khiops.sklearn.estimators

Submodule of khiops.sklearn

Scikit-Learn Estimator Classes for the Khiops AutoML Suite

Class Overview

The diagram below describes the relationships in this module:

KhiopsEstimator(ABC, BaseEstimator)
    |
    +- KhiopsCoclustering(ClusterMixin)
    |
    +- KhiopsSupervisedEstimator
       |
       +- KhiopsPredictor
       |  |
       |  +- KhiopsClassifier(ClassifierMixin)
       |  |
       |  +- KhiopsRegressor(RegressorMixin)
       |
       +- KhiopsEncoder(TransformerMixin)

CLASS	DESCRIPTION
`KhiopsEstimator`	Base class for Khiops Scikit-learn estimators
`KhiopsCoclustering`	A Khiops Coclustering model
`KhiopsSupervisedEstimator`	Abstract Khiops Supervised Estimator
`KhiopsPredictor`	Abstract Khiops Selective Naive Bayes Predictor
`KhiopsClassifier`	Khiops Selective Naive Bayes Classifier
`KhiopsRegressor`	Khiops Selective Naive Bayes Regressor
`KhiopsEncoder`	Khiops supervised discretization/grouping encoder

Classes

`KhiopsEstimator(n_cores=None, verbose=False, output_dir=None, auto_sort=True)`

Bases: ABC, BaseEstimator

Base class for Khiops Scikit-learn estimators

Note

The input features collection X needs to have single-line records so that Khiops can handle them. Hence, multi-line records are preprocessed: carriage returns / line feeds are replaced with blank spaces before being handed over to Khiops.

PARAMETER	DESCRIPTION
`n_cores`	Maximum number of CPU cores allocated and used for all estimator operations. TYPE: `int` DEFAULT: `None`
`verbose`	If `True` it prints debug information and it does not erase temporary files when fitting, predicting or transforming. TYPE: `bool` DEFAULT: `False`
`output_dir`	Path of the output directory for the resulting artifacts of Khiops learning tasks. See concrete estimator classes for more information about this parameter. TYPE: `str` DEFAULT: `None`
`auto_sort`	Advanced.: See concrete estimator classes for information about this parameter. TYPE: `bool` DEFAULT: `True`

METHOD	DESCRIPTION
`export_report_file`	Exports the model report to a JSON file
`export_dictionary_file`	Export the model's Khiops dictionary file (.kdic)
`fit`	Fit the estimator

Methods:

`export_report_file(report_file_path)`

Exports the model report to a JSON file

PARAMETER	DESCRIPTION
`report_file_path`	The location of the exported report file. TYPE: `str`

RAISES	DESCRIPTION
`ValueError`	When the instance is not fitted.

`export_dictionary_file(dictionary_file_path)`

Export the model's Khiops dictionary file (.kdic)

`fit(X, y=None, **kwargs)`

Fit the estimator

PARAMETER	DESCRIPTION
`X`	Training dataset. Either an array-like or a dict specification for multi-table datasets (see Multi-Table Learning Primer). TYPE: `array-like of shape (n_samples, n_features_in) or dict`
`y`	The target values. TYPE: `array-like of shape (n_samples,)` DEFAULT: `None`

RETURNS	DESCRIPTION
`self`	The fitted estimator instance. TYPE: `KhiopsEstimator`

`KhiopsCoclustering(verbose=False, output_dir=None, auto_sort=True, build_name_var=True, build_distance_vars=False, build_frequency_vars=False, n_cores=None)`

Bases: ClusterMixin, KhiopsEstimator

A Khiops Coclustering model

A coclustering is a non-supervised piecewise constant density estimator.

PARAMETER	DESCRIPTION
`build_distance_vars`	If `True` includes a cluster distance variable in the deployment TYPE: `bool` DEFAULT: `False`
`build_frequency_vars`	If `True` includes the frequency variables in the deployment. TYPE: `bool` DEFAULT: `False`
`build_name_var`	If `True` includes a cluster id variable in the deployment. TYPE: `bool` DEFAULT: `False`
`verbose`	If `True` it prints debug information and it does not erase temporary files when fitting, predicting or transforming. TYPE: `bool` DEFAULT: `False`
`output_dir`	Path of the output directory for the `Coclustering.khcj` report file and the `Coclustering.kdic` modeling dictionary file. TYPE: `str` DEFAULT: `None`
`auto_sort`	Advanced. Only for multi-table inputs: If `True` input tables are automatically sorted by their key before executing Khiops. If the input tables are already sorted by their keys set this parameter to `False` to speed up the processing. This affects the predict method. Note The sort by key is performed in a left-to-right, hierarchical, lexicographic manner. TYPE: `bool` DEFAULT: `True`
`n_cores`	Maximum number of CPU cores allocated and used for all estimator operations. TYPE: `int` DEFAULT: `None`

ATTRIBUTE	DESCRIPTION
`is_multitable_model_`	`True` if the model was fitted on a multi-table dataset. TYPE: `bool`
`model_`	The Khiops dictionary domain for the trained coclustering. For coclustering it is a multi-table dictionary even though the model is single-table. TYPE: `DictionaryDomain`
`model_main_dictionary_name_`	The name of the main Khiops dictionary within the `model_` domain. TYPE: `str`
`model_report_`	The Khiops report object. TYPE: `CoclusteringResults`

Examples:

See the following functions of the samples_sklearn.py documentation script: - samples_sklearn.khiops_coclustering()

METHOD	DESCRIPTION
`fit`	Trains a Khiops Coclustering model
`simplify`	Creates a simplified coclustering model from the current instance
`predict`	Predicts the most probable cluster for the test dataset X
`fit_predict`	Performs clustering on X and returns result (instead of labels)

Methods:

`fit(X, y=None, **kwargs)`

Trains a Khiops Coclustering model

PARAMETER	DESCRIPTION
`X`	Training dataset. Either an array-like or a dict specification for multi-table datasets (see Multi-Table Learning Primer). TYPE: `array-like of shape (n_samples, n_features_in) or dict`
`id_column`	The column that contains the id of the instance. TYPE: `str`
`columns`	The columns to be co-clustered. If not specified it uses all columns. TYPE: `list`

RETURNS	DESCRIPTION
`self`	The calling estimator instance. TYPE: `KhiopsCoclustering`

`simplify(max_preserved_information=0, max_cells=0, max_total_parts=0, max_part_numbers=None)`

Creates a simplified coclustering model from the current instance

PARAMETER	DESCRIPTION
`max_preserved_information`	Maximum information preserve in the simplified coclustering. If equal to 0 there is no limit. TYPE: `int` DEFAULT: `0`
`max_cells`	Maximum number of cells in the simplified coclustering. If equal to 0 there is no limit. TYPE: `int` DEFAULT: `0`
`max_total_parts`	Maximum number of parts totaled over all variables. If equal to 0 there is no limit. TYPE: `int` DEFAULT: `0`
`max_part_numbers`	Maximum number of clusters for each of the co-clustered column. Specifically, a key-value pair of this dictionary represents the column name and its respective maximum number of clusters. If not specified, then no maximum number of clusters is imposed on any column. TYPE: `dict` DEFAULT: `None`

RETURNS	DESCRIPTION
`self`	A new, simplified KhiopsCoclustering estimator instance. TYPE: `KhiopsCoclustering`

`predict(X)`

Predicts the most probable cluster for the test dataset X

PARAMETER	DESCRIPTION
`X`	Training dataset. Either an array-like or a dict specification for multi-table datasets (see Multi-Table Learning Primer). TYPE: `array-like of shape (n_samples, n_features_in) or dict`

RETURNS	DESCRIPTION
`ndarray <numpy.ndarray>`	An array containing the encoded columns. A first column containing key column ids is added in multi-table mode.

