hypernets.pipeline package¶
Submodules¶
hypernets.pipeline.base module¶
-
class
hypernets.pipeline.base.ColumnTransformer(remainder='drop', sparse_threshold=0.3, n_jobs=None, transformer_weights=None, space=None, name=None, **hyperparams)[source]¶
-
class
hypernets.pipeline.base.DataFrameMapper(default=False, sparse=False, df_out=False, input_df=False, space=None, name=None, **hyperparams)[source]¶
-
class
hypernets.pipeline.base.HyperTransformer(transformer=None, space=None, name=None, **hyperparams)[source]¶
-
class
hypernets.pipeline.base.Pipeline(module_list, columns=None, keep_link=False, space=None, name=None)[source]¶ Bases:
hypernets.core.ops.ConnectionSpace-
input_space_cls¶ alias of
PipelineInput
-
output_space_cls¶ alias of
PipelineOutput
-
hypernets.pipeline.transformers module¶
-
class
hypernets.pipeline.transformers.AsTypeTransformer(dtype, space=None, name=None, **kwargs)[source]¶
-
class
hypernets.pipeline.transformers.Binarizer(threshold=0.0, copy=True, space=None, name=None, **kwargs)[source]¶
-
class
hypernets.pipeline.transformers.FeatureGenerationTransformer(task=None, trans_primitives=None, fix_input=False, continuous_cols=None, datetime_cols=None, max_depth=1, feature_selection_args=None, space=None, name=None, **kwargs)[source]¶
-
class
hypernets.pipeline.transformers.FeatureImportanceSelection(quantile, importances, space=None, name=None, **kwargs)[source]¶
-
class
hypernets.pipeline.transformers.FunctionTransformer(func=None, inverse_func=None, validate=False, accept_sparse=False, check_inverse=True, kw_args=None, inv_kw_args=None, space=None, name=None, **kwargs)[source]¶
-
class
hypernets.pipeline.transformers.KBinsDiscretizer(n_bins=5, encode='onehot', strategy='quantile', space=None, name=None, **kwargs)[source]¶
-
class
hypernets.pipeline.transformers.LabelBinarizer(neg_label=0, pos_label=1, sparse_output=False, space=None, name=None, **kwargs)[source]¶
-
class
hypernets.pipeline.transformers.LogStandardScaler(copy=True, with_mean=True, with_std=True, space=None, name=None, **kwargs)[source]¶
-
class
hypernets.pipeline.transformers.MaxAbsScaler(copy=True, space=None, name=None, **kwargs)[source]¶
-
class
hypernets.pipeline.transformers.MinMaxScaler(feature_range=(0, 1), copy=True, space=None, name=None, **kwargs)[source]¶
-
class
hypernets.pipeline.transformers.MultiLabelBinarizer(classes=None, sparse_output=False, space=None, name=None, **kwargs)[source]¶
-
class
hypernets.pipeline.transformers.MultiLabelEncoder(columns=None, space=None, name=None, **kwargs)[source]¶
-
class
hypernets.pipeline.transformers.MultiTargetEncoder(n_folds=None, smooth=None, split_method=None, space=None, name=None, **kwargs)[source]¶
-
class
hypernets.pipeline.transformers.Normalizer(norm='l2', copy=True, space=None, name=None, **kwargs)[source]¶
-
class
hypernets.pipeline.transformers.OneHotEncoder(categories='auto', drop=None, sparse=True, dtype=<class 'numpy.float64'>, space=None, name=None, **kwargs)[source]¶
-
class
hypernets.pipeline.transformers.OrdinalEncoder(categories='auto', dtype=<class 'numpy.float64'>, space=None, name=None, **kwargs)[source]¶
-
class
hypernets.pipeline.transformers.PCA(n_components=None, copy=True, whiten=False, svd_solver='auto', tol=0.0, iterated_power='auto', random_state=None, space=None, name=None, **kwargs)[source]¶
-
class
hypernets.pipeline.transformers.PassThroughEstimator(space=None, name=None, **kwargs)[source]¶
-
class
hypernets.pipeline.transformers.PolynomialFeatures(degree=2, interaction_only=False, include_bias=True, order='C', space=None, name=None, **kwargs)[source]¶
-
class
hypernets.pipeline.transformers.PowerTransformer(method='yeo-johnson', standardize=True, copy=True, space=None, name=None, **kwargs)[source]¶
-
class
hypernets.pipeline.transformers.QuantileTransformer(n_quantiles=1000, output_distribution='uniform', ignore_implicit_zeros=False, subsample=100000, random_state=None, copy=True, space=None, name=None, **kwargs)[source]¶
-
class
hypernets.pipeline.transformers.RobustScaler(with_centering=True, with_scaling=True, quantile_range=(25.0, 75.0), copy=True, space=None, name=None, **kwargs)[source]¶
-
class
hypernets.pipeline.transformers.SafeOneHotEncoder(categories='auto', drop=None, sparse=True, dtype=<class 'numpy.float64'>, space=None, name=None, **kwargs)[source]¶
-
class
hypernets.pipeline.transformers.SafeOrdinalEncoder(categories='auto', dtype=<class 'numpy.float64'>, space=None, name=None, **kwargs)[source]¶
-
class
hypernets.pipeline.transformers.SimpleImputer(missing_values=nan, strategy='mean', fill_value=None, verbose=0, copy=True, add_indicator=False, space=None, name=None, force_output_as_float=False, **kwargs)[source]¶
-
class
hypernets.pipeline.transformers.SkewnessKurtosisTransformer(transform_fn=None, space=None, name=None, **kwargs)[source]¶
-
class
hypernets.pipeline.transformers.StandardScaler(copy=True, with_mean=True, with_std=True, space=None, name=None, **kwargs)[source]¶
-
class
hypernets.pipeline.transformers.TfidfEncoder(flatten=None, space=None, name=None, **kwargs)[source]¶