text_helper.py

import numpy as np

def input_generate_data(data, SEQ_LENGTH=SEQ_LENGTH, VOCAB_SIZE=VOCAB_SIZE, char_to_ix = char_to_ix):
    X = np.zeros((int(len(data)/SEQ_LENGTH), SEQ_LENGTH, VOCAB_SIZE))

    y = np.zeros((int(len(data)/SEQ_LENGTH), SEQ_LENGTH, VOCAB_SIZE))
    
    for i in range(0, int(len(data)/SEQ_LENGTH)):
        X_sequence = data[i*SEQ_LENGTH:(i+1)*SEQ_LENGTH]
        X_sequence_ix = [char_to_ix[value] for value in X_sequence]
        input_sequence = np.zeros((SEQ_LENGTH, VOCAB_SIZE))
        for j in range(SEQ_LENGTH):
            input_sequence[j][X_sequence_ix[j]] = 1.
        X[i] = input_sequence

        y_sequence = data[i*SEQ_LENGTH+1:(i+1)*SEQ_LENGTH+1]
        y_sequence_ix = [char_to_ix[value] for value in y_sequence]
        target_sequence = np.zeros((SEQ_LENGTH, VOCAB_SIZE))
        for j in range(SEQ_LENGTH):
            target_sequence[j][y_sequence_ix[j]] = 1.
        y[i] = target_sequence
        
    return X, y
  
def generate_text(model, length):
    ix = [np.random.randint(VOCAB_SIZE)]
    y_char = [ix_to_char[ix[-1]]]
    X = np.zeros((1, length, VOCAB_SIZE))
    for i in range(length):
        X[0, i, :][ix[-1]] = 1
        print(ix_to_char[ix[-1]], end="")
        ix = np.argmax(model.predict(X[:, :i+1, :])[0], 1)
        y_char.append(ix_to_char[ix[-1]])
    return ('').join(y_char)