len(vectorizer.get_feature_names())
# In[375]:
max_epochs = 100
alpha = 0.025
model = Doc2Vec(alpha=alpha,
vector_size=20,
min_alpha=0.00025,
min_count=1,
dm=1,
epoch=max_epochs,
workers=multiprocessing.cpu_count())
model.build_vocab([x for x in tqdm_notebook(tagged_data)])
for epoch in tqdm_notebook(range(max_epochs)):
model.train(tagged_data,
total_examples=model.corpus_count,
epochs=model.iter)
# decrease the learning rate
model.alpha -= 0.0002
# fix the learning rate, no decay
model.min_alpha = model.alpha
model.save("d2v.model")
print("Model Saved")
# In[376]:
