python concatenate fit_Python深度学习 6.2 理解循环神经网络

SimpleRNN

SimpleRNN 可以在两种不同的模式下运行：一种是返回每 个时间步连续输出的完整序列，即形状为 (batch_size, timesteps, output_features) 的三维张量；另一种是只返回每个输入序列的最终输出，即形状为 (batch_size, output_ features) 的二维张量。这两种模式由 return_sequences 这个构造函数参数来控制。

model = Sequential()

model.add(Embedding(max_features, 32)) model.add(SimpleRNN(32))

model.add(Dense(1, activation='sigmoid'))

model.compile(optimizer='rmsprop', loss='binary_crossentropy', metrics=['acc'])

history = model.fit(input_train, y_train, epochs=10,batch_size=128, validation_split=0.2)

LSTM

SimpleRNN 的最大问题是， 在时刻 t，理论上来说，它应该能够记住许多时间步之前见过的信息，但实际上它是不可能学 到这种长期依赖的。其原因在于梯度消失问题(vanishing gradient problem)，这一效应类似于在层数较多的非循环网络(即前馈网络)中观察到的效应：随着层数的增加，网络最终变得无法训练。

LSTM 层是 SimpleRNN 层的一种变体，它增加了一种携带信息跨越多个时间步的方法。假 设有一条传送带，其运行方向平行于你所处理的序列。序列中的信息可以在任意位置跳上传送带， 然后被传送到更晚的时间步，并在需要时原封不动地跳回来。这实际上就是 LSTM 的原理：它保存信息以便后面使用，从而防止较早期的信号在处理过程中逐渐消失。

你只需要记住 LSTM 单元的作用：允许过去的信息稍后重新进入，从而解决梯度消失问题。

from keras.layers import LSTM

model = Sequential()

model.add(Embedding(max_features, 32))

model.add(LSTM(32))

model.add(Dense(1, activation='sigmoid'))

model.compile(optimizer='rmsprop', loss='binary_crossentropy', metrics=['acc'])

history = model.fit(input_train, y_train, epochs=10,batch_size=128, validation_split=0.2)

下面这个例子练手lstm

如何将时间序列转换为监督学习问题(这一点很值得学习！)https://blog.csdn.net/u012735708/article/details/82769711​blog.csdn.net

上面这个例子代码修改了一下，忘记运行read_raw()函数了。

import pandas as pd

from datetime import datetime

from matplotlib import pyplot

from sklearn.preprocessing import LabelEncoder, MinMaxScaler

from sklearn.metrics import mean_squared_error

from keras.models import Sequential

from keras.layers import Dense

from keras.layers import LSTM

from numpy import concatenate

from math import sqrt

import os

# load data

def parse(x):

return datetime.strptime(x, '%Y %m %d %H')

def read_raw():

dataset = pd.read_csv('PRSA_data_2010.1.1-2014.12.31.csv', parse_dates=[['year', 'month', 'day', 'hour']], index_col=0, date_parser=parse)

dataset.drop('No', axis=1, inplace=True)

# manually specify column names

dataset.columns = ['pollution', 'dew', 'temp', 'press', 'wnd_dir', 'wnd_spd', 'snow', 'rain']

dataset.index.name = 'date'

# mark all NA values with 0

dataset['pollution'].fillna(0, inplace=True)

# drop the first 24 hours

dataset = dataset[24:]

# summarize first 5 rows

print(dataset.head(5))

# save to file

dataset.to_csv('pollution.csv')

def drow_pollution():

dataset = pd.read_csv('pollution.csv', header=0, index_col=0)

values = dataset.values

# specify columns to plot

groups = [0, 1, 2, 3, 5, 6, 7]

i = 1

# plot each column

pyplot.figure(figsize=(10, 10))

for group in groups:

pyplot.subplot(len(groups), 1, i)

pyplot.plot(values[:, group])

pyplot.title(dataset.columns[group], y=0.5, loc='right')

i += 1

pyplot.show()

def series_to_supervised(data, n_in=1, n_out=1, dropnan=True):

