#load the data
import pandas as pd
import numpy as np
data = pd.read_csv('chapter9_task_data_train.csv')
price = data.loc[:,'close']
price.head()
1
2
3
4
5
6
1
2
3
4
5
6

#归一化
price_norm = price/max(price)
price_norm.head()
1
2
3
1
2
3

#define a method to extract x and y
def extract_data(data,time_step):
    x = []
    y = []
    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)
    y = np.array(y)
    return x,y
1
2
3
4
5
6
7
8
9
10
11
12
1
2
3
4
5
6
7
8
9
10
11
12

time_step = 10
x,y = extract_data(price_norm,time_step)
print(x.shape,y.shape)
1
2
3
1
2
3

#establish RNN model
from keras.models import Sequential
from keras.layers import Dense,SimpleRNN

model = Sequential()
model.add(SimpleRNN(units=5,input_shape=(time_step,1),activation='relu'))
model.add(Dense(units=1,activation='linear'))

model.compile(optimizer='adam',loss='mean_squared_error')
model.summary()
1
2
3
4
5
6
7
8
9
10
1
2
3
4
5
6
7
8
9
10

#train
model.fit(x,y,batch_size=30,epochs=200)
1
2
1
2

#train data predict and calculate R2
from sklearn.metrics import r2_score 
y_train_predict = model.predict(x)*max(price)
y_train = y*max(price)
r2_train = r2_score(y_train,y_train_predict)
print(r2_train)
1
2
3
4
5
6
1
2
3
4
5
6

#visualize the data
from matplotlib import pyplot as plt
fig = plt.figure(figsize=(8,5))
plt.plot(price_test,label='price_close')
plt.plot(y_test_predict,label='price_close_predict')
plt.legend()
plt.title('price close')
plt.show()
1
2
3
4
5
6
7
8
1
2
3
4
5
6
7
8

#save test results to csv
result_y_test = np.array(y_test).reshape(-1,1)
result_y_test_predict = y_test_predict
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)
result = pd.DataFrame(result,columns=['real_price_test','predict_price_test'])
result.to_csv('homework9_9_predict_test.csv')
1
2
3
4
5
6
7
8
1
2
3
4
5
6
7
8