"""
Shared utilities for preprocessing modules.
Provides logging setup, seed initialization, and a timing decorator
used by all dataset-specific preprocessors.
"""

import os
import time
import logging
import random
import numpy as np
import joblib
import pandas as pd
from sklearn.preprocessing import LabelEncoder, StandardScaler, MinMaxScaler
try:
    from utils.project_paths import LOGS_DIR
except ImportError:
    from project_paths import LOGS_DIR

# Setup logging configuration
os.makedirs(LOGS_DIR, exist_ok=True)
logging.basicConfig(
    level=logging.INFO,
    format='%(asctime)s [%(levelname)s] %(message)s',
    handlers=[
        logging.StreamHandler(),
        logging.FileHandler(os.path.join(LOGS_DIR, "preprocessing.log"))
    ]
)
logger = logging.getLogger(__name__)


def set_seeds(seed: int = 42):
    """Set random seeds for reproducibility."""
    random.seed(seed)
    np.random.seed(seed)
    logger.info(f"Random seeds set to {seed} for reproducibility.")


def time_tracker(func):
    """Decorator to measure and log the execution time of functions."""
    def wrapper(*args, **kwargs):
        start_time = time.time()
        logger.info(f"Starting: {func.__name__}")
        result = func(*args, **kwargs)
        elapsed = time.time() - start_time
        logger.info(f"Finished: {func.__name__} ({elapsed:.2f}s)")
        return result
    return wrapper