Skripsi/backup/multinomial_naive_bayes.ipynb

2854 lines
106 KiB
Plaintext
Raw Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 73
},
"id": "EMnX7B87MgpN",
"outputId": "14ed4621-d746-48a9-a97a-f9c96958d1f2"
},
"outputs": [
{
"data": {
"text/html": [
"\n",
" <input type=\"file\" id=\"files-9ea630b8-f055-4575-8ebd-97b8f1c3abbb\" name=\"files[]\" multiple disabled\n",
" style=\"border:none\" />\n",
" <output id=\"result-9ea630b8-f055-4575-8ebd-97b8f1c3abbb\">\n",
" Upload widget is only available when the cell has been executed in the\n",
" current browser session. Please rerun this cell to enable.\n",
" </output>\n",
" <script>// Copyright 2017 Google LLC\n",
"//\n",
"// Licensed under the Apache License, Version 2.0 (the \"License\");\n",
"// you may not use this file except in compliance with the License.\n",
"// You may obtain a copy of the License at\n",
"//\n",
"// http://www.apache.org/licenses/LICENSE-2.0\n",
"//\n",
"// Unless required by applicable law or agreed to in writing, software\n",
"// distributed under the License is distributed on an \"AS IS\" BASIS,\n",
"// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
"// See the License for the specific language governing permissions and\n",
"// limitations under the License.\n",
"\n",
"/**\n",
" * @fileoverview Helpers for google.colab Python module.\n",
" */\n",
"(function(scope) {\n",
"function span(text, styleAttributes = {}) {\n",
" const element = document.createElement('span');\n",
" element.textContent = text;\n",
" for (const key of Object.keys(styleAttributes)) {\n",
" element.style[key] = styleAttributes[key];\n",
" }\n",
" return element;\n",
"}\n",
"\n",
"// Max number of bytes which will be uploaded at a time.\n",
"const MAX_PAYLOAD_SIZE = 100 * 1024;\n",
"\n",
"function _uploadFiles(inputId, outputId) {\n",
" const steps = uploadFilesStep(inputId, outputId);\n",
" const outputElement = document.getElementById(outputId);\n",
" // Cache steps on the outputElement to make it available for the next call\n",
" // to uploadFilesContinue from Python.\n",
" outputElement.steps = steps;\n",
"\n",
" return _uploadFilesContinue(outputId);\n",
"}\n",
"\n",
"// This is roughly an async generator (not supported in the browser yet),\n",
"// where there are multiple asynchronous steps and the Python side is going\n",
"// to poll for completion of each step.\n",
"// This uses a Promise to block the python side on completion of each step,\n",
"// then passes the result of the previous step as the input to the next step.\n",
"function _uploadFilesContinue(outputId) {\n",
" const outputElement = document.getElementById(outputId);\n",
" const steps = outputElement.steps;\n",
"\n",
" const next = steps.next(outputElement.lastPromiseValue);\n",
" return Promise.resolve(next.value.promise).then((value) => {\n",
" // Cache the last promise value to make it available to the next\n",
" // step of the generator.\n",
" outputElement.lastPromiseValue = value;\n",
" return next.value.response;\n",
" });\n",
"}\n",
"\n",
"/**\n",
" * Generator function which is called between each async step of the upload\n",
" * process.\n",
" * @param {string} inputId Element ID of the input file picker element.\n",
" * @param {string} outputId Element ID of the output display.\n",
" * @return {!Iterable<!Object>} Iterable of next steps.\n",
" */\n",
"function* uploadFilesStep(inputId, outputId) {\n",
" const inputElement = document.getElementById(inputId);\n",
" inputElement.disabled = false;\n",
"\n",
" const outputElement = document.getElementById(outputId);\n",
" outputElement.innerHTML = '';\n",
"\n",
" const pickedPromise = new Promise((resolve) => {\n",
" inputElement.addEventListener('change', (e) => {\n",
" resolve(e.target.files);\n",
" });\n",
" });\n",
"\n",
" const cancel = document.createElement('button');\n",
" inputElement.parentElement.appendChild(cancel);\n",
" cancel.textContent = 'Cancel upload';\n",
" const cancelPromise = new Promise((resolve) => {\n",
" cancel.onclick = () => {\n",
" resolve(null);\n",
" };\n",
" });\n",
"\n",
" // Wait for the user to pick the files.\n",
" const files = yield {\n",
" promise: Promise.race([pickedPromise, cancelPromise]),\n",
" response: {\n",
" action: 'starting',\n",
" }\n",
" };\n",
"\n",
" cancel.remove();\n",
"\n",
" // Disable the input element since further picks are not allowed.\n",
" inputElement.disabled = true;\n",
"\n",
" if (!files) {\n",
" return {\n",
" response: {\n",
" action: 'complete',\n",
" }\n",
" };\n",
" }\n",
"\n",
" for (const file of files) {\n",
" const li = document.createElement('li');\n",
" li.append(span(file.name, {fontWeight: 'bold'}));\n",
" li.append(span(\n",
" `(${file.type || 'n/a'}) - ${file.size} bytes, ` +\n",
" `last modified: ${\n",
" file.lastModifiedDate ? file.lastModifiedDate.toLocaleDateString() :\n",
" 'n/a'} - `));\n",
" const percent = span('0% done');\n",
" li.appendChild(percent);\n",
"\n",
" outputElement.appendChild(li);\n",
"\n",
" const fileDataPromise = new Promise((resolve) => {\n",
" const reader = new FileReader();\n",
" reader.onload = (e) => {\n",
" resolve(e.target.result);\n",