`fit_predict(X, y=None, **kwargs)`

Performs clustering on X and returns result (instead of labels)

PARAMETER	DESCRIPTION
`X`	Training dataset. Either an array-like or a dict specification for multi-table datasets (see Multi-Table Learning Primer). TYPE: `array-like of shape (n_samples, n_features_in) or dict`
`y`	The target values. TYPE: `array-like of shape (n_samples,)` DEFAULT: `None`

RETURNS	DESCRIPTION
`results`	TYPE: `numpy.array`

`KhiopsSupervisedEstimator(n_features=1000, n_trees=10, n_text_features=10000, type_text_features='words', specific_pairs=None, all_possible_pairs=True, construction_rules=None, n_feature_parts=0, keep_selected_variables_only=True, verbose=False, output_dir=None, auto_sort=True, n_cores=None)`

Bases: KhiopsEstimator

Abstract Khiops Supervised Estimator

METHOD	DESCRIPTION
`fit`	Fits a supervised estimator according to X,y

Methods:

`fit(X, y=None, **kwargs)`

Fits a supervised estimator according to X,y

Called by the concrete sub-classes KhiopsEncoder, KhiopsClassifier, KhiopsRegressor.

PARAMETER	DESCRIPTION
`X`	Training dataset. Either an array-like or a dict specification for multi-table datasets (see Multi-Table Learning Primer). TYPE: `array-like of shape (n_samples, n_features_in) or dict`
`y`	The target values. TYPE: `array-like of shape (n_samples,)` DEFAULT: `None`

RETURNS	DESCRIPTION
`self`	The calling estimator instance. TYPE: `KhiopsSupervisedEstimator`

`KhiopsPredictor(n_features=1000, n_trees=10, n_text_features=10000, type_text_features='words', n_selected_features=0, n_evaluated_features=0, specific_pairs=None, all_possible_pairs=True, construction_rules=None, n_feature_parts=0, keep_selected_variables_only=True, verbose=False, output_dir=None, auto_sort=True, n_cores=None)`

Bases: KhiopsSupervisedEstimator

Abstract Khiops Selective Naive Bayes Predictor

METHOD	DESCRIPTION
`predict`	Predicts the target variable for the test dataset X

Methods:

`predict(X)`

Predicts the target variable for the test dataset X

See the documentation of concrete subclasses for more details.

`KhiopsClassifier(n_features=1000, n_pairs=0, n_trees=10, n_text_features=10000, type_text_features='words', n_selected_features=0, n_evaluated_features=0, specific_pairs=None, all_possible_pairs=True, construction_rules=None, n_feature_parts=0, group_target_value=False, keep_selected_variables_only=True, verbose=False, output_dir=None, auto_sort=True, n_cores=None)`

Bases: ClassifierMixin, KhiopsPredictor

Khiops Selective Naive Bayes Classifier

This classifier supports automatic feature engineering on multi-table datasets. See Multi-Table Learning Primer for more details.

Note

Visit the Khiops site to learn about the automatic feature engineering algorithm.

