CatBoostWrapper.py

from sklearn.base import BaseEstimator, TransformerMixin
import numpy as np
from catboost import CatBoostRegressor
import pandas as pd
# ---------------------------
# Full  CatBoost
# ---------------------------
class CatBoostWrapper(BaseEstimator):
    def __init__(self, iterations=2000, learning_rate=0.03, depth=6, l2_leaf_reg=5, random_seed=42):
        self.iterations = iterations
        self.learning_rate = learning_rate
        self.depth = depth
        self.l2_leaf_reg = l2_leaf_reg
        self.random_seed = random_seed
        self.model = None

    def fit(self, X, y):
        self.model = CatBoostRegressor(
            iterations=self.iterations,
            learning_rate=self.learning_rate,
            depth=self.depth,
            l2_leaf_reg=self.l2_leaf_reg,
            eval_metric='RMSE',
            random_seed=self.random_seed,
            early_stopping_rounds=100,
            verbose=100
        )
        self.model.fit(X, y)
        return self

    def predict(self, X):
        return self.model.predict(X)

    def feature_importances_(self, feature_names):
        return pd.DataFrame({
            'Feature': feature_names,
            'Importance': self.model.get_feature_importance()
        }).sort_values(by='Importance', ascending=False)