def fit()

in src/sagemaker_sklearn_extension/preprocessing/base.py [0:0]

• 20 lines of code
• 5 McCabe index (conditional complexity)

    def fit(self, X, y=None):
        """Compute the lower and upper quantile cutoffs and which columns to transform.

        Parameters
        ----------
        X : array-like, shape [n_samples, n_features]
            The data array to transform. Must be numeric, non-sparse, and two-dimensional.

        Returns
        -------
        self : BaseExtremeValueTransformer
        """
        if not 0 <= self.quantile <= 100:
            raise ValueError(
                "Parameter `quantile` {} is invalid. `quantile` must be an integer between 0 and 100".format(
                    self.quantile
                )
            )

        X = check_array(X)
        _, self.n_input_features_ = X.shape

        self.quantiles_ = np.percentile(X, [100 - self.quantile, self.quantile], axis=0)

        nonstandard_threshold_stds = self.threshold_std * np.std(X, axis=0)
        col_means = np.mean(X, axis=0)
        threshold_upper_bound = nonstandard_threshold_stds + col_means
        threshold_lower_bound = -nonstandard_threshold_stds + col_means

        self.cols_to_transform_ = [
            j
            for j in range(self.n_input_features_)
            if self.quantiles_[0, j] < threshold_lower_bound[j] or self.quantiles_[1, j] > threshold_upper_bound[j]
        ]

        return self