PARAMETER	DESCRIPTION
`n_features`	Maximum number of features to construct automatically. See Multi-Table Learning Primer for more details on the multi-table-specific features. TYPE: `int` DEFAULT: `1000`
`n_pairs`	Maximum number of pair features to construct. These features exploit bivariate partitions of native or automatically constructed variables, excluding features derived from the text variables. TYPE: `int` DEFAULT: `0`
`n_trees`	Maximum number of decision trees to construct. The trees combine native variables and automatically constructed variables, excluding features derived from the text variables or from variable pairs. Decision trees usually improve the classifier's performance at the cost of the interpretability of the model. TYPE: `int` DEFAULT: `10`
`n_text_features`	Maximum number of text features to construct. TYPE: `int` DEFAULT: `10000`
`type_text_features`	Type of the text features to construct. Can be either one of: - "words": sequences of non-space characters - "ngrams": sequences of bytes - "tokens": user-defined TYPE: `str` DEFAULT: `"words"`
`n_selected_features`	Maximum number of features to be selected in the SNB predictor. If equal to 0 it selects all the features kept in the training. TYPE: `int` DEFAULT: `0`
`n_evaluated_features`	Maximum number of features to be evaluated in the SNB predictor training. If equal to 0 it evaluates all informative features. TYPE: `int` DEFAULT: `0`
`specific_pairs`	User-specified pairs as a list of 2-tuples of feature names. If a given tuple contains only one non-empty feature name, then it generates all the pairs containing it (within the maximum limit `n_pairs`). These pairs have top priority: they are constructed first. TYPE: `list of tuple` DEFAULT: `None`
`all_possible_pairs`	If `True` tries to create all possible pairs within the limit `n_pairs`. Pairs specified with `specific_pairs` have top priority: they are constructed first. TYPE: `bool` DEFAULT: `True`
`construction_rules`	Allowed rules for the automatic feature construction. If not set, Khiops uses the multi-table construction rules listed in `kh.DEFAULT_CONSTRUCTION_RULES <khiops.core.api.DEFAULT_CONSTRUCTION_RULES>`. TYPE: `list of str` DEFAULT: `None`
`n_feature_parts`	Maximum number of variable parts produced by preprocessing methods. If equal to 0 it is automatically calculated. TYPE: `int` DEFAULT: `0`
`group_target_value`	Allows grouping of the target values in classification. It can substantially increase the training time. TYPE: `bool` DEFAULT: `False`
`keep_selected_variables_only`	Keeps only predictor-selected variables in the supervised analysis report. TYPE: `bool` DEFAULT: `True`
`verbose`	If `True` it prints debug information and it does not erase temporary files when fitting, predicting or transforming. TYPE: `bool` DEFAULT: `False`
`output_dir`	Path of the output directory for the `AllReports.khj` report file and the `Modeling.kdic` modeling dictionary file. By default these files are deleted. TYPE: `str` DEFAULT: `None`
`auto_sort`	Advanced. Only for multi-table inputs: If `True` input tables are pre-sorted by their key before executing Khiops. If the input tables are already sorted by their keys set this parameter to `False` to speed up the processing. This affects the fit, predict and predict_proba methods. Note The sort by key is performed in a left-to-right, hierarchical, lexicographic manner. TYPE: `bool` DEFAULT: `True`
`n_cores`	Maximum number of CPU cores allocated and used for all estimator operations. TYPE: `int` DEFAULT: `None`

ATTRIBUTE	DESCRIPTION
`n_classes_`	The number of classes seen in training. TYPE: `int`
`classes_`	The list of classes seen in training. Depending on the training target, the contents are `int` or `str`. TYPE: `ndarray <numpy.ndarray>` of shape (n_classes\_,)
`n_features_in_`	The number of features in the main table of the training dataset. TYPE: `int`
`is_multitable_model_`	`True` if the model was fitted on a multi-table dataset. TYPE: `bool`
`model_`	The Khiops dictionary domain for the trained classifier. TYPE: `DictionaryDomain`
`model_main_dictionary_name_`	The name of the main Khiops dictionary within the `model_` domain. TYPE: `str`
`model_report_`	The Khiops report object. TYPE: `AnalysisResults`

Examples:

See the following functions of the samples_sklearn.py documentation script: - samples_sklearn.khiops_classifier() - samples_sklearn.khiops_classifier_multiclass() - samples_sklearn.khiops_classifier_multitable_star() - samples_sklearn.khiops_classifier_multitable_snowflake() - samples_sklearn.khiops_classifier_pickle()

METHOD	DESCRIPTION
`fit`	Fits a Selective Naive Bayes classifier according to X, y
`predict`	Predicts the most probable class for the test dataset X
`predict_proba`	Predicts the class probabilities for the test dataset X

Methods:

`fit(X, y, **kwargs)`

Fits a Selective Naive Bayes classifier according to X, y

PARAMETER	DESCRIPTION
`X`	Training dataset. Either an array-like or a dict specification for multi-table datasets (see Multi-Table Learning Primer). TYPE: `array-like of shape (n_samples, n_features_in) or dict`
`y`	The target values. TYPE: `array-like of shape (n_samples,)`

RETURNS	DESCRIPTION
`self`	The calling estimator instance. TYPE: `KhiopsClassifier`

`predict(X)`

Predicts the most probable class for the test dataset X

The predicted class of an input sample is the arg-max of the conditional probabilities P(y|X) for each value of y.

