|
|
|
|
|
|
|
import numpy as np |
|
import re |
|
import string |
|
|
|
|
|
|
|
stopwords= set(['br', 'the', 'i', 'me', 'my', 'myself', 'we', 'our', 'ours', 'ourselves', 'you', "you're", "you've",\ |
|
"you'll", "you'd", 'your', 'yours', 'yourself', 'yourselves', 'he', 'him', 'his', 'himself', \ |
|
'she', "she's", 'her', 'hers', 'herself', 'it', "it's", 'its', 'itself', 'they', 'them', 'their',\ |
|
'theirs', 'themselves', 'what', 'which', 'who', 'whom', 'this', 'that', "that'll", 'these', 'those', \ |
|
'am', 'is', 'are', 'was', 'were', 'be', 'been', 'being', 'have', 'has', 'had', 'having', 'do', 'does', \ |
|
'did', 'doing', 'a', 'an', 'the', 'and', 'but', 'if', 'or', 'because', 'as', 'until', 'while', 'of', \ |
|
'at', 'by', 'for', 'with', 'about', 'against', 'between', 'into', 'through', 'during', 'before', 'after',\ |
|
'above', 'below', 'to', 'from', 'up', 'down', 'in', 'out', 'on', 'off', 'over', 'under', 'again', 'further',\ |
|
'then', 'once', 'here', 'there', 'when', 'where', 'why', 'how', 'all', 'any', 'both', 'each', 'few', 'more',\ |
|
'most', 'other', 'some', 'such', 'only', 'own', 'same', 'so', 'than', 'too', 'very', \ |
|
's', 't', 'can', 'will', 'just', 'don', "don't", 'should', "should've", 'now', 'd', 'll', 'm', 'o', 're', \ |
|
've', 'y', 'ain', 'aren', "aren't", 'couldn', "couldn't", 'didn', "didn't", 'doesn', "doesn't", 'hadn',\ |
|
"hadn't", 'hasn', "hasn't", 'haven', "haven't", 'isn', "isn't", 'ma', 'mightn', "mightn't", 'mustn',\ |
|
"mustn't", 'needn', "needn't", 'shan', "shan't", 'shouldn', "shouldn't", 'wasn', "wasn't", 'weren', "weren't", \ |
|
'won', "won't", 'wouldn', "wouldn't"]) |
|
|
|
def decontracted(phrase): |
|
|
|
phrase = re.sub(r"won't", "will not", phrase) |
|
phrase = re.sub(r"can\'t", "can not", phrase) |
|
|
|
|
|
phrase = re.sub(r"n\'t", " not", phrase) |
|
phrase = re.sub(r"\'re", " are", phrase) |
|
phrase = re.sub(r"\'s", " is", phrase) |
|
phrase = re.sub(r"\'d", " would", phrase) |
|
phrase = re.sub(r"\'ll", " will", phrase) |
|
phrase = re.sub(r"\'t", " not", phrase) |
|
phrase = re.sub(r"\'ve", " have", phrase) |
|
phrase = re.sub(r"\'m", " am", phrase) |
|
return phrase |
|
|
|
|
|
def preprocess_text(text): |
|
text = text.lower() |
|
text = re.sub(r"\n", " ", text) |
|
text = re.sub(r"\d", " ", text) |
|
text = re.sub(r"<.*?>+", "", text) |
|
text = re.sub("\[.*?\]", "", text) |
|
text = re.sub("https?://S+|www.\.\S+", "", text) |
|
text = text.translate(str.maketrans("", "", string.punctuation)) |
|
text = re.sub(r'xx', '', text) |
|
text = decontracted(text) |
|
words = text.split() |
|
words = [word for word in words if not word in stopwords] |
|
words = [re.sub(r"(.)\1{1,}", r"\1\1", word) for word in words] |
|
words = [word.strip() for word in words if len(word.strip()) > 1] |
|
text = " ".join(words) |
|
return text |
|
|
|
|