" };\n",
" reader.readAsArrayBuffer(file);\n",
" });\n",
" // Wait for the data to be ready.\n",
" let fileData = yield {\n",
" promise: fileDataPromise,\n",
" response: {\n",
" action: 'continue',\n",
" }\n",
" };\n",
"\n",
" // Use a chunked sending to avoid message size limits. See b/62115660.\n",
" let position = 0;\n",
" do {\n",
" const length = Math.min(fileData.byteLength - position, MAX_PAYLOAD_SIZE);\n",
" const chunk = new Uint8Array(fileData, position, length);\n",
" position += length;\n",
"\n",
" const base64 = btoa(String.fromCharCode.apply(null, chunk));\n",
" yield {\n",
" response: {\n",
" action: 'append',\n",
" file: file.name,\n",
" data: base64,\n",
" },\n",
" };\n",
"\n",
" let percentDone = fileData.byteLength === 0 ?\n",
" 100 :\n",
" Math.round((position / fileData.byteLength) * 100);\n",
" percent.textContent = `${percentDone}% done`;\n",
"\n",
" } while (position < fileData.byteLength);\n",
" }\n",
"\n",
" // All done.\n",
" yield {\n",
" response: {\n",
" action: 'complete',\n",
" }\n",
" };\n",
"}\n",
"\n",
"scope.google = scope.google || {};\n",
"scope.google.colab = scope.google.colab || {};\n",
"scope.google.colab._files = {\n",
" _uploadFiles,\n",
" _uploadFilesContinue,\n",
"};\n",
"})(self);\n",
"</script> "
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Saving ulasan_balanced.csv to ulasan_balanced.csv\n"
]
}
],
"source": [
"# 📌 STEP 1: Upload File\n",
"from google.colab import files # Gunakan ini kalau di Google Colab\n",
"uploaded = files.upload()\n",
"\n",
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "0TZG8_QDMhUM",
"outputId": "b52f732e-7f0a-4816-e8ea-a66a52def34f"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Jumlah total data: 801\n"
]
}
],
"source": [
"# Baca file yang diupload\n",
"df = pd.read_csv(list(uploaded.keys())[0])\n",
"print(\"Jumlah total data:\", df.shape[0])\n",
"df = df[['content', 'sentimen']] # pastikan kolom ini tersedia"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"background_save": true,
"base_uri": "https://localhost:8080/",
"height": 941,
"referenced_widgets": [
"60a4813f62f4466ba2a71b7c3362fc68",
"0333fcc6fcc3462fa13307a5abd8664f",
"bd9c17e6c9d7480b965e2af5a6112e87",
"991069bf5ccf41aa946c0d072641143c",
"39e645405b084c099dd3a11c7ed73182",
"9188837dbd9841598699f9aa82f1bdb4",
"8cd9b296a8f34f68ad79fd9ac28d37a8",
"3525c7104e8441d495ccc41f5999f38f",
"f220995fe6b64f6b80fe6c5870af5551",
"2b9b905c8de54c66861c23a40e2a8f6e",
"445f1cca6dba47dc81c99023728f4c84",
"ac5c5538d33f4ea39c852b93124ae909",
"b74546ff99ed421badfaacd198fa1b50",
"90b7901e18874b26b1fc74d36744e00f",
"d34e98e5733f458892d0e95d738da39f",
"26d0d64c6a8b4fd68aabb1bc3785afa4",
"87695724463742ffa9bf5efbb24041a9",
"5eb49e95ea1a4357a524171c8a06be7d",
"78f75459909b4da481a32591720162a2",
"8bb9926716b44e13a3c1374a6e1823ab",
"317fe2e189cd44b483d590acdfc6bac7",
"865ed3b75c7d46e9ade43eff616de933",
"49e7aa892a304a17ab76ee99b835f30d",
"61be3f13ac3f41a097adcc4bb28bb36d",
"b5aecee5eef4477cbf615c10b38a74ae",
"a7f5b41512534a2983b36fdc71997ccf",
"0b70605c91844febada70077fa6f6e7e",
"856cc3881caf4e449605e1bdcee78aa4",
"cd59e69dc8c44272966e98993cea37a6",
"0d0e89b55af846039fd60a7553a9e2ff",
"d8d4c4678c2c4b39bd58d6d6bc595265",
"1ab7f19f2dbd4353be7b6ffea07d5646",
"877aeb3166cb4f228ee68ccd7bfd2573",
"027a5a41b42f459eb7f3539a45b59713",
"d813653c327c45328a469ca29f13799f",
"15b3848798ff4af1ac2dcf1dde15a2b9",
"a7d1c460f6b84e6c8c4f414965e4dfce",
"ad81ce0e9a9c4c83acac65e085d38681",
"21b451b61d5d43d2a5ba6578a330adbe",
"63f42e476aee4110b49f57bd2049a38d",
"842cb203e02c498aba42c67a54b62d22",
"92ab5931c05b40acbe2a3dc70d19ead8",
"68355c7f1eb94e3c907f0cefd26075c6",
"68764f862c084262b9d7f88afea7d1d4",
"34dc529069d14f3982a4ab985cf111dc",
"b0aefee87d724e8ebd5c051de9ad92bb",
"77535182be2141f781d5c3e417ccd8d6",
"5d2a57b16f8548ec935e448d244309b9",
"407d307dd90049af83712c94e2864747",
"ceef3242b7ce445d957272c196faa1ab",
"4937b2372ecc43f4b42ce6e7a754094a",
"5bbf012121fe452e8c35fab62677c0fc",
"1256d41026c44650aa5be7e145cf688b",
"b7a3963bc47144e190b6675ee357b11e",
"a370fa2eafeb403fa99f0b168a8fdb56",
"58444e78b25840978b90b7ac64e58d00",
"2d323c6fe68c47eab442e2c806c7e56d",
"e4d1f59fb5444a46aaef64a56b82d136",
"1d6b2b7558604c22a0887f1646e28452",
"5ce13cc488cd425ab5845917872b65e2",
"24a77e500911480bb2e94c996326bbf7",
"56e5fdf6355b408c806b184829c8880a",
"6c9b2bbbc6d54b199e53fde1c91da225",
"3b90e28c2a674353aed636dc092e83bc",
"289a0a21f7084b158d64365cf32e1fa8",
"814431c6aa8e42efb6c3680f1da1d1d4"
]
},
"id": "VK1jOCnsMkmu",
"outputId": "d9190c46-c62b-4788-d623-0d450b41c1ff"
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Requirement already satisfied: transformers in /usr/local/lib/python3.11/dist-packages (4.52.4)\n",
"Collecting nlpaug\n",
" Downloading nlpaug-1.1.11-py3-none-any.whl.metadata (14 kB)\n",
"Requirement already satisfied: filelock in /usr/local/lib/python3.11/dist-packages (from transformers) (3.18.0)\n",
"Requirement already satisfied: huggingface-hub<1.0,>=0.30.0 in /usr/local/lib/python3.11/dist-packages (from transformers) (0.32.4)\n",
"Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.11/dist-packages (from transformers) (2.0.2)\n",
"Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.11/dist-packages (from transformers) (24.2)\n",
"Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.11/dist-packages (from transformers) (6.0.2)\n",
"Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.11/dist-packages (from transformers) (2024.11.6)\n",
"Requirement already satisfied: requests in /usr/local/lib/python3.11/dist-packages (from transformers) (2.32.3)\n",
"Requirement already satisfied: tokenizers<0.22,>=0.21 in /usr/local/lib/python3.11/dist-packages (from transformers) (0.21.1)\n",
"Requirement already satisfied: safetensors>=0.4.3 in /usr/local/lib/python3.11/dist-packages (from transformers) (0.5.3)\n",
"Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.11/dist-packages (from transformers) (4.67.1)\n",
"Requirement already satisfied: pandas>=1.2.0 in /usr/local/lib/python3.11/dist-packages (from nlpaug) (2.2.2)\n",
"Requirement already satisfied: gdown>=4.0.0 in /usr/local/lib/python3.11/dist-packages (from nlpaug) (5.2.0)\n",
"Requirement already satisfied: beautifulsoup4 in /usr/local/lib/python3.11/dist-packages (from gdown>=4.0.0->nlpaug) (4.13.4)\n",
"Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.11/dist-packages (from huggingface-hub<1.0,>=0.30.0->transformers) (2025.3.2)\n",
"Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.11/dist-packages (from huggingface-hub<1.0,>=0.30.0->transformers) (4.14.0)\n",
"Requirement already satisfied: hf-xet<2.0.0,>=1.1.2 in /usr/local/lib/python3.11/dist-packages (from huggingface-hub<1.0,>=0.30.0->transformers) (1.1.2)\n",
"Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.11/dist-packages (from pandas>=1.2.0->nlpaug) (2.9.0.post0)\n",
"Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.11/dist-packages (from pandas>=1.2.0->nlpaug) (2025.2)\n",
"Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.11/dist-packages (from pandas>=1.2.0->nlpaug) (2025.2)\n",
"Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.11/dist-packages (from requests->transformers) (3.4.2)\n",
"Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.11/dist-packages (from requests->transformers) (3.10)\n",
"Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.11/dist-packages (from requests->transformers) (2.4.0)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.11/dist-packages (from requests->transformers) (2025.4.26)\n",
"Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.11/dist-packages (from python-dateutil>=2.8.2->pandas>=1.2.0->nlpaug) (1.17.0)\n",
"Requirement already satisfied: soupsieve>1.2 in /usr/local/lib/python3.11/dist-packages (from beautifulsoup4->gdown>=4.0.0->nlpaug) (2.7)\n",
"Requirement already satisfied: PySocks!=1.5.7,>=1.5.6 in /usr/local/lib/python3.11/dist-packages (from requests[socks]->gdown>=4.0.0->nlpaug) (1.7.1)\n",
"Downloading nlpaug-1.1.11-py3-none-any.whl (410 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m410.5/410.5 kB\u001b[0m \u001b[31m12.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hInstalling collected packages: nlpaug\n",
"Successfully installed nlpaug-1.1.11\n",
"Train: 640, Test: 120, Val: 41\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/usr/local/lib/python3.11/dist-packages/huggingface_hub/utils/_auth.py:94: UserWarning: \n",
"The secret `HF_TOKEN` does not exist in your Colab secrets.\n",
"To authenticate with the Hugging Face Hub, create a token in your settings tab (https://huggingface.co/settings/tokens), set it as secret in your Google Colab and restart your session.\n",
"You will be able to reuse this secret in all of your notebooks.\n",
"Please note that authentication is recommended but still optional to access public models or datasets.\n",
" warnings.warn(\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "60a4813f62f4466ba2a71b7c3362fc68",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"tokenizer_config.json: 0%| | 0.00/2.00 [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "ac5c5538d33f4ea39c852b93124ae909",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"config.json: 0%| | 0.00/1.53k [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "49e7aa892a304a17ab76ee99b835f30d",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"vocab.txt: 0%| | 0.00/229k [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "027a5a41b42f459eb7f3539a45b59713",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"special_tokens_map.json: 0%| | 0.00/112 [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "34dc529069d14f3982a4ab985cf111dc",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"pytorch_model.bin: 0%| | 0.00/498M [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"The following layers were not sharded: encoder.layer.*.output.LayerNorm.bias, encoder.layer.*.attention.output.dense.bias, encoder.layer.*.output.dense.bias, encoder.layer.*.attention.self.key.weight, encoder.layer.*.attention.self.query.weight, embeddings.word_embeddings.weight, encoder.layer.*.intermediate.dense.weight, embeddings.token_type_embeddings.weight, encoder.layer.*.attention.self.key.bias, encoder.layer.*.intermediate.dense.bias, embeddings.position_embeddings.weight, encoder.layer.*.attention.self.value.weight, encoder.layer.*.output.dense.weight, encoder.layer.*.attention.output.LayerNorm.weight, embeddings.LayerNorm.bias, encoder.layer.*.attention.output.LayerNorm.bias, encoder.layer.*.output.LayerNorm.weight, encoder.layer.*.attention.self.query.bias, encoder.layer.*.attention.self.value.bias, embeddings.LayerNorm.weight, encoder.layer.*.attention.output.dense.weight\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "58444e78b25840978b90b7ac64e58d00",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"model.safetensors: 0%| | 0.00/498M [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# Install dependencies jika belum\n",
