股票预测LSTM （Keras）

import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import math
from keras.models import Sequential
from keras.layers import Dense, Activation, Dropout, LSTM
from sklearn.preprocessing import MinMaxScaler
from sklearn.metrics import mean_squared_error
from keras import optimizers
import time

def create_dataset(dataset, look_back):
#这里的look_back与timestep相同
    dataX, dataY = [], []
    for i in range(len(dataset) - look_back - 1):
        #dataX  多维数组
        a = dataset[i:(i + look_back)]
        dataX.append(a)
        dataY.append(dataset[i + look_back])
    return np.array(dataX), np.array(dataY)
'''假如这个data是[1,2,3,4,5]，look_back为1的话.
x
[[1]
[2]
[3]] y就是[2 3 4]，意思就是用前一个数据预测后一个，
这是look_back为1的意思。假如是为8，那前8个数据预测第9个数据。'''


dataframe = pd.read_csv('zgpa_train.csv',
                        header=0, parse_dates=[0],
                        index_col=0, usecols=[0, 5], squeeze=True)
dataset = dataframe.values
dataframe.head(10)

plt.figure(figsize=(12, 8))
dataframe.plot()
plt.ylabel('price')
plt.yticks(np.arange(0, 300000000, 100000000))
plt.show()
#归一化
scaler = MinMaxScaler(feature_range=(0, 1))
dataset = scaler.fit_transform(dataset.reshape(-1, 1))
#分割数据集大小
train_size = int(len(dataset)*0.8)
test_size = len(dataset)-train_size
train, test = dataset[0: train_size], dataset[train_size: len(dataset)]
#准备训练用的数据集格式
look_back = 1
trainX, trainY = create_dataset(train, look_back)
testX, testY = create_dataset(test, look_back)
#建立模型，这里注意下如果是多层lstm的话一定要注意前后维度对接，
# 也就是input和output维度，当前层的input维度是上一次层的output维度。
# return_sequences=True表示返回这个维度给下面。
model = Sequential()
#input_dim 输入维度
model.add(LSTM(input_dim=1, output_dim=50, return_sequences=True))
#model.add(Dropout(0.2))

model.add(LSTM(input_dim=50, output_dim=100, return_sequences=True))
#model.add(Dropout(0.2))

model.add(LSTM(input_dim=100, output_dim=200, return_sequences=True))
#model.add(Dropout(0.2))

model.add(LSTM(300, return_sequences=False))
model.add(Dropout(0.2))

model.add(Dense(100))
model.add(Dense(output_dim=1))

model.add(Activation('relu'))
start = time.time()
model.compile(loss='mean_squared_error', optimizer='Adam')
model.summary()
#validation_split=0.1表示拿出训练集的10%作为验证集
history = model.fit(trainX, trainY, batch_size=64, epochs=50,
                    validation_split=0.1, verbose=2)
print('compilatiom time:', time.time()-start)

trainPredict = model.predict(trainX)
testPredict = model.predict(testX)
#反归一化
trainPredict = scaler.inverse_transform(trainPredict)
trainY = scaler.inverse_transform(trainY)
testPredict = scaler.inverse_transform(testPredict)
testY = scaler.inverse_transform(testY)

trainScore = math.sqrt(mean_squared_error(trainY, trainPredict[:, 0]))
print('Train Sccore %.2f RMSE' %(trainScore))
testScore = math.sqrt(mean_squared_error(testY, testPredict[:, 0]))
print('Train Sccore %.2f RMSE' %(testScore))
#empty_like方法表示创建一个空数组，这个空数组很像dataset，为什么呢，
# 因为维度一样，但是值还没初始化。 然后我们让其全为空后进行填值。
# 最后一行的操作相当于是一个100个数值的数值，我填了前面70个，
# 因为前面70个是我训练集的预测值，后面30为空。
trainPredictPlot = np.empty_like(dataset)
trainPredictPlot[:] = np.nan
trainPredictPlot = np.reshape(trainPredictPlot, (dataset.shape[0], 1))
trainPredictPlot[look_back: len(trainPredict)+look_back, :] = trainPredict
#30个测试集填充
testPredictPlot = np.empty_like(dataset)
testPredictPlot[:] = np.nan
testPredictPlot = np.reshape(testPredictPlot, (dataset.shape[0], 1))
testPredictPlot[len(trainPredict)+(look_back*2)+1: len(dataset)-1, :] = testPredict

fig1 = plt.figure(figsize=(12, 8))
plt.plot(history.history['loss'])
plt.title('model loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.show()

fig2 = plt.figure(figsize=(20, 15))
plt.plot(scaler.inverse_transform(dataset))
plt.plot(trainPredictPlot)
plt.plot(testPredictPlot)
plt.ylabel('price')
plt.xlabel('date')
plt.show()

原文：https://blog.csdn.net/ABin_203/article/details/106243249?ops_request_misc=%257B%2522request%255Fid%2522%253A%2522160705669819195271649496%2522%252C%2522scm%2522%253A%252220140713.130102334..%2522%257D&request_id=160705669819195271649496&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~all~sobaiduend~default-2-106243249.pc_first_rank_v2_rank_v28&utm_term=lstm%E6%97%B6%E9%97%B4%E5%BA%8F%E5%88%97%E9%A2%84%E6%B5%8B