-
Notifications
You must be signed in to change notification settings - Fork 0
/
model.py
52 lines (43 loc) · 1.67 KB
/
model.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
from sklearn.naive_bayes import MultinomialNB
from sklearn.tree import DecisionTreeClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.feature_extraction.text import TfidfTransformer
from .preprocess import FeaturesTransformer
class NaiveBayesModel(object):
def __init__(self):
self.clf = self._init_pipeline()
@staticmethod
def _init_pipeline():
pipeline = Pipeline([
("features_transformer", FeaturesTransformer('vietnamese-stopwords/vietnamese-stopwords-dash.txt')),
('bow', CountVectorizer()),
('tfidf', TfidfTransformer()),
('clf', MultinomialNB())
])
return pipeline
class DecisionTreeModel(object):
def __init__(self):
self.clf = self._init_pipeline()
@staticmethod
def _init_pipeline():
pipeline = Pipeline([
("features_transformer", FeaturesTransformer('vietnamese-stopwords/vietnamese-stopwords-dash.txt')),
('bow', CountVectorizer()),
('tfidf', TfidfTransformer()),
('clf', DecisionTreeClassifier(max_features=10))
])
return pipeline
class LogisticRegressionModel(object):
def __init__(self):
self.clf = self._init_pipeline()
@staticmethod
def _init_pipeline():
pipeline = Pipeline([
("features_transformer", FeaturesTransformer('vietnamese-stopwords/vietnamese-stopwords-dash.txt')),
('bow', CountVectorizer()),
('tfidf', TfidfTransformer()),
('clf', LogisticRegression())
])
return pipeline