def transform(dataframe: pd.DataFrame, scaler: TransformerMixin) -> pd.DataFrame: fields_to_normalize = dataframe.filter( ['preco', 'prazo', 'frete', 'latitude', 'longitude']).to_numpy() feature_scaled = scaler.fit_transform(fields_to_normalize) dataframe['features'] = list(feature_scaled) return dataframe
def _fit_transform_with_state_restore_check(transformer: TransformerMixin, X, **kwargs): transformed = transformer.fit_transform(X, **kwargs) LOGGER.debug('transformed: %s', transformed) LOGGER.debug('transformed.shape: %s', transformed.shape) restored_transformer = _get_state_and_restore(transformer) restored_transformed = restored_transformer.transform(X) LOGGER.debug('restored_transformed: %s', restored_transformed) assert restored_transformed.tolist() == transformed.tolist() return transformed
def produce_fit(kmeans_alg, features: np.ndarray, transformer: TransformerMixin): start_time = perf_counter() # dim reduction features_transformed = transformer.fit_transform(features) # K-means return kmeans_alg.fit_predict(features_transformed), perf_counter() - start_time
def scale_data(dataset: array, scaler: TransformerMixin) -> array: assert scaler is not None and dataset is not None return scaler.fit_transform(dataset)