PARAMETER	DESCRIPTION
`X`	Training dataset. Either an array-like or a dict specification for multi-table datasets (see Multi-Table Learning Primer). TYPE: `array-like of shape (n_samples, n_features_in) or dict`

RETURNS	DESCRIPTION
`ndarray <numpy.ndarray>`	An array containing the encoded columns. A first column containing key column ids is added in multi-table mode. The numpy.dtype of the array matches the type of `y` used during training. It will be integer, float, or boolean if the classifier was trained with a `y` of the corresponding type. Otherwise it will be `str`. The key columns are added for multi-table tasks.

`predict_proba(X)`

Predicts the class probabilities for the test dataset X

PARAMETER	DESCRIPTION
`X`	Training dataset. Either an array-like or a dict specification for multi-table datasets (see Multi-Table Learning Primer). TYPE: `array-like of shape (n_samples, n_features_in) or dict`

RETURNS	DESCRIPTION
`ndarray or str`	The probability of the samples for each class in the model. The columns are named with the pattern `Prob<class>` for each `<class>` found in the training dataset. The output data container is of type numpy.ndarray. The key columns are added for multi-table tasks.

`KhiopsRegressor(n_features=1000, n_trees=0, n_text_features=10000, type_text_features='words', n_selected_features=0, n_evaluated_features=0, construction_rules=None, n_feature_parts=0, keep_selected_variables_only=True, verbose=False, output_dir=None, auto_sort=True, n_cores=None)`

Bases: RegressorMixin, KhiopsPredictor

Khiops Selective Naive Bayes Regressor

This regressor supports automatic feature engineering on multi-table datasets. See Multi-Table Learning Primer for more details.

Note

Visit the Khiops site to learn about the automatic feature engineering algorithm.

PARAMETER	DESCRIPTION
`n_features`	Maximum number of features to construct automatically. See Multi-Table Learning Primer for more details on the multi-table-specific features. TYPE: `int` DEFAULT: `1000`
`n_trees`	Maximum number of decision trees to construct. The trees combine native variables and automatically constructed variables, excluding features derived from the text variables or from variable pairs. Decision trees usually improve the regressor's performance at the cost of the interpretability of the model. TYPE: `int` DEFAULT: `10`
`n_text_features`	Maximum number of text features to construct. TYPE: `int` DEFAULT: `10000`
`type_text_features`	Type of the text features to construct. Can be either one of: - "words": sequences of non-space characters - "ngrams": sequences of bytes - "tokens": user-defined TYPE: `str` DEFAULT: `"words"`
`n_selected_features`	Maximum number of features to be selected in the SNB predictor. If equal to 0 it selects all the features kept in the training. TYPE: `int` DEFAULT: `0`
`n_evaluated_features`	Maximum number of features to be evaluated in the SNB predictor training. If equal to 0 it evaluates all informative features. TYPE: `int` DEFAULT: `0`
`construction_rules`	Allowed rules for the automatic feature construction. If not set, Khiops uses the multi-table construction rules listed in `kh.DEFAULT_CONSTRUCTION_RULES <khiops.core.api.DEFAULT_CONSTRUCTION_RULES>`. TYPE: `list of str` DEFAULT: `None`
`n_feature_parts`	Maximum number of variable parts produced by preprocessing methods. If equal to 0 it is automatically calculated. TYPE: `int` DEFAULT: `0`
`keep_selected_variables_only`	Keeps only predictor-selected variables in the supervised analysis report. TYPE: `bool` DEFAULT: `True`
`verbose`	If `True` it prints debug information and it does not erase temporary files when fitting, predicting or transforming. TYPE: `bool` DEFAULT: `False`
`output_dir`	Path of the output directory for the `AllReports.khj` report file and the `Modeling.kdic` modeling dictionary file. By default these files are deleted. TYPE: `str` DEFAULT: `None`
`auto_sort`	Advanced. Only for multi-table inputs: If `True` input tables are pre-sorted by their key before executing Khiops. If the input tables are already sorted by their keys set this parameter to `False` to speed up the processing. This affects the fit and predict methods. Note The sort by key is performed in a left-to-right, hierarchical, lexicographic manner. TYPE: `bool` DEFAULT: `True`
`n_cores`	Maximum number of CPU cores allocated and used for all estimator operations. TYPE: `int` DEFAULT: `None`

