nonstationary_feature_remover.py

from sklearn.base import BaseEstimator, TransformerMixin
import lightgbm as lgb
import numpy as np
import pandas as pd

class NonstationaryFeatureRemover(BaseEstimator, TransformerMixin):
    def __init__(self, remove_count=None, remove_ratio=None):
        if remove_count and remove_ratio:
            raise Exception('remove_count and remove_ratio cannot be set simultaneously')
        self.remove_count = remove_count
        self.remove_ratio = remove_ratio

    def fit(self, X, y=None):
        X = self._validate_data(X)

        model = lgb.LGBMRegressor(n_jobs=-1, random_state=1)

        model.fit(X, np.arange(X.shape[0]))
        importances = model.feature_importances_

        if self.remove_count:
            remove_count = self.remove_count
        else:
            remove_count = int(self.remove_ratio * X.shape[1])

        features = list(range(X.shape[1]))
        feature_imp = pd.DataFrame(zip(importances, features), columns=['value', 'feature'])
        feature_imp = feature_imp.sort_values('value')

        for i in range(X.shape[1] - remove_count, X.shape[1]):
            features.remove(int(feature_imp['feature'].iloc[i]))

        self.selected_features_ = np.array(features)

        return self

    def transform(self, X, y=None):
        X = self._validate_data(X)

        return X[:, self.selected_features_].copy()

    def inverse_transform(self, X, y=None):
        raise Exception('inverse_transform not implemented')