Spaces:
Build error
Build error
File size: 16,319 Bytes
dbb343d 9716e1f dbb343d b3ecaa7 dbb343d b3ecaa7 dbb343d b3ecaa7 dbb343d b3ecaa7 dbb343d 57b9989 dbb343d b3ecaa7 57b9989 dbb343d 57b9989 dbb343d b3ecaa7 dbb343d b3ecaa7 dbb343d b3ecaa7 dbb343d b3ecaa7 dbb343d b3ecaa7 dbb343d b3ecaa7 dbb343d b3ecaa7 dbb343d b3ecaa7 dbb343d b3ecaa7 dbb343d b3ecaa7 dbb343d b3ecaa7 dbb343d b3ecaa7 dbb343d b3ecaa7 dbb343d b3ecaa7 dbb343d b3ecaa7 dbb343d b3ecaa7 dbb343d b3ecaa7 dbb343d b3ecaa7 dbb343d b3ecaa7 dbb343d b3ecaa7 dbb343d b3ecaa7 dbb343d b3ecaa7 dbb343d b3ecaa7 dbb343d b3ecaa7 dbb343d b3ecaa7 dbb343d b3ecaa7 dbb343d 57b9989 b3ecaa7 57b9989 b3ecaa7 57b9989 b3ecaa7 57b9989 b3ecaa7 57b9989 dbb343d |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"%load_ext autoreload\n",
"%autoreload 2\n",
"\n",
"import sys\n",
"sys.path.append(\"..\")\n",
"from src.preprocessing import PreprocessingPipeline\n",
"import pandas as pd\n",
"import vaex"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"----\n",
"### Test vaex"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"df = pd.read_csv(\"../data/test_en.csv\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<table>\n",
"<thead>\n",
"<tr><th># </th><th>label </th><th>text </th></tr>\n",
"</thead>\n",
"<tbody>\n",
"<tr><td><i style='opacity: 0.6'>0</i> </td><td>0 </td><td>"I think it's time John Rambo move on with his l...</td></tr>\n",
"<tr><td><i style='opacity: 0.6'>1</i> </td><td>1 </td><td>"I've just watch 2 films of Pang brothers, The E...</td></tr>\n",
"<tr><td><i style='opacity: 0.6'>2</i> </td><td>1 </td><td>'Jewel Thief is *THE* crime thriller of Bollywoo...</td></tr>\n",
"<tr><td><i style='opacity: 0.6'>3</i> </td><td>0 </td><td>'This so called remake is terrible. I went to se...</td></tr>\n",
"<tr><td><i style='opacity: 0.6'>4</i> </td><td>1 </td><td>'When Northfork debuted at the Cannes Film Festi...</td></tr>\n",
"<tr><td>... </td><td>... </td><td>... </td></tr>\n",
"<tr><td><i style='opacity: 0.6'>4,995</i></td><td>0 </td><td>'The title tells it all -- Ed Gein, the butcher ...</td></tr>\n",
"<tr><td><i style='opacity: 0.6'>4,996</i></td><td>0 </td><td>"This film makes about as much sense as an 'Ozzi...</td></tr>\n",
"<tr><td><i style='opacity: 0.6'>4,997</i></td><td>0 </td><td>'"Sex and the City" has some great things going ...</td></tr>\n",
"<tr><td><i style='opacity: 0.6'>4,998</i></td><td>0 </td><td>'Please...if anybody gets the chance to read thi...</td></tr>\n",
"<tr><td><i style='opacity: 0.6'>4,999</i></td><td>0 </td><td>'...a film comes along that manages to be absolu...</td></tr>\n",
"</tbody>\n",
"</table>"
],
"text/plain": [
"# label text\n",
"0 0 \"I think it's time John Rambo move on with his l...\n",
"1 1 \"I've just watch 2 films of Pang brothers, The E...\n",
"2 1 'Jewel Thief is *THE* crime thriller of Bollywoo...\n",
"3 0 'This so called remake is terrible. I went to se...\n",
"4 1 'When Northfork debuted at the Cannes Film Festi...\n",
"... ... ...\n",
"4,995 0 'The title tells it all -- Ed Gein, the butcher ...\n",
"4,996 0 \"This film makes about as much sense as an 'Ozzi...\n",
"4,997 0 '\"Sex and the City\" has some great things going ...\n",
"4,998 0 'Please...if anybody gets the chance to read thi...\n",
"4,999 0 '...a film comes along that manages to be absolu..."
