使用 Python 和机器学习 (LSTM) 预测未来“x”天的股票价格

Question

我已经按照这个教程https://www.youtube.com/watch?v=QIUxPv5PJOY 预测未来一天苹果的股价。代码是：

#Import the libraries
import math
import pandas_datareader as web
import numpy as np
import pandas as pd
from sklearn.preprocessing import MinMaxScaler
from keras.models import Sequential 
from keras.layers import Dense, LSTM
import matplotlib.pyplot as plt
plt.style.use('fivethirtyeight')

#Get the stock quote
df = web.DataReader('AAPL', data_source='yahoo', start='2012-01-01', end='2020-12-07')

#Show the data
df
#Get the number of rows and columns in the data set
df.shape

#Visualize the closing price history
#We create a plot with name 'Close Price History'
plt.figure(figsize=(16,8))
plt.title('Close Price History')
#We give the plot the data (the closing price of our stock)
plt.plot(df['Close'])
#We label the axis
plt.xlabel('Date', fontsize=18)
plt.ylabel('Close Price USD ($)', fontsize=18)
#We show the plot
plt.show()

#Create a new dataframe with only the 'Close' column
data = df.filter(['Close'])

#Convert the dataframe to a numpy array
dataset = data.values
#Get the number of rows to train the model on
training_data_len = math.ceil( len(dataset) * 0.8 )

training_data_len

#Scale the data
scaler = MinMaxScaler(feature_range=(0,1))
scaled_data = scaler.fit_transform(dataset)

scaled_data

#Create the training data set 
#Create the scaled training data set
train_data = scaled_data[0:training_data_len, :]
#Split the data into x_train and y_train data sets
x_train = []
y_train = []
#We create a loop
for i in range(60, len(train_data)):
  x_train.append(train_data[i-60:i, 0]) #Will conaint 60 values (0-59)
  y_train.append(train_data[i, 0]) #Will contain the 61th value (60)
  if i <= 60:
    print(x_train)
    print(y_train)
    print()


#Convert the x_train and y_train to numpy arrays
x_train, y_train = np.array(x_train), np.array(y_train)

#Reshape the data
x_train = np.reshape(x_train, (x_train.shape[0], x_train.shape[1], 1))
x_train.shape

#Build the LSTM model
model = Sequential()
model.add(LSTM(50, return_sequences=True, input_shape=(x_train.shape[1], 1)))
model.add(LSTM(50, return_sequences=False))
model.add(Dense(25))
model.add(Dense(1))

#Compile the model
model.compile(optimizer='adam', loss='mean_squared_error')

#Train the model
model.fit(x_train, y_train, batch_size=1, epochs=1)

#Create the testing data set
#Create a new array containing scaled values from index 1738 to 2247
test_data = scaled_data[training_data_len - 60:]
#Create the data set x_test and y_test
x_test = []
y_test = dataset[training_data_len:, :]
for i in range(60, len(test_data)):
  x_test.append(test_data[i-60:i, 0])

#Convert the data to a numpy array
x_test = np.array(x_test)

#Reshape the data
x_test = np.reshape(x_test, (x_test.shape[0], x_test.shape[1], 1))

#Get the model's predicted price values for the x_test data set
predictions = model.predict(x_test)
predictions = scaler.inverse_transform(predictions)
predictions

#Evaluate model (get the root mean quared error (RMSE))
rmse = np.sqrt( np.mean( predictions - y_test )**2 )
rmse

#Plot the data
train = data[:training_data_len]
valid = data[training_data_len:]
valid['Predictions'] = predictions
#Visualize the data
plt.figure(figsize=(16,8))
plt.title('Model')
plt.xlabel('Date', fontsize=18)
plt.ylabel('Close Price USD ($)', fontsize=18)
plt.plot(train['Close'])
plt.plot(valid[['Close', 'Predictions']])
plt.legend(['Train', 'Validation', 'Predictions'], loc='lower right')
plt.show()

现在我想扩展图表的预测部分以显示未来日期（未来“x”天）。我想我可以通过获取第二天的预测价格，然后在输入中使用该价格来获取第二天的价格，然后使用当天的价格来获取第二天的价格，等等。我该怎么做？我想将第二天的预测价格附加到用于训练模型的数据集中，但我没有成功。谢谢你的帮助。

Answer 1

你的直觉是正确的。我以这种方式完成了您的想法：

X_FUTURE = 100
predictions = np.array([])
last = x_test[-1]
for i in range(X_FUTURE):
  curr_prediction = model.predict(np.array([last]))
  print(curr_prediction)
  last = np.concatenate([last[1:], curr_prediction])
  predictions = np.concatenate([predictions, curr_prediction[0]])
predictions = scaler.inverse_transform([predictions])[0]
print(predictions)

我已经基本用新的预测构建了移位数组

之后我构建了包含新预测的数据框：

import datetime
from datetime import timedelta
dicts = []
curr_date = data.index[-1]
for i in range(X_FUTURE):
  curr_date = curr_date + timedelta(days=1)
  dicts.append({'Predictions':predictions[i], "Date": curr_date})

new_data = pd.DataFrame(dicts).set_index("Date")

我绘制了结果：

#Plot the data
train = data
#Visualize the data
plt.figure(figsize=(16,8))
plt.title('Model')
plt.xlabel('Date', fontsize=18)
plt.ylabel('Close Price USD ($)', fontsize=18)
plt.plot(train['Close'])
plt.plot(new_data['Predictions'])
plt.legend(['Train', 'Predictions'], loc='lower right')
plt.show()

为什么看起来这么糟糕（反正我们不知道未来……）？ 我确实在所有数据集上重新训练了模型，但这里的问题是我走得越远，不确定性就越大。我不是时间序列预测的专家，但我认为模型在时间序列下没有学到任何好的模式。但是作为例子，它做了它需要做的事情

Answer 2

你可以按照建议的去做，但是二阶堂显示结果不会很好，从我做过的测试来看，如果在最后一天价格上涨，价格会继续上涨，如果在最后一天股价下跌，所以它会继续下跌。这可能是因为模型没有学到任何好的模式，或者因为模型知道最后一天是预测最重要的一天。