utils/preprocessing.py

# utils/preprocessing.py

import pandas as pd
import numpy as np

def preprocess_data(data):
    # If data has MultiIndex columns, select the first level
    if isinstance(data.columns, pd.MultiIndex):
        data.columns = data.columns.get_level_values(0)
    
    # Add technical indicators
    data['SMA_20'] = data['Close'].rolling(window=20).mean()
    data['SMA_50'] = data['Close'].rolling(window=50).mean()
    
    # Calculate RSI
    delta = data['Close'].diff()
    gain = (delta.where(delta > 0, 0)).rolling(window=14).mean()
    loss = (-delta.where(delta < 0, 0)).rolling(window=14).mean()
    rs = gain / loss
    data['RSI'] = 100 - (100 / (1 + rs))
    
    # Calculate MACD
    exp1 = data['Close'].ewm(span=12, adjust=False).mean()
    exp2 = data['Close'].ewm(span=26, adjust=False).mean()
    data['MACD'] = exp1 - exp2
    data['Signal_Line'] = data['MACD'].ewm(span=9, adjust=False).mean()
    
    # Handle missing values
    data = data.fillna(method='ffill')
    
    return data