khiops.core.analysis_results

Submodule of khiops.core

Classes to access Khiops JSON reports

Class Overview

Below we describe with diagrams the relationships of the classes in this modules. They are mostly compositions (has-a relations) and we omit native attributes (str, int, float, etc).

The main class of this module is AnalysisResults and it is largely a composition of sub-reports objects given by the following structure:

AnalysisResults
|- preparation_report           |
|- text_preparation_report      |->  PreparationReport
|- tree_preparation_report      |
|- bivariate_preparation_report  ->  BivariatePreparationReport
|- modeling_report               ->  ModelingReport
|- train_evaluation_report      |
|- test_evaluation_report       |->  EvaluationReport
|- evaluation_report            |

These sub-classes in turn use other tertiary classes to represent specific information pieces of each report. The dependencies for the classes PreparationReport and BivariatePreparationReport are:

PreparationReport
|- variables_statistics -> list of VariableStatistics
|- trees                -> list of Tree (only for tree_preparation_report)

BivariatePreparationReport
|- variable_pair_statistics -> list of VariablePairStatistics

VariableStatistics
|- data_grid       -> DataGrid
|- modl_histograms -> ModlHistograms

VariablePairStatistics
|- data_grid -> DataGrid

Tree
|- target_partition -> TargetPartition
|- nodes -> list of TreeNode

TargetPartition
|- partition -> list of PartInterval

DataGrid
|- dimensions -> list of DataGridDimension

ModlHistograms
|- histograms -> list of Histogram

DataGridDimension
|- partition -> list of PartInterval OR
|               list of PartValue OR
|               list of PartValueGroup

for class ModelingReport:

ModelingReport
|- trained_predictors -> list of TrainedPredictors

TrainedPredictor
|- selected_variables -> list of SelectedVariable

and for class EvaluationReport:

EvaluationReport
|- predictors_performance -> list of PredictorPerformance
|- classification_lift_curves -> list of PredictorCurve (classification only)
|- regression_rec_curves -> list of PredictorCurve (regression only)

PredictorPerformance
|- confusion_matrix -> ConfusionMatrix (classification only)

To have a complete illustration of the access to the information of all classes in this module look at their to_dict methods which write Python dictionaries in the same format as the Khiops JSON reports.

CLASS	DESCRIPTION
`AnalysisResults`	Main class containing the information of a Khiops JSON file
`PreparationReport`	Univariate data preparation report: discretizations and groupings
`BivariatePreparationReport`	Bivariate data preparation report: 2D grid models
`ModelingReport`	Modeling report of all predictors created in a supervised analysis
`EvaluationReport`	Evaluation report for predictors
`VariableStatistics`	Variable information and statistics
`VariablePairStatistics`	Variable pair information and statistics
`Tree`	A decision tree feature
`TargetPartition`	Target partition details (for regression trees only)
`TreeNode`	A decision tree node
`ModlHistograms`	A histogram density estimation for numerical data
`Histogram`	A histogram
`DataGrid`	A piecewise constant probability density estimation
`DataGridDimension`	A dimension (variable) of a data grid
`PartInterval`	Element of a numerical interval partition in a data grid
`PartValue`	Element of a value partition (singletons) in a data grid
`PartValueGroup`	Element of a categorical partition in a data grid
`TrainedPredictor`	Trained predictor information
`SelectedVariable`	Information about a selected variable in a predictor
`PredictorPerformance`	A predictor's performance evaluation
`ConfusionMatrix`	A classifier's confusion matrix
`PredictorCurve`	A lift curve for a classifier or a REC curve for a regressor

FUNCTION	DESCRIPTION
`read_analysis_results_file`	Reads a Khiops JSON report

Classes

`AnalysisResults(json_data=None)`

Bases: KhiopsJSONObject

Main class containing the information of a Khiops JSON file

Sub-reports not available in the JSON data are optional (set to None).

PARAMETER	DESCRIPTION
`json_data`	A dictionary representing the data of a Khiops JSON report file. If not specified it returns an empty instance. Note See also the read_analysis_results_file function to obtain an instance of this class from a Khiops JSON file. TYPE: `dict` DEFAULT: `None`

ATTRIBUTE	DESCRIPTION
`tool`	Name of the Khiops tool that generated the report. TYPE: `str`
`version`	Version of the Khiops tool that generated the report. TYPE: `str`
`short_description`	Short description defined by the user. TYPE: `str`
`khiops_encoding`	Encoding of the Khiops report file. TYPE: `str`
`logs`	2-tuples linking each sub-task name to a list containing the warnings and errors found during the execution of that sub-task. Available only if there were errors or warnings. TYPE: `list of tuples`
`preparation_report`	A report about the variables' discretizations and groupings. TYPE: `PreparationReport`
`bivariate_preparation_report`	A report of the grid models created from pairs of variables. Available only when pair of variables were created in the analysis. TYPE: `(BivariatePreparationReport, optional)`
`modeling_report`	A report describing the predictor models. Available only in supervised analysis. TYPE: `ModelingReport`
`train_evaluation_report`	An evaluation report of the trained models on the train dataset split. Available only in supervised analysis. TYPE: `EvaluationReport`
`test_evaluation_report`	An evaluation report of the trained models on the test dataset split. Available only in supervised analysis and when the test split was not empty. TYPE: `EvaluationReport`
`evaluation_report`	An EvaluationReport instance for evaluations created with an explicit evaluation (either with the api.evaluate_predictor core API function or the Evaluate Predictor feature of the Khiops desktop app). Available only when the report was generated with the aforementioned features. TYPE: `EvaluationReport`

See class docstring

METHOD	DESCRIPTION
`get_reports`	Returns all available sub-reports
`write_report_file`	Writes a TSV report file with the object's information
`to_dict`	Transforms this instance to a dict with the Khiops JSON file structure
`write_report`	Writes the instance's TSV report into a writer object

Methods:

`get_reports()`

Returns all available sub-reports

RETURNS	DESCRIPTION
`list`	All available sub-reports.

`write_report_file(report_file_path)`

Writes a TSV report file with the object's information

Warning

This method is deprecated since Khiops 11.0.0 and will be removed in Khiops 12. Use the to_dict method instead.

PARAMETER	DESCRIPTION
`report_file_path`	Path of the output TSV report file. TYPE: `str`

`to_dict()`

Transforms this instance to a dict with the Khiops JSON file structure

`write_report(stream_or_writer)`

Writes the instance's TSV report into a writer object

Warning

This method is deprecated since Khiops 11.0.0 and will be removed in Khiops 12. Use the to_dict method instead.

PARAMETER	DESCRIPTION
`stream_or_writer`	Output stream or writer. TYPE: `IOBase or KhiopsOutputWriter`

`PreparationReport(json_data=None)`

Univariate data preparation report: discretizations and groupings

The attributes related to the target variable and null model are available only in the case of a supervised learning task (classification or regression).

PARAMETER	DESCRIPTION
`json_data`	JSON data of the `preparationReport` field of a Khiops JSON report file. If not specified it returns an empty instance. TYPE: `dict` DEFAULT: `None`

