{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "fcdce269",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2025-05-08 14:34:09.368546: 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",
      "2025-05-08 14:34:09.369289: 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",
      "2025-05-08 14:34:09.371530: 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",
      "2025-05-08 14:34:09.377960: 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 00:00:1746689649.388328   77963 cuda_dnn.cc:8579] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n",
      "E0000 00:00:1746689649.391591   77963 cuda_blas.cc:1407] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n",
      "W0000 00:00:1746689649.399815   77963 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
      "W0000 00:00:1746689649.399831   77963 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
      "W0000 00:00:1746689649.399832   77963 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
      "W0000 00:00:1746689649.399833   77963 computation_placer.cc:177] computation placer already registered. Please check linkage and avoid linking the same target more than once.\n",
      "2025-05-08 14:34:09.402412: 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": [
      "['alarm', 'sempit', 'sore', '05.45', 'pecaharian', 'alat', 'langsung', 'pantai', 'kebijakan', 'dipengaruhi', 'hidrat', 'perak', '11', 'membatasi', 'wilayah', 'perairan', 'kedatangan', 'diselenggarakan', 'jauh', 'penyerbukan', 'barang-barang', 'tiba', 'sama', 'diaz', 'ombak', 'terluas', 'negara-negara', 'menarik', 'kering', 'mewadahi', 'semakin', '1998', 'sendiri', 'keturunan', 'simbol', 'diminta', 'sekitarnya', 'kemarau', 'bartholomeus', 'februari', 'keberagaman', '?', 'kanan', 'pertambangan', 'pbb', 'harian', '1949', 'jatuhnya', 'curah', 'faktor', 'sangat', 'sistem', 'tropis', 'terdiri', 'anggota', 'perkembangan', 'ada', 'pengalaman', 'kapal', 'beraneka', 'resources', 'perang', 'penduduk', 'alami', 'geografis', 'disebabkan', 'nelayan', 'manusia', 'mengolah', 'luas', 'toko', 'lembaga', 'menjadi', 'waktu', 'suatu', '2004', 'ini', 'setelah', 'pit', '3', 'buka', 'agama', 'mengoptimalkan', 'rata-rata', 'terjadi', 'tentang', 'pemuda', 'permukaan', 'disegani', 'kelembaban', '1950', 'makanan', 'kandungan', 'politik', 'bagaimana', 'rapat', 'perilaku', 'sumpah', 'tentu', 'mineral', '2016', 'meningkatkan', 'budayaanya', '2021', 'konser', 'mempunyai', 'bukan', 'bara', 'terjaga', '2025', 'mengarungi', 'hilangnya', 'tanah', 'gerbang', '1497', 'menjelang', '127,67', 'bahan', 'sepuluh', 'rombongan', 'sesuatu', 'kebutuhan', 'hobi', 'pembangunan', 'terpaksa', 'lima', 'alam', 'ikut', 'geologis', 'puluhan', 'dinihari', 'bagian', 'tercatat', 'menayangkan', 'kondisi', 'unsur', 'kesenangan', 'tanggal', 'siang', 'kurang', 'ruang', 'jam', 'laku', 'memahami', 'diperoleh', 'kebiasaan', 'liar', 'bung', 'diamati', 'dasar', 'meninggal', 'maraknya', 'dimilikinya', 'sebuah', 'bermain', '(', 'berkembang', 'selama', 'bertemu', 'pelajaran', 'intelegensi', 'oktober', 'ketenagakerjaan', 'budaya', 'modal', 'keuangan', 'sdm', 'ujung', 'angin', 'lahir', 'kualitas', 'malaka', 'mobil', 'kekayaan', 'daratan', 'urutan', 'dilatarbelakangi', 'listrik', 'kehidupan', 'ke', 'lepas', 'asing', 'berhasil', 'bandara', 'afrika', 'renewable', 'dijadwalkan', 'pelabuhan', 'berupa', 'kota', '09.00', 'portugis', 