TAIEX.s46_LSTM(2). Future select by Decision Tree.

使用決策樹進行特徵選擇，並使用選擇的特徵來訓練 LSTM 模型。

最後打印所選的特徵變數並顯示實際值和預測值圖

import os
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.dates as mdates
from sklearn.metrics import mean_squared_error, mean_absolute_error
from sklearn.preprocessing import MinMaxScaler
from sklearn.tree import DecisionTreeRegressor
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import LSTM, Dense, Dropout
from google.colab import drive

# Mount Google Drive
drive.mount('/content/drive', force_remount=True)

# Check file path
file_path = '/content/drive/My Drive/MSCI_Taiwan_30_data_with_OBV.csv'
if os.path.exists(file_path):
    print("File exists")
    data = pd.read_csv(file_path)
else:
    print("File does not exist")

# Ensure the date column is converted to datetime type
data['Date'] = pd.to_datetime(data['Date'])

# Print column names to check if 'Close_TAIEX' column exists
print(data.columns)

# Feature Engineering using Adj_Close for moving averages
data['MA7'] = data['Adj_Close'].rolling(window=7).mean()
data['MA21'] = data['Adj_Close'].rolling(window=21).mean()

def compute_rsi(data, window=14):
    delta = data['Adj_Close'].diff(1)
    gain = (delta.where(delta > 0, 0)).rolling(window=window).mean()
    loss = (-delta.where(delta < 0, 0)).rolling(window=window).mean()
    rs = gain / loss
    rsi = 100 - (100 / (1 + rs))
    return rsi

data['RSI14'] = compute_rsi(data)

def compute_macd(data, fast=12, slow=26, signal=9):
    exp1 = data['Adj_Close'].ewm(span=fast, adjust=False).mean()
    exp2 = data['Adj_Close'].ewm(span=slow, adjust=False).mean()
    macd = exp1 - exp2
    signal_line = macd.ewm(span=signal, adjust=False).mean()
    return macd, signal_line

data['MACD Line'], data['MACD Signal'] = compute_macd(data)

# Prepare data
if 'Close_TAIEX' in data.columns:
    data = data.dropna(subset=['Close_TAIEX'])
    series = data[['Date', 'Close_TAIEX']]
    series.set_index('Date', inplace=True)
else:
    print("The data does not contain 'Close_TAIEX' column")
    raise KeyError("The data does not contain 'Close_TAIEX' column")

# Selecting Features (excluding non-numeric columns)
numeric_data = data.select_dtypes(include=[np.number])
X = numeric_data.drop(['Close_TAIEX'], axis=1).fillna(0)
y = numeric_data['Close_TAIEX']

# Feature Selection using Decision Tree
tree = DecisionTreeRegressor(random_state=42)
tree.fit(X, y)

# Get feature importances
importances = tree.feature_importances_
indices = np.argsort(importances)[::-1]

# Select top 6 features
selected_features = X.columns[indices][:6]
print("Selected features:", selected_features)

# Using the selected features for LSTM model
X_selected = data[selected_features].fillna(0)

# Scale data
scaler_X = MinMaxScaler(feature_range=(0, 1))
scaler_y = MinMaxScaler(feature_range=(0, 1))
scaled_X = scaler_X.fit_transform(X_selected)
scaled_y = scaler_y.fit_transform(y.values.reshape(-1, 1))

# Prepare training and testing datasets
train_size = int(len(scaled_X) * 0.8)
train_X, test_X = scaled_X[:train_size], scaled_X[train_size:]
train_y, test_y = scaled_y[:train_size], scaled_y[train_size:]

# Create sequences
def create_sequences(data_X, data_y, seq_length):
    X, y = [], []
    for i in range(len(data_X) - seq_length):
        X.append(data_X[i:i+seq_length])
        y.append(data_y[i+seq_length])
    return np.array(X), np.array(y)

seq_length = 60
X_train, y_train = create_sequences(train_X, train_y, seq_length)
X_test, y_test = create_sequences(test_X, test_y, seq_length)

# Build LSTM model
model = Sequential()
model.add(LSTM(units=50, return_sequences=True, input_shape=(seq_length, len(selected_features))))
model.add(Dropout(0.2))
model.add(LSTM(units=50, return_sequences=False))
model.add(Dropout(0.2))
model.add(Dense(units=1))

model.compile(optimizer='adam', loss='mean_squared_error')
model.fit(X_train, y_train, epochs=50, batch_size=32)

# Make predictions
predicted = model.predict(X_test)
predicted = scaler_y.inverse_transform(predicted)

# Calculate errors
y_test_inverse = scaler_y.inverse_transform(y_test)
mse = mean_squared_error(y_test_inverse, predicted)
mae = mean_absolute_error(y_test_inverse, predicted)

# Plot actual values and predictions
plt.figure(figsize=(12, 6))

# Plot actual values
plt.plot(series.index[-len(y_test):], y_test_inverse, label='Actual', color='blue')

# Plot predictions
plt.plot(series.index[-len(predicted):], predicted, label='LSTM Forecast', color='red')

plt.title('LSTM Model Forecast vs Actual')
plt.xlabel('Date')
plt.ylabel('Close_TAIEX')
plt.legend()

# Set date format and rotate x-axis labels
plt.gca().xaxis.set_major_locator(mdates.MonthLocator())
plt.gca().xaxis.set_major_formatter(mdates.DateFormatter('%Y-%m'))
plt.gca().tick_params(axis='x', rotation=90)

# Add grid
plt.grid(True, which='both', linestyle='--', linewidth=0.5)
plt.minorticks_on()
plt.grid(True, which='minor', linestyle=':', linewidth=0.5)

# Show plot
plt.show()

# Print MSE and MAE
print(f'LSTM Model Mean Squared Error (MSE): {mse}')
print(f'LSTM Model Mean Absolute Error (MAE): {mae}')

# Print all selected features for reference
print("Selected features used in the model:", selected_features)

LSTM Model Mean Squared Error (MSE): 5569100.154651171
LSTM Model Mean Absolute Error (MAE): 1710.4892850633682
Selected features used in the model: Index(['OBV', 'Signal Line', 'Market Return', 'MACD Histogram', 'Aroon Down', 'CCI20'],dtype='object')