import pandas as pd from sklearn.model_selection import train_test_split def split_time_series_data(date_column,X, y, test_size=0.2): """Split time series data into training and testing sets.""" # Sort the data by date X_sorted = X.sort_values(by=date_column) y_sorted = y.loc[X_sorted.index] # Calculate the split index split_index = int(len(X_sorted) * (1 - test_size)) # Split the data X_train, X_test = X_sorted.iloc[:split_index], X_sorted.iloc[split_index:] y_train, y_test = y_sorted.iloc[:split_index], y_sorted.iloc[split_index:] return X_train, X_test, y_train, y_test