Spaces:
Running
Running
File size: 19,435 Bytes
078c1e1 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 |
import numpy as np
import pandas as pd
import string
from unidecode import unidecode
from collections import Counter
class TextPreprocessor:
def __init__(self, remove_punct: bool = True, remove_digits: bool = True,
remove_stop_words: bool = True,
remove_short_words: bool = False, minlen: int = 1, maxlen: int = 1, top_p: float = None,
bottom_p: float = None):
self.remove_punct = remove_punct
self.remove_digits = remove_digits
self.remove_stop_words = remove_stop_words
self.remove_short_words = remove_short_words
self.minlen = minlen
self.maxlen = maxlen
self.top_p = top_p
self.bottom_p = bottom_p
self.words_to_remove = []
self.stop_words = ["'d", "a", "b", "c", "d", "e", "f", "g", "h", "i", "j", "k", "l", "m", "n", "o", "p", "q", "r", "s", "t", "u", "v", "w", "x", "y", "z",
'about',
'above',
'across',
'after',
'afterwards',
'again',
'against',
'ain',
'all',
'almost',
'alone',
'along',
'already',
'also',
'although',
'always',
'am',
'among',
'amongst',
'amount',
'an',
'and',
'another',
'any',
'anyhow',
'anyone',
'anything',
'anyway',
'anywhere',
'are',
'around',
'as',
'at',
'back',
'be',
'became',
'because',
'become',
'becomes',
'becoming',
'been',
'before',
'beforehand',
'behind',
'being',
'below',
'beside',
'besides',
'between',
'beyond',
'both',
'bottom',
'but',
'by',
'ca',
'call',
'can',
'cannot',
'could',
'couldn',
"couldn't",
'd',
'did',
'do',
'does',
'doing',
'done',
'down',
'due',
'during',
'each',
'eight',
'either',
'eleven',
'else',
'elsewhere',
'empty',
'enough',
'even',
'ever',
'every',
'everyone',
'everything',
'everywhere',
'except',
'few',
'fifteen',
'fifty',
'first',
'five',
'for',
'former',
'formerly',
'forty',
'four',
'from',
'front',
'full',
'further',
'get',
'give',
'go',
'had',
'has',
'have',
'having',
'he',
'hence',
'her',
'here',
'hereafter',
'hereby',
'herein',
'hereupon',
'hers',
'herself',
'him',
'himself',
'his',
'how',
'however',
'hundred',
'i',
'if',
'in',
'indeed',
'into',
'is',
'it',
"it's",
'its',
'itself',
'just',
'keep',
'last',
'latter',
'latterly',
'least',
'less',
'll',
'm',
'ma',
'made',
'make',
'many',
'say',
'said',
'says',
'told',
'tell',
'may',
'me',
'meanwhile',
'might',
'mine',
'more',
'moreover',
'most',
'mostly',
'move',
'much',
'must',
'my',
'myself',
'name',
'namely',
'neither',
'never',
'nevertheless',
'next',
'nine',
'no',
'nobody',
'none',
'noone',
'nor',
'not',
'nothing',
'now',
'nowhere',
'o',
'of',
'off',
'often',
'on',
'once',
'one',
'only',
'onto',
'or',
'other',
'others',
'otherwise',
'our',
'ours',
'ourselves',
'out',
'over',
'own',
'part',
'per',
'perhaps',
'please',
'put',
'quite',
'rather',
're',
'rs',
'really',
'regarding',
's',
'same',
'say',
'see',
'seem',
'seemed',
'seeming',
'seems',
'serious',
'several',
'shan',
"shan't",
'she',
"she's",
'should',
"should've",
'shouldn',
"shouldn't",
'show',
'side',
'since',
'six',
'sixty',
'so',
'some',
'somehow',
'someone',
'something',
'sometime',
'sometimes',
'somewhere',
'still',
'such',
't',
'take',
'ten',
'than',
'that',
"that'll",
'the',
'their',
'theirs',
'them',
'themselves',
'then',
'thence',
'there',
'thereafter',
'thereby',
'therefore',
'therein',
'thereupon',
'these',
'they',
'third',
'this',
'those',
'though',
'three',
'through',
'throughout',
'thru',
'thus',
'to',
'together',
'too',
'top',
'toward',
'towards',
'twelve',
'twenty',
'two',
'under',
'unless',
'until',
'up',
'upon',
'us',
'used',
'using',
'various',
've',
'very',
'via',
'was',
'wasn',
"wasn't",
'we',
'well',
'were',
'weren',
"weren't",
'what',
'whatever',
'when',
'whence',
'whenever',
'where',
'whereafter',
'whereas',
'whereby',
'wherein',
'whereupon',
'wherever',
'whether',
'which',
'while',
'whither',
'who',
'whoever',
'whole',
'whom',
'whose',
'why',
'will',
'with',
'within',
'without',
'won',
"won't",
'would',
'wouldn',
"wouldn't",
'y',
'yet',
'you',
"you'd",
"you'll",
"you're",
"you've",
'your',
'yours',
'yourself',
'yourselves',
'‘d',
'‘ll',
'‘m',
'‘re',
'‘s',
'‘ve',
'’d',
'’ll',
'’m',
'’re',
'new',
'old',
'’s',
