params.yaml

# Diamond Price Predictor - Model Parameters and Configuration

# Data Ingestion Configuration
data_ingestion:
  source_url: "data/raw/sample_diamonds.csv"
  local_data_file: "data/raw/diamonds.csv"
  raw_data_path: "data/raw"
  train_test_split_ratio: 0.2
  random_state: 42
  
  # Data validation schema
  required_columns:
    - "carat"
    - "cut" 
    - "color"
    - "clarity"
    - "depth"
    - "table"
    - "price"
    - "x"
    - "y"
    - "z"
  
  # Data type expectations
  column_types:
    carat: "float64"
    cut: "object"
    color: "object"
    clarity: "object"
    depth: "float64"
    table: "float64"
    price: "int64"
    x: "float64"
    y: "float64"
    z: "float64"
  
  # Data validation ranges
  validation_ranges:
    carat: [0.2, 5.01]
    depth: [43.0, 79.0]
    table: [43.0, 95.0]
    price: [326, 18823]
    x: [0.0, 10.74]
    y: [0.0, 58.9]
    z: [0.0, 31.8]

# Model Training Configuration
model_trainer:
  model_name: "xgboost"
  test_size: 0.2
  random_state: 42
  
  # Performance targets
  target_accuracy: 0.95  # 95%+ R² score requirement
  max_training_time_minutes: 10
  cv_folds: 5
  
  # XGBoost hyperparameter search space for optimization
  xgboost:
    n_estimators: [100, 150, 200]
    learning_rate: [0.01, 0.1, 0.2] 
    max_depth: [3, 5, 7]
    subsample: [0.8, 0.9, 1.0]
    colsample_bytree: [0.8, 0.9, 1.0]
    reg_alpha: [0, 0.1, 0.5]
    reg_lambda: [1, 1.5, 2]
    random_state: 42
    
  # Alternative models for comparison
  random_forest:
    n_estimators: [100, 200, 300]
    max_depth: [10, 15, 20]
    min_samples_split: [2, 5, 10]
    min_samples_leaf: [1, 2, 4]
    random_state: 42
    
  # Model evaluation metrics
  metrics:
    - "mean_absolute_error"
    - "mean_squared_error"
    - "root_mean_squared_error" 
    - "r2_score"
    - "mean_absolute_percentage_error"
  primary_metric: "r2_score"
  
  # Hyperparameter optimization
  optimization_method: "grid_search"  # grid_search, random_search
  n_jobs: -1  # Use all available cores
  verbose: 1

# Data Transformation Configuration  
data_transformation:
  preprocessor_obj_file_path: "artifacts/preprocessor.pkl"
  
# Model Evaluation Configuration
model_evaluation:
  model_path: "artifacts/model.pkl"
  target_column: "price"
  
# MLflow Configuration
mlflow:
  experiment_name: "diamond_price_prediction"
  run_name: "xgboost_baseline"
  tracking_uri: "http://localhost:5000"
  
# Logging Configuration
logging:
  level: "INFO"
  format: "%(asctime)s - %(name)s - %(levelname)s - %(message)s"
  file: "logs/diamond_predictor.log"