Quotes_input_LSTM.py

window = 5 # max_seq_length
sequences, next_words = [], []
for quote in quotes:
    words = quote.split(' ')
    for i in range(0,len(words) - window + 1):
        sequences.append(words[i:i+window])
        if (i + window) < len(words):
            next_words.append(words[i+window])
        else:
            next_words.append(';')
            
 tot_seq = len(next_words)

X = np.zeros((tot_seq, window, num_dim))
Y = np.zeros((tot_seq,vocab_len))
for i,seq in enumerate(sequences):
    for j,word in enumerate(seq):
        num_id = word_to_int[word]
        X[i][j] = np.squeeze(emb[num_id])
    num_id = word_to_int[next_words[i]]
    Y[i][num_id] = 1