'hadir', 'singgah', 'dalam', '10', 'naluri', 'selain', 'kedua', 'kelestariannya', 'km2', '1945', 'eropa', 'belanda', 'inc', 'bersyukur', 'brunei', 'mundur', 'kereta', 'kerja', 'jika', 'bus', 'berolahraga', 'terakhir', 'libur', 'dua', 'hindia', 'bangsa-bangsa', 'pertandingan', '23.15', 'belajar', 'memperhatikan', 'sejarah', 'tujuh', 'pariwisata', 'air', 'pemadaman', 'selesai', 'tayang', 'negara', 'angkatan', 'pemilu', 'petir', 'psbb', 'membentuk', 'gama', 'pelajari', 'matahari', 'samudera', '-', 'varietas', 'secara', 'hutan', '18.00', 'saya', 'kafe', 'pusat', 'tengah', 'mengelola', 'teks', 'stadion', 'januari', 'raga', 'landas', 'cara', 'mulai', 'diperbarui', 'asia-afrika', 'mendarat', 'inilah', 'darussalam', 'patut', '2', 'goa', 'diperingati', 'tidak', 'akan', 'hidup', 'tata', 'badan', 'bandang', 'saat', 'barat', 'hawaii', 'dimiliki', 'dilaksanakan', 'selatan', 'rumah', 'jenis', '2024', 'mata', 'baik', 'mei', 'film', 'berakhir', 'kombinasi', 'tanaman', 'sarapan', 'fisik', 'bugis', 'praktik', 'jiwa', 'biasanya', 'kelas', 'ibu', 'penyinaran', 'juga', 'memenuhi', 'melanjutkan', 'sudah', 'merupakan', 'kebudayaan', 'wawancara', 'asean', 'daerah', 'big', 'nanti', 'abad', 'norma', 'satu', 'prakiraan', 'presiden', 'laporan', 'udara', 'tsunami', 'besar', '1.910.932,37', 'bumi', 'acara', '.', 'kita', 'dilantik', '1511', 'bagi', 'bangun', 'pernah', '14', '6', 'dibuka', '7.30', 'harapan', 'berlangsung', 'jadwal', 'kelima', 'layanan', 'yang', 'masyarakat', 'sawah', 'ditetapkan', 'penjelajahan', 'tersebut', 'kedalaman', 'non', 'dibahas', 'terhadap', '9', 'hujan', 'meliputi', 'yaitu', 'dan', 'suhu', 'musim', 'harinya', '5,8', '00.30', 'dapat', 'pinisinya', 'salah', 'misalnya', 'bawah', 'oleh', 'statistik', 'adat', 'block', 'peristiwa', 'berpakaian', 'hingga', 'reformasi', 'sebagai', 'disahkan', 'perbedaan', 'seseorang', 'sebesar', 'berdasarkan', 'emas', 'perkotaan', 'dunia', 'dengan', 'mengikis', 'merancang', 'tingkah', 'maritim', 'berbelok', 'keadaan', '12', 'kemaritiman', 'aceh', 'awal', 'periode', 'tenggara', 'digelar', 'keagamaan', 'kalikut', 'bangsa', 'sampai', 'unsur-unsur', '13.00', '18', 'da', '6.30', 'batu', 'masih', 'apakah', 'karena', 'contoh', 'memungkinkan', 'daya', 'lebih', 'menggunakan', ')', 'lapangan', 'individu', 'mengakui', 'delapan', 'atau', 'atas', 'membantu', 'berada', '4', 'armada', '22', 'adalah', 'dirinci', 'sumber', 'dari', 'cenderung', '21.00', ',', '17.00', 'kawasan', 'semangat', 'proses', 'menelusuri', 'berita', 'sholat', 'tinggal', 'serangkaian', 'jatuh', 'tambang', 'laut', 'moor', 'berinteraksi', 'rancangan', 'tanjung', '8', 'telah', '06.00', 'memulai', 'freeport', 'arang', 'manfaatnya', 'berbunyi', 'obama', 'proklamasi', 'tahunan', 'samudra', 'makan', 'setiap', 'penyebab', 'lawu', 'karakter', 'sebelum', 'april', 'kami', 'konstantinopel', 'pribadi', 'tiga', 'iklim', 'global', 'dihasilkan', 'bahwa', 'letak', 'mencakup', 'desember', 'hal', 'beberapa', 'november', 'mencapai', 'mencatat', '08.00', 'upacara', 'tuan', 'peringkat', 'mengurangi', 'mengumumkan', 'karakteristik', 'begitu', '270', 'dimanfaatkan', 'peserta', 'singkat', 'penjelasan', '2023', '21', '1955', 'sejak', 'grasberg', 'menguasai', 'orang', 'pemandangan', 'kemudian', 'ii', 'malam', 'kesatuan', 'lalu', 'nilai-nilai', 'perdagangan', 'pelaut', 'jumlah', 'berlayar', 'dianggap', 'tahun', 'cadangan', 'kitab', 'melalui', 'soeharto', 'menguntungkan', 