-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathgenerate_dataset.py
173 lines (124 loc) · 6.77 KB
/
generate_dataset.py
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
contraction_mapping = {"ain't": "is not", "aren't": "are not", "can't": "cannot", "'cause": "because",
"could've": "could have", "couldn't": "could not",
"didn't": "did not", "doesn't": "does not", "don't": "do not", "hadn't": "had not",
"hasn't": "has not", "haven't": "have not",
"he'd": "he would", "he'll": "he will", "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", "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",
"this's": "this is", "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", "here's": "here 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"}
import numpy as np
import pandas as pd
import re
from bs4 import BeautifulSoup
from nltk.corpus import stopwords
data = pd.read_csv("Data/AmazonReviews/Reviews.csv")
data.drop_duplicates(subset=['Text'], inplace=True) # dropping duplicates
data.dropna(axis=0, inplace=True) # dropping na
print(data['Text'][:10])
print(data.info())
stop_words = set(stopwords.words('english'))
def text_cleaner(text, num):
newString = text.lower()
newString = BeautifulSoup(newString, "lxml").text
newString = re.sub(r'\([^)]*\)', '', newString)
newString = re.sub('"', '', newString)
newString = ' '.join([contraction_mapping[t] if t in contraction_mapping else t for t in newString.split(" ")])
newString = re.sub(r"'s\b", "", newString)
newString = re.sub("[^a-zA-Z]", " ", newString)
newString = re.sub('[m]{2,}', 'mm', newString)
if (num == 0):
tokens = [w for w in newString.split() if not w in stop_words]
else:
tokens = newString.split()
long_words = []
for i in tokens:
if len(i) > 1: # removing short word
long_words.append(i)
return (" ".join(long_words)).strip()
# call the function
cleaned_text = []
for t in data['Text']:
cleaned_text.append(text_cleaner(t, 0))
print(cleaned_text[:5])
# call the function
cleaned_summary = []
for t in data['Summary']:
cleaned_summary.append(text_cleaner(t, 1))
print(cleaned_summary[:10])
data['cleaned_text'] = cleaned_text
data['cleaned_summary'] = cleaned_summary
data.replace('', np.nan, inplace=True)
data.dropna(axis=0, inplace=True)
import matplotlib.pyplot as plt
text_word_count = []
summary_word_count = []
# populate the lists with sentence lengths
for i in data['cleaned_text']:
text_word_count.append(len(i.split()))
for i in data['cleaned_summary']:
summary_word_count.append(len(i.split()))
length_df = pd.DataFrame({'text': text_word_count, 'summary': summary_word_count})
length_df.hist(bins=30)
plt.show()
cnt = 0
for i in data['cleaned_summary']:
if (len(i.split()) <= 8):
cnt = cnt + 1
print("Proportion of the length of summaries below 8: ", cnt / len(data['cleaned_summary']))
cnt = 0
for i in data['cleaned_text']:
if (len(i.split()) <= 30):
cnt = cnt + 1
print("Proportion of the length of reviews below 30: ", cnt / len(data['cleaned_text']))
max_text_len = 30
max_summary_len = 8
cleaned_text = np.array(data['cleaned_text'])
cleaned_summary = np.array(data['cleaned_summary'])
short_text = []
short_summary = []
for i in range(len(cleaned_text)):
if (len(cleaned_summary[i].split()) <= max_summary_len and len(cleaned_text[i].split()) <= max_text_len):
short_text.append(cleaned_text[i])
short_summary.append(cleaned_summary[i])
df = pd.DataFrame({'text': short_text, 'summary': short_summary})
df['summary'] = df['summary'].apply(lambda x: 'sostok ' + x + ' eostok')
from pickle import dump, load
dump(df.head(80000), open('dataset_df.pkl', 'wb'))
print("Successfully saved pre-processed dataset.")