"!pip install transformers nlpaug\n",
"\n",
"# Import\n",
"import nlpaug.augmenter.word as naw\n",
"import pandas as pd\n",
"\n",
"from sklearn.model_selection import train_test_split\n",
"\n",
"# Split dataset\n",
"df_temp, df_val = train_test_split(df, test_size=0.05, random_state=42, stratify=df['sentimen'])\n",
"test_size_adjusted = 0.15 / (1 - 0.05)\n",
"df_train, df_test = train_test_split(df_temp, test_size=test_size_adjusted, random_state=42, stratify=df_temp['sentimen'])\n",
"\n",
"print(f\"Train: {df_train.shape[0]}, Test: {df_test.shape[0]}, Val: {df_val.shape[0]}\")\n",
"\n",
"# Load IndoBERT augmenter\n",
"aug = naw.ContextualWordEmbsAug(\n",
" model_path='indobenchmark/indobert-base-p1',\n",
" action=\"insert\",\n",
" top_k=10,\n",
" device='cpu'\n",
")\n",
"\n",
"# Fungsi augmentasi lebih banyak\n",
"def augment_text(text, n=5): # <- di sini kamu bisa set mau augment berapa kali\n",
" try:\n",
" augmented = aug.augment(text, n=n)\n",
" return augmented if isinstance(augmented, list) else [augmented]\n",
" except Exception as e:\n",
" print(f\"Error augmenting: {e}\")\n",
" return []\n",
"\n",
"# Lakukan augmentasi\n",
"augmented_rows = []\n",
"for idx, row in df_train.iterrows():\n",
" aug_texts = augment_text(row['content'], n=5) # <-- augment 5x per data\n",
" for aug_text in aug_texts:\n",
" augmented_rows.append({'content': aug_text, 'sentimen': row['sentimen']})\n",
" if idx % 500 == 0:\n",
" print(f\"Augmenting row {idx}/{df_train.shape[0]}\")\n",
"\n",
"# Gabungkan hasil augmentasi\n",
"df_augmented = pd.DataFrame(augmented_rows)\n",
"df_train_augmented = pd.concat([df_train, df_augmented], ignore_index=True)\n",
"\n",
"print(f\"Jumlah data setelah augmentasi: {df_train_augmented.shape[0]}\")\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "036vmokdOYnd"
},
"outputs": [],
"source": [
"pip install Sastrawi"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "yYi1S6Y1OZcd"
},
"outputs": [],
"source": [
"from Sastrawi.Stemmer.StemmerFactory import StemmerFactory\n",
"factory = StemmerFactory()\n",
"stemmer = factory.create_stemmer()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "zV0pVMvNMo0I"
},
"outputs": [],
"source": [
"# 📌 STEP 3: Preprocessing Teks (SETELAH AUGMENTASI)\n",
"import re\n",
"import nltk\n",
"nltk.download('stopwords')\n",
"from nltk.corpus import stopwords\n",
"\n",
"stop_words = set(stopwords.words('indonesian'))\n",
"\n",
"def clean_text(text):\n",
" text = str(text).lower()\n",
" text = re.sub(r'http\\S+|www\\S+', '', text) # hapus URL\n",
" text = re.sub(r'[^a-zA-Z\\s]', '', text) # hapus simbol, angka, dll\n",
" text = re.sub(r'[\\U00010000-\\U0010ffff]', '', text) # hapus emoji\n",
" words = text.split()\n",
" words = [w for w in words if w not in stop_words and len(w) > 2]\n",
" return words\n",
"\n",
"# Terapkan ke semua bagian\n",
"df_train_augmented['clean'] = df_train_augmented['content'].apply(clean_text)\n",
"df_test['clean'] = df_test['content'].apply(clean_text)\n",
"df_val['clean'] = df_val['content'].apply(clean_text)\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "62OU3kQ0MttG"
},
"outputs": [],
"source": [
"# Gabungkan token hasil cleaning menjadi string\n",
"df_train_augmented['clean_str'] = df_train_augmented['clean'].apply(lambda x: ' '.join(x))\n",
"df_test['clean_str'] = df_test['clean'].apply(lambda x: ' '.join(x))\n",
"df_val['clean_str'] = df_val['clean'].apply(lambda x: ' '.join(x))\n",
"\n",
"# TF-IDF Vectorizer\n",
"from sklearn.feature_extraction.text import TfidfVectorizer\n",
"\n",
"vectorizer = TfidfVectorizer()\n",
"X_train = vectorizer.fit_transform(df_train_augmented['clean_str'])\n",
"X_test = vectorizer.transform(df_test['clean_str'])\n",
"X_val = vectorizer.transform(df_val['clean_str'])\n",
"\n",
"# Target labels\n",
"y_train = df_train_augmented['sentimen']\n",
"y_test = df_test['sentimen']\n",
"y_val = df_val['sentimen']\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "U5f-DKCSMvHt"
},
"outputs": [],
"source": [
"# 📌 STEP 5: Latih Naive Bayes\n",
"from sklearn.naive_bayes import MultinomialNB\n",
"from sklearn.metrics import classification_report, accuracy_score\n",
"\n",
"model = MultinomialNB()\n",
"model.fit(X_train, y_train)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "4QWA5b0XMwNF"
},
"outputs": [],
"source": [
"# 📌 STEP 6: Evaluasi\n",
"print(\"\\n📊 Evaluasi pada Test Set:\")\n",
"y_pred_test = model.predict(X_test)\n",
