-
Notifications
You must be signed in to change notification settings - Fork 0
/
feature_engineering.py
122 lines (94 loc) · 5.47 KB
/
feature_engineering.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
"""
Detecting duplicate quora questions
feature engineering
@author: Abhishek Thakur
"""
import cPickle
import pandas as pd
import numpy as np
import gensim
from fuzzywuzzy import fuzz
from nltk.corpus import stopwords
from tqdm import tqdm
from scipy.stats import skew, kurtosis
from scipy.spatial.distance import cosine, cityblock, jaccard, canberra, euclidean, minkowski, braycurtis
from nltk import word_tokenize
stop_words = stopwords.words('english')
def wmd(s1, s2):
s1 = str(s1).lower().split()
s2 = str(s2).lower().split()
stop_words = stopwords.words('english')
s1 = [w for w in s1 if w not in stop_words]
s2 = [w for w in s2 if w not in stop_words]
return model.wmdistance(s1, s2)
def norm_wmd(s1, s2):
s1 = str(s1).lower().split()
s2 = str(s2).lower().split()
stop_words = stopwords.words('english')
s1 = [w for w in s1 if w not in stop_words]
s2 = [w for w in s2 if w not in stop_words]
return norm_model.wmdistance(s1, s2)
def sent2vec(s):
words = str(s).lower().decode('utf-8')
words = word_tokenize(words)
words = [w for w in words if not w in stop_words]
words = [w for w in words if w.isalpha()]
M = []
for w in words:
try:
M.append(model[w])
except:
continue
M = np.array(M)
v = M.sum(axis=0)
return v / np.sqrt((v ** 2).sum())
data = pd.read_csv('data/quora_duplicate_questions.tsv', sep='\t')
data = data.drop(['id', 'qid1', 'qid2'], axis=1)
data['len_q1'] = data.question1.apply(lambda x: len(str(x)))
data['len_q2'] = data.question2.apply(lambda x: len(str(x)))
data['diff_len'] = data.len_q1 - data.len_q2
data['len_char_q1'] = data.question1.apply(lambda x: len(''.join(set(str(x).replace(' ', '')))))
data['len_char_q2'] = data.question2.apply(lambda x: len(''.join(set(str(x).replace(' ', '')))))
data['len_word_q1'] = data.question1.apply(lambda x: len(str(x).split()))
data['len_word_q2'] = data.question2.apply(lambda x: len(str(x).split()))
data['common_words'] = data.apply(lambda x: len(set(str(x['question1']).lower().split()).intersection(set(str(x['question2']).lower().split()))), axis=1)
data['fuzz_qratio'] = data.apply(lambda x: fuzz.QRatio(str(x['question1']), str(x['question2'])), axis=1)
data['fuzz_WRatio'] = data.apply(lambda x: fuzz.WRatio(str(x['question1']), str(x['question2'])), axis=1)
data['fuzz_partial_ratio'] = data.apply(lambda x: fuzz.partial_ratio(str(x['question1']), str(x['question2'])), axis=1)
data['fuzz_partial_token_set_ratio'] = data.apply(lambda x: fuzz.partial_token_set_ratio(str(x['question1']), str(x['question2'])), axis=1)
data['fuzz_partial_token_sort_ratio'] = data.apply(lambda x: fuzz.partial_token_sort_ratio(str(x['question1']), str(x['question2'])), axis=1)
data['fuzz_token_set_ratio'] = data.apply(lambda x: fuzz.token_set_ratio(str(x['question1']), str(x['question2'])), axis=1)
data['fuzz_token_sort_ratio'] = data.apply(lambda x: fuzz.token_sort_ratio(str(x['question1']), str(x['question2'])), axis=1)
model = gensim.models.KeyedVectors.load_word2vec_format('data/GoogleNews-vectors-negative300.bin.gz', binary=True)
data['wmd'] = data.apply(lambda x: wmd(x['question1'], x['question2']), axis=1)
norm_model = gensim.models.KeyedVectors.load_word2vec_format('data/GoogleNews-vectors-negative300.bin.gz', binary=True)
norm_model.init_sims(replace=True)
data['norm_wmd'] = data.apply(lambda x: norm_wmd(x['question1'], x['question2']), axis=1)
question1_vectors = np.zeros((data.shape[0], 300))
error_count = 0
for i, q in tqdm(enumerate(data.question1.values)):
question1_vectors[i, :] = sent2vec(q)
question2_vectors = np.zeros((data.shape[0], 300))
for i, q in tqdm(enumerate(data.question2.values)):
question2_vectors[i, :] = sent2vec(q)
data['cosine_distance'] = [cosine(x, y) for (x, y) in zip(np.nan_to_num(question1_vectors),
np.nan_to_num(question2_vectors))]
data['cityblock_distance'] = [cityblock(x, y) for (x, y) in zip(np.nan_to_num(question1_vectors),
np.nan_to_num(question2_vectors))]
data['jaccard_distance'] = [jaccard(x, y) for (x, y) in zip(np.nan_to_num(question1_vectors),
np.nan_to_num(question2_vectors))]
data['canberra_distance'] = [canberra(x, y) for (x, y) in zip(np.nan_to_num(question1_vectors),
np.nan_to_num(question2_vectors))]
data['euclidean_distance'] = [euclidean(x, y) for (x, y) in zip(np.nan_to_num(question1_vectors),
np.nan_to_num(question2_vectors))]
data['minkowski_distance'] = [minkowski(x, y, 3) for (x, y) in zip(np.nan_to_num(question1_vectors),
np.nan_to_num(question2_vectors))]
data['braycurtis_distance'] = [braycurtis(x, y) for (x, y) in zip(np.nan_to_num(question1_vectors),
np.nan_to_num(question2_vectors))]
data['skew_q1vec'] = [skew(x) for x in np.nan_to_num(question1_vectors)]
data['skew_q2vec'] = [skew(x) for x in np.nan_to_num(question2_vectors)]
data['kur_q1vec'] = [kurtosis(x) for x in np.nan_to_num(question1_vectors)]
data['kur_q2vec'] = [kurtosis(x) for x in np.nan_to_num(question2_vectors)]
cPickle.dump(question1_vectors, open('data/q1_w2v.pkl', 'wb'), -1)
cPickle.dump(question2_vectors, open('data/q2_w2v.pkl', 'wb'), -1)
data.to_csv('data/quora_features.csv', index=False)