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"vaex.from_pandas(df)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"df_small = df.iloc[:1000]"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<table>\n",
"<thead>\n",
"<tr><th># </th><th>label </th><th>text </th></tr>\n",
"</thead>\n",
"<tbody>\n",
"<tr><td><i style='opacity: 0.6'>0</i> </td><td>0 </td><td>"I think it's time John Rambo move on with his l...</td></tr>\n",
"<tr><td><i style='opacity: 0.6'>1</i> </td><td>1 </td><td>"I've just watch 2 films of Pang brothers, The E...</td></tr>\n",
"<tr><td><i style='opacity: 0.6'>2</i> </td><td>1 </td><td>'Jewel Thief is *THE* crime thriller of Bollywoo...</td></tr>\n",
"<tr><td><i style='opacity: 0.6'>3</i> </td><td>0 </td><td>'This so called remake is terrible. I went to se...</td></tr>\n",
"<tr><td><i style='opacity: 0.6'>4</i> </td><td>1 </td><td>'When Northfork debuted at the Cannes Film Festi...</td></tr>\n",
"<tr><td>... </td><td>... </td><td>... </td></tr>\n",
"<tr><td><i style='opacity: 0.6'>995</i></td><td>1 </td><td>"It's a funny business, reviewing movies. These ...</td></tr>\n",
"<tr><td><i style='opacity: 0.6'>996</i></td><td>1 </td><td>'Right from the start you see that "Anchors Awei...</td></tr>\n",
"<tr><td><i style='opacity: 0.6'>997</i></td><td>0 </td><td>'I saw this movie in NEW York city. I was waitin...</td></tr>\n",
"<tr><td><i style='opacity: 0.6'>998</i></td><td>0 </td><td>'Firstly, this is NOT an adaptation of a Stephen...</td></tr>\n",
"<tr><td><i style='opacity: 0.6'>999</i></td><td>1 </td><td>"Barbra Streisand's debut television special is ...</td></tr>\n",
"</tbody>\n",
"</table>"
],
"text/plain": [
"# label text\n",
"0 0 \"I think it's time John Rambo move on with his l...\n",
"1 1 \"I've just watch 2 films of Pang brothers, The E...\n",
"2 1 'Jewel Thief is *THE* crime thriller of Bollywoo...\n",
"3 0 'This so called remake is terrible. I went to se...\n",
"4 1 'When Northfork debuted at the Cannes Film Festi...\n",
"... ... ...\n",
"995 1 \"It's a funny business, reviewing movies. These ...\n",
"996 1 'Right from the start you see that \"Anchors Awei...\n",
"997 0 'I saw this movie in NEW York city. I was waitin...\n",
"998 0 'Firstly, this is NOT an adaptation of a Stephen...\n",
"999 1 \"Barbra Streisand's debut television special is ..."
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"vaex.from_pandas(df_small)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"----"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"# df = pd.read_csv(\"../data/test_en.csv\")\n",
"df = pd.read_excel(\"../data/test_chinese.xlsx\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"pre_steps = [\n",
" \"normalize_unicode\",\n",
" \"normalize_acronyms\",\n",
" \"normalize_bullet_points\",\n",
" \"normalize_hyphenated_words\",\n",
" \"normalize_quotation_marks\",\n",
" \"normalize_whitespaces\",\n",
" \"normalize_repeating_words\",\n",
" \"normalize_repeating_chars\",\n",
" \"normalize_useless_spaces\",\n",
" # \"replace_currency_symbols\",\n",
" # \"replace_emails\",\n",
" # \"replace_emojis\",\n",
" # \"replace_hashtags\",\n",
" # \"replace_numbers\",\n",
" # \"replace_phone_numbers\",\n",
" # \"replace_urls\",\n",
" # \"replace_user_handles\",\n",
" # \"remove_accents\",\n",
" # \"remove_brackets\",\n",
" # \"remove_html_tags\",\n",
" # \"remove_non_words\",\n",
" # \"remove_punctuation\",\n",
" # \"lowercase\",\n",
" \"strip\",\n",
"]\n"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"post_steps = [\n",
" \"lowercase\",\n",
" # \"replace_currency_symbols\",\n",
" # \"replace_urls\",\n",
" # \"replace_emails\",\n",
" # \"replace_user_handles\",\n",
" # \"replace_hashtags\",\n",
" # \"replace_emojis\",\n",
" # \"replace_phone_numbers\",\n",
" # \"replace_numbers\",\n",
" # \"remove_html_tags\",\n",
" # \"remove_accents\",\n",
" # \"remove_brackets\",\n",
" \"remove_non_words\",\n",