'disewanya', '26', 'serangan', 'pencaharian', 'singapura', '2017', 'pagi', 'seperti', 'lingkungan', 'itu', 'nafsu', 'tepat', '22.00', 'benua', 'membincangkan', 'terutama', 'berhubungan', 'penerbangan', 'timur', 'dibedakan', 'sekitar', 'open', 'lisabon', 'kalah', 'tertentu', '1970', '1488', 'syarat', '28', 'tanahnya', 'juta', 'hanya', 'potensi', 'sehari-hari', 'minyak', 'menit', 'bajak', 'pola', 'pelayaran', 'sehingga', 'segala', 'mengajar', 'berbagi', 'bertahan', 'berbagai', 'berikut', 'sembilan', 'suku', 'dmlz', 'yuk', 'pulang', 'untuk', 'istiadat', '20.00', 'berharga', 'terdapat', 'pengaruh', 'terbit', 'karno', 'menghasilkan', 'keragaman', 'cave', 'ribuan', 'menemukan', 'bulan', 'apabila', 'memengaruhi', 'mencerminkan', 'pintu', 'dirayakan', 'pengetahuan', 'juli', 'lain', 'ragam', 'undang-undang', 'jakarta', '19.30', 'tempat', 'termasuk', 'kemajuan', 'asia', 'mengambil', '1453', 'masehi', 'pukul', 'dilakukan', 'sosial', 'kemerdekaan', 'pahlawan', 'vasco', 'penting', 'kuat', 'ia', '2020', 'simak', 'beragam', 'peranan', 'cuaca', 'maret', '1498', 'menempati', 'sih', 'memiliki', 'konferensi', 'hubungannya', '17', 'gambir', 'yakni', 'doz', 'sedangkan', 'mcmorran', 'berlimpah', 'juni', 'barack', '1961', 'apa', 'merdeka', 'habibie', 'hukum', 'aktivitas', 'keyakinan', 'terbenam', 'pada', 'malaysia', 'kucing', 'mengubah', 'empat', 'manusianya', 'menguap', 'tembaga', 'selalu', 'perlu', 'berangkat', 'fotosintesis', 'kepribadian-kepribadian', 'dilayari', 'agustus', 'kelompok', '5', '7', 'senjata', 'antara', 'orang-orang', 'siaran', 'dibandingkan', 'pertemuan', 'september', 'india', 'tinggalmu', 'di', 'sedikit', 'thailand', '1', 'pemerintah', 'pesawat', 'pembelajaran', 'membedakan', 'gossan', 'televisi', 'stasiun', 'kegiatan', 'banyak', 'kadar', 'sering', 'rute', 'dimulai', 'bandung', 'diadakan', 'pelanggan', 'kalian', 'diperkirakan', 'pokok', 'seperempat', 'dia', 'hindu-buddha', 'bermata', 'lautan', 'banjir', 'indonesia', 'kaya', 'hari', 'resource', 'lagi', 'papua', 'petunjuk', 'relatif', 'silahkan']\n",
      "{'alarm': 2, 'sempit': 3, 'sore': 4, '05.45': 5, 'pecaharian': 6, 'alat': 7, 'langsung': 8, 'pantai': 9, 'kebijakan': 10, 'dipengaruhi': 11, 'hidrat': 12, 'perak': 13, '11': 14, 'membatasi': 15, 'wilayah': 16, 'perairan': 17, 'kedatangan': 18, 'diselenggarakan': 19, 'jauh': 20, 'penyerbukan': 21, 'barang-barang': 22, 'tiba': 23, 'sama': 24, 'diaz': 25, 'ombak': 26, 'terluas': 27, 'negara-negara': 28, 'menarik': 29, 'kering': 30, 'mewadahi': 31, 'semakin': 32, '1998': 33, 'sendiri': 34, 'keturunan': 35, 'simbol': 36, 'diminta': 37, 'sekitarnya': 38, 'kemarau': 39, 'bartholomeus': 40, 'februari': 41, 'keberagaman': 42, '?': 43, 'kanan': 44, 'pertambangan': 45, 'pbb': 46, 'harian': 47, '1949': 48, 'jatuhnya': 49, 'curah': 50, 'faktor': 51, 'sangat': 52, 'sistem': 53, 'tropis': 54, 'terdiri': 55, 'anggota': 56, 'perkembangan': 57, 'ada': 58, 'pengalaman': 59, 'kapal': 60, 'beraneka': 61, 'resources': 62, 'perang': 63, 'penduduk': 64, 'alami': 65, 'geografis': 66, 'disebabkan': 67, 'nelayan': 68, 'manusia': 69, 'mengolah': 70, 'luas': 71, 'toko': 72, 'lembaga': 73, 'menjadi': 74, 'waktu': 75, 'suatu': 76, '2004': 77, 'ini': 78, 'setelah': 79, 'pit': 80, '3': 81, 'buka': 82, 'agama': 83, 'mengoptimalkan': 84, 'rata-rata': 85, 'terjadi': 86, 'tentang': 87, 'pemuda': 88, 'permukaan': 89, 'disegani': 90, 'kelembaban': 