def train(data=SST_KAGGLE, alg='log'):
_, train_y, _ = vectorize_text(data=data)
train_x, test_x = read_doc2vec_pickle(dm=False)
# train_x_1, test_x_1 = senti_lexicon_vectorizor(data=data, tfidf=True)
# train_x_2, test_x_2 = senti_wordnet_vectorizer(data=data, tfidf=True)
#
# train_x = sparse.hstack((train_x_1, train_x_2))
# test_x = sparse.hstack((test_x_1, test_x_2))
print "shape for training data is", train_x.shape
if alg == 'svm':
clf = SVC(verbose=1)
elif alg == 'log':
clf = LogisticRegression(verbose=1) # 61.756, no phrase,
elif alg == 'nb':
clf = MultinomialNB()
else:
raise NotImplementedError
print "training..."
clf.fit(train_x, train_y)
predicted = clf.predict(test_x)
save_csv(predicted)
def doc2vec_kaggle_dataset():
train_x, test_x = read_doc2vec_pickle(dm=True, concat=False)
_, train_y, _ = read_sst_kaggle_pickle()
return train_x, train_y, test_x