'’ve']
self.contraction_to_expansion = {"ain't": "am not",
"aren't": "are not",
"can't": "cannot",
"can't've": "cannot have",
"'cause": "because",
"could've": "could have",
"couldn't": "could not",
"couldn't've": "could not have",
"didn't": "did not",
"doesn't": "does not",
"don't": "do not",
"hadn't": "had not",
"hadn't've": "had not have",
"hasn't": "has not",
"haven't": "have not",
"he'd": "he would",
"he'd've": "he would have",
"he'll": "he will",
"he'll've": "he will have",
"he's": "he is",
"how'd": "how did",
"how'd'y": "how do you",
"how'll": "how will",
"how's": "how is",
"i'd": "i would",
"i'd've": "i would have",
"i'll": "i will",
"i'll've": "i will have",
"i'm": "i am",
"i've": "i have",
"isn't": "is not",
"it'd": "it had",
"it'd've": "it would have",
"it'll": "it will",
"it'll've": "it will have",
"it's": "it is",
"let's": "let us",
"ma'am": "madam",
"mayn't": "may not",
"might've": "might have",
"mightn't": "might not",
"mightn't've": "might not have",
"must've": "must have",
"mustn't": "must not",
"mustn't've": "must not have",
"needn't": "need not",
"needn't've": "need not have",
"o'clock": "of the clock",
"oughtn't": "ought not",
"oughtn't've": "ought not have",
"shan't": "shall not",
"sha'n't": "shall not",
"shan't've": "shall not have",
"she'd": "she would",
"she'd've": "she would have",
"she'll": "she will",
"she'll've": "she will have",
"she's": "she is",
"should've": "should have",
"shouldn't": "should not",
"shouldn't've": "should not have",
"so've": "so have",
"so's": "so is",
"that'd": "that would",
"that'd've": "that would have",
"that's": "that is",
"there'd": "there had",
"there'd've": "there would have",
"there's": "there is",
"they'd": "they would",
"they'd've": "they would have",
"they'll": "they will",
"they'll've": "they will have",
"they're": "they are",
"they've": "they have",
"to've": "to have",
"wasn't": "was not",
"we'd": "we had",
"we'd've": "we would have",
"we'll": "we will",
"we'll've": "we will have",
"we're": "we are",
"we've": "we have",
"weren't": "were not",
"what'll": "what will",
"what'll've": "what will have",
"what're": "what are",
"what's": "what is",
"what've": "what have",
"when's": "when is",
"when've": "when have",
"where'd": "where did",
"where's": "where is",
"where've": "where have",
"who'll": "who will",
"who'll've": "who will have",
"who's": "who is",
"who've": "who have",
"why's": "why is",
"why've": "why have",
"will've": "will have",
"won't": "will not",
"won't've": "will not have",
"would've": "would have",
"wouldn't": "would not",
"wouldn't've": "would not have",
"y'all": "you all",
"y'alls": "you alls",
"y'all'd": "you all would",
"y'all'd've": "you all would have",
"y'all're": "you all are",
"y'all've": "you all have",
"you'd": "you had",
"you'd've": "you would have",
"you'll": "you you will",
"you'll've": "you you will have",
"you're": "you are",
"you've": "you have"
}
@staticmethod
def __remove_double_whitespaces(string: str):
return " ".join(string.split())
def __remove_url(self, string_series: pd.Series):
"""
Removes URLs m text
:param string_series: pd.Series, input string series
:return: pd.Series, cleaned string series
"""
clean_string_series = string_series.str.replace(
pat=r"(https?:\/\/(?:www\.|(?!www))[a-zA-Z0-9][a-zA-Z0-9-]+[a-zA-Z0-9]\.[^\s]{2,}|www\.[a-zA-Z0-9][a-zA-Z0-9-]+[a-zA-Z0-9]\.[^\s]{2,}|https?:\/\/(?:www\.|(?!www))[a-zA-Z0-9]+\.[^\s]{2,}|www\.[a-zA-Z0-9]+\.[^\s]{2,})",
repl=" ", regex=True).copy()
return clean_string_series.map(self.__remove_double_whitespaces)
def __expand(self, string_series: pd.Series):
"""
Replaces contractions with expansions. eg. don't wit do not.
:param string_series: pd.Series, input string series
:return: pd.Series, cleaned string series
"""
clean_string_series = string_series.copy()
for c, e in self.contraction_to_expansion.items():
clean_string_series = clean_string_series.str.replace(pat=c, repl=e, regex=False).copy()
return clean_string_series.map(self.__remove_double_whitespaces)
def __remove_punct(self, string_series: pd.Series):
"""
Removes punctuations from the input string.