91, '1950': 92, 'makanan': 93, 'kandungan': 94, 'politik': 95, 'bagaimana': 96, 'rapat': 97, 'perilaku': 98, 'sumpah': 99, 'tentu': 100, 'mineral': 101, '2016': 102, 'meningkatkan': 103, 'budayaanya': 104, '2021': 105, 'konser': 106, 'mempunyai': 107, 'bukan': 108, 'bara': 109, 'terjaga': 110, '2025': 111, 'mengarungi': 112, 'hilangnya': 113, 'tanah': 114, 'gerbang': 115, '1497': 116, 'menjelang': 117, '127,67': 118, 'bahan': 119, 'sepuluh': 120, 'rombongan': 121, 'sesuatu': 122, 'kebutuhan': 123, 'hobi': 124, 'pembangunan': 125, 'terpaksa': 126, 'lima': 127, 'alam': 128, 'ikut': 129, 'geologis': 130, 'puluhan': 131, 'dinihari': 132, 'bagian': 133, 'tercatat': 134, 'menayangkan': 135, 'kondisi': 136, 'unsur': 137, 'kesenangan': 138, 'tanggal': 139, 'siang': 140, 'kurang': 141, 'ruang': 142, 'jam': 143, 'laku': 144, 'memahami': 145, 'diperoleh': 146, 'kebiasaan': 147, 'liar': 148, 'bung': 149, 'diamati': 150, 'dasar': 151, 'meninggal': 152, 'maraknya': 153, 'dimilikinya': 154, 'sebuah': 155, 'bermain': 156, '(': 157, 'berkembang': 158, 'selama': 159, 'bertemu': 160, 'pelajaran': 161, 'intelegensi': 162, 'oktober': 163, 'ketenagakerjaan': 164, 'budaya': 165, 'modal': 166, 'keuangan': 167, 'sdm': 168, 'ujung': 169, 'angin': 170, 'lahir': 171, 'kualitas': 172, 'malaka': 173, 'mobil': 174, 'kekayaan': 175, 'daratan': 176, 'urutan': 177, 'dilatarbelakangi': 178, 'listrik': 179, 'kehidupan': 180, 'ke': 181, 'lepas': 182, 'asing': 183, 'berhasil': 184, 'bandara': 185, 'afrika': 186, 'renewable': 187, 'dijadwalkan': 188, 'pelabuhan': 189, 'berupa': 190, 'kota': 191, '09.00': 192, 'portugis': 193, 'hadir': 194, 'singgah': 195, 'dalam': 196, '10': 197, 'naluri': 198, 'selain': 199, 'kedua': 200, 'kelestariannya': 201, 'km2': 202, '1945': 203, 'eropa': 204, 'belanda': 205, 'inc': 206, 'bersyukur': 207, 'brunei': 208, 'mundur': 209, 'kereta': 210, 'kerja': 211, 'jika': 212, 'bus': 213, 'berolahraga': 214, 'terakhir': 215, 'libur': 216, 'dua': 217, 'hindia': 218, 'bangsa-bangsa': 219, 'pertandingan': 220, '23.15': 221, 'belajar': 222, 'memperhatikan': 223, 'sejarah': 224, 'tujuh': 225, 'pariwisata': 226, 'air': 227, 'pemadaman': 228, 'selesai': 229, 'tayang': 230, 'negara': 231, 'angkatan': 232, 'pemilu': 233, 'petir': 234, 'psbb': 235, 'membentuk': 236, 'gama': 237, 'pelajari': 238, 'matahari': 239, 'samudera': 240, '-': 241, 'varietas': 242, 'secara': 243, 'hutan': 244, '18.00': 245, 'saya': 246, 'kafe': 247, 'pusat': 248, 'tengah': 249, 'mengelola': 250, 'teks': 251, 'stadion': 252, 'januari': 253, 'raga': 254, 'landas': 255, 'cara': 256, 'mulai': 257, 'diperbarui': 258, 'asia-afrika': 259, 'mendarat': 260, 'inilah': 261, 'darussalam': 262, 'patut': 263, '2': 264, 'goa': 265, 'diperingati': 266, 'tidak': 267, 'akan': 268, 'hidup': 269, 'tata': 270, 'badan': 271, 'bandang': 272, 'saat': 273, 'barat': 274, 'hawaii': 275, 'dimiliki': 276, 'dilaksanakan': 277, 'selatan': 278, 'rumah': 279, 'jenis': 280, '2024': 281, 'mata': 282, 'baik': 283, 'mei': 284, 'film': 285, 'berakhir': 286, 'kombinasi': 287, 'tanaman': 288, 'sarapan': 289, 'fisik': 290, 'bugis': 291, 'praktik': 292, 'jiwa': 293, 'biasanya': 294, 'kelas': 295, 'ibu': 296, 'penyinaran': 297, 'juga': 298, 'memenuhi': 299, 'melanjutkan': 300, 'sudah': 301, 'merupakan': 302, 'kebudayaan': 303, 'wawancara': 304, 'asean': 305, 'daerah': 306, 'big': 307, 'nanti': 308, 'abad': 309, 