# convert series to supervised learning

n_vars = 1 if type(data) is list else data.shape[1]

df = pd.DataFrame(data)

cols, names = list(), list()

# input sequence (t-n, ... t-1)

for i in range(n_in, 0, -1):

cols.append(df.shift(i))

names += [('var%d(t-%d)' % (j + 1, i)) for j in range(n_vars)]

# forecast sequence (t, t+1, ... t+n)

for i in range(0, n_out):

cols.append(df.shift(-i))

if i == 0:

names += [('var%d(t)' % (j + 1)) for j in range(n_vars)]

else:

names += [('var%d(t+%d)' % (j + 1, i)) for j in range(n_vars)]

# put it all together

agg = pd.concat(cols, axis=1)

agg.columns = names

# drop rows with NaN values

if dropnan:

agg.dropna(inplace=True)

return agg

def cs_to_sl():

# load dataset

dataset = pd.read_csv('pollution.csv', header=0, index_col=0)

values = dataset.values

# integer encode direction

encoder = LabelEncoder()

values[:, 4] = encoder.fit_transform(values[:, 4])

# ensure all data is float

values = values.astype('float32')

# normalize features

scaler = MinMaxScaler(feature_range=(0, 1))

scaled = scaler.fit_transform(values)

# frame as supervised learning

reframed = series_to_supervised(scaled, 1, 1)

# drop columns we don't want to predict

reframed.drop(reframed.columns[[9, 10, 11, 12, 13, 14, 15]], axis=1, inplace=True)

print(reframed.head())

return reframed, scaler

def train_test(reframed):

# split into train and test sets

values = reframed.values

n_train_hours = 365 * 24

train = values[:n_train_hours, :]

test = values[n_train_hours:, :]

# split into input and outputs

train_X, train_y = train[:, :-1], train[:, -1]

test_X, test_y = test[:, :-1], test[:, -1]

# reshape input to be 3D [samples, timesteps, features]

train_X = train_X.reshape((train_X.shape[0], 1, train_X.shape[1]))

test_X = test_X.reshape((test_X.shape[0], 1, test_X.shape[1]))

print(train_X.shape, train_y.shape, test_X.shape, test_y.shape)

return train_X, train_y, test_X, test_y

def fit_network(train_X, train_y, test_X, test_y, scaler):

model = Sequential()

model.add(LSTM(50, input_shape=(train_X.shape[1], train_X.shape[2])))

model.add(Dense(1))

model.compile(loss='mae', optimizer='adam')

# fit network

history = model.fit(train_X, train_y, epochs=50, batch_size=72, validation_data=(test_X, test_y), verbose=2,

shuffle=False)

# plot history

pyplot.plot(history.history['loss'], label='train')

pyplot.plot(history.history['val_loss'], label='test')

pyplot.legend()

pyplot.show()

# make a prediction

yhat = model.predict(test_X)

test_X = test_X.reshape((test_X.shape[0], test_X.shape[2]))

# invert scaling for forecast

inv_yhat = concatenate((yhat, test_X[:, 1:]), axis=1)

inv_yhat = scaler.inverse_transform(inv_yhat)

inv_yhat = inv_yhat[:, 0]

# invert scaling for actual

inv_y = scaler.inverse_transform(test_X)

inv_y = inv_y[:, 0]

# calculate RMSE

rmse = sqrt(mean_squared_error(inv_y, inv_yhat))

print('Test RMSE: %.3f' % rmse)

if __name__ == '__main__':

os.environ['CUDA_VISIBLE_DEVICES'] = '0'

read_raw()

drow_pollution()

reframed, scaler = cs_to_sl()

train_X, train_y, test_X, test_y = train_test(reframed)

fit_network(train_X, train_y, test_X, test_y, scaler)