sentiment-analysis/module.py at main · menraromial/sentiment-analysis · GitHub

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
import re
import string


def cleaning(text):
    # converting to lowercase, removing URL links, special characters, punctuations...
    text = text.lower() # converting to lowercase
    text = re.sub('https?://\S+|www\.\S+', '', text) # removing URL links
    text = re.sub(r"\b\d+\b", "", text) # removing number
    text = re.sub('<.*?>+', '', text) # removing special characters,
    text = re.sub('[%s]' % re.escape(string.punctuation), '', text) # punctuations
    text = re.sub('\n', '', text)
    text = re.sub('[’“”…]', '', text)

    #removing emoji:
    emoji_pattern = re.compile("["
                           u"\U0001F600-\U0001F64F"  # emoticons
                           u"\U0001F300-\U0001F5FF"  # symbols & pictographs
                           u"\U0001F680-\U0001F6FF"  # transport & map symbols
                           u"\U0001F1E0-\U0001F1FF"  # flags (iOS)
                           u"\U00002702-\U000027B0"
                           u"\U000024C2-\U0001F251"
                           "]+", flags=re.UNICODE)
    text = emoji_pattern.sub(r'', text)

   # removing short form:

    text=re.sub("isn't",'is not',text)
    text=re.sub("he's",'he is',text)
    text=re.sub("wasn't",'was not',text)
    text=re.sub("there's",'there is',text)
    text=re.sub("couldn't",'could not',text)
    text=re.sub("won't",'will not',text)
    text=re.sub("they're",'they are',text)
    text=re.sub("she's",'she is',text)
    text=re.sub("There's",'there is',text)
    text=re.sub("wouldn't",'would not',text)
    text=re.sub("haven't",'have not',text)
    text=re.sub("That's",'That is',text)
    text=re.sub("you've",'you have',text)
    text=re.sub("He's",'He is',text)
    text=re.sub("what's",'what is',text)
    text=re.sub("weren't",'were not',text)
    text=re.sub("we're",'we are',text)
    text=re.sub("hasn't",'has not',text)
    text=re.sub("you'd",'you would',text)
    text=re.sub("shouldn't",'should not',text)
    text=re.sub("let's",'let us',text)
    text=re.sub("they've",'they have',text)
    text=re.sub("You'll",'You will',text)
    text=re.sub("i'm",'i am',text)
    text=re.sub("we've",'we have',text)
    text=re.sub("it's",'it is',text)
    text=re.sub("don't",'do not',text)
    text=re.sub("that´s",'that is',text)
    text=re.sub("I´m",'I am',text)
    text=re.sub("it’s",'it is',text)
    text=re.sub("she´s",'she is',text)
    text=re.sub("he’s'",'he is',text)
    text=re.sub('I’m','I am',text)
    text=re.sub('I’d','I did',text)
    text=re.sub("he’s'",'he is',text)
    text=re.sub('there’s','there is',text)

    # removing frequent word :
    text = re.sub('movie', '',text)
    text = re.sub('film', '',text)
    text = re.sub('one', '',text)
    text = re.sub('like', '',text)
    text = re.sub('even', '',text)
    text = re.sub('would', '',text)
    text = re.sub('time', '',text)
    text = re.sub('really', '',text)
    text = re.sub('story', '',text)


    return text