"print(\"Akurasi:\", accuracy_score(y_test, y_pred_test))\n",
"print(classification_report(y_test, y_pred_test))\n",
"\n",
"print(\"\\n📊 Evaluasi pada Validation Set:\")\n",
"y_pred_val = model.predict(X_val)\n",
"print(\"Akurasi:\", accuracy_score(y_val, y_pred_val))\n",
"print(classification_report(y_val, y_pred_val))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "Ax79G3jticm8"
},
"outputs": [],
"source": [
"import joblib\n",
"joblib.dump(model, 'model_nb.pkl')\n",
"joblib.dump(vectorizer, 'tfidf_vectorizer.pkl')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "JMNNKXcXM2kJ"
},
"outputs": [],
"source": [
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"from sklearn.metrics import confusion_matrix\n",
"from wordcloud import WordCloud\n",
"\n",
"# CONFUSION MATRIX - Test\n",
"cm_test = confusion_matrix(y_test, y_pred_test, labels=model.classes_)\n",
"\n",
"plt.figure(figsize=(7, 5))\n",
"sns.heatmap(cm_test, annot=True, fmt='d', cmap='Blues', xticklabels=model.classes_, yticklabels=model.classes_)\n",
"plt.title('Confusion Matrix - Test Set')\n",
"plt.xlabel('Predicted Label')\n",
"plt.ylabel('True Label')\n",
"plt.show()\n",
"\n",
"# CONFUSION MATRIX - Validation\n",
"cm_val = confusion_matrix(y_val, y_pred_val, labels=model.classes_)\n",
"\n",
"plt.figure(figsize=(7, 5))\n",
"sns.heatmap(cm_val, annot=True, fmt='d', cmap='Greens', xticklabels=model.classes_, yticklabels=model.classes_)\n",
"plt.title('Confusion Matrix - Validation Set')\n",
"plt.xlabel('Predicted Label')\n",
"plt.ylabel('True Label')\n",
"plt.show()\n",
"\n",
"# DISTRIBUSI PREDIKSI - Test\n",
"plt.figure(figsize=(6, 4))\n",
"sns.countplot(x=y_pred_test, order=model.classes_, palette='viridis')\n",
"plt.title('Distribusi Prediksi - Test Set')\n",
"plt.xlabel('Label Prediksi')\n",
"plt.ylabel('Jumlah')\n",
"plt.show()\n",
"\n",
"# WORD CLOUD PER SENTIMEN (opsional & keren)\n",
"from wordcloud import WordCloud\n",
"import matplotlib.pyplot as plt\n",
"\n",
"sentimen_list = ['positif', 'negatif', 'netral']\n",
"for label in sentimen_list:\n",
" # Gabungkan token jadi string per baris → lalu semua baris jadi satu string\n",
" text = \" \".join(df_train_augmented[df_train_augmented['sentimen'] == label]['clean'].apply(lambda x: ' '.join(x)))\n",
"\n",
" wc = WordCloud(width=800, height=400, background_color='white').generate(text)\n",
" plt.figure(figsize=(10, 5))\n",
" plt.imshow(wc, interpolation='bilinear')\n",
" plt.axis('off')\n",
" plt.title(f'Word Cloud - {label.upper()}')\n",
" plt.show()\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "ZJj_FGsiNLka"
},
"outputs": [],
"source": [
"# Plot distribusi sentimen dalam train set\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"\n",
"plt.figure(figsize=(6, 4))\n",
"sns.countplot(x=df_train['sentimen'], order=df_train_augmented['sentimen'].value_counts().index, palette='Set2')\n",
"plt.title(\"Distribusi Sentimen di Train Set\")\n",
"plt.xlabel(\"Sentimen\")\n",
"plt.ylabel(\"Jumlah Data\")\n",
"plt.grid(axis='y', linestyle='--', alpha=0.7)\n",
"plt.tight_layout()\n",
"plt.show()\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "RQHF89mmhH2L"
},
"source": [
"## save file"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "IEzeVAuJhP2s"
},
"outputs": [],
"source": [
"df_train.to_csv(\"train_original.csv\", index=False)\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "iZ1a01flNofP"
},
"outputs": [],
"source": [
"# Simpan ke CSV versi augmented (3x lipat)\n",
"df_train_augmented.to_csv(\"train_augmented.csv\", index=False)\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "HS0v7k4whJNt"
},
"outputs": [],
"source": [
"# Simpan test dan val\n",
"df_test.to_csv(\"test.csv\", index=False)\n",
"df_val.to_csv(\"val.csv\", index=False)"
]
}
],
"metadata": {
"colab": {
"toc_visible": true,
"provenance": []
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"name": "python"
},
"widgets": {
"application/vnd.jupyter.widget-state+json": {
"027a5a41b42f459eb7f3539a45b59713": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "HBoxModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HBoxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HBoxView",
"box_style": "",
"children": [
"IPY_MODEL_d813653c327c45328a469ca29f13799f",
"IPY_MODEL_15b3848798ff4af1ac2dcf1dde15a2b9",
"IPY_MODEL_a7d1c460f6b84e6c8c4f414965e4dfce"
],
"layout": "IPY_MODEL_ad81ce0e9a9c4c83acac65e085d38681"
}
},
"0333fcc6fcc3462fa13307a5abd8664f": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HTMLView",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_9188837dbd9841598699f9aa82f1bdb4",
"placeholder": "",
"style": "IPY_MODEL_8cd9b296a8f34f68ad79fd9ac28d37a8",
"value": "tokenizer_config.json:100%"
}
},
"0b70605c91844febada70077fa6f6e7e": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "1.2.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"0d0e89b55af846039fd60a7553a9e2ff": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "1.2.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"1256d41026c44650aa5be7e145cf688b": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "ProgressStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "ProgressStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"bar_color": null,
