print ("Method = Linear SVM with doc2vec features")
np.random.seed(0)
class LabeledLineSentence(object):
def __init__(self, data ): self.data = data
def __iter__(self):
for uid, line in enumerate( self.data ): yield TaggedDocument( line.split(" ") , ["S_%s" % uid] )
model = Doc2Vec( alpha=0.025 , min_alpha=0.025 )
sentences = LabeledLineSentence( train_texts + test_texts )
model.build_vocab( sentences )
model.train( sentences )
for w in model.vocab.keys():
try: model[w] = embeddings[w]
except : continue
for epoch in range(10):
model.train(sentences)
model.alpha -= 0.002
model.min_alpha = model.alpha
train_rep = np.array( [ model.docvecs[i] for i in range( train_matrix.shape[0] ) ] )
test_rep = np.array( [ model.docvecs[i + train_matrix.shape[0]] for i in range( test_matrix.shape[0] ) ] )
model = LinearSVC( random_state=0 )
model.fit( train_rep , train_labels )
results = model.predict( test_rep )
print ("Accuracy = " + repr( sklearn.metrics.accuracy_score( test_labels , results ) ))
print (sklearn.metrics.classification_report( test_labels , results ))
