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()) async 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) async 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) async 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) async 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 async 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 async 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) async 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 async 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.map(lambda x: x.split("Highlights:")[0]) string_series = string_series.str.replace("
", " ") string_series = string_series.str.lower().copy() string_series = string_series.map(unidecode).copy() string_series = await self.__remove_url(string_series=string_series) string_series = await self.__expand(string_series=string_series) if self.remove_punct: string_series = await self.__remove_punct(string_series=string_series) if self.remove_digits: string_series = await self.__remove_digits(string_series=string_series) if self.remove_stop_words: string_series = await self.__remove_stop_words(string_series=string_series) if self.remove_short_words: string_series = await self.__remove_short_words(string_series=string_series, minlen=self.minlen, maxlen=self.maxlen) string_series = await 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 async def get_frequent_words_html(df): text_preprocess = TextPreprocessor() preprocessed_txt = await text_preprocess.preprocess(df['title'] + ' ' + df['description']) counter = Counter(' '.join([*preprocessed_txt]).split()) freq_tokens_html = '
' n = 1 for i, j in counter.most_common(25): freq_tokens_html += f'{i}{" " * np.random.randint(3, 7, 1)[0]}' if n == 5: freq_tokens_html += '
' n += 1 freq_tokens_html += '
' return freq_tokens_html