File size: 18,788 Bytes
acf97d8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 | {
"cells": [
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"c:\\Users\\admin\\Documents\\DocBERT2\\news-category-dataset\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Cloning into 'news-category-dataset'...\n",
"c:\\Users\\admin\\AppData\\Local\\Programs\\Python\\Python312\\Lib\\site-packages\\IPython\\core\\magics\\osm.py:417: UserWarning: This is now an optional IPython functionality, setting dhist requires you to install the `pickleshare` library.\n",
" self.shell.db['dhist'] = compress_dhist(dhist)[-100:]\n"
]
}
],
"source": [
"# Dataset is from Heegyu Kim, available at https://huggingface.co/datasets/heegyu/news-category-dataset, under CC-BY 4.0 license.\n",
"# The dataset is a collection of news articles from various categories from Huffington Post.\n",
"!git clone https://huggingface.co/datasets/heegyu/news-category-dataset"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>link</th>\n",
" <th>headline</th>\n",
" <th>category</th>\n",
" <th>short_description</th>\n",
" <th>authors</th>\n",
" <th>date</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>https://www.huffpost.com/entry/covid-boosters-...</td>\n",
" <td>Over 4 Million Americans Roll Up Sleeves For O...</td>\n",
" <td>U.S. NEWS</td>\n",
" <td>Health experts said it is too early to predict...</td>\n",
" <td>Carla K. Johnson, AP</td>\n",
" <td>2022-09-23</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>https://www.huffpost.com/entry/american-airlin...</td>\n",
" <td>American Airlines Flyer Charged, Banned For Li...</td>\n",
" <td>U.S. NEWS</td>\n",
" <td>He was subdued by passengers and crew when he ...</td>\n",
" <td>Mary Papenfuss</td>\n",
" <td>2022-09-23</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>https://www.huffpost.com/entry/funniest-tweets...</td>\n",
" <td>23 Of The Funniest Tweets About Cats And Dogs ...</td>\n",
" <td>COMEDY</td>\n",
" <td>\"Until you have a dog you don't understand wha...</td>\n",
" <td>Elyse Wanshel</td>\n",
" <td>2022-09-23</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>https://www.huffpost.com/entry/funniest-parent...</td>\n",
" <td>The Funniest Tweets From Parents This Week (Se...</td>\n",
" <td>PARENTING</td>\n",
" <td>\"Accidentally put grown-up toothpaste on my to...</td>\n",
" <td>Caroline Bologna</td>\n",
" <td>2022-09-23</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>https://www.huffpost.com/entry/amy-cooper-lose...</td>\n",
" <td>Woman Who Called Cops On Black Bird-Watcher Lo...</td>\n",
" <td>U.S. NEWS</td>\n",
" <td>Amy Cooper accused investment firm Franklin Te...</td>\n",
" <td>Nina Golgowski</td>\n",
" <td>2022-09-22</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" link \\\n",
"0 https://www.huffpost.com/entry/covid-boosters-... \n",
"1 https://www.huffpost.com/entry/american-airlin... \n",
"2 https://www.huffpost.com/entry/funniest-tweets... \n",
"3 https://www.huffpost.com/entry/funniest-parent... \n",
"4 https://www.huffpost.com/entry/amy-cooper-lose... \n",
"\n",
" headline category \\\n",
"0 Over 4 Million Americans Roll Up Sleeves For O... U.S. NEWS \n",
"1 American Airlines Flyer Charged, Banned For Li... U.S. NEWS \n",
"2 23 Of The Funniest Tweets About Cats And Dogs ... COMEDY \n",
"3 The Funniest Tweets From Parents This Week (Se... PARENTING \n",
"4 Woman Who Called Cops On Black Bird-Watcher Lo... U.S. NEWS \n",
"\n",
" short_description authors \\\n",
"0 Health experts said it is too early to predict... Carla K. Johnson, AP \n",
"1 He was subdued by passengers and crew when he ... Mary Papenfuss \n",
"2 \"Until you have a dog you don't understand wha... Elyse Wanshel \n",
"3 \"Accidentally put grown-up toothpaste on my to... Caroline Bologna \n",
"4 Amy Cooper accused investment firm Franklin Te... Nina Golgowski \n",
"\n",
" date \n",
"0 2022-09-23 \n",
"1 2022-09-23 \n",
"2 2022-09-23 \n",
"3 2022-09-23 \n",
"4 2022-09-22 "
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = pd.read_json(\"./news-category-dataset/data.json\", lines=True)\n",
"df.head(5)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Unique categories in the dataset: ['U.S. NEWS' 'COMEDY' 'PARENTING' 'WORLD NEWS' 'CULTURE & ARTS' 'TECH'\n",
" 'SPORTS' 'ENTERTAINMENT' 'POLITICS' 'WEIRD NEWS' 'ENVIRONMENT'\n",
" 'EDUCATION' 'CRIME' 'SCIENCE' 'WELLNESS' 'BUSINESS' 'STYLE & BEAUTY'\n",
" 'FOOD & DRINK' 'MEDIA' 'QUEER VOICES' 'HOME & LIVING' 'WOMEN'\n",
" 'BLACK VOICES' 'TRAVEL' 'MONEY' 'RELIGION' 'LATINO VOICES' 'IMPACT'\n",
" 'WEDDINGS' 'COLLEGE' 'PARENTS' 'ARTS & CULTURE' 'STYLE' 'GREEN' 'TASTE'\n",
" 'HEALTHY LIVING' 'THE WORLDPOST' 'GOOD NEWS' 'WORLDPOST' 'FIFTY' 'ARTS'\n",
" 'DIVORCE']\n"
]
}
],
"source": [
"unique_categories = df['category'].unique()\n",
"print(\"Unique categories in the dataset: \", unique_categories)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Number of WORLD category articles: 9542\n"
]
}
],
"source": [
"world_category = df[(df['category'] == 'WORLD') | (df['category'] == 'WORLD NEWS') | (df['category'] == 'WORLDPOST') | (df['category'] == 'THE WORLDPOST')]\n",
"print(\"Number of WORLD category articles: \", len(world_category))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Number of SPORTS category articles: 5077\n"
]
}
],
"source": [
"sports_category = df[(df['category'] == 'SPORTS') | (df['category'] == 'SPORT')]\n",
"print(\"Number of SPORTS category articles: \", len(sports_category))"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Number of BUSINESS category articles: 5992\n"
]
}
],
"source": [
