def fit()

in src/sagemaker_sklearn_extension/feature_extraction/sequences.py [0:0]

• 23 lines of code
• 4 McCabe index (conditional complexity)

    def fit(self, X, y=None):
        X = check_array(X, dtype=None, force_all_finite="allow-nan")

        if self.sequences_lengths_q25 is None:
            self.sequences_lengths_q25 = [DEFAULT_INPUT_SEQUENCE_LENGTH] * X.shape[1]

        if len(self.sequences_lengths_q25) != X.shape[1]:
            raise ValueError(
                f"length of sequences_lengths_q25 should be equal to number of columns in X (={X.shape[1]})."
            )

        ts_flattener = TSFlattener(max_allowed_length=self.max_allowed_length, trim_beginning=self.trim_beginning)
        tsfresh_feature_extractors = []
        for sequence_column_i, sequence_column in enumerate(X.T):
            numeric_sequences = ts_flattener.transform(sequence_column.reshape(-1, 1))
            tsfresh_feature_extractor = TSFreshFeatureExtractor(
                augment=self.augment,
                interpolation_method=self.interpolation_method,
                extraction_type=self.extraction_type,
                extraction_seed=self.extraction_seed,
                sequence_length_q25=self.sequences_lengths_q25[sequence_column_i],
            )
            tsfresh_feature_extractor.fit(numeric_sequences)
            tsfresh_feature_extractors.append(tsfresh_feature_extractor)
        self.tsfresh_feature_extractors_ = tsfresh_feature_extractors
        return self