'norma': 310, 'satu': 311, 'prakiraan': 312, 'presiden': 313, 'laporan': 314, 'udara': 315, 'tsunami': 316, 'besar': 317, '1.910.932,37': 318, 'bumi': 319, 'acara': 320, '.': 321, 'kita': 322, 'dilantik': 323, '1511': 324, 'bagi': 325, 'bangun': 326, 'pernah': 327, '14': 328, '6': 329, 'dibuka': 330, '7.30': 331, 'harapan': 332, 'berlangsung': 333, 'jadwal': 334, 'kelima': 335, 'layanan': 336, 'yang': 337, 'masyarakat': 338, 'sawah': 339, 'ditetapkan': 340, 'penjelajahan': 341, 'tersebut': 342, 'kedalaman': 343, 'non': 344, 'dibahas': 345, 'terhadap': 346, '9': 347, 'hujan': 348, 'meliputi': 349, 'yaitu': 350, 'dan': 351, 'suhu': 352, 'musim': 353, 'harinya': 354, '5,8': 355, '00.30': 356, 'dapat': 357, 'pinisinya': 358, 'salah': 359, 'misalnya': 360, 'bawah': 361, 'oleh': 362, 'statistik': 363, 'adat': 364, 'block': 365, 'peristiwa': 366, 'berpakaian': 367, 'hingga': 368, 'reformasi': 369, 'sebagai': 370, 'disahkan': 371, 'perbedaan': 372, 'seseorang': 373, 'sebesar': 374, 'berdasarkan': 375, 'emas': 376, 'perkotaan': 377, 'dunia': 378, 'dengan': 379, 'mengikis': 380, 'merancang': 381, 'tingkah': 382, 'maritim': 383, 'berbelok': 384, 'keadaan': 385, '12': 386, 'kemaritiman': 387, 'aceh': 388, 'awal': 389, 'periode': 390, 'tenggara': 391, 'digelar': 392, 'keagamaan': 393, 'kalikut': 394, 'bangsa': 395, 'sampai': 396, 'unsur-unsur': 397, '13.00': 398, '18': 399, 'da': 400, '6.30': 401, 'batu': 402, 'masih': 403, 'apakah': 404, 'karena': 405, 'contoh': 406, 'memungkinkan': 407, 'daya': 408, 'lebih': 409, 'menggunakan': 410, ')': 411, 'lapangan': 412, 'individu': 413, 'mengakui': 414, 'delapan': 415, 'atau': 416, 'atas': 417, 'membantu': 418, 'berada': 419, '4': 420, 'armada': 421, '22': 422, 'adalah': 423, 'dirinci': 424, 'sumber': 425, 'dari': 426, 'cenderung': 427, '21.00': 428, ',': 429, '17.00': 430, 'kawasan': 431, 'semangat': 432, 'proses': 433, 'menelusuri': 434, 'berita': 435, 'sholat': 436, 'tinggal': 437, 'serangkaian': 438, 'jatuh': 439, 'tambang': 440, 'laut': 441, 'moor': 442, 'berinteraksi': 443, 'rancangan': 444, 'tanjung': 445, '8': 446, 'telah': 447, '06.00': 448, 'memulai': 449, 'freeport': 450, 'arang': 451, 'manfaatnya': 452, 'berbunyi': 453, 'obama': 454, 'proklamasi': 455, 'tahunan': 456, 'samudra': 457, 'makan': 458, 'setiap': 459, 'penyebab': 460, 'lawu': 461, 'karakter': 462, 'sebelum': 463, 'april': 464, 'kami': 465, 'konstantinopel': 466, 'pribadi': 467, 'tiga': 468, 'iklim': 469, 'global': 470, 'dihasilkan': 471, 'bahwa': 472, 'letak': 473, 'mencakup': 474, 'desember': 475, 'hal': 476, 'beberapa': 477, 'november': 478, 'mencapai': 479, 'mencatat': 480, '08.00': 481, 'upacara': 482, 'tuan': 483, 'peringkat': 484, 'mengurangi': 485, 'mengumumkan': 486, 'karakteristik': 487, 'begitu': 488, '270': 489, 'dimanfaatkan': 490, 'peserta': 491, 'singkat': 492, 'penjelasan': 493, '2023': 494, '21': 495, '1955': 496, 'sejak': 497, 'grasberg': 498, 'menguasai': 499, 'orang': 500, 'pemandangan': 501, 'kemudian': 502, 'ii': 503, 'malam': 504, 'kesatuan': 505, 'lalu': 506, 'nilai-nilai': 507, 'perdagangan': 508, 'pelaut': 509, 'jumlah': 510, 'berlayar': 511, 'dianggap': 512, 'tahun': 513, 'cadangan': 514, 'kitab': 515, 'melalui': 516, 'soeharto': 517, 'menguntungkan': 518, 'disewanya': 519, '26': 520, 'serangan': 521, 'pencaharian': 522, 'singapura': 523, '2017': 524, 'pagi': 525, 'seperti': 526, 'lingkungan': 