File size: 9,680 Bytes
8821593
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
import re
from bs4 import BeautifulSoup
import distance
from fuzzywuzzy import fuzz
import pickle
import numpy as np

cv = pickle.load(open('cv.pkl','rb'))


def test_common_words(q1,q2):
    w1 = set(map(lambda word: word.lower().strip(), q1.split(" ")))
    w2 = set(map(lambda word: word.lower().strip(), q2.split(" ")))
    return len(w1 & w2)

def test_total_words(q1,q2):
    w1 = set(map(lambda word: word.lower().strip(), q1.split(" ")))
    w2 = set(map(lambda word: word.lower().strip(), q2.split(" ")))
    return (len(w1) + len(w2))


def test_fetch_token_features(q1, q2):
    SAFE_DIV = 0.0001

    STOP_WORDS = pickle.load(open('stopwords.pkl','rb'))

    token_features = [0.0] * 8

    # Converting the Sentence into Tokens:
    q1_tokens = q1.split()
    q2_tokens = q2.split()

    if len(q1_tokens) == 0 or len(q2_tokens) == 0:
        return token_features

    # Get the non-stopwords in Questions
    q1_words = set([word for word in q1_tokens if word not in STOP_WORDS])
    q2_words = set([word for word in q2_tokens if word not in STOP_WORDS])

    # Get the stopwords in Questions
    q1_stops = set([word for word in q1_tokens if word in STOP_WORDS])
    q2_stops = set([word for word in q2_tokens if word in STOP_WORDS])

    # Get the common non-stopwords from Question pair
    common_word_count = len(q1_words.intersection(q2_words))

    # Get the common stopwords from Question pair
    common_stop_count = len(q1_stops.intersection(q2_stops))

    # Get the common Tokens from Question pair
    common_token_count = len(set(q1_tokens).intersection(set(q2_tokens)))

    token_features[0] = common_word_count / (min(len(q1_words), len(q2_words)) + SAFE_DIV)
    token_features[1] = common_word_count / (max(len(q1_words), len(q2_words)) + SAFE_DIV)
    token_features[2] = common_stop_count / (min(len(q1_stops), len(q2_stops)) + SAFE_DIV)
    token_features[3] = common_stop_count / (max(len(q1_stops), len(q2_stops)) + SAFE_DIV)
    token_features[4] = common_token_count / (min(len(q1_tokens), len(q2_tokens)) + SAFE_DIV)
    token_features[5] = common_token_count / (max(len(q1_tokens), len(q2_tokens)) + SAFE_DIV)

    # Last word of both question is same or not
    token_features[6] = int(q1_tokens[-1] == q2_tokens[-1])

    # First word of both question is same or not
    token_features[7] = int(q1_tokens[0] == q2_tokens[0])

    return token_features


def test_fetch_length_features(q1, q2):
    length_features = [0.0] * 3

    # Converting the Sentence into Tokens:
    q1_tokens = q1.split()
    q2_tokens = q2.split()

    if len(q1_tokens) == 0 or len(q2_tokens) == 0:
        return length_features

    # Absolute length features
    length_features[0] = abs(len(q1_tokens) - len(q2_tokens))

    # Average Token Length of both Questions
    length_features[1] = (len(q1_tokens) + len(q2_tokens)) / 2

    strs = list(distance.lcsubstrings(q1, q2))
    length_features[2] = len(strs[0]) / (min(len(q1), len(q2)) + 1)

    return length_features


def test_fetch_fuzzy_features(q1, q2):
    fuzzy_features = [0.0] * 4

    # fuzz_ratio
    fuzzy_features[0] = fuzz.QRatio(q1, q2)

    # fuzz_partial_ratio
    fuzzy_features[1] = fuzz.partial_ratio(q1, q2)

    # token_sort_ratio
    fuzzy_features[2] = fuzz.token_sort_ratio(q1, q2)

    # token_set_ratio
    fuzzy_features[3] = fuzz.token_set_ratio(q1, q2)

    return fuzzy_features


def preprocess(q):
    q = str(q).lower().strip()

    # Replace certain special characters with their string equivalents
    q = q.replace('%', ' percent')
    q = q.replace('$', ' dollar ')
    q = q.replace('₹', ' rupee ')
    q = q.replace('€', ' euro ')
    q = q.replace('@', ' at ')

    # The pattern '[math]' appears around 900 times in the whole dataset.
    q = q.replace('[math]', '')

    # Replacing some numbers with string equivalents (not perfect, can be done better to account for more cases)
    q = q.replace(',000,000,000 ', 'b ')
    q = q.replace(',000,000 ', 'm ')
    q = q.replace(',000 ', 'k ')
    q = re.sub(r'([0-9]+)000000000', r'\1b', q)
    q = re.sub(r'([0-9]+)000000', r'\1m', q)
    q = re.sub(r'([0-9]+)000', r'\1k', q)

    # Decontracting words
    # 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"
    }

    q_decontracted = []

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

        q_decontracted.append(word)

    q = ' '.join(q_decontracted)
    q = q.replace("'ve", " have")
    q = q.replace("n't", " not")
    q = q.replace("'re", " are")
    q = q.replace("'ll", " will")

    # Removing HTML tags
    q = BeautifulSoup(q)
    q = q.get_text()

    # Remove punctuations
    pattern = re.compile('\W')
    q = re.sub(pattern, ' ', q).strip()

    return q


def query_point_creator(q1, q2):
    input_query = []

    # preprocess
    q1 = preprocess(q1)
    q2 = preprocess(q2)

    # fetch basic features
    input_query.append(len(q1))
    input_query.append(len(q2))

    input_query.append(len(q1.split(" ")))
    input_query.append(len(q2.split(" ")))

    input_query.append(test_common_words(q1, q2))
    input_query.append(test_total_words(q1, q2))
    input_query.append(round(test_common_words(q1, q2) / test_total_words(q1, q2), 2))

    # fetch token features
    token_features = test_fetch_token_features(q1, q2)
    input_query.extend(token_features)

    # fetch length based features
    length_features = test_fetch_length_features(q1, q2)
    input_query.extend(length_features)

    # fetch fuzzy features
    fuzzy_features = test_fetch_fuzzy_features(q1, q2)
    input_query.extend(fuzzy_features)

    # bow feature for q1
    q1_bow = cv.transform([q1]).toarray()

    # bow feature for q2
    q2_bow = cv.transform([q2]).toarray()

    return np.hstack((np.array(input_query).reshape(1, 22), q1_bow, q2_bow))