File size: 5,018 Bytes
407b426
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
"""
This file contains functions for text preprocessing
"""

import re


def decontracting_words(sentence):
    """
    Decontracting words (e.g. I'm -> I am, I've -> I have, etc.)
    https://en.wikipedia.org/wiki/Wikipedia%3aList_of_English_contractions
    https://stackoverflow.com/a/19794953
    """
    contractions = {
        "ain't": "am not",
        "aren't": "are not",
        "can't": "can not",
        "can't've": "can not 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 would",
        "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 as",
        "that'd": "that would",
        "that'd've": "that would have",
        "that's": "that is",
        "there'd": "there would",
        "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 would",
        "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'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 would",
        "you'd've": "you would have",
        "you'll": "you will",
        "you'll've": "you will have",
        "you're": "you are",
        "you've": "you have"
    }

    sentence_decontracted = []

    for word in sentence.split():
        if word in contractions:
            word = contractions[word]

        sentence_decontracted.append(word)

    sentence = ' '.join(sentence_decontracted)
    sentence = sentence.replace("'ve", " have")
    sentence = sentence.replace("n't", " not")
    sentence = sentence.replace("'re", " are")
    sentence = sentence.replace("'ll", " will")
    sentence = sentence.replace("'d", " would")
    sentence = sentence.replace("'s", " is")
    sentence = sentence.replace("'m", " am")

    return sentence



def space_punc(line):
    """
    Add a space before and after a punctuation mark
    and remove more than one space
    print(space_punc('bla. bla? "bla"bla.bla! bla...'))
    >> bla . bla ? " bla " bla . bla ! bla . . .
    """

    line = re.sub('([.,:;\-।!?"()\'])', r" \1 ", line)
    line = re.sub("\s{2,}", " ", line)
    return line