527, 'itu': 528, 'nafsu': 529, 'tepat': 530, '22.00': 531, 'benua': 532, 'membincangkan': 533, 'terutama': 534, 'berhubungan': 535, 'penerbangan': 536, 'timur': 537, 'dibedakan': 538, 'sekitar': 539, 'open': 540, 'lisabon': 541, 'kalah': 542, 'tertentu': 543, '1970': 544, '1488': 545, 'syarat': 546, '28': 547, 'tanahnya': 548, 'juta': 549, 'hanya': 550, 'potensi': 551, 'sehari-hari': 552, 'minyak': 553, 'menit': 554, 'bajak': 555, 'pola': 556, 'pelayaran': 557, 'sehingga': 558, 'segala': 559, 'mengajar': 560, 'berbagi': 561, 'bertahan': 562, 'berbagai': 563, 'berikut': 564, 'sembilan': 565, 'suku': 566, 'dmlz': 567, 'yuk': 568, 'pulang': 569, 'untuk': 570, 'istiadat': 571, '20.00': 572, 'berharga': 573, 'terdapat': 574, 'pengaruh': 575, 'terbit': 576, 'karno': 577, 'menghasilkan': 578, 'keragaman': 579, 'cave': 580, 'ribuan': 581, 'menemukan': 582, 'bulan': 583, 'apabila': 584, 'memengaruhi': 585, 'mencerminkan': 586, 'pintu': 587, 'dirayakan': 588, 'pengetahuan': 589, 'juli': 590, 'lain': 591, 'ragam': 592, 'undang-undang': 593, 'jakarta': 594, '19.30': 595, 'tempat': 596, 'termasuk': 597, 'kemajuan': 598, 'asia': 599, 'mengambil': 600, '1453': 601, 'masehi': 602, 'pukul': 603, 'dilakukan': 604, 'sosial': 605, 'kemerdekaan': 606, 'pahlawan': 607, 'vasco': 608, 'penting': 609, 'kuat': 610, 'ia': 611, '2020': 612, 'simak': 613, 'beragam': 614, 'peranan': 615, 'cuaca': 616, 'maret': 617, '1498': 618, 'menempati': 619, 'sih': 620, 'memiliki': 621, 'konferensi': 622, 'hubungannya': 623, '17': 624, 'gambir': 625, 'yakni': 626, 'doz': 627, 'sedangkan': 628, 'mcmorran': 629, 'berlimpah': 630, 'juni': 631, 'barack': 632, '1961': 633, 'apa': 634, 'merdeka': 635, 'habibie': 636, 'hukum': 637, 'aktivitas': 638, 'keyakinan': 639, 'terbenam': 640, 'pada': 641, 'malaysia': 642, 'kucing': 643, 'mengubah': 644, 'empat': 645, 'manusianya': 646, 'menguap': 647, 'tembaga': 648, 'selalu': 649, 'perlu': 650, 'berangkat': 651, 'fotosintesis': 652, 'kepribadian-kepribadian': 653, 'dilayari': 654, 'agustus': 655, 'kelompok': 656, '5': 657, '7': 658, 'senjata': 659, 'antara': 660, 'orang-orang': 661, 'siaran': 662, 'dibandingkan': 663, 'pertemuan': 664, 'september': 665, 'india': 666, 'tinggalmu': 667, 'di': 668, 'sedikit': 669, 'thailand': 670, '1': 671, 'pemerintah': 672, 'pesawat': 673, 'pembelajaran': 674, 'membedakan': 675, 'gossan': 676, 'televisi': 677, 'stasiun': 678, 'kegiatan': 679, 'banyak': 680, 'kadar': 681, 'sering': 682, 'rute': 683, 'dimulai': 684, 'bandung': 685, 'diadakan': 686, 'pelanggan': 687, 'kalian': 688, 'diperkirakan': 689, 'pokok': 690, 'seperempat': 691, 'dia': 692, 'hindu-buddha': 693, 'bermata': 694, 'lautan': 695, 'banjir': 696, 'indonesia': 697, 'kaya': 698, 'hari': 699, 'resource': 700, 'lagi': 701, 'papua': 702, 'petunjuk': 703, 'relatif': 704, 'silahkan': 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": [
      "[[ 42 551 425 ...   0   0   0]\n",
      " [ 96 433  66 ...   0   0   0]\n",
      " [ 96 575 433 ...   0   0   0]\n",
      " ...\n",
      " [641 496 429 ...   0   0   0]\n",
      " [672 486  10 ...   0   0   0]\n",
      " [593 151 203 ...   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": [
