RNN實現股價預測

簡介

import pandas as pd
import numpy as np
data = pd.read_csv('zgpa_train.csv')
data.head()

price = data.loc[:,'close']
price.head()

# 歸一化處理
price_norm = price/max(price)
print(price_norm)


from matplotlib import pyplot as plt
fig1 = plt.figure(figsize=(8,5))
plt.plot(price)
plt.title('close price')
plt.xlabel('time')
plt.ylabel('price')
plt.show()

# define X and y
# define method to extract X and y
def extract_data(data,time_step):
    X=[]
    y=[]
    # 0,1,2...9:10個樣本： time_step=8;0,1...7;1,2...8;2,3
    for i in range(len(data) - time_step):
        X.append([a for a in data[i:i+time_step]])
        y.append(data[i+time_step])
    X=np.array(X)
    X=X.reshape(X.shape[0],X.shape[1],1)
    return X,y


time_step=8

# define X and y
X,y = extract_data(price_norm,time_step)
print(X)

# set up the model
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, SimpleRNN
model = Sequential()
#input_shape 訓練長度 每個數據的維度
model.add(SimpleRNN(units=5,input_shape=(time_step,1),activation="relu"))
#輸出層
#輸出數值 units =1 1個神經元 "linear"線性模型
model.add(Dense(units=1, activation="linear"))
#配置模型 迴歸模型y
model.compile(optimizer="adam",loss="mean_squared_error")
model.summary()


y = np.array(y)


# train the model
model.fit(X,y,batch_size=30,epochs=200)


# make prediction based on the training data 
y_train_predict = model.predict(X)*max(price)
y_train = y*max(price)
print(y_train_predict,y_train)


fig2 = plt.figure(figsize=(10,5))
plt.plot(y_train,label = "real price")
plt.plot(y_train_predict,label = "predict price")
plt.title("price")
plt.xlabel("time")
plt.ylabel("price")
plt.legend()
plt.show()

data_test = pd.read_csv('zgpa_test.csv')
data_test.head()
price_test=data_test.loc[:,'close']
price_test.head()
price_test_norm = price_test/max(price)
#extract X_test and y_test
X_test_norm,y_test_norm = extract_data(price_test_norm,time_step)
print(X_test_norm.shape,len(y_test_norm))


# make prediction based on the test data
y_test_predict = model.predict(X_test_norm)*max(price)
y_test = [i*max(price) for i in y_test_norm]


fig3 = plt.figure(figsize=(10,5))
plt.plot(y_test,label = "real price test")
plt.plot(y_test_predict,label = "predict price test")
plt.title("price")
plt.xlabel("time")
plt.ylabel("price")
plt.legend()
plt.show()


# result_y_test = y_test.reshap(-1,1)
result_y_test = np.array(y_test).reshape(-1,1)
result_y_test_predict = np.array(y_test_predict).reshape(-1,1)
print(result_y_test.shape,result_y_test_predict.shape)
result = np.concatenate((result_y_test,result_y_test_predict),axis=1)
print(result.shape)
reslut = pd.DataFrame(result,columns=['real_price_test','predict_price_test'])
reslut.to_csv('zgpa_predict_test.csv')

image

參考鏈接

https://gitee.com/nickdlk/python_machine_learning