config/config.py

# ============================================
# ENUMERATION CLASSES
# ============================================
from dataclasses import asdict, dataclass, field
from enum import Enum
import json
import logging
from pathlib import Path
from typing import Dict, List, Optional
from venv import logger


class DataType(Enum):
    """Data types"""
    NUMERIC = "numeric"
    CATEGORICAL = "categorical"
    TEMPORAL = "temporal"
    TEXT = "text"


class PreprocessingMethod(Enum):
    """Data preprocessing methods"""
    FILL_MEAN = "fill_mean"
    FILL_MEDIAN = "fill_median"
    FILL_INTERPOLATE = "fill_interpolate"
    FILL_KNN = "fill_knn"
    REMOVE = "remove"
    CLIP = "clip"
    WINSORIZE = "winsorize"
    NORMALIZE = "normalize"
    STANDARDIZE = "standardize"
    LOG_TRANSFORM = "log_transform"
    BOX_COX = "box_cox"
    DIFFERENCING = "differencing"


class SeasonalityType(Enum):
    """Seasonality types"""
    DAILY = "daily"
    WEEKLY = "weekly"
    MONTHLY = "monthly"
    QUARTERLY = "quarterly"
    YEARLY = "yearly"
    MULTIPLE = "multiple"


# ============================================
# CLASS 1: CONFIGURATION
# ============================================
@dataclass
class Config:
    """Experiment configuration for data preprocessing"""
    
    # Paths and directories
    data_path: str = 'temp_data.csv'
    results_dir: str = 'data_preprocessing_results'
    
    # Temporal parameters
    start_year: int = 1970
    end_year: int = 1990
    freq: str = 'D'  # Data frequency: D (daily), H (hourly), M (monthly)
    
    # Target variable
    target_column: str = 'raskhodvoda'
    
    # Feature parameters
    max_lags: int = 12
    seasonal_period: int = 365
    rolling_windows: List[int] = field(default_factory=lambda: [7, 30, 90, 365])
    expanding_windows: List[int] = field(default_factory=lambda: [30, 90, 365])
    
    # Processing parameters
    missing_threshold: float = 0.3  # Threshold for dropping columns with missing values
    outlier_method: str = 'iqr'  # Outlier detection method: iqr, zscore, lof
    outlier_alpha: float = 1.5  # IQR multiplier
    outlier_contamination: float = 0.1  # For methods like LOF
    
    # Data splitting
    test_size: float = 0.2
    validation_size: float = 0.1
    split_method: str = 'time'  # time, random, expanding_window
    
    # Scaling
    scaling_method: str = 'robust'  # standard, minmax, robust, none
    
    # Feature selection
    feature_selection_method: str = 'correlation'  # correlation, mutual_info, rf, pca
    max_features: int = 50
    
    # Validation
    enable_validation: bool = True
    validation_rules: Dict = field(default_factory=dict)
    
    # Visualisation
    save_plots: bool = True
    plot_style: str = 'seaborn'
    
    # Performance
    use_multiprocessing: bool = False
    n_jobs: int = -1
    chunk_size: int = 10000
    
    # Logging
    log_level: str = 'INFO'
    save_reports: bool = True
    
    def __post_init__(self):
        """Post-initialisation for creating directories and setting up logging"""
        self.create_directories()
        self.setup_logging()
        
        # Setting default validation rules
        if not self.validation_rules:
            self.validation_rules = {
                'min_rows': 100,
                'max_missing_percentage': 30,
                'min_unique_values': 2,
                'max_skewness': 3,
                'max_kurtosis': 10
            }
    
    def create_directories(self) -> None:
        """Create directories for preprocessing results"""
        dirs = [
            self.results_dir,
            f'{self.results_dir}/plots',
            f'{self.results_dir}/plots/time_series',
            f'{self.results_dir}/plots/distributions',
            f'{self.results_dir}/plots/correlations',
            f'{self.results_dir}/plots/features',
            f'{self.results_dir}/tables',
            f'{self.results_dir}/processed_data',
            f'{self.results_dir}/models',
            f'{self.results_dir}/reports',
            f'{self.results_dir}/logs',
            f'{self.results_dir}/checkpoints'
        ]
        
        for directory in dirs:
            Path(directory).mkdir(parents=True, exist_ok=True)
        
        logger.info(f"Directories created in {self.results_dir}")
    
    def setup_logging(self) -> None:
        """Configure logging"""
        log_level = getattr(logging, self.log_level.upper())
        logger.setLevel(log_level)
    
    def to_dict(self) -> Dict:
        """Convert configuration to dictionary"""
        return asdict(self)
    
    def save(self, path: Optional[str] = None) -> None:
        """Save configuration to file"""
        if path is None:
            path = f'{self.results_dir}/config.json'
        
        with open(path, 'w', encoding='utf-8') as f:
            json.dump(self.to_dict(), f, indent=4, ensure_ascii=False)
        
        logger.info(f"Configuration saved to {path}")
    
    @classmethod
    def load(cls, path: str) -> 'Config':
        """Load configuration from file"""
        with open(path, 'r', encoding='utf-8') as f:
            config_dict = json.load(f)
        
        return cls(**config_dict)