ATTRIBUTE	DESCRIPTION
`report_type`	Report type. TYPE: `"Preparation" (only possible value)`
`dictionary`	Name of the training data table dictionary. TYPE: `str`
`variable_types`	The different types of variables. TYPE: `list of str`
`variable_numbers`	Number of variables for each type. Synchronized with `variable_types`. TYPE: `list of int`
`database`	Path of the main training data table file. TYPE: `str`
`sample_percentage`	Percentage of instances used in training. TYPE: `int`
`sampling_mode`	Sampling mode used to split the train and datasets. TYPE: `str`
`selection_variable`	Name of the variable used to select training instances. TYPE: `str`
`selection_value`	Value of `selection_variable` to select training instance. TYPE: `str`
`constructed_variable_number`	Number of constructed variables. TYPE: `int`
`instance_number`	Number of training instances. TYPE: `int`
`learning_task`	Name of the associated learning task. Possible values: - "Classification analysis" - "Regression analysis" - "Unsupervised analysis" TYPE: `str`
`target_variable`	Target variable name. TYPE: `str`
`main_target_value`	Main value of a categorical target variable. TYPE: `str`
`target_stats_min`	Minimum of a numerical target variable. TYPE: `float`
`target_stats_max`	Maximum of a numerical target variable. TYPE: `float`
`target_stats_mean`	Mean of a numerical target variable. TYPE: `float`
`target_stats_std_dev`	Standard deviation of a numerical target variable. TYPE: `float`
`target_stats_missing_number`	Number of missing values for a numerical or categorical target variable. TYPE: `int`
`target_stats_sparse_missing_number`	Number of missing values for a sparse block of numerical or categorical target variables. TYPE: `int`
`target_stats_mode`	Mode of a categorical target variable. TYPE: `str`
`target_stats_mode_frequency`	Mode frequency of a categorical target variable. TYPE: `int`
`target_values`	Values of a categorical target variable. TYPE: `list of str`
`target_value_frequencies`	Frequencies for each target value. Synchronized with `target_values`. TYPE: `list of int`
`evaluated_variable_number`	Number of variables analyzed. TYPE: `int`
`informative_variable_number`	Supervised analysis only: Number of informative variables. TYPE: `int`
`selected_variable_number`	Number of selected variables. TYPE: `int`
`native_variable_number`	Number of native variables. TYPE: `int`
`max_constructed_variables`	Maximum number of constructed variable specified for the analysis. TYPE: `int`
`max_text_features`	Maximum number of text features specified for the analysis. TYPE: `int`
`max_trees`	Maximum number of constructed trees specified for the analysis. TYPE: `int`
`max_pairs`	Maximum number of constructed variables pairs specified for the analysis. TYPE: `int`
`discretization`	Type of discretization method used. TYPE: `str`
`value_grouping`	Type of grouping method used. TYPE: `str`
`null_model_construction_cost`	Coding length of the null construction model. TYPE: `float`
`null_model_preparation_cost`	Coding length of the null preparation model. TYPE: `float`
`null_model_data_cost`	Coding length of the data given the null model. TYPE: `float`
`variables_statistics`	Variable statistics for each variable analyzed. TYPE: `list of VariableStatistics`
`trees`	Tree details for each tree built. TYPE: `list of Tree`

See class docstring

METHOD	DESCRIPTION
`get_variable_names`	Returns the names of the variables analyzed during the preparation
`get_variable_statistics`	Returns the statistics of the specified variable
`get_tree`	Returns the tree with the specified name
`to_dict`	Transforms this instance to a dict with the Khiops JSON file structure
`write_report`	Writes the instance's TSV report into a writer object

Methods:

`get_variable_names()`

Returns the names of the variables analyzed during the preparation

RETURNS	DESCRIPTION
`list of str`	The names of the variables analyzed during the preparation.

`get_variable_statistics(variable_name)`

Returns the statistics of the specified variable

PARAMETER	DESCRIPTION
`variable_name`	Name of the variable. TYPE: `str`

RETURNS	DESCRIPTION
`VariableStatistics`	The statistics of the specified variable.

RAISES	DESCRIPTION
`KeyError`	If no variable with the specified names exist.

`get_tree(tree_name)`

Returns the tree with the specified name

PARAMETER	DESCRIPTION
`tree_name`	Name of the tree. TYPE: `str`

RETURNS	DESCRIPTION
`Tree`	The tree which has the specified name.

RAISES	DESCRIPTION
`KeyError`	If no tree with the specified name exists.