ATTRIBUTE	DESCRIPTION
`n_features_in_`	The number of features in the main table of the training dataset. TYPE: `int`
`is_multitable_model_`	`True` if the model was fitted on a multi-table dataset. TYPE: `bool`
`model_`	The Khiops dictionary domain for the trained regressor. TYPE: `DictionaryDomain`
`model_main_dictionary_name_`	The name of the main Khiops dictionary within the `model_` domain. TYPE: `str`
`model_report_`	The Khiops report object. TYPE: `AnalysisResults`

Examples:

See the following functions of the samples_sklearn.py documentation script: - samples_sklearn.khiops_regressor()

METHOD	DESCRIPTION
`fit`	Fits a Selective Naive Bayes regressor according to X, y
`predict`	Predicts the regression values for the test dataset X

Methods:

`fit(X, y=None, **kwargs)`

Fits a Selective Naive Bayes regressor according to X, y

Warning

Make sure that the type of y is float. This is easily done with y = y.astype(float).

PARAMETER	DESCRIPTION
`X`	Training dataset. Either an array-like or a dict specification for multi-table datasets (see Multi-Table Learning Primer). TYPE: `array-like of shape (n_samples, n_features_in) or dict`
`y`	The target values. TYPE: `array-like of shape (n_samples,)` DEFAULT: `None`

RETURNS	DESCRIPTION
`self`	The calling estimator instance. TYPE: `KhiopsRegressor`

`predict(X)`

Predicts the regression values for the test dataset X

The predicted value is estimated by the Selective Naive Bayes Regressor learned during fit step.

PARAMETER	DESCRIPTION
`X`	Training dataset. Either an array-like or a dict specification for multi-table datasets (see Multi-Table Learning Primer). TYPE: `array-like of shape (n_samples, n_features_in) or dict`

RETURNS	DESCRIPTION
`ndarray or str`	An array containing the encoded columns. A first column containing key column ids is added in multi-table mode. The key columns are added for multi-table tasks. The array is in the form of a numpy.ndarray if X is array-like, or dataset spec containing pandas.DataFrame tables.

`KhiopsEncoder(categorical_target=True, n_features=1000, n_pairs=0, n_trees=0, n_text_features=10000, type_text_features='words', specific_pairs=None, all_possible_pairs=True, construction_rules=None, n_feature_parts=0, informative_features_only=True, group_target_value=False, keep_initial_variables=False, transform_type_categorical='part_id', transform_type_numerical='part_id', transform_type_pairs='part_id', verbose=False, output_dir=None, auto_sort=True, n_cores=None)`