"business_category = df[(df['category'] == 'BUSINESS')]\n",
"print(\"Number of BUSINESS category articles: \", len(business_category))"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Number of SCIENCE category articles: 4310\n"
]
}
],
"source": [
"science_category = df[(df['category'] == 'SCIENCE') | (df['category'] == 'SCIENCE & TECH') | (df['category'] == 'SCIENCE & TECH') | (df['category'] == 'TECH')]\n",
"print(\"Number of SCIENCE category articles: \", len(science_category))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"C:\\Users\\admin\\AppData\\Local\\Temp\\ipykernel_6844\\3064268492.py:1: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" science_category['Description'] = science_category['headline'] + \"\\n\\n\" + science_category['short_description']\n",
"C:\\Users\\admin\\AppData\\Local\\Temp\\ipykernel_6844\\3064268492.py:2: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" science_category['Class Index'] = 3\n",
"C:\\Users\\admin\\AppData\\Local\\Temp\\ipykernel_6844\\3064268492.py:4: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" business_category['Description'] = business_category['headline'] + \"\\n\\n\" + business_category['short_description']\n",
"C:\\Users\\admin\\AppData\\Local\\Temp\\ipykernel_6844\\3064268492.py:5: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" business_category['Class Index'] = 2\n",
"C:\\Users\\admin\\AppData\\Local\\Temp\\ipykernel_6844\\3064268492.py:7: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" sports_category['Description'] = sports_category['headline'] + \"\\n\\n\" + sports_category['short_description']\n",
"C:\\Users\\admin\\AppData\\Local\\Temp\\ipykernel_6844\\3064268492.py:8: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" sports_category['Class Index'] = 1\n",
"C:\\Users\\admin\\AppData\\Local\\Temp\\ipykernel_6844\\3064268492.py:10: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" world_category['Description'] = world_category['headline'] + \"\\n\\n\" + world_category['short_description']\n",
"C:\\Users\\admin\\AppData\\Local\\Temp\\ipykernel_6844\\3064268492.py:11: SettingWithCopyWarning: \n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" world_category['Class Index'] = 0\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Description</th>\n",
" <th>Class Index</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>Trump’s Saudi Trip Should Be About Ending The ...</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Russia Vows To Expand 'Black List' Of American...</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>It's Been A Long, Crazy Year Since Britain's S...</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>First Penis Transplants In U.S. Planned For Wo...</td>\n",
" <td>3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>U.S.-Backed Forces Prepare For ISIS To Use Che...</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>The European Migrant Crisis Is A Nightmare. Cl...</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>A Bunch Of Strange Things Just Went Down At NB...</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>Minor Explosion Rattles IMF Headquarters In Pa...</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>Shalane Flanagan Becomes First U.S. Woman To W...</td>\n",
" <td>1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>10 Instagrams To Celebrate Crown Prince Hussei...</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Description Class Index\n",
"0 Trump’s Saudi Trip Should Be About Ending The ... 0\n",
"1 Russia Vows To Expand 'Black List' Of American... 0\n",
"2 It's Been A Long, Crazy Year Since Britain's S... 0\n",
"3 First Penis Transplants In U.S. Planned For Wo... 3\n",
"4 U.S.-Backed Forces Prepare For ISIS To Use Che... 0\n",
"5 The European Migrant Crisis Is A Nightmare. Cl... 0\n",
"6 A Bunch Of Strange Things Just Went Down At NB... 1\n",
"7 Minor Explosion Rattles IMF Headquarters In Pa... 0\n",
"8 Shalane Flanagan Becomes First U.S. Woman To W... 1\n",
"9 10 Instagrams To Celebrate Crown Prince Hussei... 0"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"science_category['Description'] = science_category['headline'] + \"\\n\\n\" + science_category['short_description']\n",
"science_category['Class Index'] = 3\n",
"\n",
"business_category['Description'] = business_category['headline'] + \"\\n\\n\" + business_category['short_description']\n",
"business_category['Class Index'] = 2\n",
"\n",
"sports_category['Description'] = sports_category['headline'] + \"\\n\\n\" + sports_category['short_description']\n",
"sports_category['Class Index'] = 1\n",
"\n",
"world_category['Description'] = world_category['headline'] + \"\\n\\n\" + world_category['short_description']\n",
"world_category['Class Index'] = 0\n",
"\n",
"science_category = science_category[['Description', 'Class Index']]\n",
"business_category = business_category[['Description', 'Class Index']]\n",
"sports_category = sports_category[['Description', 'Class Index']]\n",
"world_category = world_category[['Description', 'Class Index']]\n",
"\n",
"test_data_df = pd.concat([science_category, business_category, sports_category, world_category], ignore_index=True)\n",
"# Shuffle the DataFrame\n",
"test_data_df = test_data_df.sample(frac=1, random_state=42).reset_index(drop=True)\n",
"\n",
"test_data_df.head(10)"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [],
"source": [
"test_data_df.to_csv(\"test_data.csv\", index=False)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"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": "3.12.1"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|