code.py

from __future__ import print_function
from keras.models import Sequential
from keras.layers import Dense, Activation, Dropout
from keras.layers import LSTM
from keras.optimizers import RMSprop
from keras.utils.data_utils import get_file
import numpy as np
import random
import sys

path = get_file('nietzsche.txt', origin="https://s3.amazonaws.com/text-datasets/nietzsche.txt")
text = open(path).read().lower()
print('corpus length:', len(text))
chars = sorted(list(set(text)))
print('total chars:', len(chars))
char_indices = dict((c, i) for i, c in enumerate(chars))
indices_char = dict((i, c) for i, c in enumerate(chars))

maxlen = 40
step = 3
sentences = []
next_chars = []
for i in range(0, len(text) - maxlen, step):
    sentences.append(text[i: i + maxlen])
    next_chars.append(text[i + maxlen])
print('nb sequences:', len(sentences))


print('Vectorization...')
X = np.zeros((len(sentences), maxlen, len(chars)), dtype=np.bool)
Y= np.zeros((len(sentences), len(chars)), dtype=np.bool)
for i, sentence in enumerate(sentences):
    for t, char in enumerate(sentence):
        X[i, t, char_indices[char]] = 1
    Y[i, char_indices[next_chars[i]]] = 1


print('Build model...')
model = Sequential()
model.add(LSTM(128, input_shape=(maxlen, len(chars) ) ) )
model.add(Dense(len(chars)))
model.add(Activation('softmax'))

optimizer = RMSprop(lr=0.01)
model.compile(loss='categorical_crossentropy', optimizer=optimizer)
model.fit(X, Y, batch_size=128, nb_epoch=1)


# def sample(preds, temperature=1.0):
#     # helper function to sample an index from a probability array
#     preds = np.asarray(preds).astype('float64')
#     preds = np.log(preds) / temperature
#     exp_preds = np.exp(preds)
#     preds = exp_preds / np.sum(exp_preds)
#     probas = np.random.multinomial(1, preds, 1)
#     return np.argmax(probas)
#
# for iteration in range(1, 60):
#     print()
#     print('-' * 50)
#     print('Iteration', iteration)
#     model.fit(X, y, batch_size=128, nb_epoch=1)
#
#     start_index = random.randint(0, len(text) - maxlen - 1)
#
#     for diversity in [0.2, 0.5, 1.0, 1.2]:
#         print()
#         print('----- diversity:', diversity)
#
#         generated = ''
#         sentence = text[start_index: start_index + maxlen]
#         generated += sentence
#         print('----- Generating with seed: "' + sentence + '"')
#         sys.stdout.write(generated)
#
#         for i in range(400):
#             x = np.zeros((1, maxlen, len(chars)))
#             for t, char in enumerate(sentence):
#                 x[0, t, char_indices[char]] = 1.
#
#             preds = model.predict(x, verbose=0)[0]
#             next_index = sample(preds, diversity)
#             next_char = indices_char[next_index]
#
#             generated += next_char
#             sentence = sentence[1:] + next_char
#
#             sys.stdout.write(next_char)
#             sys.stdout.flush()
#         print()