Bases: TransformerMixin, KhiopsSupervisedEstimator

Khiops supervised discretization/grouping encoder

PARAMETER	DESCRIPTION
`categorical_target`	`True` if the target column is categorical. TYPE: `bool` DEFAULT: `True`
`n_features`	Maximum number of features to construct automatically. See Multi-Table Learning Primer for more details on the multi-table-specific features. TYPE: `int` DEFAULT: `1000`
`n_pairs`	Maximum number of pair features to construct. These features exploit bivariate partitions of native or automatically constructed variables, excluding features derived from the text variables. TYPE: `int` DEFAULT: `0`
`n_trees`	Maximum number of decision trees to construct. The trees combine native variables and automatically constructed variables, excluding features derived from the text variables or from variable pairs. Decision trees usually improve the encoder's performance at the cost of the interpretability of the model. TYPE: `int` DEFAULT: `10`
`n_text_features`	Maximum number of text features to construct. TYPE: `int` DEFAULT: `10000`
`type_text_features`	Type of the text features to construct. Can be either one of: - "words": sequences of non-space characters - "ngrams": sequences of bytes - "tokens": user-defined TYPE: `str` DEFAULT: `"words"`
`specific_pairs`	User-specified pairs as a list of 2-tuples of feature names. If a given tuple contains only one non-empty feature name, then it generates all the pairs containing it (within the maximum limit `n_pairs`). These pairs have top priority: they are constructed first. TYPE: `list of tuple` DEFAULT: `None`
`all_possible_pairs`	If `True` tries to create all possible pairs within the limit `n_pairs`. Pairs specified with `specific_pairs` have top priority: they are constructed first. TYPE: `bool` DEFAULT: `True`
`construction_rules`	Allowed rules for the automatic feature construction. If not set, Khiops uses the multi-table construction rules listed in `kh.DEFAULT_CONSTRUCTION_RULES <khiops.core.api.DEFAULT_CONSTRUCTION_RULES>`. TYPE: `list of str` DEFAULT: `None`
`n_feature_parts`	Maximum number of variable parts produced by preprocessing methods. If equal to 0 it is automatically calculated. TYPE: `int` DEFAULT: `0`
`informative_features_only`	If `True` keeps only informative features. TYPE: `bool` DEFAULT: `True`
`group_target_value`	Allows grouping of the target values in classification. It can substantially increase the training time. TYPE: `bool` DEFAULT: `False`
`keep_initial_variables`	If `True` the original columns are kept in the transformed data. TYPE: `bool` DEFAULT: `False`
`transform_type_categorical`	Type of transformation for categorical features. Valid values: - "part_id" - "part_label" - "dummies" - "conditional_info" See the documentation for the `categorical_recoding_method` parameter of the api.train_recoder function for more details. TYPE: `str` DEFAULT: `"part_id"`
`transform_type_numerical`	One of the following strings are valid: - "part_id" - "part_label" - "dummies" - "conditional_info" - "center_reduction" - "0-1_normalization" - "rank_normalization" See the documentation for the `numerical_recoding_method` parameter of the api.train_recoder function for more details. TYPE: `str` DEFAULT: `"part_id"`
`transform_type_pairs`	Type of transformation for bivariate features. Valid values: - "part_id" - "part_label" - "dummies" - "conditional_info" TYPE: `str` DEFAULT: `"part_id"`
`verbose`	If `True` it prints debug information and it does not erase temporary files when fitting, predicting or transforming. TYPE: `bool` DEFAULT: `False`
`output_dir`	Path of the output directory for the `AllReports.khj` report file and the `Modeling.kdic` modeling dictionary file. By default these files are deleted. TYPE: `str` DEFAULT: `None`
`auto_sort`	Advanced. Only for multi-table inputs: If `True` input tables are pre-sorted by their key before executing Khiops. If the input tables are already sorted by their keys set this parameter to `False` to speed up the processing. This affects the fit and transform methods. Note The sort by key is performed in a left-to-right, hierarchical, lexicographic manner. TYPE: `bool` DEFAULT: `True`
`n_cores`	Maximum number of CPU cores allocated and used for all estimator operations. TYPE: `int` DEFAULT: `None`

ATTRIBUTE	DESCRIPTION
`is_multitable_model_`	`True` if the model was fitted on a multi-table dataset. TYPE: `bool`
`model_`	The Khiops dictionary domain for the trained encoder. TYPE: `DictionaryDomain`
`model_main_dictionary_name_`	The name of the main Khiops dictionary within the `model_` domain. TYPE: `str`
`model_report_`	The Khiops report object. TYPE: `AnalysisResults`

Examples:

See the following functions of the samples_sklearn.py documentation script: - samples_sklearn.khiops_encoder() - samples_sklearn.khiops_encoder_multitable_star() - samples_sklearn.khiops_encoder_multitable_snowflake()

METHOD	DESCRIPTION
`fit`	Fits the Khiops Encoder according to X, y
`transform`	Transforms X with a fitted Khiops supervised encoder
`fit_transform`	Fit and transforms its inputs

Methods:

`fit(X, y=None, **kwargs)`

Fits the Khiops Encoder according to X, y

PARAMETER	DESCRIPTION
`X`	Training dataset. Either an array-like or a dict specification for multi-table datasets (see Multi-Table Learning Primer). TYPE: `array-like of shape (n_samples, n_features_in) or dict`
`y`	The target values. TYPE: `array-like of shape (n_samples,)` DEFAULT: `None`

RETURNS	DESCRIPTION
`self`	The calling estimator instance. TYPE: `KhiopsEncoder`

`transform(X)`

Transforms X with a fitted Khiops supervised encoder

Note

Numerical features are encoded to categorical ones. See the transform_type_numerical parameter for details.