      "2025-05-08 14:34:12.231050: 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 18ms/step - loss: 3.6158 - ner_output_accuracy: 0.9415 - ner_output_loss: 1.4945 - srl_output_accuracy: 0.7447 - srl_output_loss: 2.1213 - val_loss: 0.7665 - val_ner_output_accuracy: 0.9463 - val_ner_output_loss: 0.2785 - val_srl_output_accuracy: 0.8550 - val_srl_output_loss: 0.4881\n",
      "Epoch 2/10\n",
      "\u001b[1m63/63\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 9ms/step - loss: 0.8915 - ner_output_accuracy: 0.9478 - ner_output_loss: 0.2724 - srl_output_accuracy: 0.8253 - srl_output_loss: 0.6190 - val_loss: 0.6997 - val_ner_output_accuracy: 0.9463 - val_ner_output_loss: 0.2667 - val_srl_output_accuracy: 0.8538 - val_srl_output_loss: 0.4330\n",
      "Epoch 3/10\n",
      "\u001b[1m63/63\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 9ms/step - loss: 0.7365 - ner_output_accuracy: 0.9564 - ner_output_loss: 0.2132 - srl_output_accuracy: 0.8416 - srl_output_loss: 0.5233 - val_loss: 0.6682 - val_ner_output_accuracy: 0.9463 - val_ner_output_loss: 0.2577 - val_srl_output_accuracy: 0.8575 - val_srl_output_loss: 0.4105\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: 0.7311 - ner_output_accuracy: 0.9505 - ner_output_loss: 0.2344 - srl_output_accuracy: 0.8466 - srl_output_loss: 0.4967 - val_loss: 0.6193 - val_ner_output_accuracy: 0.9463 - val_ner_output_loss: 0.2365 - val_srl_output_accuracy: 0.8813 - val_srl_output_loss: 0.3828\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: 0.7166 - ner_output_accuracy: 0.9486 - ner_output_loss: 0.2280 - srl_output_accuracy: 0.8665 - srl_output_loss: 0.4886 - val_loss: 0.5963 - val_ner_output_accuracy: 0.9463 - val_ner_output_loss: 0.2299 - val_srl_output_accuracy: 0.8875 - val_srl_output_loss: 0.3664\n",
      "Epoch 6/10\n",
      "\u001b[1m63/63\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 9ms/step - loss: 0.6772 - ner_output_accuracy: 0.9565 - ner_output_loss: 0.1832 - srl_output_accuracy: 0.8551 - srl_output_loss: 0.4940 - val_loss: 0.5593 - val_ner_output_accuracy: 0.9463 - val_ner_output_loss: 0.2167 - val_srl_output_accuracy: 0.8950 - val_srl_output_loss: 0.3426\n",
      "Epoch 7/10\n",
      "\u001b[1m63/63\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 10ms/step - loss: 0.6840 - ner_output_accuracy: 0.9439 - ner_output_loss: 0.2195 - srl_output_accuracy: 0.8772 - srl_output_loss: 0.4646 - val_loss: 0.5333 - val_ner_output_accuracy: 0.9463 - val_ner_output_loss: 0.2071 - val_srl_output_accuracy: 0.8975 - val_srl_output_loss: 0.3262\n",
      "Epoch 8/10\n",
      "\u001b[1m63/63\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 9ms/step - loss: 0.5664 - ner_output_accuracy: 0.9525 - ner_output_loss: 0.1749 - srl_output_accuracy: 0.8891 - srl_output_loss: 0.3915 - val_loss: 0.5044 - val_ner_output_accuracy: 0.9463 - val_ner_output_loss: 0.1980 - val_srl_output_accuracy: 0.9162 - val_srl_output_loss: 0.3064\n",
      "Epoch 9/10\n",
      "\u001b[1m63/63\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 9ms/step - loss: 0.5864 - ner_output_accuracy: 0.9497 - ner_output_loss: 0.1924 - srl_output_accuracy: 0.8918 - srl_output_loss: 0.3941 - val_loss: 0.4887 - val_ner_output_accuracy: 0.9463 - val_ner_output_loss: 0.1913 - val_srl_output_accuracy: 0.9200 - val_srl_output_loss: 0.2974\n",
      "Epoch 10/10\n",
