helper class to make custom mentrics easier in sklearn

FuncScorer.py

import numpy as np

from sklearn.preprocessing import QuantileTransformer
from sklearn.metrics._scorer import _BaseScorer


class FuncScorer(_BaseScorer):
    def _score(self, method_caller, estimator, X, y_true, sample_weight=None):
        """Evaluate predicted target values for X relative to y_true.

        Parameters
        ----------
        method_caller : callable
            Returns predictions given an estimator, method name, and other
            arguments, potentially caching results.

        estimator : object
            Trained estimator to use for scoring. Must have a `predict`
            method; the output of that is used to compute the score.

        X : {array-like, sparse matrix}
            Test data that will be fed to estimator.predict.

        y_true : array-like
            Gold standard target values for X.

        sample_weight : array-like of shape (n_samples,), default=None
            Sample weights.

        Returns
        -------
        score : float
            Score function applied to prediction of estimator on X.
        """

        y_pred = method_caller(estimator, "predict", X)
        if sample_weight is not None:
            return self._sign * self._score_func(estimator, X, y_true, y_pred, sample_weight=sample_weight, **self._kwargs)
        else:
            return self._sign * self._score_func(estimator, X, y_true, y_pred, **self._kwargs)