PARAMETER	DESCRIPTION
`X`	Training dataset. Either an array-like or a dict specification for multi-table datasets (see Multi-Table Learning Primer). TYPE: `array-like of shape (n_samples, n_features_in) or dict`

RETURNS	DESCRIPTION
`ndarray`	An array containing the encoded columns. A first column containing key column ids is added in multi-table mode.

`fit_transform(X, y=None, **kwargs)`

Fit and transforms its inputs

PARAMETER	DESCRIPTION
`X`	Training dataset. Either an array-like or a dict specification for multi-table datasets (see Multi-Table Learning Primer). TYPE: `array-like of shape (n_samples, n_features_in) or dict`
`y`	The target values. TYPE: `array-like of shape (n_samples,)` DEFAULT: `None`

RETURNS	DESCRIPTION
`self`	The calling estimator instance. TYPE: `KhiopsEncoder`

khiops.sklearn.estimators

Classes

KhiopsEstimator(n_cores=None, verbose=False, output_dir=None, auto_sort=True)

Methods:

export_report_file(report_file_path)

export_dictionary_file(dictionary_file_path)

fit(X, y=None, **kwargs)

KhiopsCoclustering(verbose=False, output_dir=None, auto_sort=True, build_name_var=True, build_distance_vars=False, build_frequency_vars=False, n_cores=None)

Methods:

fit(X, y=None, **kwargs)

simplify(max_preserved_information=0, max_cells=0, max_total_parts=0, max_part_numbers=None)

predict(X)

fit_predict(X, y=None, **kwargs)

KhiopsSupervisedEstimator(n_features=1000, n_trees=10, n_text_features=10000, type_text_features='words', specific_pairs=None, all_possible_pairs=True, construction_rules=None, n_feature_parts=0, keep_selected_variables_only=True, verbose=False, output_dir=None, auto_sort=True, n_cores=None)

Methods:

fit(X, y=None, **kwargs)

Methods:

predict(X)

Methods:

fit(X, y, **kwargs)

predict(X)

predict_proba(X)

KhiopsRegressor(n_features=1000, n_trees=0, n_text_features=10000, type_text_features='words', n_selected_features=0, n_evaluated_features=0, construction_rules=None, n_feature_parts=0, keep_selected_variables_only=True, verbose=False, output_dir=None, auto_sort=True, n_cores=None)

Methods:

fit(X, y=None, **kwargs)

predict(X)

Methods:

fit(X, y=None, **kwargs)

transform(X)

fit_transform(X, y=None, **kwargs)

Functions:

`KhiopsEstimator(n_cores=None, verbose=False, output_dir=None, auto_sort=True)`

`export_report_file(report_file_path)`

`export_dictionary_file(dictionary_file_path)`

`fit(X, y=None, **kwargs)`

`KhiopsCoclustering(verbose=False, output_dir=None, auto_sort=True, build_name_var=True, build_distance_vars=False, build_frequency_vars=False, n_cores=None)`

`fit(X, y=None, **kwargs)`

`simplify(max_preserved_information=0, max_cells=0, max_total_parts=0, max_part_numbers=None)`

`predict(X)`

`fit_predict(X, y=None, **kwargs)`

`KhiopsSupervisedEstimator(n_features=1000, n_trees=10, n_text_features=10000, type_text_features='words', specific_pairs=None, all_possible_pairs=True, construction_rules=None, n_feature_parts=0, keep_selected_variables_only=True, verbose=False, output_dir=None, auto_sort=True, n_cores=None)`

`fit(X, y=None, **kwargs)`

`predict(X)`

`fit(X, y, **kwargs)`

`predict(X)`

`predict_proba(X)`

`KhiopsRegressor(n_features=1000, n_trees=0, n_text_features=10000, type_text_features='words', n_selected_features=0, n_evaluated_features=0, construction_rules=None, n_feature_parts=0, keep_selected_variables_only=True, verbose=False, output_dir=None, auto_sort=True, n_cores=None)`

`fit(X, y=None, **kwargs)`

`predict(X)`

`fit(X, y=None, **kwargs)`

`transform(X)`

`fit_transform(X, y=None, **kwargs)`