tf-lstm-stock.py

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.preprocessing import MinMaxScaler
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import LSTM, Dense, Activation


from matplotlib.dates import DateFormatter, WeekdayLocator, DayLocator, MONDAY,YEARLY
#import matplotlib
import tushare as ts
import pandas as pd
import matplotlib.pyplot as plt
from matplotlib.pylab import date2num
import datetime
import numpy as np
from pandas import DataFrame
from numpy import row_stack,column_stack
import pandas

df=ts.get_hist_data('601857',start='2016-06-15',end='2018-01-12')
dd=df[['open','high','low','close']]

#print(dd.values.shape[0])

dd1=dd .sort_index()

dd2=dd1.values.flatten()

dd3=pandas.DataFrame(dd1['close'])

def load_data(df, sequence_length=10, split=0.8):
    
    #df = pd.read_csv(file_name, sep=',', usecols=[1])
    #data_all = np.array(df).astype(float)
    
    data_all = np.array(df).astype(float)
    scaler = MinMaxScaler()
    data_all = scaler.fit_transform(data_all)
    data = []
    for i in range(len(data_all) - sequence_length - 1):
        data.append(data_all[i: i + sequence_length + 1])
    reshaped_data = np.array(data).astype('float64')
    #np.random.shuffle(reshaped_data)
    # 对x进行统一归一化，而y则不归一化
    x = reshaped_data[:, :-1]
    y = reshaped_data[:, -1]
    split_boundary = int(reshaped_data.shape[0] * split)
    train_x = x[: split_boundary]
    test_x = x[split_boundary:]

    train_y = y[: split_boundary]
    test_y = y[split_boundary:]

    return train_x, train_y, test_x, test_y, scaler


def build_model():
    # input_dim是输入的train_x的最后一个维度，train_x的维度为(n_samples, time_steps, input_dim)
    model = Sequential()

    
    model.add(LSTM(100, return_sequences=False))
    model.add(Dense(1))
    model.add(Activation('linear'))

    model.compile(loss='mse', optimizer='rmsprop')
    return model


def train_model(train_x, train_y, test_x, test_y):
    model = build_model()

    try:
        model.fit(train_x, train_y, batch_size=512, epochs=300, validation_split=0.1)
        predict = model.predict(test_x)
        predict = np.reshape(predict, (predict.size, ))
    except KeyboardInterrupt:
        print(predict)
        print(test_y)
    print(predict)
    print(test_y)
    try:
        fig = plt.figure(1)
        plt.plot(predict, 'r:')
        plt.plot(test_y, 'g-')
        plt.legend(['predict', 'true'])
    except Exception as e:
        print(e)
    return predict, test_y


if __name__ == '__main__':
    #train_x, train_y, test_x, test_y, scaler = load_data('international-airline-passengers.csv')
    train_x, train_y, test_x, test_y, scaler =load_data(dd3, sequence_length=10, split=0.8)
    train_x = np.reshape(train_x, (train_x.shape[0], train_x.shape[1], 1))
    test_x = np.reshape(test_x, (test_x.shape[0], test_x.shape[1], 1))
    predict_y, test_y = train_model(train_x, train_y, test_x, test_y)
    predict_y = scaler.inverse_transform([[i] for i in predict_y])
    test_y = scaler.inverse_transform(test_y)
    fig2 = plt.figure(2)
    plt.plot(predict_y, 'g:')
    plt.plot(test_y, 'r-')
    plt.show()