"description_width": ""
}
},
"15b3848798ff4af1ac2dcf1dde15a2b9": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "FloatProgressModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "FloatProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "ProgressView",
"bar_style": "success",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_842cb203e02c498aba42c67a54b62d22",
"max": 112,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_92ab5931c05b40acbe2a3dc70d19ead8",
"value": 112
}
},
"1ab7f19f2dbd4353be7b6ffea07d5646": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "1.2.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"1d6b2b7558604c22a0887f1646e28452": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HTMLView",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_289a0a21f7084b158d64365cf32e1fa8",
"placeholder": "",
"style": "IPY_MODEL_814431c6aa8e42efb6c3680f1da1d1d4",
"value": "498M/498M[00:03&lt;00:00,148MB/s]"
}
},
"21b451b61d5d43d2a5ba6578a330adbe": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "1.2.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"24a77e500911480bb2e94c996326bbf7": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "1.2.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"26d0d64c6a8b4fd68aabb1bc3785afa4": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "1.2.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"289a0a21f7084b158d64365cf32e1fa8": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "1.2.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"2b9b905c8de54c66861c23a40e2a8f6e": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "1.2.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"2d323c6fe68c47eab442e2c806c7e56d": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HTMLView",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_24a77e500911480bb2e94c996326bbf7",
"placeholder": "",
"style": "IPY_MODEL_56e5fdf6355b408c806b184829c8880a",
"value": "model.safetensors:100%"
}
},
"317fe2e189cd44b483d590acdfc6bac7": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "1.2.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"34dc529069d14f3982a4ab985cf111dc": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "HBoxModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HBoxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HBoxView",
"box_style": "",
"children": [
"IPY_MODEL_b0aefee87d724e8ebd5c051de9ad92bb",
"IPY_MODEL_77535182be2141f781d5c3e417ccd8d6",
"IPY_MODEL_5d2a57b16f8548ec935e448d244309b9"
],
"layout": "IPY_MODEL_407d307dd90049af83712c94e2864747"
}
},
"3525c7104e8441d495ccc41f5999f38f": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "1.2.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"39e645405b084c099dd3a11c7ed73182": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "1.2.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"3b90e28c2a674353aed636dc092e83bc": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "ProgressStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "ProgressStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"bar_color": null,
"description_width": ""
}
},
"407d307dd90049af83712c94e2864747": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "1.2.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"445f1cca6dba47dc81c99023728f4c84": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "DescriptionStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"4937b2372ecc43f4b42ce6e7a754094a": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "DescriptionStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"49e7aa892a304a17ab76ee99b835f30d": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "HBoxModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HBoxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HBoxView",
"box_style": "",
"children": [
"IPY_MODEL_61be3f13ac3f41a097adcc4bb28bb36d",
"IPY_MODEL_b5aecee5eef4477cbf615c10b38a74ae",
"IPY_MODEL_a7f5b41512534a2983b36fdc71997ccf"
],
"layout": "IPY_MODEL_0b70605c91844febada70077fa6f6e7e"
}
},
"56e5fdf6355b408c806b184829c8880a": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "DescriptionStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"58444e78b25840978b90b7ac64e58d00": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "HBoxModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HBoxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HBoxView",
"box_style": "",
"children": [
"IPY_MODEL_2d323c6fe68c47eab442e2c806c7e56d",
"IPY_MODEL_e4d1f59fb5444a46aaef64a56b82d136",
"IPY_MODEL_1d6b2b7558604c22a0887f1646e28452"
],
"layout": "IPY_MODEL_5ce13cc488cd425ab5845917872b65e2"
}
},
"5bbf012121fe452e8c35fab62677c0fc": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "1.2.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"5ce13cc488cd425ab5845917872b65e2": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "1.2.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"5d2a57b16f8548ec935e448d244309b9": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HTMLView",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_b7a3963bc47144e190b6675ee357b11e",
