/
classifiers.py
73 lines (63 loc) · 2.85 KB
/
classifiers.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
__author__ = 'NLP-PC'
from sklearn.naive_bayes import MultinomialNB
from save_data import dump_picle
from load_data import load_pickle, load_train_data
import logging
from sklearn import svm
from sklearn import linear_model
from sklearn.neighbors import KNeighborsClassifier
from logger_manager import log_state
from sklearn.naive_bayes import GaussianNB
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
def mNB(train_data, train_labels, test, save_result=False):
log_state('Use multinomial Naive bayes classifier')
clf = MultinomialNB()
clf.fit(train_data, train_labels)
predict_labels = clf.predict(test)
predict_proba = clf.predict_proba(test)
if save_result == True:
dump_picle(predict_labels, './data/predict_labels/predict_labels.p')
dump_picle(predict_proba, './data/predict_labels/predict_proba.p')
logger.info('Classifier training complete, saved predict labels to pickle')
return predict_labels
def gNB(train_data, train_labels, test, save_result=False):
log_state('Use Gaussian Naive Bayes classifier')
clf = GaussianNB()
clf.fit(train_data, train_labels)
predict_labels = clf.predict(test)
predict_proba = clf.predict_proba(test)
if save_result == True:
dump_picle(predict_labels, './data/predict_labels/predict_labels.p')
dump_picle(predict_proba, './data/predict_labels/predict_proba.p')
logger.info('Classifier training complete, saved predict labels to pickle')
return predict_labels
def svm_classify(train_data, train_labels, test):
log_state('Use SVM classifier')
clf = svm.SVC(C=5.0, kernel='linear')
clf.fit(train_data, train_labels)
predict_labels = clf.predict(test)
dump_picle(predict_labels, './data/predict_labels/predict_labels.p')
logger.info('SVM classifier training complete, saved predict labels to pickle')
return
def logit(train_data, train_labels, test):
log_state('Use logistic regression classifier')
clf = linear_model.LogisticRegression(C=1e5)
clf.fit(train_data, train_labels)
predict_labels = clf.predict(test)
dump_picle(predict_labels, './data/predict_labels/predict_labels.p')
logger.info('MaxEnt classifier training complete, saved predict labels to pickle')
return
def kNN(train_data, train_labels, test):
log_state('Use kNN classifier')
clf = KNeighborsClassifier(n_neighbors=5)
clf.fit(train_data, train_labels)
predict_labels = clf.predict(test)
dump_picle(predict_labels, './data/predict_labels/predict_labels.p')
logger.info('kNN classifier training complete, saved predict labels to pickle')
return
if __name__ == "__main__":
train_data = load_pickle('./data/transformed_data/transformed_train.p')
test = load_pickle('./data/transformed_data/transformed_test.p')
_, train_labels = load_train_data()
mNB(train_data, train_labels, test)