:param string_series: pd.Series, input string series
:return: pd.Series, cleaned string series
"""
clean_string_series = string_series.copy()
puncts = [r'\n', r'\r', r'\t']
puncts.extend(list(string.punctuation))
for i in puncts:
clean_string_series = clean_string_series.str.replace(pat=i, repl=" ", regex=False).copy()
return clean_string_series.map(self.__remove_double_whitespaces)
def __remove_digits(self, string_series: pd.Series):
"""
Removes digits from the input string.
:param string_series: pd.Series, input string series
:return: pd.Series, cleaned string series
"""
clean_string_series = string_series.str.replace(pat=r'\d', repl=" ", regex=True).copy()
return clean_string_series.map(self.__remove_double_whitespaces)
@staticmethod
def __remove_short_words(string_series: pd.Series, minlen: int = 1, maxlen: int = 1):
"""
Reomves words/tokens where minlen <= len <= maxlen.
:param string_series: pd.Series, input string series
:param minlen: int, minimum length of token to be removed.
:param maxlen: int, maximum length of token to be removed.
:return: pd.Series, cleaned string series
"""
clean_string_series = string_series.map(lambda string: " ".join([word for word in string.split() if
(len(word) > maxlen) or (len(word) < minlen)]))
return clean_string_series
def __remove_stop_words(self, string_series: pd.Series):
"""
Removes stop words from the input string.
:param string_series: pd.Series, input string series
:return: pd.Series, cleaned string series
"""
def str_remove_stop_words(string: str):
stops = self.stop_words
return " ".join([token for token in string.split() if token not in stops])
return string_series.map(str_remove_stop_words)
def __remove_top_bottom_words(self, string_series: pd.Series, top_p: int = None,
bottom_p: int = None, dataset: str = 'train'):
"""
Reomoves top_p percent (frequent) words and bottom_p percent (rare) words.
:param string_series: pd.Series, input string series
:param top_p: float, percent of frequent words to remove.
:param bottom_p: float, percent of rare words to remove.
:param dataset: str, "train" for training set, "tesrt" for val/dev/test set.
:return: pd.Series, cleaned string series
"""
if dataset == 'train':
if top_p is None:
top_p = 0
if bottom_p is None:
bottom_p = 0
if top_p > 0 or bottom_p > 0:
word_freq = pd.Series(" ".join(string_series).split()).value_counts()
n_words = len(word_freq)
if top_p > 0:
self.words_to_remove.extend([*word_freq.index[: int(np.ceil(top_p * n_words))]])
if bottom_p > 0:
self.words_to_remove.extend([*word_freq.index[-int(np.ceil(bottom_p * n_words)):]])
if len(self.words_to_remove) == 0:
return string_series
else:
clean_string_series = string_series.map(lambda string: " ".join([word for word in string.split()
if word not in self.words_to_remove]))
return clean_string_series
def preprocess(self, string_series: pd.Series, dataset: str = "train"):
"""
Entry point.
:param string_series: pd.Series, input string series
:param dataset: str, "train" for training set, "tesrt" for val/dev/test set.
:return: pd.Series, cleaned string series
"""
string_series = string_series.str.lower().copy()
string_series = string_series.map(unidecode).copy()
string_series = self.__remove_url(string_series=string_series)
string_series = self.__expand(string_series=string_series)
if self.remove_punct:
string_series = self.__remove_punct(string_series=string_series)
if self.remove_digits:
string_series = self.__remove_digits(string_series=string_series)
if self.remove_stop_words:
string_series = self.__remove_stop_words(string_series=string_series)
if self.remove_short_words:
string_series = self.__remove_short_words(string_series=string_series,
minlen=self.minlen,
maxlen=self.maxlen)
string_series = self.__remove_top_bottom_words(string_series=string_series,
top_p=self.top_p,
bottom_p=self.bottom_p, dataset=dataset)
string_series = string_series.str.strip().copy()
string_series.replace(to_replace="", value="this is an empty message", inplace=True)
return string_series
def get_frequent_words_html(df):
text_preprocess = TextPreprocessor()
preprocessed_txt = text_preprocess.preprocess(df['title'] + ' ' + df['description'])
counter = Counter(' '.join([*preprocessed_txt]).split())
freq_tokens_html = '<div class="word-cloud-container">'
n = 1
for i, j in counter.most_common(25):
freq_tokens_html += f'<a class="wc-tokens" onclick=wc_search("{i}")>{i}</a>{" " * np.random.randint(3, 7, 1)[0]}'
if n == 5:
freq_tokens_html += '<div class="word-cloud-section" id="word-cloud-section-id">'
n += 1
freq_tokens_html += '</div></div>'
return freq_tokens_html |