" # \"remove_numbers\",\n",
" # \"remove_punctuation\",\n",
" \"normalize_repeating_words\",\n",
" \"normalize_repeating_chars\",\n",
" \"normalize_useless_spaces\",\n",
" \"strip\",\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"pipe = PreprocessingPipeline(\n",
" language=\"Chinese\",\n",
" lemmatization_step=\"Spacy lemmatizer (keep stopwords)\", # \"Disable lemmatizer\",\n",
" pre_steps=pre_steps,\n",
" post_steps=post_steps,\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'全金属 指纹识别 垃圾 买手机 不行 指纹识别 不好 太慢 好多 失败 电池 哥哥 一部 华为 mate7 手机 旅游 丢掉 我哥 算是 二手 二手手机 用个 两天 毛 手机 只能 大半天 玩 手机游戏 最多 看个 新闻 微信 不行 急 手机 买手机 谈谈 通话 想 问 一句 手机 通话 保证 畅通 手机 意义 一部 MP4 区别 第一次 通话 五分钟 声音 说 女朋友 手机 朋友 父母 打电话 情况 毛呢 所有人 手机 利用 全金属 吸引 眼球 做工 体验 不好 电池 耐用 通话 易 无声 加油 拿出 诚意'"
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.text[0]"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'全金属 指纹识别 垃圾 买手机 不行 指纹识别 不好 太慢 好多 失败 电池 哥哥 一部 华为 mate7 手机 旅游 丢掉 我哥 算是 二手 二手手机 用个 两天 毛 手机 只能 大半天 玩 手机游戏 最多 看个 新闻 微信 不行 急 手机 买手机 谈谈 通话 想 问 一句 手机 通话 保证 畅通 手机 意义 一部 MP4 区别 第一次 通话 五分钟 声音 说 女朋友 手机 朋友 父母 打电话 情况 毛呢 所有人 手机 利用 全金属 吸引 眼球 做工 体验 不好 电池 耐用 通话 易 无声 加油 拿出 诚意'"
]
},
"execution_count": 14,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pipe.pre(df.text[0])"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'全金属 指纹识别 垃圾 买手机 不行 指纹识别 不好 太慢 好多 失败 电池 哥哥 一部 华为 mate7 手机 旅游 丢掉 我哥 算是 二手 二手手机 用个 两天 毛 手机 只能 大半天 玩 手机游戏 最多 看个 新闻 微信 不行 急 手机 买手机 谈谈 通话 想 问 一句 手机 通话 保证 畅通 手机 意义 一部 MP4 区别 第一次 通话 五分钟 声音 说 女朋友 手机 朋友 父母 打电话 情况 毛呢 所有人 手机 利用 全金属 吸引 眼球 做工 体验 不好 电池 耐用 通话 易 无声 加油 拿出 诚意'"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pipe.lemma(pipe.nlp(pipe.pre(df.text[0])))"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'全金属 指纹识别 垃圾 买手机 不行 指纹识别 不好 太慢 好多 失败 电池 哥哥 一部 华为 mate 手机 旅游 丢掉 我哥 算是 二手 二手手机 用个 两天 毛 手机 只能 大半天 玩 手机游戏 最多 看个 新闻 微信 不行 急 手机 买手机 谈谈 通话 想 问 一句 手机 通话 保证 畅通 手机 意义 一部 mp 区别 第一次 通话 五分钟 声音 说 女朋友 手机 朋友 父母 打电话 情况 毛呢 所有人 手机 利用 全金属 吸引 眼球 做工 体验 不好 电池 耐用 通话 易 无声 加油 拿出 诚意'"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pipe.post(pipe.lemma(pipe.nlp(pipe.pre(df.text[0]))))"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Compose(<function strip at 0x7ff4894750e0>, <function normalize_useless_spaces at 0x7ff48946eef0>, <function normalize_repeating_chars at 0x7ff48946ef80>, <function normalize_repeating_words at 0x7ff4871a7170>, <function punctuation at 0x7ff48946e4d0>, <function remove_numbers at 0x7ff4894754d0>, <function lowercase at 0x7ff489475050>)"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"pipe.post"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"odf = pipe.vaex_process(df, \"text\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"odf"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"steps = list(PreprocessingPipeline.pipeline_components().keys())\n",
"default_pre_steps_idx = [steps.index(i) for i in pre_steps]\n",
"default_post_steps_idx = [steps.index(i) for i in post_steps]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"default_pre_steps_idx"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"default_post_steps_idx"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"sorted(list(PreprocessingPipeline.pipeline_components().keys()))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"list(PreprocessingPipeline.lemmatization_component().keys())"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import re"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"_re_non_words = re.compile(\"[^A-Za-z]+\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"_re_non_words.sub(\" \", \"Mimmo23\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"interpreter": {
"hash": "aa7efd0b3ada76bb0689aa8ed0b61d7de788847e3d11d2d142fc5800c765982f"
},
"kernelspec": {
"display_name": "Python 3.7.11 64-bit ('wordify': conda)",
"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": "3.7.11"
},
"orig_nbformat": 4
},
"nbformat": 4,
"nbformat_minor": 2
}
|