sklearnの分類ツールを比較

from sklearn.linear_model import LogisticRegression
from sklearn.naive_bayes import GaussianNB 
from sklearn.ensemble import RandomForestClassifier
from sklearn.svm import LinearSVC

train_X = bag.toarray()
train_y = pd.Series(train_df.label)

bag_dev, text_series = tp.get_vectorizer(dev_df.text, mode='dev')
dev_X = bag_dev.toarray()
dev_y = pd.Series(dev_df.label)

clf_list = [LogisticRegression(), GaussianNB(), RandomForestClassifier(), LinearSVC()]

for clf in clf_list:
    clf.fit(train_X, train_y)
    train_score = clf.score(train_X, train_y)
    dev_score = clf.score(dev_X, dev_y)
    print("{} --> train_socre={}, dev_score={}".format(
        clf.__class__.__name__, train_score, dev_score))