx9flJeVkOsBdPGcjVzksqZs5JKGi+ds5JKGi+dsvLr4RMZBsz64LUL1ej3Cw8MBAP7+/jAYDDh58qRojq+vL1QqFZRKJdLS0uDt7Y2ZM2cCAGpra9HU1ASdTida4+3tDZVKBZVKhcWLF5tdNzIyEnl5eWhubkZBQQEMBgMCAwPv2X2Fh4fj9OnT+O9//4v//ve/+Ne//iXcZ2cwxnDs2DF8+OGHmDFjxj3J0djUiPb2dqjValG/Wq1GXV0duR5AF8/ZyEUua8pGLmm4eM5GLmm4eM7Gq4uQDlx+RUtlZSWKi4uRn58PAJDL5QgNDYVer8f06dOFebm5uXB3d8fZs2exdu1aZGdnw87Orkt3fn4+bt68iZiYGJhMJrNxLy8vaLVaHDx4EP/85z+xdOlSyOXityk5ORnJycnC6/Pnz2P48OHdurfBgwcjICAA2dnZYIwhICAAgwYNsjj3yJEjUKlUaG1tRUdHB5YsWWLx4Ui3aGlpQUtLi6iP2SqgUCi6lY0gCIIgCIIgiO5jtQ8G6mO4LEL1ej3a2tpEx2gZY1AoFEhPTxf6XF1dodVqodVq0dbWhqCgIJw9exYKhQKDBw+Gk5MTKisrRe5bxeKAAQPQ1NRk8fqRkZHYsWMHzp8/j+Li4v/X3nnHx5S2//866dIbQnQhJCEiIUTv0TurRLf66pJoYZXoq1trtcU2u8ta3aprWc9aEkFICCIEaUJIz+f3x9ec35zMTKScYRLX+3nltY8zM5+5T5lz7s99Xfd1q7w+duxY6tevn/hvTem+mhgxYgRNnDiRiIg2bdqk8X2tWrWiLVu2kJGREZUvX17FDOcmODiYFi5cKNk2Z14QzZ2valxtrG1IX1+fEhISJNsTEhI0mmJNsFbJ0NLltrEWaxWntrFWydDS5baxVsnQ0uW26aoWU3LQuXTcrKws+u6772j16tUUEhIi/oWGhlL58uXphx9+UPu5Pn36kIGBAW3evJnoXa55v379aO/evfT06dMCtWHgwIEUFhZGbm5u5OLiovK6ra0tOTk5iX/vM4e58fX1pYyMDMrMzKQOHTpofJ+ZmRk5OTlRpUqV8vUdgYGBlJycLPmb6R+o9r2GRkZU28WVrvxzWdyWk5NDV65cprruHgXaH9YqGVq63DbWYq3i1DbWKhlautw21ioZWrrcNl3VYkoOOhcJPXz4MCUlJdHIkSPJyspK8lrv3r1p+/bt5Ovrq/I5QRDoiy++oAULFtCYMWPI1NSUli5dSufOnaOGDRvSl19+SV5eXmRmZkY3btygy5cvk5ubm9o22NjYUGxs7HtTewuLvr4+hYeHi/9fLoyNVVNv0/JYVtRv6HCaN9ufXF3dyK1OXdq7ZzelpqZSj569CvzdrFUytHS5bazFWsWpbaxVMrR0uW2sVTK0dLltuqqla3A2buHQORO6fft2atu2rYoBpXcmdMWKFfTq1Su1nx06dCjNmTOHNm7cSLNmzSI7Ozv63//+R8uXL6eVK1fSgwcPSE9Pj2rUqEH9+/enKVOmaGyHtbW1rPuVG0tLS63q5wffjp0oKTGRNm9cT/HxceRcqzZt3vot2RUiNYK1SoaWLreNtVirOLWNtUqGli63jbVKhpYut01XtZiSgQBN654wJYK8IqEMwzAMwzAMo2uY6FyYTDOxyfIsn1gUylkZfewmFBidmxPKMAzDMAzDMAzDlFzYhDIMwzAMwzAMwzAfjGIU7GYYhmEYhmEYhtEdBC5NVCg4EsowDMMwDMMwDMN8MDgSyjAMw8hKTo689e709HiUmWEYRoFNg4myaSX9u1E2LYYpCGxCGYZhGIZhGIZhCgOPkxYKTsdlGIZhGIZhGIZhPhhsQnWUx48f04gRI6h8+fJkZGRElStXpsmTJ1NCQoKs3/Pj9/uoY7vW1MCjDg36rC+F3bjBWp+4li63jbWKv9bXmzeQR51akr+eXTsWSuu/q//SpPFjqW3LpuTu6kxnTv9ZKB1ldPGYsdbH1dLltrFWydDKj56+QGSkT2SsT/T8r5V0bvd0at/EhYiIbCxNaY1/Xwo9MI8SL6+hiKNf0upZfcjS3ET8vK2VGf2+cTxFnVxCL698RZHHFtFX/n0/6H7Kfcx0BUEH/oojbEJ1kKioKPLy8qLIyEj64Ycf6N69e/T111/T6dOnqXHjxpSYmCjL9xw/dpRWrQimMeMn0I/7D5Czcy0aN2ZkoYwua5UMLV1uG2uVDC0ioupONejU2b/Evx3ffV8ondTUt+Ts7EyBc4MK9fnc6OoxY62Pp6XLbWOtkqGVXz0QUVYOUUY2UZNBK+nc/yJo/1efU+1qDlSutBWVK21FgV8dIM++S2l00F5q5+NCXwcNEj+fk5NDh8/foD5TtlLdHl/S6KA91MrbmQzzcAK6fMyYEgAYncPX1xcVKlTA27dvJdtjY2NhamqKsWPH5lsrNVPzX6/efTAvaKH47zfp2WjStCk2bt6a5+dYq+Rq6XLbWKv4aL1Jz9H4t/qrdejStVue78n9l5821qxZE0eOnyrUNa8Lx4y1dFNLl9vGWiVDqzB6JvUmwKTeBCS8TMGYBXvFfyv/DZzxLdLSM2DmOUnt6yb1JmDa8p+Rk6Obx6w48Sw546P/FUc4EqpjJCYm0okTJ2j8+PFUqlQpyWsODg40aNAg+umnnwgoWvXJzIwMCr99ixo19hG36enpUaNGPnQj9DprfYJautw21ioZWgqiox9Ru9bNqItvW5rtP4NiY58WSkdOdPWYsRbfE1mr5GoVVk9PT6C+HTzJrJQRXbnxQO17LC1M6NWbNMrOzlH7ernSVtS9dT3SVMxcl4+ZriEIH/+vOMImVMeIjIwkAFS7dm21r9euXZuSkpIoLi6uSN+T9DKJsrOzyc7OTrLdzs6O4uPjWesT1NLltrFWydAiInKr405fLgqmTVu+pdnzgujJkxgaMXQwvXmTUmAtOdHVY8ZafE9krZKrVVA9gf5vTmjylbW0fk5/6j99G92JeqaiaWdtRoGjO9KOXy+pvLY7eBglXFpDUSeX0Ks3aZSp3qPq9DFjSga8RIuOUphIZ3p6OqWnp0t19I3J2NhYxpYxDMMUnqbNmov/v6azM9Wp406dOrSmkyeOU89efT5q2xiGYXQZ0P/NCW01ZBX1bOtB2770o/aj1kmMqIWZCR1YP47Co2Jp8dYjKhqzVv1KS7YeoxqVy9CXk7qRgd7/zTVlCo9QbEsDfVw4EqpjODk5kSAIFB4ervb18PBwsrGxodKlS6u8FhwcTFZWVpK/lcuD1erYWNuQvr6+yoTwhIQEsre3L1CbWatkaOly21irZGipw8LSkipVrkKPox8VWaso6OoxYy2+J7JWydUqjB6I6Hr4Y5q/4RCFRTyhCQNaiq+ZmxrToU3j6fXbNOo/bRtlqXGXzxNeU8TD53TkfBhNWvwDGWhwArp8zJiSAZtQHcPOzo7atWtHmzdvptTUVMlrz549o3379lH//v1JUJMAHhgYSMnJyZK/mf6Bar/H0MiIaru40pV/LovbcnJy6MqVy1TX3aNAbWatkqGly21jrZKhpY63b99QzOPHZK9mYO1DoqvHjLX4nshaJVerqHp6gkDGRv+X1GhhZkKHt0ykjMxs6jNlK6VnZL33uwW9/+tLqovj6fIxY0oGnI6rg2zcuJF8fHyoQ4cOtHjxYqpatSrdunWLZs6cSY6OjrRkyRK1nzM2Vk29TcvjHuQ3dDjNm+1Prq5u5FanLu3ds5tSU1OpR89eBW4za5UMLV1uG2uVDK01q5ZT8xatqHz58vQi7gV9vWkj6enrkW/HLgXWevvmDUVHR4v/fhITQ3fCw8nKyorKlS9fYD1dPWas9fG0dLltrFUytPKrZ6BHpKgx5OpUnvp39KLmXjWo6/jN/2dAN0+gUiZGNHzObrI0MyFLs/9bIzQuKYVyckAdmrpQGVtL+u/WI0p5m04u1cvR0qk9KAf/F10tbsdMp+Bs3ELBJlQHqVGjBl29epWCgoKoX79+lJiYSA4ODtSjRw8KCgoiW1tbWb7Ht2MnSkpMpM0b11N8fBw516pNm7d+S3aFSI1grZKhpcttY62SofX8+XMK9J9OyS9fko2NLdWr70nf7fupUPe1W7du0qjhQ8R/r1rxf9MPunXvSYuWLiuwnq4eM9b6eFq63DbWKhlaBdEz0v+//x7dOoluRj6hruM305krd6iZZw1qWLcqERHd/mOB5DPOneZTdGwipaZl0ohePrRiRi8yNjSgmOcv6fczIVS1UrkPsp9yHzOm+COgqGt9MDpNXpFQhmEYbZCjqeZ/IdHT42FmhmEYBTYNJsqmlfTvRtm05MSkGIXJ4lM+fmfb3rwYHbB38JxQhmEYhmEYhmEY5oPBJpRhGIZhGIZhGIb5YBS/2C3DMAzDMAzDMIwOoGbBCiYfcCSUYRiGYRiGYRiG+WBwYaISDhcmYhiGYRiGYYoTxakwUeKb7I/dBLI10//YTSgwHAllGIZhGIZhGIZhPhhsQhmGYRiGYRiGYZgPxidlQocNG0aCIJAgCGRoaEhVq1alWbNmUVpa2ns/GxwcTPr6+rRy5UqV13bt2iXq6unpUbly5ah///4UHR2t8t579+7RiBEjqFKlSmRsbEyOjo7Upk0b2rdvH2Vl/f/c2SVLlpCPjw+ZmpqStbW1DHuvnh+/30cd27WmBh51aNBnfSnsxg3W+sS1dLltrMVaxaltrFUytHS5baxVMrR0uW26qqVLCMLH/yuW4BNi6NCh8PX1RWxsLKKjo3HgwAFYWlpi1qxZ7/2sk5MTAgICUKtWLZXXdu7cCUtLS8TGxuLp06f4+++/4e7ujoYNG0red+XKFVhYWKBRo0Y4dOgQIiIiEBERge+//x5NmjRBSEiI+N758+djzZo1mDZtGqysrAq9z6mZmv8OHDoCV1dX/PDzL7gZHonA2XPh6eWFmGfxeX6OtUquli63jbVYqzi1jbVKhpYut421SoaWLrftY2oVJxLfZH30v+LIJ2dCu3fvLtnWq1cveHh45Pm5c+fOwdHRERkZGShfvjz+/vtvyes7d+5UMYrr168HESE5ORkAkJOTg9q1a8PT0xPZ2dlqvycnJ0dlmzrtgpDXDaFX7z6YF7RQ/Peb9Gw0adoUGzdvLfDNhbVKhpYut421WKs4tY21SoaWLreNtUqGli637WNqFSc+tgEtrib0k0rHzc3Nmzfp0qVLZGRklOf7tm/fTgMGDCBDQ0MaMGAAbd++Pc/3v3jxgg4cOED6+vqkr/9/1apCQkIoPDycZsyYQXp66g+78AHj6ZkZGRR++xY1auwjbtPT06NGjXzoRuh11voEtXS5bazFWsWpbaxVMrR0uW2sVTK0dLltuqrFlBw+ORN6+PBhMjc3JxMTE6pTpw69ePGCZs6cqfH9r169ol9++YUGDx5MRESDBw+mn3/+mVJSUiTvS05OJnNzczIzM6OyZcvS2bNnacKECWRmZkZERBEREURE5OzsLH7mxYsXZG5uLv5t3rxZS3utStLLJMrOziY7OzvJdjs7O4qPj2etT1BLl9vGWqxVnNrGWiVDS5fbxlolQ0uX26arWkzJ4ZMzoa1ataKQkBC6cuUKDR06lIYPH069e/emv/76S2II9+3bR0REP/zwA1WvXp3c3d2JiKhevXpUuXJl+umnnyS6FhYWFBISQlevXqXVq1dT/fr1acmSJXm2xc7OjkJCQigkJISsra0pIyOjSPuWnp5Or169kvylp6cXSZNhGIZhGIZhGPV87KJExbUw0SdnQs3MzMjJyYnc3d1px44ddOXKFdq+fTt5eXmJhjAkJIS6detG9C4V99atW2RgYCD+3b59m3bs2CHR1dPTIycnJ6pduzZNmzaNGjVqROPGjRNfr1GjBhER3b17V9ymr69PTk5O5