      "\u001b[1m63/63\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 9ms/step - loss: 0.5106 - ner_output_accuracy: 0.9608 - ner_output_loss: 0.1370 - srl_output_accuracy: 0.8946 - srl_output_loss: 0.3736 - val_loss: 0.4705 - val_ner_output_accuracy: 0.9463 - val_ner_output_loss: 0.1820 - val_srl_output_accuracy: 0.9187 - val_srl_output_loss: 0.2885\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "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": 10,
   "id": "aeef32c1",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 421ms/step\n",
      "\n",
      "📊 [NER] Test Set Classification Report:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "        DATE       0.00      0.00      0.00         5\n",
      "       EVENT       0.00      0.00      0.00         1\n",
      "         LOC       1.00      0.43      0.60         7\n",
      "         ORG       0.00      0.00      0.00         2\n",
      "         PER       0.00      0.00      0.00         1\n",
      "        TIME       0.00      0.00      0.00         4\n",
      "\n",
      "   micro avg       0.60      0.15      0.24        20\n",
      "   macro avg       0.17      0.07      0.10        20\n",
      "weighted avg       0.35      0.15      0.21        20\n",
      "\n",
      "\n",
      "📊 [SRL] Test Set Classification Report:\n",
      "              precision    recall  f1-score   support\n",
      "\n",
      "         CAU       0.00      0.00      0.00         1\n",
      "         COM       0.00      0.00      0.00         2\n",
      "         LOC       0.00      0.00      0.00         8\n",
      "         MNR       0.00      0.00      0.00         2\n",
      "         MOD       0.00      0.00      0.00         3\n",
      "         PRP       0.00      0.00      0.00         1\n",
      "         RG0       1.00      0.11      0.20         9\n",
      "         RG1       0.19      0.17      0.18        24\n",
      "         RG2       0.33      0.50      0.40         4\n",
      "         SRC       0.00      0.00      0.00         1\n",
      "         TMP       0.22      0.22      0.22         9\n",
      "           _       1.00      0.11      0.19        19\n",
      "\n",
      "   micro avg       0.28      0.13      0.18        83\n",
      "   macro avg       0.23      0.09      0.10        83\n",
      "weighted avg       0.43      0.13      0.16        83\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/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: 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: 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: 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: 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: ARGM-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: 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: ARGM-CAU 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",
      "/mnt/disc1/code/thesis_quiz_project/lstm-quiz/myenv/lib64/python3.10/site-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: AM-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-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-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-COM 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-MOD 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": 11,
   "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": 12,
   "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": 13,
   "id": "4ba2b85c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "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
}