encode_corpus

encode_corpus.py

    from keras.preprocessing.text import one_hot
    from keras.preprocessing.sequence import pad_sequences    
    
    def encode_corpus(self,data):
        encoded_docs = [one_hot(' '.join(d), self.vocab_length) for d in data]
        vocab_file = "vocab_mapping.txt"+version
        with open(vocab_file,'w') as f:
            for i in range(len(data)):
                for j in range(len(data[i])):
                    ss = data[i][j]+" "+str(encoded_docs[i][j])+"\n"
                    f.write(ss)
        

        return pad_sequences(encoded_docs, maxlen=self.max_len, padding='post')