gistfile1.py

#initialize glove embeddings
TEXT.build_vocab(train_data,min_freq=3,vectors = "glove.6B.100d")  
LABEL.build_vocab(train_data)

#No. of unique tokens in text
print("Size of TEXT vocabulary:",len(TEXT.vocab))

#No. of unique tokens in label
print("Size of LABEL vocabulary:",len(LABEL.vocab))

#Commonly used words
print(TEXT.vocab.freqs.most_common(10))  

#Word dictionary
print(TEXT.vocab.stoi)