OTkRAYGRV+VNzg4mKysrCR/K5cHq32vjbUN6evrU0JCgmR7QkIC2dvbF+h7WatkaOly21iLtYpT21irZGjpcttYq2Ro6XLbdFWLKTl8ciZUGT09PZo9ezbNnTuXiEg0hE5OTmRhYUFhYWF09epVOnfunMSgnjt3ji5fvkx37tzRqB0QEEA//fQTXbt2jYiIPDw8qFatWrRq1SrKycnRyv4EBgZScnKy5G+mf6Da9xoaGVFtF1e68s9lcVtOTg5duXKZ6rp7FOh7WatkaOly21iLtYpT21irZGjpcttYq2Ro6XLbdFWLKTkUPfxWzOnbty/NnDmTNm3aRDNmzJC8tn37dmrYsCE1b95c5XMNGjSg7du3q103lIioYsWK1LNnT5o/fz4dPnyYBEGgnTt3Urt27ahJkyYUGBhItWvXpszMTLpw4QLFxcWJRYyIiKKjoykxMZGio6MpOzubQkJCiN4ZZXNzc7XfaWxsTMbGxpJtaVlq30pERH5Dh9O82f7k6upGbnXq0t49uyk1NZV69OyV90FjrRKrpcttYy3WKk5tY62SoaXLbWOtkqGly23TVS1dQ6Bimg/7kfnkTaiBgQFNnDiRVqxYQePGjRMLCWVkZNDevXvJ399f7ed69+5Nq1evpqVLl2rUnjp1KjVu3Jj+97//UcOGDalRo0b033//0dKlS2nChAn07NkzMjMzI3d3d/rqq69oxIgR4mfnz59Pu3fvFv/t4fF/I0Vnz56lli1byrLvvh07UVJiIm3euJ7i4+PIuVZt2rz1W7IrRGoEa5UMLV1uG2uxVnFqG2uVDC1dbhtrlQwtXW6brmoxJQMBAD52IxjtkVcklGEYhmEYhmF0DZNiFCZ7laadaXYFwdKk+M2wLH4tZhiGYRiGYRiGYYotbEIZhmEYhmEYhmGYD0YxCnYzDMMwDMMwDMPoDlyWqHBwJJRhGIZhGIZhGIb5YHAklGEYhpGVzGx5izQY6vN4KcMwDKOjcCi0UPCTnWEYhmEYhmEYhvlgsAllGIZhGIZhGIZhPhhsQnWQrl27kq+vr9rX/vrrLxIEgW7cuCHLd/34/T7q2K41NfCoQ4M+60thRdBlrZKhpcttY63ir5WdnU1bNq6jbr5tqUmDetS9U3v6dutmKsqS1bq4n6xVcrR0uW2sVTK0dLltuqqlSwg68L9iCRid48CBA9DT08Pjx49VXhs+fDi8vLzyrZWaqfnvwKEjcHV1xQ8//4Kb4ZEInD0Xnl5eiHkWn+fnWKvkauly21ir+Gi9SsvW+Ld2w2Y0aNgQR0+exp370fjt0FHUq1cP32zfpfEzurqfrFXytXS5baxVMrR0uW0fU6s48Tot56P/FUfYhOogmZmZKFu2LBYtWiTZ/vr1a5ibm2PLli351srrhtCrdx/MC1oo/vtNejaaNG2KjZu3FvjmwlolQ0uX28ZaxUcrLxM6YtRozPAPkGwbM24CJk+dXigTWlKOGWvpppYut421SoaWLrftY2oVJ1LScz76X3GE03F1EAMDAxoyZAjt2rVLkqK2f/9+ys7OpgEDBhT5OzIzMij89i1q1NhH3Kanp0eNGvnQjdDrrPUJauly21irZGgREdV196B/r/xDjx4+ICKiiLt3KPT6NfJp2qzAWrq6n6xVMrR0uW2sVTK0dLltuqrFlBzYhOooI0aMoPv379P58+fFbTt37qTevXuTlZVVkfWTXiZRdnY22dnZSbbb2dlRfHw8a32CWrrcNtYqGVpERMNGjqb2vp2oT/fO5F2/Dg3q14sGDB5CHTt3LbCWru4na5UMLV1uG2uVDC1dbpuuajElB14nVEepVasW+fj40I4dO6hly5Z07949+uuvv+jLL7/U+Jn09HRKT0+XbIO+MRkbG3+AFjMMw7yfUyeO0fEjh2nxspVUvXoNuns3nNasCKbSpctQl+49PnbzGIZhGKZAFNOyQB8djoTqMCNHjqRff/2VXr9+TTt37qTq1atTixYtNL4/ODiYrKysJH8rlwerfa+NtQ3p6+tTQkKCZHtCQgLZ29sXqJ2sVTK0dLltrFUytIiI1q9ZRUNHjqIOHTuTU82a1LlrdxrgN5R2bv+mwFq6up+sVTK0dLltrFUytHS5bbqqxZQc2ITqMP369SM9PT36/vvv6bvvvqMRI0aQIGgebwkMDKTk5GTJ30z/QLXvNTQyotournTln8vitpycHLpy5TLVdfcoUDtZq2Ro6XLbWKtkaBERpaWlkp4gffTo6+kTkFNgLV3dT9YqGVq63DbWKhlautw2XdXSSQQd+CuGcDquDmNubk79+/enwMBAevXqFQ0bNizP9xsbq6bepmVpfr/f0OE0b7Y/ubq6kVudurR3z25KTU2lHj17FbitrFUytHS5baxVMrSatWhFO7ZtJYdy5aha9Rp0985t2rdnF3Xrwdcra+meli63jbVKhpYut01XtZiSAZtQHWfkyJG0fft26tSpE5UvX15Wbd+OnSgpMZE2b1xP8fFx5FyrNm3e+i3ZFSI1grVKhpYut421SobWzMC59PXGdbRsyZeUlJhI9qXLUK8+/Wj02PEF1pK7bazFWsWpbaxVMrR0uW26qsWUDAQorwHClDjyioQyDMNog8zsgqfW5oWhPs8cYRiG+ZQwKUZhstTMj90ColKGBXv/pk2baOXKlfTs2TNyd3enDRs2UMOGDbXVPLXwk51hGIZhGIZhGOYT4KeffqJp06ZRUFAQXbt2jdzd3alDhw704sWLD9oOjoSWcDgSyjDMh4YjoQzDMExRKE6RUF3oaxfkeHl7e1ODBg1o48aNRO+KRFWsWJEmTZpEAQEB2mtkLvjJzjAMwzAMwzAMU8LJyMig//77j9q2bStu09PTo7Zt29Lly5fz/KzcFKNxBoZhGIZhGIZhGEaZ9PR0Sk9Pl2xTt2pGfHw8ZWdnU9myZSXby5YtS3fu3PkgbRUB80mTlpaGoKAgpKWllVgtXW4ba5UMLV1uG2uxVnFqG2uVDC1dbhtrlQwtRkpQUBCISPIXFBSk8r4nT56AiHDp0iXJ9pkzZ6Jhw4YfsMUAzwn9xHn16hVZWVlRcnIyWVpalkgtXW4ba5UMLV1uG2uxVnFqG2uVDC1dbhtrlQwtRkp+I6EZGRlkampKv/zyC/Xo0UPcPnToUHr58iX9/vvvH6zNPCeUYRiGYRiGYRimmGJsbEyWlpaSv9wGlIjIyMiIPD096fTp0+K2nJwcOn36NDVu3PiDtpnnhDIMwzAMwzAMw3wCTJs2jYYOHUpeXl7UsGFDWrt2Lb1584aGDx/+QdvBJpRhGIZhGIZhGOYToH///hQXF0fz58+nZ8+eUb169ej48eMqxYq0DZvQTxxjY2MKCgpSG7IvKVq63DbWKhlautw21mKt4tQ21ioZWrrcNtYqGVpM0Zg4cSJNnDjxo7aBCxMxDMMwDMMwDMMwHwwuTMQwDMMwDMMwDMN8MNiEMgzDMAzDMAzDMB8MNqEMwzAMwzAMwzDMB4NNKMMUU3Jycj52ExiGYT4psrOzP3YTGKZYkpCQwP0WRgKbUKZQJCcnU1pamuy6ctXJUtzoSmLdrcjISHry5Anp6fHP92Mi57VVEq9TRjukpqbKpqW4h8vdMZTjei5Km2JiYigrK6vIbcjN9evXKSgoiN68eSO7Nt8DGDlRdz19zGvs5cuX5OzsTN9///1HawOje3Avlikwz58/p3r16tGdO3eIZLixRUdH086dOyk7O5sEQSiyXkREBM2dO5eePn0qi15RPp+SkkKJiYlF+n5lQkNDqVatWnTo0CFZ9JT3TfH/C7u/KSkpFBcXR48fP5albdqiKPuZmppKiYmJlJWVRYIgFKkdyhGVomopExcXJ5tWSaO4d/RDQkJo/Pjx9PTp0yJrxcbGkru7O124cIH09PRkMaKvXr0ienc9F+ZYP336lI4cOUJEVOhBtpSUFGrVqpXsnd3Q0FDy9PSkzMxMMjMzK7LekydP6NChQ7RhwwYime8B2ojW6sJvJz09ndLT0yklJUVW3aLsW2JiIoWFhVFkZKQsgxOvX7+mx48fF/o3npqaSunp6fT48WN6/vw5xcTEiM9kQRA+WiTS1NSUmjVrRocOHRLvEwzDJpQpMGXLliUzMzNav3495eTkFOnhCYCWLFlCK1eupO3btxfZiCYlJVGXLl1o/fr1tHz5cnry5EmB9B4+fEhfffUVLVmyhA4fPkxUhA5VREQEjR07lrZt2yZLp/HGjRvUuHFjmj17No0bN67IevRuQCEyMpLu379PL168ICrk/t65c4dGjhxJI0eOpN9//53S09OL1K7U1FRKTk6mzMxMcVtROgqKqMizZ8/ESFJBH8iRkZE0duxYGjFiBK1cubJIbVJo+fr60pgxYyghIaFQOrkJDAykoKAgysjIKLTG/fv3acGCBeTn50f79u2jmJiY937mxYsXdPfuXfrf//4n2V6Y4yNnBzopKYmePHlCN2/eJJKho//s2TO6cuUKHTt27IOnZYaGhpKXlxeVLVuWypcvX2S9lJQUqlGjBn322Wd0+fLlIhvRW7dukbW1tcRUFeT837p1i7p3705r166lEydOFLod2dnZZGRkVOR7kDK3b98mHx8fWrJkCS1fvrzIejdv3qRu3brRTz/9RLdu3SpydDs2NpaOHz9OBw4coMTERNLX1y/S9ZmYmEg3btygr7/+mvbs2UOJiYmF+i0/e/aMTpw4QcePHy/y+YiIiKBp06bR6NGj6Y8//ijS/uXk5FBmZiY9efKEAIj3hYLu482bN6lt27bUrVs3cnV1pZkzZ4qD84UhPDyc/Pz8yM/Pj3799Vd6+/ZtgT8/ePBg8vLyourVq5OTkxO5uLhQ+/btafbs2UTvBnc+xoCCkZERtWnThs6cOUPx8fFEPKWIof/70TFMgcjOzsb8+fPh7u6O2NhYAEBOTk6h9RISEuDn5wcfHx9s2bIFWVlZhdaMi4uDu7s7HBwc0KNHD4wbNw4xMTH50gsJCUGFChXQtGlTVKtWDaVKlcL27dsLtU+hoaFwcHDAsGHDcOzYsUJpKHPnzh3Y2Njg888/F7cV5ZgDQHBwMJo0aQJra2sIggAXFxesXr26wPo3btyAvb09/P39ZdnX27dvo2fPnqhTpw569eqF33//vUh69+/fx9SpU1G/fn2YmpqiQYMGWLZsWYE0QkNDUb58ecyaNQunTp0St6empgIFPBchISGws7ND9+7d0bFjR9jZ2aFZs2Z4+/ZtgdqUm6lTp6JUqVK4efNmoTVCQkLg4OAAHx8fuLi4QBAEjB07FomJiRo/ExoaimrVqqF27doQBAHt27fHDz/8IL5ekGNz69YtjBo1SvzNFoWwsDA0adIELi4uMDU1xeTJk4ukd+PGDdSqVQv169eHIAjo1atXkduYX65fvw5TU1MEBgbKqhseHo4BAwbA3t4ely5dAt7d3wvDvHnzIAgCBEHAypUrxe35Of83b96EnZ0dZsyYgYiICJXXC9qmkSNHws/PDwDE50lhCQsLg62tLapUqYKkpKQia96+fRvW1taYPXs24uLiitQ2vPv91a5dG87OzrC1tYWbmxuePXtWpPa1a9cOnp6eKFWqFExNTVGuXDls2rQJ8fHx+da5desWvL290atXL4wbN67Q7cG7356DgwOmTp2KnTt3FvoaxbvnQWBgILy8vFClShV4e3vj+++/F89Ffu9XoaGhMDMzw+TJk3Hy5EnMmTMHJiYmmD17NjIzMwv8fA4LC0Pp0qURGBiIc+fOFXi/bty4ASsrK0yYMAFBQUEwMTFBlSpVYGBggHLlyqFcuXJYunRpgXULg+L8ZGZmArmOqYeHBz777LMP0g5G92ETyhSK58+fw8rKCgsWLCiSjuJhnpiYiIEDB8LHxwebN28ulBFVvPfIkSPw9PTEyJEj4ePjg/Hjx+PJkyd56oWGhsLU1BQBAQFIT0/HtWvX4OLigrp16+LFixfiTTU/7Xn48CEqVKiAgIAAZGRkvLe97+P69eswMzODIAjo06cP7t27l6/P5cXMmTNRunRp7N27F3///Tf279+Pnj17QhAETJ06Nd9tjImJgbOzM6ZMmSLZXthOQkhICKytrTF8+HAsXboU5cuXR926dXHr1q1C6d24cQNVqlTB0KFD8eWXX2LXrl3o0qUL9PT0MHz48Hy19969e3B0dMSsWbMk25ctWwY3Nzc8ffoUyOf5vHHjBszMzDBv3jzgnYk9d+4c9PT0sGTJkkLtIwBMnjwZ1tbWCAkJkWxPTk7Ot8aNGzdgYWGBoKAg8brduHEjBEHAn3/+qfYzz549Q7Vq1TBr1izcvHkTN27cQLt27dC4cWN8+eWX4jHJz7G5f/8+KlasCEEQ0KFDhyJ1pMPDw2FnZ4eAgACcOHEC+/fvh56eHjZv3lwovdu3b8POzg5z5szBw4cPERISAkEQcPHiRcn7ijowpI4HDx5AT08PX375JaB0z1y2bBkOHTpUKE1F5xDv9k0OI3rixAk0btwY06dPh5GREYKDg8XX8jouSUlJaNSoEaZNm6byWlpaWr6+O/cAztKlS1GnTp18fX9ehISEoFSpUmjevDlat24NPz8/PH78GCjkMUpJSUGXLl0kg4lFbZ+pqSn8/f0RFRWFXbt2wcDAAEOHDi2UEQoJCYG9vT2mTp2Kixcv4tWrV7h+/Tp69+4NAwMDLFu2LF/3lLCwMNjY2GDevHmS3/GFCxcQGhpaoDY9ePAAlSpVwowZMyTbC3PMbty4gerVq2PAgAGYNWsW1q1bh4YNG8LMzAxTp04VB9Xfx507d2BpaYkvvvhCsn3gwIGoXr06Xr9+XaB2PX36FC4uLpg4caJke36vsRcvXsDDwwMBAQGIiIiAiYkJFixYgBcvXmDjxo0wMzODnZ0d2rZtW6B2FYabN2+iTZs2ePToEaB0v1Lcc1asWAFPT0+xH6ONeyZTfGATyuQbxc1C0UFdsGABvL29ERUVVSCdN2/eSP6tzohu37493zdgxeezs7ORk5ODu3fvol+/fjh16hS++eYbeHp65mlEY2NjUbZsWXTp0kWyvVWrVqhQoQKeP3+O9PR0tcdCHevXr4evr6+kA/Xo0SMcP34cy5Ytw4EDB/Klg3cG1MDAACtWrMDjx49hZWWFLl26FMmIHjhwAFWrVsW///4r2f7o0SPMmTMHgiBgxYoV+dLav38/mjZtinv37hX5YXLz5k2Ym5tj/vz54rZ9+/ZBEAT88ssvkvfm59pQmPdZs2ZJrrknT55g1apVMDQ0xKRJk/LUyMnJwZw5c9C9e3dJFGDx4sWwtLRElSpV4OTklC8j+ubNG3h7e6N06dIS/VevXqFOnTqFNqFz586Fqakp7t+/L27LyspCp06dcPTo0XxpJCUlQU9PD02bNhW3ZWdnIzExEY6Ojvjmm2/Ufu7vv/9G9erVxQ4H3nWIJk6ciIYNG0oi63nx9u1bzJo1C71798aZM2dQpUoVtGrVqlBG9OXLl+jevbtKB3H06NEYOHAgUMCOT2JiIjp37ixGUhWf9fX1xYEDB7Bv3z7cvXu3wO3MDzk5Odi/fz+sra0xcuRIcfvSpUthamqKkydP5lvr8ePHOHLkiPhv5Wiewog6Ojriv//+K1Able+/Xl5eGD58OLZt2wY9PT3JfUTTMY+IiECdOnVw/fp1cdvff/+NhQsXonr16mjWrBm+++47jZkCjx8/Rvny5dGuXTuMGDEC27dvx9KlS+Ht7S35TeTVBnXcvHkTgiBg4cKFwLsBmSZNmsDPz0+M1BfUiCYkJKBmzZqSTIG82pdXex8+fAgTExOJec/OzkaVKlXg6+ubbx0FikEoxQBZ7n0bOHAgzM3Ncfr06Tw1nz9/jvr166tkHixfvhyCIGDYsGEFytZYt24dOnTogNjY2CI9YxSRy4CAALx69Ury2ueffw5ra2sEBQWJ2S15sWbNGgiCgE2bNuHFixdiu5YtW4Z69eoV+L514MABeHt7F/o+cu3aNbi5ueH69euYPHky7O3txXt2UlISFi9eDENDQ9SuXRspKSlaM35RUVGoVq0aiAiWlpb46quv8PbtW8m95vHjx7CxsUFQUJBW2sAUL9iEMnkSFRWFfv364d9//8XLly8lr/3555+wsrLCwYMHgXw+6J49e4ZKlSpJjBhyGdE+ffqgcePGuHLlynt1IyMjERgYqGKoJk6ciPr16yMnJwfr169Hw4YNNRrRf//9F927d4eHh4fYaV+6dCkEQYCXlxe6dOmC9u3bIygoCP/++y9SUlLy3MegoCC0bNlSPF7ff/89evbsibJly8LJyQmCIGDRokXvPVYxMTHw9fVFQECAuC08PLzIRjQ4OBgdOnRAamqqSlpZdHQ0Bg0ahNq1ayMmJua953T69OmoWbOm2s6Y4rMpKSlqU+yUSUtLg4eHBxwdHSVRz4CAAPFhf/bsWZWHu6b2KaJHixcvBtSkBSUkJGDOnDkwNTV9r1Hz8fGRGID79++jd+/eOH78OB49eoQWLVqgWrVqohHVREZGBn7//XfY29tj0KBB4vaoqCgYGxtr7Jjmxb///gsLCwsMGDAAz58/F/e1QYMGaNasWYFG5AMCAlCqVCls2rRJTL+9desWDAwMNKZZ//fff3B0dMSFCxfE78a746vIRFBEZ/O6ltLS0rB79278/PPPwLvoc+XKlfM0opr04uLi0KZNG+zdu1eyfeXKlWjQoAFQwHTKly9fYvXq1ZIo86JFi6Cnp4cWLVrAwcEBDRo0wP79+/OtmR+U74k//PADHB0dMWbMGHz11Vewt7cvUOp7eno6evXqBW9vb/F+jVzHISQkBN26dUPHjh3zFe3K/TzAu2hop06d8N9//2HFihX5Ss29d+8eypUrh/Xr1wMANmzYgIYNG6JFixYICAhAhw4dUKlSJY0RtLi4OGzcuBGrVq1C27Zt4ePjgzJlykAQBLRt2xa9evXC9u3bcfHiRcTExOQr7f3Ro0fYu3evStp+UY3o9evXIQgC/ve//2l8T1paGtasWfNere+//x5OTk747LPPxEG24OBgCIKAevXq4YsvvsCECRPw33//vTftNyEhAYIgoE2bNpLtOTk54jWSlZUFd3d3tGzZMk+tCxcuwMXFBdeuXROPzerVq2FkZIQFCxagatWqGDlyJMLCwt67jwDQu3dvlXYpUOi/fv1aTJVWh6bIpfLg8sCBA2FjYyMZUMuL2bNno1KlSuI1kpCQACsrq3w923Mzd+5c1KhRQ23mlOI3k5aWpvE5unPnTpiYmAAA7t69i88//xyNGjXCV199BQC4cuUKiEhloF1O3r59iylTpqB379746quvYGtrCyJCo0aNEBgYiKSkJHFgPjg4GG5ubrhz547W2sMUD9iEMnmydetW1KtXDxYWFujRowd27dolSeUaMmQI3N3dkZCQkG/N/v37w8bGRjIqD6UOUXJyMqpXr66S4pmbuLg4VK9eHYIgwNLSErNnzxZH/1JSUtC9e3ccPnwYUJr/OGTIEDHlRvnBfPnyZQwePBju7u4YPHgwypQpg99++w3x8fG4ePEiduzYAWdnZzg6OqJJkyYqDwtlrS1btsDGxgaTJk1C//79YWtriy+++AJnz55Feno6VqxYAXt7+zyN2YMHDzB48GDJ3BDFd965c6dIRrR79+5o0aKFxtf/+OMP6OnpITw8/L1as2bNgrOzs/hvdR2yhQsXYuPGje/VOn36NGrUqIGBAwciOjoaK1asgLm5Obp27YqgoCDY2NigSZMm6NChAzZv3qyxs5CTk4Mff/wR5ubmkvQm5esW7yId1tbWeaZoJiYmwt3dXYwOKDSUo6JRUVEq36WJrKwsHD16FNbW1vj8888RGxuLihUrYsKECe/9rCaCg4PRoEEDBAQE4P79+/D29oavr69oJBSdGHXnJj4+XmLy5syZA319fezbtw83b95E+fLlVTpuyjx//hzVq1eXpBcqfsfx8fEoX758vucx5s6QiIiIEI2owmBnZWVJImaaUP5tKdqzZcsWNGvWTPK+/KYrKw88nT59Whx8e/PmDTIzM9G4cWP069cvX1r5ITo6Gq1bt8bDhw/Fdu7btw/VqlWTpAHnvqbz4vr16/D19UX79u0lg4DKRnT37t2oWLGimHKqifDwcJiYmGDcuHHYu3eveHyioqJQv359/PTTT4BS9Ct3RDwyMlK8t7169QoTJ05E+fLlUb16dZiYmCA4OBg3btwQ329lZSVJ71VoaEpHPnPmDARBwPjx49G/f380atQIpqamKFOmDNq2bZtntCslJQXOzs7Ytm2b2mNUWCOak5ODyMhIWFhYIDg4WOO5O3nyJDp27KgSrVOgaHtqaip27doFb29vDBw4EAsWLIC9vT22bNmCa9euYfXq1ejXrx/Kli2LihUrvnfqzIQJE2BhYYGdO3dqzFaaM2cO3Nzc1A5AKFi+fDlsbGwk2y5cuCCm9J84cQKVKlVC//7984wYZmdnIzMzE927d0fPnj2BPK73oKAg/Pbbbxq1ckcu1e2bYorRhg0bNOrkJiAgAFWrVsXs2bPh6OgoeQYUJNq4aNEiODg4iL8jdddTQECAxsyS77//HgYGBti5cyfw7rcxatQoNG3aFEFBQahYsSJKly4t9qm0FQndsWMH9u3bB7wzvvXr14e1tTWqVKmCSpUqYdq0aQgLC8PVq1dRsWJFsX9WlDm+TPGGTSiTL3bu3ImBAwdCX18fLVq0wLx585CSkoLff/8dDRs2xJkzZ4AC3ExGjRoFc3NzFSOqeMiMGzfuvYU/Xr58iXHjxqFNmzZo27Ytpk2bhsaNG6N58+bYvn072rRpI5nfuHDhQrRt2xaxsbFISEhA48aNJZ3/S5cuwc/PD6VKlRJTsJRJTk7GpUuXVFK8FFrKD6DAwEB07NgRTZs2xfHjxyWFXXbu3Ak3N7c8izzs2LEDdnZ2Kg8LxQNT2Yjmbo8mFFpz585F+fLlJZ085dcfPHgAa2vrfM3dOXv2LARBkHQQlQ16WloaBg4ciB07dqj9/MOHD3Hu3DlxRPrMmTOoWrUq6tSpA2tra5w9e1Z87+PHj3HhwgW0a9cO3t7eePDggcZ2vXz5Et999x0cHBwkUcysrCzJMa1WrRrmzJkj+WxUVJTkewcOHIhy5cqpmDrFf589e4auXbuKD19lXr16hZiYGCQnJ0vS2Y8ePQo7OzsIgiAxefn9/ezevRtbtmwR/x0cHIx69eqhbNmyaN68uYpeUlIShg4dKkn3un37NszNzTF58mTJXKjZs2dDEASYmZmpmMsXL17g/PnzOHz4sNgRPXHiBAwMDMSos/Kx+fzzz9G7d2+1+6CspdzhVj4/d+/eFY1odHS0+HvP3QnWpKVsHrZv3y5GQgHA398fkyZNUht90KSHdwZRYXIV+v7+/vDx8SmQKcyLc+fOwcPDA97e3oiOjgbeXdP79u1D5cqVMXToUPG9+flOxXUQFhaGtm3bqhhRxTG4cuUKXF1dRfOrSWvBggUQBAE1a9bEkCFDULVqVRw4cABxcXH49ddf4ebmhri4OLx9+xarV6+GIAhipBMAxo8fL5lr/OjRIxw9ehRr166VXKNZWVmIjY2Fj4+PJCVfEVHcunWrpF3K107r1q2xbt068bWoqChcvXr1vVkZSUlJcHFxUUlBV/5tbtq0CU2aNMHw4cPF85NfunfvjnLlyuHq1atqX/f394efn59aoxwTE4MuXbqIBj4tLQ07duxAgwYNIAiCJMqt4OLFi1i/fr3GFFjlaOCkSZNgbGyMnTt3qo0YT548GY0aNVLJJFD+986dO2FlZYWQkBCV+5nyM8jb21ttpkZMTIxk3xXXjyLbArnORVxcHLp37/7ezABF5HLlypUqRhTvBh/s7OwkkXsF0dHR2LNnD7755huVCG5gYCCMjIzQuHHjfBdqzMnJkezDhQsXYGtri6lTp4rHUvm8ZGdnY+jQoWoHTOPj4+Ho6AhBEODk5CQO0kVGRmLkyJEoU6YMvLy84OPjgz179sh2j3of2dnZuHTpEpo2bYoaNWpg3LhxaNKkiTgNxt7eHh4eHgWeP8uULNiEMiokJSUhPDwcO3fuxM8//yyZ2xgaGoohQ4agRo0acHJyQlBQEIyNjTF48OD36ubk5EhuzqNHj4a5ubnadMj+/ftj5syZGrUUN/C4uDhMnjwZHTp0wJw5c/D69WsEBARgxIgRYqVGZZOmiNjGxcUhMDAQdevWhb+/v/j65cuX4efnBzc3N9Eg5+Tk5HnjVtZSbnNKSoraDu6MGTM0prwpjs+dO3dQrVo1scOkfNyUjai9vT2aN2+epyHLzYkTJyAIAmbNmiWJYCt0z5w5A09PT6xevRqhoaFihz8lJQXPnj3DjRs3RFOdnJyMbt26SdLpFGRmZmLevHlwdnbW2Klt3749qlSpgj///FM8VhcuXEDVqlXRokULjSlbeY3EK79n165dKFu2rMSIKs7l9evX4enpKQ6gKLYZGhriu+++E7cdPHgQZcqUQY8ePdQOHMydOxcuLi4qkVlFgYYaNWrA09MTW7duFfcxOzsbx48fR8WKFSWpufkxoS9evECXLl3g7e2N3bt3i9u/+uorVKtWDRMmTJBEshISEuDs7IxOnTpJdNavXw9BEKCnp4cvvvhCjDZCKYK1adMmMSpy69YtNG3aFD179lSJqqxfvx56enqYM2eOxLT17NkTY8eOVdmHvLRyFwGLiIhA9erVYWlpCWNjY5XOe360oDT4g3cRHT09PbVpkXnpqSMnJwd+fn6YNGmSrCP6f/75J1q1agVPT08VI+ro6Ci5btSlFytvy87OVjGiHTp0ECOWCmbMmIGmTZu+9/cVExODGTNmQF9fH3/88QdWr16NTp06oVatWhg+fDhcXV3FuYMvX77Ehg0bJGn22dnZGD58OCwsLN47r3X+/PmoVauW+PsKCQmBmZmZxgi7Yj87duyIIUOGSLblF03VdZV1tmzZAldXV4wdO1bt8Y+JicH+/fsREBCATZs24Y8//gDeXc+urq6oWrUqzpw5I0a/nj17hoCAAJQpUwa3b99W267Tp0+LRZIU0fC0tDTs3LkTDRs2RJ8+fUS93HUMcqO4D+YeZJkwYQKMjY2xa9cuiRF9+fIl+vXrpzKX7/r16+jYsaP4vdeuXYOhoSECAwMlz03F8z87OxuTJk3C6NGjVYx2Wloa3Nzc4OPjI3731atXUadOHbi7u6sUAsO7KGj9+vXFqTZ5ERAQgEqVKmHVqlUSI5qTk4Nr166hUaNGYnEuBYrq34pBvtKlS+Pvv/9WaYNC932pzxEREZg5cyZ69+6NrVu3IikpCW/fvkXv3r3h6Oioks6blpaG+fPno3r16mrrb0RHR6NatWooXbo09PT04OLiIrbv/v37GD16NBwdHWFrays+h+W6Tz1//hxnz57F+fPnJf1E5d/DpUuX0Lx5c9SqVQshISFo06YNLCwsYGpqChsbG7UDAsynA5tQRkJ4eDh8fX3h4eEBIyMjGBkZoWrVqti1a5doPN6+fYtnz55h0qRJ6NixIwRBgI2NDZKSklRGACMjI8URbMVryg+mUaNGwdTUFLt370ZMTAxevnwppraom6SvuHlmZ2eLD9lnz56JS3Ao0lUyMjKwe/ducZ6WuptubGwsFi1ahNq1a0uM6KVLlzB48GC4urrme96VspZyFVVlE/rixQv4+/vD2tpaJQqZm8TERNjb20tG+pVR3ORv3ryJypUraxyNP3z4MLZt24ZvvvlGcgyCgoJgYGCAgIAAcV5GTk4Onj17hlq1asHOzg6Ojo6YNGkSYmJicOvWLXTu3BnOzs6wsbFB2bJl4e/vj4cPH+L+/fto0aIFzMzMMGzYMBw5cgRbtmzBkCFDYGNjk2f65Nu3b9GkSRN4eHjg1KlT4vE6d+4cqlatioEDB+LatWvi+zUNBjx58gQnTpzA8uXLsW3bNnHgITMzE7t27UKZMmUkRhTvKgQ3b95cNF8hISEwNzeXXAuKYz1z5kw4ODigefPmCAsLw/Pnz3Hp0iWMHz8eFhYWKvsYEhICS0tLjB07Fj/88AO8vLzg6OiIv/76S7IvitRc5chWfggJCcHgwYPRpEkTMQUL7wpjeHh4YPLkyXj+/DkyMzPh4uKCDh06iO9RjuAOGTIE48aNg4mJCUaOHCnpEChSc7ds2YJ//vkHdnZ2mD9/vmRA4ezZs+Jc2B07dsDY2BgdOnTAgAEDMGLECJiZmalEYMLCwjRqaUpvHDBgAOzs7Aqlpbhmvv32W7Rv3x5Lly6FkZGR2gI8hWnbnDlzUK5cuSLPb8odpQeA48ePo2XLlhIjqkjNrVKlCrp166ZW6/bt22jTpg22bNmiUjEZ74rQdOrUCY0bN8acOXPw+++/44svvkCZMmXyXb30+fPnGDp0qHj9v3nzBocOHULDhg1hamoqmi5oiAzl5ORg8ODBsLS0lCx7pODChQuYOnUqrKysxN/XjRs3UKpUKTE9XsGRI0fE46M4Pxs3bkSbNm1Uok7qKEh1XWWtb7/9Vu0AYGhoKJycnNCwYUNxiSAzMzOMGjUK6enp+Pvvv+Hl5QVjY2N4eXmhefPm8PHxQZUqVST3O3WcOHECXbp0QfPmzSVGdMeOHfD29kbPnj1FQ6jpfnn37l1MnDgRPj4+cHZ2xogRIyRz0hVGVDkiOnfuXFSvXl0yBURRPVgxIKA4TvPmzYOenh6WLl0qGWxNS0uDv78/SpcurXG6x+XLl1G5cmX4+vqKz/jt27ejRo0aqFChAnbs2IGwsDAcOXIEo0ePFqOuyuQVuVQY0ZUrV0oG3mbMmIEWLVpI7oHK1YcTExNx/Phx2Nvbo127dkhJSZEYfX9/f1SvXh1ffvmlxiwnxRJYHTt2RLt27SAIglhY6unTp2jZsiXs7e3RoUMH/P7771ixYgX8/Pze+xzds2cP3N3d0ahRIwiCAFtbWwwaNAhz5sxB165dYWxsjHr16uW74GB+uHXrFnx8fNCtWze100mUfyeXLl1Cy5YtIQgCzM3NcezYMVy5ciXfWVxMyYVNKCMSEhKC0qVLY/LkyTh79izi4uJw6dIltGnTBqamptiwYYNK6sTjx49x8OBBtSO3L1++hKmpKQRBwKhRo7Bw4UK10b9p06bBysoKVatWRfPmzSUpJcpERERg/PjxaNq0KWrXro0ePXqIUazExERMnz4dnp6ealNplVGObD558gSLFy9GrVq1VIzosGHDUL58+TxH6jVp5R6lnzlzJvr374+aNWuq3bd79+7B398fZ86cwX///YeMjAx06tQJa9euFb9H+TuhZHA1LQPj7++PSpUqoW7duhAEAf369RM7J4mJiWIlXCcnJ/Tt2xcDBw5E3bp10atXL6SmpuLVq1dITU1FWFgYrKysMHHiROzfvx/Hjh0To9hNmzZFREQEHj9+jNmzZ6N8+fKws7NDzZo10a9fvzyrICqOW2pqKho2bKhiRBWpuX5+fnkW8rhx4wacnZ3h4+MDOzs72NjYwNTUFAsWLEBsbCyys7NVIqKLFi2CpaWlOBig6NzOnTtXov3nn38iLS0NmZmZWLx4MWrWrAl9fX1YW1vDzc0N3t7eKp32W7duwcLCQnIN/P333xAEQaXgSEZGBo4dOwZBEFSWbVCH8oM9NDQUAwcOVDGiy5cvh5eXF8aPH48qVaqgffv2aj+fkZGBQYMGYcqUKfjvv/9gYmKC0aNHSzph8+fPBxGhQoUKKh2NFStWwNLSEgMGDBAjr6GhoZg4cSJ69OihtvhIbGws6tatqzJ/dsWKFbCyspJoKaJ3y5YtgyAIKr+bgmjhnWEQBAF2dnYqhcwKqqeoWtu/f3+UK1fuvcbhfYSHh2PgwIGYPXs2bt++LYmqX7hwAc2aNUP9+vXF7cnJydixYwdcXFxUIkA5OTmYMGEC9PT0EBwcDGtrayxduhQnTpyQvO/27dvw9/cXozwdO3bUmHmQkJCAmzdv4tixY5KBlJSUFAwaNAimpqZiCntcXJwYsVEuTvb48WOcOnUK//77r+R+pjCiyvfZXbt2oUePHmjZsqXYpkePHsHMzExl7u2SJUtgaGiosozTsWPHYG5u/t6CYYWprptXYauIiAhxeSCFyQkPD8fcuXNhaGgoVmjOyMjA4sWLMXr0aHz22WfYvHmzWkOrzkAfPnwYXbp0QbNmzVSMaJMmTdCmTRuVeZ0KQkNDYWtri6FDh2Lq1KmYN28eHB0d4eDggOnTp4vvmzhxIoyNjfHzzz9j9uzZKFWqlOQ6v379OkqVKoXZs2dL9DMzM5GUlISJEydCEAR06tQJy5cvx8KFC9GvXz/Y29trrMCsOL5Xr15F+fLl0b59e/E58fPPP6Nr166ikalZsybatGmjMqCbn8ilshF9+/YtFi1aBCsrK4lWTEwMLC0tJUt5AYC7uzs8PDwk2QUKxo8fjzp16qitkREaGgpzc3PMnTtXTB0fNGgQTExMREP+/PlzzJs3D3Xq1IGtrS2cnZ3h5+encm3nHtC/ceMG+vXrh3PnzmH8+PGwtraGvb09vL29MX78eJw4cQL9+/dHu3bt8lzzOb8o1s6dO3eu5P5z6dIlyWCc4vikpaWha9eusLW1LfRya0zJhE0oA7y7iZmbm4sjzLlHrjt16gQ7OztcvnwZyMP45Mbf3x9z587FunXr0LlzZ1SoUAHBwcEqizEfP34ce/bswcGDB9UuVB8aGgo7OzsMGjQI8+bNw9ixY+Hq6irp2MfFxWHq1Klo2LChuKaegkePHmHFihVo27YtvL290bdvX9EgvXjxAosXL1aJiF64cAFjxoxR6YjkV0vZhGzcuBHz589XO/KXlZWFadOmoU6dOnB2doaRkRFat24NQRDg4uKCU6dO4dKlS5JKhcqoizJMmTIF1tbW+PfffxETE4MtW7ZAEASVOSWHDh3CqFGj4O3tjXHjxolzqBQkJCSgQYMGatfw27x5M8qXL4/OnTuLlQlfvnyJmzdvIiEhQe2conv37mH//v2Ij4+XtPvNmzdo2LAh3N3dcerUKXGE+dy5c7C0tMTo0aPVrhl4584d2NjYYPbs2YiJiUF2djZu3boldoC++OILMd1p165dqFChAipWrIhSpUqJaZ1RUVEwMzMT0+8ULFq0CGZmZmIHIScnB7Gxsfj555/xzTff4NKlSyqpV9nZ2ejUqRPMzc0lnfV58+ZBEATMmzcPe/bswd27dyX7c/LkyTwjaY8fP1a7Vq3CiDZt2hQ//vijuH3VqlUwNTVFnz59xG0vXrxQqSAZERGBihUr4p9//sG5c+dgZGSEMWPGSIzo4MGDUatWLUnkYtWqVbC1tcX48ePRokUL+Pn5icZDcW9QF4U5dOgQ6tWr914tRVQrPT0dv//+u9qoSUG1Ll++jIoVK2o0WgXVu3XrFsaPH5+vAl55kZqaijZt2kAQBBgbG6Ny5cpwc3PDxIkT8fPPPyM9PR2HDx9G7969JWmHr1690lhYKSQkBFWqVMHFixdx8uRJsTJujx498Ndff4nXQU5ODtLT08XfiDrCwsLQoEEDuLu7w9jYGIIgoEWLFmIl4zdv3sDPzw8mJibioGDueb19+/ZFnTp1YGJiAkEQ0KNHD7EoCdQY0ejoaFy6dEkSqXry5AmqVauGzp07i9+zYsUKlC5dGsePH1d7DFxdXd+79qOc1XWzs7Mxfvx4Saq0goSEBKxevRp6enr5Xp7i5s2b6NSpE+bMmSPJOsC7e6Ovry+aN28uzpdMS0vD5s2b0bZtW7XFpR4/fgwnJyeVefARERHo378/7OzsJM/OqVOnQhAEmJiYSIzjzZs3YWJiorKs1Pr168W54UlJSdi1axdcXFzg4OCAunXrYvTo0Sr3udjYWPzzzz8qbf3333/h4OCAdu3aifeSt2/fIiQkBCdPnkRERIRK2nhBI5dOTk5o0qSJ5Hmg4OTJk/D29kbLli3FNiuqD7u7u2PgwIHo168ffvzxR0nWlvI1qyApKQnm5uYqhdEGDRoEY2NjhIWFqfR7IiMj8fr1a5WU5Xv37mHJkiUqRQkHDBiAdu3aAe+Wz2vQoAFmzpwpRmWjoqLeOyCTH2JjY+Hu7q5SOHL58uUwNDTEhAkTJPOuMzIysGLFChgbG+erqBzzacEmlMGLFy8gCAI6d+4s2a5selJSUuDk5KQx/UsTK1euRMeOHcV/b9u2DV988QVMTEwwd+5c/Prrr+/ViImJgZOTk2SpErwbXR41ahQMDAzEuXHPnz/HzJkzUbNmTSxfvhx414lycXFBt27dMHz4cAwePBjVqlWDubm52HF/9uyZmE6rPLKb+wFQUC1lI6rOuCs6kYqHbFxcHP7++2/8/vvv6NKlCwRBQK1atWBlZQU3Nzc0atQIkyZNynOR+rVr10IQBMmo+tmzZ2Fubi4pHqNAnblVnj/m7u4uPjxyz49dtWoVBEFQibKo48WLFzAzMxM7d02aNMHevXvFkfyMjAxxDtyJEyfEDsNff/2FyMhIFb2MjAyMHj1ajG7m3oeAgADo6+uL896Sk5OxdetWeHl5SR6G169fh42NDfz8/MSOyPLly1G6dGkxHbsgc2gePnyIhg0bolWrVrh27RqCg4NhaWmJUaNGYd26dahRo4aYBjdnzhxxKSJN7N69G1ZWVjh//rxaIxoSEoLu3bujY8eOkuOkKPqCd4NMiqjEtGnT8Pr1a9EEjxo1Spz7ePToURgZGWH8+PFi5cqAgADUqFFD0qZNmzaJJnvbtm1o1qwZevTogaSkJLVtVFBQrbwoiJYiMpFXEYyC6CmiCXIWImratCmGDBmCoKAg/PTTT2jevDkqV66MmjVromvXrhgyZAgcHR1Rt25dtR1dBVlZWUhPT8fYsWPFIiuvXr3Cy5cvIQgCXF1dUa9ePRw9evS9y2TcunULVlZWmDZtGq5fv45bt27h4MGDqFKlCipUqCAW73n58iWGDRsGS0tLyXUXGhqKcuXKYdy4cfj1119x/fp17N69G/b29nB3d5fMSR0yZAhsbW0labwKFNfUgwcPUK9ePXTt2hWjR4+Gra2tZE63AsXvOK/qq9qqrtu0aVONa23GxsaiU6dOaNCgAd6+fZtnAZvMzExxcEIxcNaoUSP06tULv/zyC5KTk3H06FEMHjwYLVq0EI1cenq6xjm9v//+O5o3b45nz56J167iv/fu3UPr1q1Rt25dialatmyZJNvj1atXaNeuHWxtbSWmLjg4GObm5ioDzCkpKUhKSkJGRobK7yU6Ohr29vYQBAH9+/fHlClTEBISIg6C/fvvv3ByckLbtm3fu7ROYSKXU6dOha2trdqUdQA4deoU2rVrhxYtWmDy5MkoU6YM9uzZg4cPH+Knn37CnDlz4ODgAAcHB/Tv3x/IoyjR/PnzUapUKWzfvh1QMm1ubm7w8/MT27569Wo8ePBAbST7+fPnKF++PARBQNmyZbF48WKx3/H8+XP4+vqKz4nAwEA0adIE48aNkyX6qeDkyZNwc3NDWFiYeDyXLVuGUqVKYcaMGahUqRK++OILiRHdu3dvkQfrmJIJm1AGAPDZZ5+hdOnS+OWXX1QiTooHx5QpU+Dl5fXedTJzU7duXck8yW7duqF06dJo3bq1GP07ffq0SuEiBfv374e3t7f4YFJ+kDx+/Bh9+/aFjY2N2AGPi4vD3Llz8eDBA7GIhb+/vyS6ExYWhl69esHc3Fycj/TkyRMsXboUDg4OaguSyKmFd2ssWlhY4NatW6KBUt7/P/74Ax07dsTt27cRGRmJffv2YdKkSejdu3eeKS3btm2Dvr6+mJacnZ0NDw8PmJiYoHHjxujatStGjRqFQ4cO4e3bt3lGtY8cOQIjIyOV71M+B25ubvlaYuTp06cYO3YsBEHAhAkTMH36dNStWxempqZo3749Fi5cKJZu79y5M/7444/3Rtw9PT1V5ocpH8M2bdqgTp064jWt6IzjXQRH0Ym6ePEiqlWrhmHDhmHixImwtbWVdKYVaOqsvHr1CvHx8WKU7PHjx6hfvz4qV64MKysriUl/+/Ytbt++jQkTJqBFixZqDXZuGjRogBo1auDChQtqTZ5ivVDl6JKCrKws7N+/H4IgwNPTEw0bNhR/k9euXcOJEydQtmxZcQ7kqVOnIAgCpk6diuzsbKxZswZWVlZ5Fr8aNWoU2rdv/971Nwui9T6DJ6eWNvQKyokTJ9C0aVP07t1bzKxISUnBhg0bMHXqVJQrVw56enoQBCHP6rUKvv76a5QpU0bszI4ePRrlypXDTz/9hPHjx6NUqVJ5LgWSkpKCTp06qf1tx8TEoHbt2nBychINyosXL9CnTx+UK1cOb9++lczfzN35v3btGqpUqYIGDRqIUzmys7PRq1cvVKpUSW0HXHFtRUVFwdPTE4IgSOa4KX4Pc+bMgaura57Vx7VVXTcnJwe1a9fGuHHj1L4GAD/++COMjIzUZvzkfm9kZCS8vLzQo0cPrFq1Cvv370eHDh3g5uYGOzs7+Pn5oU2bNnBzc4Obm5vG+5OCuXPnomLFihq/7/z589DT08tzkDMjIwNbt25Fs2bNxEHp9evXw87OToxka6rqnpvTp0/D29sb9vb2aNu2Lfr37w9ra2vUqlULkyZNwo8//ohz587B1tYWQ4YM0XitogiRS+XrJDo6Gt9//z02bNggmqZz586J8zdzV0zGu+I/Bw8eVJvJkpKSItn3L7/8EgYGBujatSvKli2L48ePIyMjA+np6Th16hQmTZoEOzs7uLu7q1y/in/7+fmhVatWaNmyJaZMmYI6deqgR48e2L17N9q2bSv2N3JycjBt2jS0bds2z0GrghIUFAQHBwfJtsOHD4vn/qeffkKFChUwYsQILjrEvBc2oZ84yjdIRUrUL7/8oray3ujRo9G0aVONI30JCQkICQkRTZXifV9//bVYeGXIkCFwcHBAVFQUkpKS8M8//6Br165qixApCAgIgIuLi8bXDx06BGNjY4lpyM7ORnh4OAwMDFTWl1Pw4MEDtGnTBhUrVhTTKmNjY7Fq1SqVVBc5taBUuEY5zTW3Cb969apKGhTySIU+fvw4EhISkJWVhZ07d4qFh3x8fNChQwfcuXMH169fx8mTJ9GiRQu4u7tDEIQ8iy9dvHgRgiCInZLcnYmcnBx4enpizJgxGjWUR+VjYmLw+eefw9zcXLxO/vrrLwQEBIiRXsXSJZ06ddI4rykjIwNxcXGoVKmSmI6tfFwUx3Hp0qWoXLmyykhwdHQ0mjVrhkOHDkkirop1Z5XXNVVeVsDHx0dF69atW2jZsiWcnJxga2srLp3y+PFjNG7cGHXq1FGJDijQNKCjbm1Pb29vVKtWTWJElV+vV6+eSifpxo0boolYs2YN9PX18e2332LdunWYOXMmTE1NMWPGDBgZGWHp0qWS+bgKI3TgwAGYmppi8eLFYnQy9/ePHz8e48aN01iRU/G+j6WlLpVbG23LL9HR0fjxxx/x7bffIjY2Vjzfp0+fRuPGjdG9e3exuqyC2NhYXLt2TcUkP3jwAGvWrMGUKVNU5sd169YNK1euxIABA+Dg4CCJaJ0+fTrP5UWePXsGZ2dnsbhb7vmQ9+/fh7GxsWSAMSEhAU+fPlU7f1Nh8hTH8sqVKxAEQcxYUZBXlVOF+Y+OjoaHhwc6dOggue/PmzcPRkZGauf8KtBWdV1FRkmPHj3g5uYmMSXK9/Vt27bBzc1N4zX08OFDHDp0SMySCQ8Ph4uLC7p37y7OyXzz5g127dqFwMBAODk5QU9PDyYmJu+tkr5mzRo4ODjgwYMHkn1StC8xMREODg74+uuvVdodHR0tzq1UFP5r3LgxatSoASsrK3GqjjJr1659b9XaEydOoHfv3vDx8cHDhw8RGRmJnTt3omnTpnB2dkaVKlVQs2ZNMTKdV/S4MJFLBaGhoahYsSLc3NwgCAKqVKkiLi12/Phx+Pr6okmTJqI5zczMzLMtd+/eRe/evbFx40bJc0xReXzSpElqP5eamqryu7x27RoEQUBYWBgePXqEzz//HL6+vli6dCni4uIwduxY+Pn5ianTynPX5TaCmzZtgr29Pe7cuaNx/7/44gs0bdo0z4wBhgGbUAa5Ou/KRlS545aYmIhevXqpzAFRoOiIN2/eHAsXLpSkvd28eRP29vaoWbMmKlWqpHF9NE1s2LAB5ubmKkZV+QZobm4uWTcxKysLCxcuhCAIYppS7o5EdnY2fvzxR5iZmeH8+fOS7crIqQWlioK5Czooj1ZmZWUhOTkZzs7OYnRVXbRUwfjx41G7dm1RIzMzEzt27BAr2eYmLS0NT58+lRS00USLFi1QtWpVsTOhuF6ysrLw9u1bdOrUSTz2udt28+ZNlcXqY2NjMWjQIJiZmYnmTHGcLl++jJ07d6J79+5qo72508x69eqFmjVriml3uc3bhg0b4O7urmJmMzMz4erqivr16+P48ePitf6///0P1atXx4ABAyTFkObNmwcDAwOVa/f69eswMzPDpEmTsGrVKgwbNgx6enrYs2cP8M6Ienp6olWrVpIKoIrOtKaHeHJyMp49e4akpCTJvL+GDRuKRlS5ExsREYE6depIIqEhISEq888WLFgAExMTbNq0CTk5Ofjnn38wffp0VKtWDb/88gvi4+Nx+/ZtlVH9fv36icXJlDs1qamp8Pf3R9myZVU+Ex8fj/DwcJ3T0oZeQQgNDUWlSpXg7e0NQRDQsmVLSdTjzz//hI+PD3r16qViRHNz48YN1KxZE8OHD8eKFStU0o0VaXK1a9cWDWp+F6oPCQmBjY2NON9SOfqruAcMGjQI7du3V0mVVMzf7NKliyRdNndRtV69eqFbt25IS0tTW3xNeVvuJUWioqJQr149tGvXDv/88w/mz5+vdtAu9/GSu7pu7uN5/vx5CIKA0aNHS+ZlKu7fkyZNQq9evdSm40ZHR8PQ0BDOzs749ddfxX0NDw+Hm5sb2rVrJ1kvE+8M6T///KN2DujDhw/xxx9/iPe/q1evQl9fXzLvU3n/7t27B3d3d5UU57dv38LPzw+urq7i8y0jIwPfffcdvL290bBhQ9FwKPZTsZZs7pRvddHGM2fOoE2bNmjSpIn4+3r9+jXevHmDzZs3IzAwENWrV1cpAidX5FJxXSxYsAAxMTF4+vQpGjRogNq1a4tzio8cOQJfX180btxY/C5N10VoaKhYCE/xLFBm6dKl0NfXx7Zt2yTb1UWMQ0JCYGFhIVn+7eHDhxgzZgy8vLxEo5ycnIw1a9aI6blyLheljOL6XrZsmcr1qxiImThxIsaPH5/n4B/DgE3op0lUVJTKg0x5xEqdEZ0zZw5q1KihtrDOzZs3YWdnhzlz5qhUyVXcpJYvXw4HB4f3rgkHpYjqzZs3kZWVhWPHjsHMzAzz588Xo1DKo/J3795FnTp1VEZinz9/js8//xwmJibiaHluk5Kamgo9PT18//33ebZJLi1NEdXFixejQYMGKp3Ili1bqi0KpMzUqVPVlnB/8+YN9uzZA0NDQ0nVV3WphHnN4/vhhx9QsWJFuLq6StYpy8nJwfz58+Ho6Kh2/TIodUQEQcDSpUvF7YrlQUqVKiW5FtUt46NAYWiVK8xu3boVpUuXxujRo9UWIBk5ciQGDhyIjIwMUVth3jIzM9GkSRPUrVtXYkT/+usvVKtWDf369cPt27dF45a7cxseHg5DQ0PJuXz58iWaNWsGLy8vsQOpMKLt2rUT157NizVr1qBDhw6wt7eHlZUVunbtir1794qve3t7w8nJCXv27MHt27dx/fp1eHh44LPPPhPfc+vWLUm1X+XOjWJARfk4JicnIywsDB4eHqhVq5ZYREkx8JCWloYuXbrAyMgIvXr1wm+//YYVK1Zg6NChsLOzU6kOq6ta2tArCMoVRZOTk/HkyRPo6enhwIEDkvedOHECPj4+6Nu3r8b51hEREbC3t0dAQIDGiMPr169Ru3ZtlYq/+SE+Ph5ly5aVVG3O3bEdPHgwWrduLdmWe/5m27ZtJWZaWaN169bo0aOH5PP379/HN998Iw44Kc9Df/DgAapVqyYOBj148ABeXl6wtraGubl5ngOcclfXVTbeuU3z2rVrYWBggL59+4pZJHfv3sXcuXNhaWmpcS7u/fv3YW5uDkNDQ9SrVw+//PKL+Ey4c+cO3Nzc4OvrK1Yizovchlah88UXX6it1I13WUdubm5q76VHjx5F79690aRJE/H7FUa0cePG6NKli5hBMGfOHLX3THXRRsUcyePHj6NDhw5o1KiR2gHI3IZGrsil4rro27evZPvZs2dhYmIiGVQ+evQounTpgtq1a2tMy46KikLlypUxe/bsPI3g/Pnzoa+vL+6/OsLDw2FpaYnJkycDueo3REdHY+zYsWjQoAG++uorjRpFIS4uDuHh4SqFo6ZMmQIDAwPJOtJ4dz0EBATIMljHfBqwCf3EiIuLE+cVTZ8+HevXr1f7PoURPXbsGObMmYNSpUqprWwWFxeHBg0aqCxIn/vme+bMGbHSK/KYI6IcUV2wYIHYuRo6dChMTEywZs0alQfk3LlzNT44ExISMGrUKJiYmIgdIeUUuxMnTsDV1TVf61UVVUs5oqq8IHZwcDDs7OwkFR4Vun379kX//v01Ri+mTp2KMmXKSM5Ndna2mOaZkZGBHTt2wNDQUKUiojJ3794VzWDuDlVOTg62bNkCJycnmJiYYPDgwfDz80P//v3zLLePd+lRjRs3xsyZM2FsbCwZgVcYUVNTU7E4UV7RXk2Gdvjw4bCzs0P37t0RFhYmLgcRGBgIS0tLyfy63GRmZoops7mNqLOzM8qXLw8zMzOVzq266LgiuqNIlUpPTxc7zzExMahWrRq6deumMcUY79aqK1u2LDZt2oSff/4Zy5cvh4eHBwwNDbFq1SrxfT179kSdOnVgbm6Oxo0bS6pxhoSEwN7eHk5OTuK27OxsyW9u0aJFEAQBa9euxevXr8UUxVmzZuHMmTMICgqCvr6+ZO1AAJg1axbc3d1hYGAAZ2dnDBkyRGXgSVe1tKFXECIiIqCnpyfOY1RcL23atMG8efMwfvx4bNy4UbwG//zzT7i4uMDPz09tJH/06NHo27ev2jR0KP2WVq5ciVatWr13HqlyWq/ifuLv7w8LCwtJlgmU1jT97LPPxIEOdd+tHK1Ujq5lZWXhyZMn6NKli9gJV6xTbG9vjypVqmDdunWSzIdHjx6hXLlyGDZsmKTITFRUFNq2bfvetZflrK778OFD9O7dW/I55f1PS0vDnj17YGNjAyMjI5iZmaFOnTpwdXXVOJCh2J/Vq1dj2rRp8PX1RaVKldQa0S5duqhdW1UZdYY2JycHUVFRYupm7969sWnTJuzYsQNjxoyBhYWFSvuU9+vkyZPo3r27RiPat29fTJ8+XW212byijYpMFuVoo8LEqHsmyBm5VI7anz59Wvw9KdZwzv18O3jwIPr06aMx9Xnjxo3o0KEDXr16Jbb50aNHOH/+PFauXIljx46J3/Hll19CEAR89913KjrXr1+HtbW1GNFVFFdTjlwrjKi3t7fsRjQsLAyenp6oUaMGTExMJHPDIyMjMXToULGg1JYtW7B8+XIMHDgQdnZ2efYJGEYZNqGfIGPGjMHMmTOxZMkSNGrUCHXr1sWWLVtUOlmDBg2CIAgwNTXVeFO5ePEi6tSpo3EOjvJNf/DgwXB2dtbYrrwiqllZWejTpw8MDAzQuXNn/Pjjj9i2bRsmTpwIS0vLPCMU8fHxGDlypFrzOG3aNMkI7vsoqpZyRPXGjRvYsGEDbG1tNUY7lOfm5ebs2bMQBEGcv6M4TpUrV5ZUEs7IyMDOnTthZGSkNiKSnZ2NyZMnQxAEsWORO8qbk5ODa9euYebMmWjTpg1atmyJOXPmaBztVO44eHt7Y+jQodixYwf09fUlKd3Pnj3DiBEjIAiC2jlFyuQ2tMppplOnTkX16tVhZGSESpUqwcvLC87OzuJ1ER4ejsqVK+Pzzz/H+vXrxVRXxfFp2bIlXFxcJEb0woULqF+/vkoKmALlc6k4fw8fPoSFhYUk/VhxLJ48eaIxYox3FQQrVaqkci1fvXoV/fv3R6lSpSSdldDQUJw5c0bSvmvXrsHU1BRdu3aFjY0NRo8eLb6WO61w0aJFMDY2xrRp02BoaChJUbx79y5sbGwk0VUFycnJePjwITIzM1WiE7dv39ZJLW3oFYSsrCysXr0agiCI0RooFU4ZOXIk6tWrh/Lly2Pw4MHi4MWFCxfUdnbT09Ph4eGhtto1cnXYIyMjIQiCWEFcHZrSeq9fv45mzZqhQoUK4iBITk4O3rx5g/nz54tzw9Sh2IeoqCi4u7urREQDAwPh5uYmWRP1wYMHsLGxgbW1NVq3bo2vvvpKNKKKFD91Zvd9BbHkrq776NEjVKpUCR07dpR8PrfJuX//Pk6cOIGvv/4aFy9ezHO5GOXCRZ6enoiLi8OwYcNUjOjdu3fh6OiIPn36aKwYq87QVqhQAb/99pu4X1u2bEHlypVRunRpuLq6olevXpIIbXR0NMLCwlTmFJ44cQJdu3ZVMaJ79+5FrVq1YGxsrGJA5Yw2yqmV+7po06YNrl+/jocPH8LBwQEzZsxQeS/ymMuPd1NjmjdvLv77p59+Qo8ePVC2bFlYW1ujatWqkijpihUrVPo7ivv4okWLEBAQgCpVqmDt2rUajeiECRPg7OyssgRbYbl+/bq41M3Jkyclg5YKXrx4gXXr1qFq1aqwsbGBq6srhg4dylVwmQLBJvQTIzs7G7NnzxYLLmRlZWHRokUYPnw47O3tsWHDBskI65w5c/KsuKeowKicOpWbtLQ0hISE4NChQ/Dw8FD7INYUUVUucIR3KSz169eHoaGh2genMsopnWlpaRg+fDiMjY3FjtDcuXNhZ2en0eRpSyshIQHDhw8X1wVULNGhvJ9BQUESc6mO2NhYjBo1Cubm5uL8RS8vL3Ts2FFl7mRGRgY2btyIYcOGqdWKi4vDmDFjJOY6r4XZc1eSVKDOgJ86dQqdOnXC1atXxY64shF9+vQpxo0bp/HhlZehVY6shoSEYNeuXVixYgUOHz4splhmZ2eLUVQbGxu0b98eVlZWaN26NRYvXoxbt24hMzMTzZo1Q9OmTXHs2DExAv8+86GIjpcqVQp79+5F9erVJUWa8rO4vYJZs2bBz88P2dnZKqlj//33H3x8fNClSxeNyy9cv35dXPoI7wrtmJub52lEAwMDYWpqCkEQJMslKTodbdq0wbJly/D777+r/Z3lvgbWrVunk1ra0Csojx8/RlBQECwsLPDDDz9gy5YtsLW1lczjnThxIsqVK/fepVMSEhJQqVIlcbBDXYQnJycH06dPx+PHjzFnzhyNFbU1pfUq9vnSpUvo3LkzBEFAnTp14OnpiY4dO8LR0RH//fdfoedvmpmZSZ4tis9/++236NmzJ3r27Im6deti3bp1SE9PR1xcXL5+R5qQq7pubuOSO8qbe2pDXlVwHz58iMOHD6sUounUqZOYgtmjRw9UrVoVv/zyi2h+IiMj88ze0WRoFUZUMSXh5cuXePLkCV6+fCk5948ePYIgCDA0NETFihUREBCArVu3ivfDkJAQ9OjRA82aNROfFxkZGfjxxx/VDrTJGW2UO3KpuC4ePHgAd3d3NGnSBGXKlJH0RfKarpKbQ4cOwcDAABMnThSXHZo8ebJo2CdMmKCxH4R3z8MKFSpIpuFMmTJFzA5QZ0QfPHiAadOmvbcwVX6IjIyUZGzg3T3C1tZWbQHC+Ph4PH/+HKmpqfleP55hFLAJ/QRJSkpCxYoVJekbnTp1gpWVFXx8fODi4oLmzZu/tyOEd8unGBgYiNEbdTfpxYsXIyAgACkpKRpHlt8XUVU2gVlZWYiOjkZaWhrevn2rdg0sxYPl0aNHWLhwIXJyckTDYGFhgT59+qiN8MqplRfPnz/HjBkzYGBgIK5DqHigKAxTfvQSEhIwYsQIGBsbo0qVKnmur6iuGmJuLU1RXryb8zp16lSNEcvw8HAYGxvj888/x549e8QO6MOHD+Hp6Yl9+/YBSmuLLlu2TPysus5lfg3tokWL8jxGePdgV6wbeuLECZw9exZBQUGoVq0aKlWqhGbNmmHChAkQBAEeHh4q837zIj4+HqNHj4YgCJI1cQtiXDIzM+Ht7a02Iqdg/fr1MDc311huf+XKlZKU68zMTPz222/vNaJxcXEIDAyEoaEhjh8/juXLl8Pa2hqbNm3C119/DX9/f1SvXh0uLi5o0aIFfv755zz3RVe1tKFXUGJjYzF37lxYWFhAEATxvqno3B86dAgVK1bMcxkQvJuPWLNmTcm6zbmvt//++w89e/ZUW7BGQX7SevHOQB87dgxjxozB6NGjsXnzZkRFRckyfzP3QM2ff/6Jtm3b4s6dO/D390ft2rWxfv16sUBXUQYE5Kiui3ykG+fk5CA9PV08tupS8BVGz9LSEi4uLtixY4eYUnzkyBF06tRJPCddu3ZFjRo1sG/fPo1RuPwa2ipVquCXX37Jc1rA06dPUatWLTg6OmLAgAHo2LEjqlWrhmrVqqFdu3Y4ePAgFi5ciCFDhqBFixYqNSaUkTPaqI3IJZSuiwcPHqBhw4ZwcHCQDMYX5Jp7+fIlNmzYgMaNG6N58+Y4ceKEaBzxLuOlRo0aGucaR0dHi5k1ys/F9xlROZaNysrKwoYNGyAIgrg8EZQyNjw9PbFp0yZJVJZhigKb0E8MxU0tODhYzPEfOnSoWLY9Ojoahw8fRsOGDfO1fuHdu3fh7OyMLl26iCO+uUfDJk6cKEmdVEd+I6r//vsvsrKyxBtvWFgYDA0NJfqK1x4+fIjy5ctjypQp4muJiYkYNmyYWtN48+ZN2bQ0ofygSE1NVRtRNTY2LpChTUhIwPTp0yEIgrjQe2Er4ymnGysbsfT0dDFlV93c4OzsbDGq5OTkhGHDhqFy5cr45Zdf8Pz5cxw8eBCurq54/vw53r59i7Vr16pUzVWmoIZWeZkHTR2GFy9eYOTIkZIKxomJiYiIiMDMmTPx+eefQ09PD+bm5vkaUVY+lykpKZg4cSJMTEzEzmhBz0H//v3h5eWlYjIVOn///TdsbGzyTOnNTVZWVp4RUeVMg5kzZ0IQBBgYGKhUZY2MjMTx48fRvn17jQZJucOkS1ra0CsKT548waJFi2BhYaFSvXPatGnw8fHJs4OnOF87duyQzI/OvZzMvHnz0LFjxzynB7wvrTevOdpyzN+MiorCtm3bVH5vPXv2FNMtx40bhzp16mDt2rXifeB9pkBb1XWVUZdurGxEJ06cmKehffr0KZydnVGrVi34+fnBy8tLXJc1LCwM5cqVk0SjWrduDXd3d7VrZRbG0H7//fdqMz2U0zzd3d3Rv39/HD16VCx0N2rUKNSuXRuVKlUSsyjatm2L1NRUjedFzmhjUbTyc108fPhQvC7yUwBKE+np6WoLhk2ePBmdO3dWKUKoDuVBHWgwonLz9OlTLFu2DJaWlvjmm2+wefNm2NjYYNWqVdi9ezfmzp2