tensorflow实现简单RNN
使用简单RNN预测谷歌的股票
实验数据
import numpy as np
import tensorflow.keras as keras
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.preprocessing import MinMaxScaler
def RNN(x_train, y_train):
regressor = keras.Sequential()
# add the first RNN and the Dropout to prevent overfitting
regressor.add(keras.layers.SimpleRNN(units=50, return_sequences=True,
input_shape=(x_train.shape[1], 1)))
# if the return_sequences is True, it means that it has another rnn upward,and it return
# (batch_size,time_step,units) shape matrix
# otherwise it return (batch_size,units) matrix
regressor.add(keras.layers.Dropout(0.2))
# add the second one
regressor.add(keras.layers.SimpleRNN(units=50, activation='tanh', return_sequences=True))
regressor.add(keras.layers.Dropout(0.2))
regressor.add(keras.layers.SimpleRNN(units=50))
regressor.add(keras.layers.Dropout(0.2))
# add the output layer
regressor.add(keras.layers.Dense(units=1))
# compile
regressor.compile(optimizer='adam', loss='mean_squared_error', metrics=['accuracy'])
regressor.fit(x=x_train, y=y_train, epochs=30, batch_size=32)
# print(regressor.summary())
return regressor
def visualization(real, pred):
plt.figure(figsize=(8, 4), dpi=80, facecolor='w', edgecolor='k')
plt.plot(real, color="orange", label="Real value")
plt.plot(pred, color="c", label="RNN predicted result")
plt.legend()
plt.xlabel("Days")
plt.ylabel("Values")
plt.grid(True)
plt.show()
if __name__ == "__main__":
data = pd.read_csv(r"dataset\geogle_stock_price\archive\Google_Stock_Price_Train.csv")
data = data.loc[:, ["Open"]].values
train = data[:len(data) - 50]
test = data[len(train):]
train.reshape(train.shape[0], 1)
scaler = MinMaxScaler(feature_range=(0, 1))
train_scaled = scaler.fit_transform(train)
# plt.plot(train_scaled)
# plt.show()
X_train = []
Y_train = []
time_step = 50
for i in range(time_step, train_scaled.shape[0]):
X_train.append(train_scaled[i - time_step:i, 0])
Y_train.append(train_scaled[i, 0])
X_train, Y_train = np.array(X_train), np.array(Y_train)
X_train = X_train.reshape(X_train.shape[0], X_train.shape[1], 1)
inputs = data[len(data) - len(test) - time_step:]
inputs = scaler.transform(inputs)
X_test = []
for i in range(time_step, inputs.shape[0]):
X_test.append(inputs[i - time_step:i, 0])
X_test = np.array(X_test)
X_test = X_test.reshape(X_test.shape[0], X_test.shape[1], 1)
model = RNN(X_train, Y_train)
pred = model.predict(X_test)
pred = scaler.inverse_transform(pred)
visualization(real=test, pred=pred)
- 简单的RNN会遇到例如梯度消失无法嵌套太多层、单项传播无法考虑后面对前面的影响等各种问题
LSTM模型预测
# -*-coding = utf-8
import numpy as np
import tensorflow.keras as keras
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.preprocessing import MinMaxScaler
def RNN(x_train, y_train):
regressor = keras.Sequential()
# add the first RNN and the Dropout to prevent overfitting
regressor.add(keras.layers.SimpleRNN(units=50, return_sequences=True,
input_shape=(x_train.shape[1], 1)))
# if the return_sequences is True, it means that it has another rnn upward,and it return
# (batch_size,time_step,units) shape matrix
# otherwise it return (batch_size,units) matrix
regressor.add(keras.layers.Dropout(0.2))
# add the second one
regressor.add(keras.layers.SimpleRNN(units=50, activation='tanh', return_sequences=True))
regressor.add(keras.layers.Dropout(0.2))
regressor.add(keras.layers.SimpleRNN(units=50))
regressor.add(keras.layers.Dropout(0.2))
# add the output layer
regressor.add(keras.layers.Dense(units=1))
# compile
regressor.compile(optimizer='adam', loss='mean_squared_error')
# a important point: we do not give a metric such as accuracy in the CNN or ohter neural network
#
regressor.fit(x=x_train, y=y_train, epochs=30, batch_size=32)
# print(regressor.summary())
return regressor
def LSTM(x_train, y_train):
model = keras.Sequential()
model.add(keras.layers.LSTM(units=10, activation='tanh', input_shape=(None, 1)))
# ten units LSTM
model.add(keras.layers.Dense(1))
model.compile(loss='mean_squared_error', optimizer='adam', metrics=['accuracy'])
model.fit(x_train, y_train, batch_size=1, epochs=15)
return model
def visualization(real, pred):
plt.figure(figsize=(8, 4), dpi=80, facecolor='w', edgecolor='k')
plt.plot(real, color="orange", label="Real value")
# plt.plot(pred, color="c", label="RNN predicted result")
plt.plot(pred, color='r', label='LSTM predicted result')
plt.legend()
plt.xlabel("Days")
plt.ylabel("Values")
plt.grid(True)
plt.show()
if __name__ == "__main__":
data = pd.read_csv(r"dataset\geogle_stock_price\archive\Google_Stock_Price_Train.csv")
data = data.loc[:, ["Open"]].values
train = data[:len(data) - 50]
test = data[len(train):]
train.reshape(train.shape[0], 1)
scaler = MinMaxScaler(feature_range=(0, 1))
train_scaled = scaler.fit_transform(train)
# plt.plot(train_scaled)
# plt.show()
X_train = []
Y_train = []
time_step = 50
for i in range(time_step, train_scaled.shape[0]):
X_train.append(train_scaled[i - time_step:i, 0])
Y_train.append(train_scaled[i, 0])
X_train, Y_train = np.array(X_train), np.array(Y_train)
X_train = X_train.reshape(X_train.shape[0], X_train.shape[1], 1)
inputs = data[len(data) - len(test) - time_step:]
inputs = scaler.transform(inputs)
X_test = []
for i in range(time_step, inputs.shape[0]):
X_test.append(inputs[i - time_step:i, 0])
X_test = np.array(X_test)
X_test = X_test.reshape(X_test.shape[0], X_test.shape[1], 1)
# model = RNN(X_train, Y_train)
model = LSTM(X_train, Y_train)
pred = model.predict(X_test)
pred = scaler.inverse_transform(pred)
visualization(real=test, pred=pred)
可以看到LSTM模型的预测效果比简单CNN要好很多，基本上复现了真实的股价，只是在时间上面有一些延迟。