"placeholder": "",
"style": "IPY_MODEL_a370fa2eafeb403fa99f0b168a8fdb56",
"value": "498M/498M[00:04&lt;00:00,164MB/s]"
}
},
"5eb49e95ea1a4357a524171c8a06be7d": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "DescriptionStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"60a4813f62f4466ba2a71b7c3362fc68": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "HBoxModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HBoxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HBoxView",
"box_style": "",
"children": [
"IPY_MODEL_0333fcc6fcc3462fa13307a5abd8664f",
"IPY_MODEL_bd9c17e6c9d7480b965e2af5a6112e87",
"IPY_MODEL_991069bf5ccf41aa946c0d072641143c"
],
"layout": "IPY_MODEL_39e645405b084c099dd3a11c7ed73182"
}
},
"61be3f13ac3f41a097adcc4bb28bb36d": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HTMLView",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_856cc3881caf4e449605e1bdcee78aa4",
"placeholder": "",
"style": "IPY_MODEL_cd59e69dc8c44272966e98993cea37a6",
"value": "vocab.txt:100%"
}
},
"63f42e476aee4110b49f57bd2049a38d": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "DescriptionStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"68355c7f1eb94e3c907f0cefd26075c6": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "1.2.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"68764f862c084262b9d7f88afea7d1d4": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "DescriptionStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"6c9b2bbbc6d54b199e53fde1c91da225": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "1.2.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"77535182be2141f781d5c3e417ccd8d6": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "FloatProgressModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "FloatProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "ProgressView",
"bar_style": "success",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_5bbf012121fe452e8c35fab62677c0fc",
"max": 497810400,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_1256d41026c44650aa5be7e145cf688b",
"value": 497810400
}
},
"78f75459909b4da481a32591720162a2": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "1.2.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"814431c6aa8e42efb6c3680f1da1d1d4": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "DescriptionStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"842cb203e02c498aba42c67a54b62d22": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "1.2.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"856cc3881caf4e449605e1bdcee78aa4": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "1.2.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"865ed3b75c7d46e9ade43eff616de933": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "DescriptionStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"87695724463742ffa9bf5efbb24041a9": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "1.2.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"877aeb3166cb4f228ee68ccd7bfd2573": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "DescriptionStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"8bb9926716b44e13a3c1374a6e1823ab": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "ProgressStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "ProgressStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"bar_color": null,
"description_width": ""
}
},
"8cd9b296a8f34f68ad79fd9ac28d37a8": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "DescriptionStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"90b7901e18874b26b1fc74d36744e00f": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "FloatProgressModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "FloatProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "ProgressView",
"bar_style": "success",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_78f75459909b4da481a32591720162a2",
"max": 1534,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_8bb9926716b44e13a3c1374a6e1823ab",
"value": 1534
}
},
"9188837dbd9841598699f9aa82f1bdb4": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "1.2.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"92ab5931c05b40acbe2a3dc70d19ead8": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "ProgressStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "ProgressStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"bar_color": null,
"description_width": ""
}
},
"991069bf5ccf41aa946c0d072641143c": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HTMLView",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_2b9b905c8de54c66861c23a40e2a8f6e",
"placeholder": "",
"style": "IPY_MODEL_445f1cca6dba47dc81c99023728f4c84",
"value": "2.00/2.00[00:00&lt;00:00,173B/s]"
}
},
"a370fa2eafeb403fa99f0b168a8fdb56": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "DescriptionStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"a7d1c460f6b84e6c8c4f414965e4dfce": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HTMLView",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_68355c7f1eb94e3c907f0cefd26075c6",