L8uXLw8vLC66urvkqNskwmmAT+oly5swZ2Nvbo0GDBqhYsaLKg7IgI38BAQGwtbXF8OHDJWuCvXr1CnPmzMnXyH5+IqpLlizB1KlTJdtWrlwpFqtRXvIkLi4ODg4OGDt2rIrWixcv1K6dJadWUSKq+V3CRrljnZSUhOHDh6tNp80P6tKNlbUUi9vnNff26dOnmDVrFvT19fH7779j3bp16Ny5M2rVqoWhQ4dKClMlJydj8+bNaou9FNbQ5qcwQ3x8vBg5VvfwDA8PV0mfK8i5HDlyJCwsLPJce1UTO3fuhCAIKtUSFefm119/RcuWLfHrr7/i6dOnkg6kuk6VgoyMDNGIjh07FuHh4Zg9ezYePnyoYpSXLFkCQRDEtSFza+dGV7W0oVcQ1HV2lZc2iouLEyOiinlc8+fPh7m5eZ7TH5R5/PgxRo0aBUEQMGfOHDE98+bNm5gxYwasra1lSevFu4JZyum8OTk5RZ6/+eTJE1hZWUEQBDg6OmLdunXibzI0NBRdunQRzenIkSNRv359BAcHqzVhyshdXbeghvbkyZOYOHFinvdLxXF+9OgR6tati8GDB2PXrl04e/YsmjVrhp49e8LCwgKenp6S54umqLachha51oJ1d3dHq1atJMX0oqKiEBISgunTp6N3794FmtIiR7SxMFoFuS6ioqLg5eWFBg0aaIzy5vUbV0RelV9LSkqCv78/7OzsVH6XuWswKO9j7nm/U6ZMQY0aNRAcHKz22VRYlL/7xYsXWLJkiVgYKffA86tXr/Dzzz9j0KBBGtP8GSY/sAn9hMid8jhp0iSULl06z1SavFBep3DGjBmws7ND9erVsWLFCnzxxRfo168fSpcuna9lDfIbUf3yyy8l+3Hz5k106dIFU6dOhampqWQexY4dO96bgqqMXFofIqKq3JYzZ84gOzsbycnJGDVqFExNTTWuL1hQc2xubo727dvD3Nw8X22Li4sTo41Xr17F27dvceTIETRq1AhmZmbicgV4zzGUy9AqeN+cXk1zXAt6LhMSEtC/f384ODjkme6mjtTUVAwaNAgmJibYsWOHZKQ7Li4ONWvWhLGxMcqUKYPJkyerLQijXL4/KChIEh07ePAgiAhly5aFIAioUaMGZsyYgZ9++kmioShUpIg2K5O7w9WgQQOd09KGXkHIq7N7//59VK9eHeHh4YiNjcW8efNga2uLJk2aqK0ompcBwrvO8/Tp02FoaIjSpUujdOnSqFevHlxdXdVmLOQmv2m9vXr1kqR5yjF/8+nTp2jVqhUaNWqE7t27o0ePHmjatCkGDBiAEydOoFatWpJU+4EDB6Jp06Z5drzlrq5bGENramoKCwuL994vlY1e3bp14evrKw4Gnz9/HjNmzBCLSeWVaim3oVWQO9Lbpk0blYq8ivnrysgZbZRLqzDXxb1799CsWTNJ4SwF+bkulAvGffXVV+jWrRuqV6+u8rvMj1ZISIjkmT969Gi4u7vLYkJTU1PF71P+zT5//hwrVqyAlZWVZDkfXvuTkRM2oSWQvIxGdHQ05s+fj+zsbBw4cAB169YVH5aaOg156UVFRYlVE3ft2oW+ffuiatWq8PT0xJQpUwq0VlRBIqrKI4cdOnTAyJEjcerUKZiYmEhMQX6QUwsyR1TxLkKycOFClfbiXVp1lSpVxOOiMI+CIKiYssIYqhEjRsDU1LRA6yPGx8dj2LBhKFWqlJjSm5CQIEY18tvBL4yhLUwEWt3yDAoKcy6TkpI0zvdRh3LnIjIyEn369IGenh5at26NqVOnYvr06ahTpw569uyJ2NhYPH36FFeuXHnvuZw2bZpKJOrw4cOYMWMG1qxZg5MnTyIoKAg2NjYYNGgQNm3aJL4/KCgIpUqVynMNO7yr7KiLWtrQyw/56ewOHTpU/P7Y2FjMnDlTbVXk/JrZjIwMhIWFYf369fjyyy9x8uRJyf1TEwVJ6+3UqRMSExNln7/54MEDdOrUCf369cPatWtx584d9OzZE4MHD4aBgQEcHR0lv6X3/a7krK6rzeViFOQ2ei1bthRrBBSEohjagkZ68zKNckYb5dQq7HWhzvzn97pQ6CUkJOC7777DggULVIpJFVRL+TrVVF+jINy5cwdNmzbF559/jqioKJX9ffbsGZYuXQpLS0vJlJeiFAhjGGXYhJYw8mM0lFNamzVrprLYeEH1vvjiC8lnFBGc/N6oChJRVZ6Qr+D69euoX78+Ll++jB9//BGGhoaYOXPme79XTi1l5IzOXrp0STRBykYU71IK1S3vEhcXp7ZTLbc5zo2maOP71rPLi4IYWm1ELeU8l+pQ/vy5c+fENV43b96Mli1bomrVqhg0aJDKnL3CnEsFZ8+ehaWlpdhJffr0KRYsWIBSpUrB29sb33zzDe7evYslS5bA3t5eNBTFSUsbevmhoJ1dvEtLzV2JNT+d0yFDhiAnJ6fIacT5TeuVY/7mixcvcP78efzxxx/iPkVFRaFz585o2bKlWCk4IiICixYtwp49e4B8Pkvkrq4rp6EtiNHLPbc0vxTG0BbG6DVs2FCt0ZMz2iinVlGuC3W/rcL8xtVFjIuiJQc5OTlYtWoVnJ2dMXbsWFSsWBHTpk1TKcj29OlTLF26FLa2tu+t7cEwBYVNaAkjv51TxY1s7969qFu3LuLi4oqkp4ymogBFjajevn0bgiDgs88+Q3BwsGgcXr16ha5du2L9+vXiPhkaGkrWysyNnFoK5I6o4l2qTJ8+fdCpUycYGRlJTNCYMWPyjOIh1wNLLkMld7RRHYUxtHJGLbVxLt8X0a5cubJk7nRGRoZKVUfFOSrIuVTHjBkzMGjQILFwRv/+/VGrVi0MGTIEzZs3h6GhIfbv35+v4he6qqUNvbwoaGc3r99YYTqn+WlbYdN65Zi/eevWLTRt2hQ9e/bEggULJO27d+8eunTpgmbNmuGHH37I934p75Oc1XXlNLRyGj3IaGjlTlGVM9ooh5auXxdyD5oUhn/++QcODg549OgR/v77b3GpuaFDh+Kbb74Rz/vr168xe/ZsVKxYEfHx8bLOn2c+bdiEljAK2jmNjY3NM3WrqJ1dZZ2iRlQ3btwIQRDg5uaGTp06oUqVKli/fj3u3r2LU6dOwdHRUZzn8uOPP0IQBI0jd3JqaSuiqjhGEyZMQK9evXD8+HGVc5Af5DRUckcb5TS0cphsbZ3LgkS0NbVNOepV1HO5f/9+NG7cGNnZ2Rg5ciTKli0rFhe5c+cOvvrqq3wVG9FlLW3oqUPuzq7cnVM50nqLOn8zLCwMdnZ2mD9/Ph4+fCi+78yZM6KhURjRli1bqp2nqw65q+vKfS4/xlzE/BpaOU2jnNFGObR0+brQhjkuClOmTMHw4cPFAkjx8fEwMzODtbU1nJ2dsWvXLrGQkqZgBcMUFjahJYTCdE7zc6P8mPMk1UVUly5dCn19fezfvx9r167FyJEjYWNjgwkTJsDBwQE7d+4U3/vrr7/mWaxGDi1tRFRz8+LFC1SrVg379u3D/v37YWhoKFkPTRPaMFRyRhvlMrRyXavaPJdFjWhr41w2b94cenp6KF++fL4rshY3LW3oKSNnZ1cbnVM503oLO38zNjYWdevWxcSJEyV6iqInn332mXj87t27h+7du8PDw+O967TKXV1XG8vFfIy5iB8yRVUXzZkuXxfaWpKoKBw4cABeXl7igNGYMWNQoUIFXL16FePGjYOrqyucnJwKXGiPYfIDm9BijtydU12YJ6mO3Ov8mZqa4rfffkNGRgbOnz+Pfv36oVy5cjhw4MB72yKnlpwRVQAIDAzEhAkTcPjwYUk7/f39RdOzZ88eGBoawt/fX6OOtgyVnHMki2po5b5W5T6XyhQloi33uVQcryNHjqBmzZridV6Yjo6uamlDLzdydna11TktSlqvXPM3Dx06hHr16iE8PFzctmrVKtja2mL8+PFo0aIF/Pz8xH2PjIzEZ599JomYqkPO6rraWC7mY89F1HaKqq6aM129LrS1JJEcNG/eHBMnTsTIkSPh4OAgqdIdEhKismwZw8gFm9BijNydU12bJ5nXOn/Tp0+HkZGR2PF58+ZNntXi5NTKjVzR2X/++Uc0Zb6+vvDw8MDRo0cRGxuL0NBQmJubi2Xff/jhBxgbG2PMmDFqteQ2VNqYI1kUQ6stky1npD03hY1oa8scP3v2DE5OTpg7d26+96G4aWlDT4FcnV1tdU6LYoLknL8ZEBCAGjVqSLZt2rRJLJqzbds2NGvWDD169BALNOW1JIkyclXXldO46NpcRG2kqOq6OdPF60IbSxIVBeXzevjwYVhaWsLZ2VlcLUGuAkgMkxdsQosxcndOdWmeZH7X+TMwMBDNoybk1FJGzoiqgiVLlkBPTw+rVq3CjBkz0K5dO7i7u2PHjh1o3749ZsyYIa6fun37dgwfPlyjlhyGShuRcTkMrdzXvtznUq6ItgJtmeM9e/bAzMwMV65cydf7i6OWNvQUyNHZlbtzWlQTJPf8zTVr1sDKykrF/CgzatQotG/f/r3mU5vVdeU4l7o6F1Fuo6dr5kzXrwttaBWWnJwccb9fvnyJ+Ph4xMfHw8XFRaUuB8NoGzahxRy5O6e6NE8yv+v8mZiYyLYG4fu0tBVRVX4YBgQEwMzMDEePHkVUVBS+//571KtXD8bGxujSpUueSwDk1iqKoZI72ii3oS3qtaqtcylnRFsbAx3KxMTEoGXLlu9duL44a8mpp63Orlyd06KaIDnnbyp+UwcOHICpqSkWL16MpKQkyWuK/44fPx7jxo2TLNeVG7mr68p9LnV5LqI2onC6Ys50+brQpjnOD9HR0fj222/xzTffiJkHCu0HDx6gRo0a4nrbu3btQsWKFXH9+nVZvpth8gOb0GKK3J1TXZwnqWtrEGojonru3Dm1y0NMnz4dxsbGYpQhPj4e586d07hmpzYMlZzRRjkNrRzXqrai4wqKEtHWZuq4OhTLl8iBrmrJoSdnZ1cbnVM5TFBR52/Gx8cjPDwcd+7ckbStX79+MDU1xYYNGyT3sNTUVPj7+6Ns2bIqn1FG7uisNpaL0dW5iAqKahp10Zzp8nWhrSWJ8ktoaCgqV66Mhg0bimuv79+/H3hX+M/e3h4jR44UnzGRkZGoVKkSVq5cyam4zAeDTWgxQu7OaXGYJ6lraxDKGZ1dv349BEFAtWrV8O233+L8+fOS1xUm6LvvvpNsz32utGmo5DqPRTW02rhW5TyXCooa0U5PT9eqOWYKh5ydXW11TuUwQUWZvxkWFgYPDw/UqlULgiBg3rx54hIvaWlp6NKlC4yMjNCrVy/89ttvWLFiBYYOHQo7Oztcu3ZN437JXV1XW8vFQMfmIsppGnXRnOnydaHNayw/hIaGwtTUFAEBAXjz5o34jO3cuTNev36NDRs2YNy4cSrnet68eQWqc8AwRYVNaDFBbqNRXOZJ6toahHJGZw8ePIgxY8Zg2bJlGDlyJKpWrYrx48dLFhcPDAyEkZER9u7dm2e75DZU2kgDLayh1da1Kue5lCuiDS2ZY6bwyNnZ1XbntKgmqLDzN0NCQmBmZoZZs2bhzJkzCAoKgr6+voqRmDVrFtzd3WFgYABnZ2cMGTLkvZ1eOavrym1cdHUuopymUVfNma5eF9pakii/REdHw97eXkzZVtCgQQPUrFkTr169EtcEVZBXGjzDaBM2ocUIuTunuj5PUoGurUEoV3T25s2bqFGjBv78808AwMWLFzFw4EA0atQInTt3xt9//43nz59jzZo1EAQBly5d0qglh6H6EPNdC2totWXM5DiXckW0FchpjpmiI1dnVxudU7lMUFHmb96+fRuGhoaYN2+eqHf37l3Y2Njgs88+U2lzcnIyHj58iMzMTKSlpb33+MtZXVdO46KrcxHlNHq6bM509brQ1pJE+eXBgwdo0KABunXrhosXLwLvBoAFQRC3Dx8+HBs2bEBMTIw4LYRhPgZsQosRcndOdXWepAJdXYNQzujsypUr0aRJE/GBFBISAhMTE1StWhV169ZFo0aNsG/fPhw9evS9WkUxVHKfR7kNrbaMmRznUs6ItgI509CZoiFXZ1fuzmlRTZBc8zfXrVsHQRDw66+/itsWLVoEQRDQpk0bLFu2DL///jvCwsJU2pCf+6+c1XXlOpe6OhdRbqOny+ZMF68LubUKS0REBHx9fdGtWzeMGjUKpUuXxv79+/Ho0SMcOHAAixcvRtmyZVGhQgV06dJFtrWTGaagsAktZsjdOdW1eZLq0MU1COWKzl6/fh0tW7bEgwcPEBsbi9KlS2PUqFEAgOPHj2PcuHEYOHCg+P68CgYU1VDJdR61NTChLWNW1HMpZ0RbgZwDHUzRkKuzK2fntKgmSO75m4GBgTA0NMTx48exfPlyWFtbY9OmTfj666/h7++P6tWrw8XFBS1atMh32qHc1XUh07nU5bmIchs9XTRnunpdaEOrKNy9exft2rWDiYkJVq5cqfJ6fHw89u/fj8jISK21gWHeB5vQYobcnVNdmyepCV1Zg1DOiKqCAQMGoHbt2ihdujSGDRuG169fF1qrKIZKzvOojYEJua99Oc+lnBFtBXKmoTMFR+7Orlyd06KaIDnnb+ZOtRcEAQYGBjh9+rTkfZGRkTh+/Djat2+PiIgIjfumreq6cp5LXZ2LCC1E4XTFnBWH60Ib5rio3Lt3D+3bt0fHjh3FawDvBooZRhdgE1oMkbtzqkvzJDWha2sQyhFRVZid+/fvo3LlyujTp4/GOVLvM0ZyGSq5zqO2Bia0YczkOJdyRrS1MdDB5A9tdHbl7pwWxQTJMX8zr1T7JUuWQBAEcSkIFOC6lTs6qy3joqtzESGjadQlc6bL14W2rjE5UaTmdujQQZwjyjC6ApvQYoTcnVNdnSepCV1bg1Cu6GxycjJ8fX0xZMgQcVthz2lRDZWc51HOgQltGzM5zqWcEW3InIbOvB85O7va7JwWxQQVdf5mflPtDQ0N1aaNavq9yl1dV1vLxUBH5yLKYRp10Zzp8nWhzWtMbiIiItClSxc0atQIly9f/qDfzTB5wSa0GCJ351TX5kkWF+SMzl64cAFGRkY4dOhQkbWKaqjkOo/aGJjQljEryrmUM6KdGznT0BnNyNnZ1XbntKgmqKjzN/Obal+qVKl8pdrLXV1XW8vF6NpcRDlNoy6aM12+LrS5JJG2CA8PR58+fcR5xgyjC7AJLabI3TnVtXmSxQW5orOpqamoX78+Vq9eXWStwhoqbZxHbQxMaMuYFfVcyhnRViDnQAejHjk7u9rsnBbVBMk1f1PuVHs5q+vKbVx0dS6inKZRV82Zrl4X2l6SSJvweqCMrsEmtJgid+dUV+ZJfsrIOUJZFEMl53xXbQxM6LIxkzOirUDONHRGFbk6u9ronBbVBGlr/qbcNQDkqq4rp3HR1bmIcho9XTdnunhdaHtJIob5lGATWoyRu3OqS/MkP2V04UEl13nU1sCErhozOSPazIdDjs6u3J3Topogbc3fhIyp9nJX14VM51JX5yLKbfR01Zzp6nWhDS2G+ZRhE8rIii5HqZj8I+d5/NQGJnjOTfFB7s6uXJ1TuUyQ3PM3lSlsqr22orNynUtdnouojSicrpgzXb8u5NZiGIZNKKMFdDVKxRQMuc7jpzowoQsRbUYVbXR25eycymmCtLFUUlFS7eWOzmrjXOrqXEQFcplGXTJnunxdaMscMwzDJpRhmA8AD0wwuoCcnV1tdU7ljnZpaw3nwqbayxWd1Wa6sS7ORZTDNOqyOdPF60Kb1xjDMGxCGYZhmE8IOTq72u6cypkiqc01nAuTai9ndFbudGNdm4sop9HTdXOmq9eFNlPaGeZTh00owzAM88kgV2dXG51Tbc0509YazoVNtZcrOivHudTVuYjaMHq6bs506brQhhbDMFLYhDIMwzCfFHJ0duXqnGpzztmHWMO5MKn2ckZni3IudXkuIrRg9HTdnOnKdaFNLYZh/j9sQhmGYZhPCrk6u0XtnH6oOWe6uIazXNHZop5LXZyLqEAbRk/XzZmuXBfa0mIY5v/DJpRhGIb55JCjsytH5/RDzTnTlaWStBGdLcq51NW5iArkNnq6as507brQphbDMP8Hm1CGYRjmk0Huzm5RO6cfas6Zri2VJEd0Vq5zqYtzERVoIwqny+ZMl64LubUYhpGiRwzDMAzziSAIAhEReXp6Uk5ODv3333+S7fkFABER+fv7k5OTE23atInc3d3F7fmlZcuW9Pnnn9PatWspLS2NypUrR+Hh4VS5cmVydnamvXv3kpubG9WsWZPu3r1LlpaWBdJX4OjoSMeOHaMKFSoU6vNyU7ZsWQoKCqKvvvqK/ve//xVKQ65z6e3tTVFRUWRkZESjRo2ic+fO0S+//EK7d++mb775hlasWEG1a9cmW1vbPHW0cS779OlDhoaGZGhoSMeOHaMTJ06Qq6srERE5OzvTlClTxH+/D7muWbm1lNGl60JuLYZhcvGxXTDDMAzDfAzkSFGVI3Lzqc45kzM6W9RzqYtzEbUVhZNzjrA25hvr0nWhLS2GYTgdl2EYhvlEkauzK0fn9FOdc1aY6rrqKOy51PW5iNCS0dN1c/axrwttazEMw+m4DMMwzCeKXCmqrVq1ogYNGlD58uUL/FltpTUWF0xMTGTRKey5lDPdUpdTVHNTlGtWm1oKPvZ1oW0thmGI2IQyDMMwnyxydHaL0jnlOWfyUZRzqWtzEXMjt9H7lMyZXIZWbi2G+dQR8KkMtzIMwzCMDrN3714aO3YsnTlzhho2bPixm/PJ8eTJExo8eDDt2bOnyIZKG+cyLS2NTRDDMCUGg4/dAIZhGIZhtJPWyOQfRURPDqOnyymqDMMwugBHQhmGYRhGR+BoV8mBzyXDMIxm2IQyDMMwDMMwDMMwHwwuTMQwDMMwDMMwDMN8MNiEMgzDMAzDMAzDMB8MNqEMwzAMwzAMwzDMB4NNKMMwDMMwDMMwDPPBYBPKMAzDMAzDMAzDfDDYhDIMwzAMwzAMwzAfDDahDMMwDJMHw4YNox49eoj/btmyJU2ZMuWDt+PcuXMkCAK9fPnyg383wzAMw8gJm1CGYRimWDJs2DASBIEEQSAjIyNycnKiL7/8krKysrT6vb/99hstWrQoX+9l48gwDMMwqhh87AYwDMMwTGHx9fWlnTt3Unp6Oh09epQmTJhAhoaGFBgYKHlfRkYGGRkZyfKdtra2sugwDMMwzKcKR0IZhmGYYouxsTE5ODhQ5cqVady4cdS2bVs6dOiQmEK7ZMkSKl++PDk7OxMR0ePHj6lfv35kbW1Ntra21L17d3r48KGol52dTdOmTSNra2uys7OjWbNmEQDJd+ZOx01PTyd/f3+qWLEiGRsbk5OTE23fvp0ePnxIrVq1IiIiGxsbEgSBhg0bRkREOTk5FBwcTFWrVqVSpUqRu7s7/fLLL5LvOXr0KNWsWZNKlSpFrVq1krSTYRiGYYozbEIZhmGYEkOpUqUoIyODiIhOnz5Nd+/epVOnTtHhw4cpMzOTOnToQBYWFvTXX3/R33//Tebm5uTr6yt+ZvXq1bRr1y7asWMHXbx4kRITE+nAgQN5fueQIUPohx9+oPXr11N4eDht3bqVzM3NqWLFivTrr78SEdHdu3cpNjaW1q1bR0REwcHB9N1339HXX39Nt27doqlTp9LgwYPp/PnzRO/Mcq9evahr164UEhJCo0aNooCAAC0fPYZhGIb5MHA6LsMwDFPsAUCnT5+mEydO0KRJkyguLo7MzMzo22+/FdNw9+7dSzk5OfTtt9+SIAhERLRz506ytramc+fOUfv27Wnt2rUUGBhIvXr1IiKir7/+mk6cOKHxeyMiIujnn3+mU6dOUdu2bYmIqFq1auLritTdMmXKkLW1NdG7yOnSpUvpzz//pMaNG4ufuXjxIm3dupVatGhBW7ZsoerVq9Pq1auJiMjZ2ZnCwsJo+fLlWjqCDMMwDPPhYBPKMAzDFFsOHz5M5ubmlJmZSTk5OTRw4EBasGABTZgwgerUqSOZBxoaGkr37t0jCwsLiUZaWhrdv3+fkpOTKTY2lry9vcXXDAwMyMvLSyUlV0FISAjp6+tTixYt8t3me/fu0du3b6ldu3aS7RkZGeTh4UFEROHh4ZJ2EJFoWBmGYRimuMMmlGEYhim2tGrVirZs2UJGRkZUvnx5MjD4/481MzMzyXtTUlLI09OT9u3bp6JTunTpQn1/qVKlCvyZlJQUIiI6cuQIOTo6Sl4zNjYuVDsYhmEYpjjBJpRhGIYptpiZmZGTk1O+3lu/fn366aefqEyZMmRpaan2PeXKlaMrV65Q8+bNiYgoKyuL/vvvP6pfv77a99epU4dycnLo/PnzYjquMopIbHZ2trjNxcWFjI2NKTo6WmMEtXbt2nTo0CHJtn/++Sdf+8kwDMMwug4XJmIYhmE+CQYNGkT29vbUvXt3+uuvv+jBgwd07tw5+uKLLygmJoaIiCZPnkzLli2jgwcP0p07d2j8+PF5rvFZpUoVGjp0KI0YMYIOHjwoav78889ERFS5cmUSBIEOHz5McXFxlJKSQhYWFjRjxgyaOnUq7d69m+7fv0/Xrl2jDRs20O7du4mIaOzYsRQZGUkzZ86ku3fv0vfff0+7du36QEeKYRiGYbQLm1CGYRjmk8DU1JQuXLhAlSpVol69elHt2rVp5MiRlJaWJkZGp0+fTn5+fjR06FBq3LgxWVhYUM+ePfPU3bJlC/Xp04fGjx9PtWrVotGjR9ObN2+IiMjR0ZEWLlxIAQEBVLZsWZo4cSIRES1atIjmzZtHwcHBVLt2bfL19aUjR45Q1apViYioUqVK9Ouvv9LBgwfJ3d2dvv76a1q6dKnWjxHDMAzDfAgEaKq2wDAMwzAMwzAMwzAyw5FQhmEYhmEYhmEY5oPBJpRhGIZhGIZhGIb5YLAJZRiGYRiGYRiGYT4YbEIZhmEYhmEYhmGYDwabUIZhGIZhGIZhGOaDwSaUYRiGYRiGYRiG+WCwCWUYhmEYhmEYhmE+GGxCGYZhGIZhGIZhmA8Gm1CGYRiGYRiGYRjmg8EmlGEYhmEYhmEYhvlgsAllGIZhGIZhGIZhPhhsQhmGYRiGYRiGYZgPxv8DU4rGnzMSbGAAAAAASUVORK5CYII=",
|
|
"text/plain": [
|
|
"<Figure size 1000x800 with 2 Axes>"
|
|
]
|
|
},
|
|
"metadata": {},
|
|
"output_type": "display_data"
|
|
}
|
|
],
|
|
"source": [
|
|
"y_true_flat_srl = [tag for seq in y_true_srl for tag in seq]\n",
|
|
"y_pred_flat_srl = [tag for seq in y_pred_srl for tag in seq]\n",
|
|
"\n",
|
|
"plot_confusion_matrix(\n",
|
|
" y_true_flat_srl, \n",
|
|
" y_pred_flat_srl, \n",
|
|
" labels=list(tag2idx_srl.keys()), \n",
|
|
" title=\"SRL Confusion Matrix\"\n",
|
|
")\n"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "myenv",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.10.16"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|