-
Notifications
You must be signed in to change notification settings - Fork 1
/
toxic-comment-lr-v1.py
64 lines (50 loc) · 2.09 KB
/
toxic-comment-lr-v1.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
# The script is modified from
# https://www.kaggle.com/tunguz/logistic-regression-with-words-and-char-n-grams
import numpy as np
import pandas as pd
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import cross_val_score
from scipy.sparse import hstack
class_names = ['toxic', 'severe_toxic', 'obscene', 'threat', 'insult', 'identity_hate']
train = pd.read_csv('train.csv').fillna(' ')
test = pd.read_csv('test.csv').fillna(' ')
train_text = train['comment_text']
test_text = test['comment_text']
all_text = pd.concat([train_text, test_text])
word_vectorizer = TfidfVectorizer(
sublinear_tf=True,
strip_accents='unicode',
analyzer='word',
token_pattern=r'\w{1,}',
stop_words='english',
ngram_range=(1, 1),
max_features=10000)
word_vectorizer.fit(all_text)
train_word_features = word_vectorizer.transform(train_text)
test_word_features = word_vectorizer.transform(test_text)
char_vectorizer = TfidfVectorizer(
sublinear_tf=True,
strip_accents='unicode',
analyzer='char',
stop_words='english',
ngram_range=(2, 6),
max_features=50000)
char_vectorizer.fit(all_text)
train_char_features = char_vectorizer.transform(train_text)
test_char_features = char_vectorizer.transform(test_text)
train_features = hstack([train_char_features, train_word_features])
test_features = hstack([test_char_features, test_word_features])
scores = []
submission = pd.DataFrame.from_dict({'id': test['id']})
for class_name in class_names:
train_target = train[class_name]
classifier = LogisticRegression(solver='sag')
cv_score = np.mean(cross_val_score(classifier, train_features, train_target, cv=3, scoring='roc_auc'))
scores.append(cv_score)
print('CV score for class {} is {}'.format(class_name, cv_score))
classifier.fit(train_features, train_target)
submission[class_name] = classifier.predict_proba(test_features)[:, 1]
print('Total CV score is {}'.format(np.mean(scores)))
submission.to_csv('submission-lr-v1.csv', index=False)
print('save submission to submission-lr-v1.csv')