"placeholder": "",
"style": "IPY_MODEL_68764f862c084262b9d7f88afea7d1d4",
"value": "112/112[00:00&lt;00:00,9.58kB/s]"
}
},
"a7f5b41512534a2983b36fdc71997ccf": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HTMLView",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_1ab7f19f2dbd4353be7b6ffea07d5646",
"placeholder": "",
"style": "IPY_MODEL_877aeb3166cb4f228ee68ccd7bfd2573",
"value": "229k/229k[00:00&lt;00:00,524kB/s]"
}
},
"ac5c5538d33f4ea39c852b93124ae909": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "HBoxModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HBoxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HBoxView",
"box_style": "",
"children": [
"IPY_MODEL_b74546ff99ed421badfaacd198fa1b50",
"IPY_MODEL_90b7901e18874b26b1fc74d36744e00f",
"IPY_MODEL_d34e98e5733f458892d0e95d738da39f"
],
"layout": "IPY_MODEL_26d0d64c6a8b4fd68aabb1bc3785afa4"
}
},
"ad81ce0e9a9c4c83acac65e085d38681": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "1.2.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"b0aefee87d724e8ebd5c051de9ad92bb": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HTMLView",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_ceef3242b7ce445d957272c196faa1ab",
"placeholder": "",
"style": "IPY_MODEL_4937b2372ecc43f4b42ce6e7a754094a",
"value": "pytorch_model.bin:100%"
}
},
"b5aecee5eef4477cbf615c10b38a74ae": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "FloatProgressModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "FloatProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "ProgressView",
"bar_style": "success",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_0d0e89b55af846039fd60a7553a9e2ff",
"max": 229167,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_d8d4c4678c2c4b39bd58d6d6bc595265",
"value": 229167
}
},
"b74546ff99ed421badfaacd198fa1b50": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HTMLView",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_87695724463742ffa9bf5efbb24041a9",
"placeholder": "",
"style": "IPY_MODEL_5eb49e95ea1a4357a524171c8a06be7d",
"value": "config.json:100%"
}
},
"b7a3963bc47144e190b6675ee357b11e": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "1.2.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"bd9c17e6c9d7480b965e2af5a6112e87": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "FloatProgressModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "FloatProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "ProgressView",
"bar_style": "success",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_3525c7104e8441d495ccc41f5999f38f",
"max": 2,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_f220995fe6b64f6b80fe6c5870af5551",
"value": 2
}
},
"cd59e69dc8c44272966e98993cea37a6": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "DescriptionStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "DescriptionStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"description_width": ""
}
},
"ceef3242b7ce445d957272c196faa1ab": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "1.2.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "1.2.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"overflow_x": null,
"overflow_y": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"d34e98e5733f458892d0e95d738da39f": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HTMLView",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_317fe2e189cd44b483d590acdfc6bac7",
"placeholder": "",
"style": "IPY_MODEL_865ed3b75c7d46e9ade43eff616de933",
"value": "1.53k/1.53k[00:00&lt;00:00,96.7kB/s]"
}
},
"d813653c327c45328a469ca29f13799f": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "HTMLView",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_21b451b61d5d43d2a5ba6578a330adbe",
"placeholder": "",
"style": "IPY_MODEL_63f42e476aee4110b49f57bd2049a38d",
"value": "special_tokens_map.json:100%"
}
},
"d8d4c4678c2c4b39bd58d6d6bc595265": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "ProgressStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "ProgressStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"bar_color": null,
"description_width": ""
}
},
"e4d1f59fb5444a46aaef64a56b82d136": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "FloatProgressModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "FloatProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "1.5.0",
"_view_name": "ProgressView",
"bar_style": "success",
"description": "",
"description_tooltip": null,
"layout": "IPY_MODEL_6c9b2bbbc6d54b199e53fde1c91da225",
"max": 497787752,
"min": 0,
"orientation": "horizontal",
"style": "IPY_MODEL_3b90e28c2a674353aed636dc092e83bc",
"value": 497787752
}
},
"f220995fe6b64f6b80fe6c5870af5551": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "1.5.0",
"model_name": "ProgressStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "1.5.0",
"_model_name": "ProgressStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "1.2.0",
"_view_name": "StyleView",
"bar_color": null,
"description_width": ""
}
}
}
}
},
"nbformat": 4,
"nbformat_minor": 0
}