Forecast Equipment Maintenance Windows with TimesFM and XGBoost

                      
                     
import os
import pandas as pd
import numpy as np
from xgboost import XGBRegressor
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error
import logging

# Configure logging
logging.basicConfig(level=logging.INFO)

# Load environment variables
DATA_PATH = os.getenv('DATA_PATH')

# Load and preprocess data
try:
    data = pd.read_csv(DATA_PATH)
    logging.info('Data loaded successfully.')
    # Preprocessing: handle missing values
    data.fillna(method='ffill', inplace=True)
    X = data.drop(columns=['maintenance_window'])
    y = data['maintenance_window']
except Exception as e:
    logging.error(f'Error loading data: {e}')
    raise

# Split data into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Initialize and train the XGBoost model
model = XGBRegressor(objective='reg:squarederror')
try:
    model.fit(X_train, y_train)
    logging.info('Model training complete.')
except Exception as e:
    logging.error(f'Error during model training: {e}')
    raise

# Make predictions and evaluate the model
try:
    predictions = model.predict(X_test)
    mse = mean_squared_error(y_test, predictions)
    logging.info(f'Model evaluation complete. MSE: {mse}')
except Exception as e:
    logging.error(f'Error during prediction: {e}')
    raise

if __name__ == '__main__':
    logging.info('Maintenance forecasting script executed successfully.')