keras LSTM学习实例

1. 购物时间预测

http://www.cnblogs.com/arkenstone/p/5794063.html

https://github.com/CasiaFan/time_seires_prediction_using_lstm

 

2.  简单实例

#!/usr/bin/env python
# coding=utf-8

import numpy as np
from keras.models import Sequential
from keras.layers import Dense, LSTM
from keras.utils import np_utils
import string

chars = string.uppercase
char_to_int = dict((c, i) for i, c in enumerate(chars))
int_to_char = dict((i, c) for i, c in enumerate(chars))

def load_data(look_back = 3):

    data, label = [], []
    for i in range(0, len(chars)-look_back, 1):
        seq_in = chars[i:i+look_back]
        seq_out = chars[i+look_back]
        data.append([char_to_int[c] for c in seq_in])
        label.append(char_to_int[seq_out])
    return data, label

seq_length = 3
data, label = load_data(seq_length)

X = np.reshape(data, (len(data), seq_length, 1))
X = X / float(len(chars))
y = np_utils.to_categorical(label)

model = Sequential()
model.add(LSTM(32, input_shape=(X.shape[1], X.shape[2])))
model.add(Dense(128, activation='relu'))
model.add(Dense(y.shape[1], activation='softmax'))

model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
model.fit(X, y, nb_epoch=300, batch_size=32, verbose=2)
scores = model.evaluate(X, y, verbose=1)
print('accuracy: %.2f%%' % (scores[1]*100))

for p in data:
    x = np.reshape(p, (1, len(p), 1))
    x = x /float(len(chars))
    y_pred = model.predict(x, verbose=0)
    index = np.argmax(y_pred)
    result = int_to_char[index]
    seq_in = [int_to_char[v] for v in p]
    print seq_in, '-> ', result

print scores

accuracy: 100.00%
['A', 'B', 'C'] ->  D
['B', 'C', 'D'] ->  E
['C', 'D', 'E'] ->  F
['D', 'E', 'F'] ->  G
['E', 'F', 'G'] ->  H
['F', 'G', 'H'] ->  I
['G', 'H', 'I'] ->  J
['H', 'I', 'J'] ->  K
['I', 'J', 'K'] ->  L
['J', 'K', 'L'] ->  M
['K', 'L', 'M'] ->  N
['L', 'M', 'N'] ->  O
['M', 'N', 'O'] ->  P
['N', 'O', 'P'] ->  Q
['O', 'P', 'Q'] ->  R
['P', 'Q', 'R'] ->  S
['Q', 'R', 'S'] ->  T
['R', 'S', 'T'] ->  U
['S', 'T', 'U'] ->  V
['T', 'U', 'V'] ->  W
['U', 'V', 'W'] ->  X
['V', 'W', 'X'] ->  Y
['W', 'X', 'Y'] ->  Z
[0.50304841995239258, 1.0]