`to_dict()`

Transforms this instance to a dict with the Khiops JSON file structure

`write_report(writer)`

Writes the instance's TSV report into a writer object

Warning

This method is deprecated since Khiops 11.0.0 and will be removed in Khiops 12. Use the to_dict method instead.

PARAMETER	DESCRIPTION
`writer`	Output writer. TYPE: `KhiopsOutputWriter`

`BivariatePreparationReport(json_data=None)`

Bivariate data preparation report: 2D grid models

The attributes related to the target variable and null model are available only in the case of a supervised learning task (only classification in the bivariate case).

PARAMETER	DESCRIPTION
`json_data`	JSON data of the `bivariatePreparationReport` field of a Khiops JSON report file. If not specified it returns an empty instance. TYPE: `dict` DEFAULT: `None`

ATTRIBUTE	DESCRIPTION
`report_type`	Report type. TYPE: `"BivariatePreparation" (only possible value)`
`dictionary`	Name of the training data table dictionary. TYPE: `str`
`variable_types`	The different types of variables. TYPE: `list of str`
`variable_numbers`	The number of variables for each type in `variables_types` (synchronized lists). TYPE: `list of int`
`database`	Path of the main training data table file. TYPE: `str`
`sample_percentage`	Percentage of instances used in training. TYPE: `int`
`sampling_mode`	Sampling mode used to split the train and datasets. TYPE: `str`
`selection_variable`	Variable used to select instances for training. TYPE: `str`
`selection_value`	Value of selection_variable to select instances for training. TYPE: `str`
`instance_number`	Number of training instances. TYPE: `int`
`learning_task`	Name of the associated learning task. Possible values: - "Classification analysis" - "Regression analysis" - "Unsupervised analysis" TYPE: `str`
`target_variable`	Target variable name in supervised analysis. TYPE: `str`
`main_target_value`	Main modality of the target variable in supervised case. TYPE: `str`
`target_stats_mode`	Mode of a categorical target variable. TYPE: `str`
`target_stats_mode_frequency`	Mode frequency of a categorical target variable. TYPE: `int`
`target_values`	Values of a categorical target variable. TYPE: `list of str`
`target_value_frequencies`	Frequencies for each value in `target_values` (synchronized lists). TYPE: `list of int`
`evaluated_pair_number`	Number of variable pairs evaluated. TYPE: `int`
`selected_pair_number`	Number of variable pairs selected. TYPE: `int`
`informative_pair_number`	Number of informative variable pairs. A pair is considered informative if its level is greater than the sum of its components' levels. TYPE: `int`
`variable_pair_statistics`	Statistics for each analyzed pair of variables. TYPE: `list of VariablePairStatistics`

See class docstring

METHOD	DESCRIPTION
`get_variable_pair_names`	Returns the pairs of variable names available on this report
`get_variable_pair_statistics`	Returns the statistics of the specified pair of variables
`to_dict`	Transforms this instance to a dict with the Khiops JSON file structure
`write_report`	Writes the instance's TSV report into a writer object

Methods:

`get_variable_pair_names()`

Returns the pairs of variable names available on this report

RETURNS	DESCRIPTION
`list of tuple`	The pair of variable names available on this report

`get_variable_pair_statistics(variable_name_1, variable_name_2)`

Returns the statistics of the specified pair of variables

Note

The variable names can be given in any order.

PARAMETER	DESCRIPTION
`variable_name_1`	Name of the first variable. TYPE: `str`
`variable_name_2`	Name of the second variable. TYPE: `str`

RETURNS	DESCRIPTION
`VariablePairStatistics`	The statistics of the specified pair of variables.

RAISES	DESCRIPTION
`KeyError`	If no pair with the specified names exist.

`to_dict()`

Transforms this instance to a dict with the Khiops JSON file structure

`write_report(writer)`

Writes the instance's TSV report into a writer object

Warning

This method is deprecated since Khiops 11.0.0 and will be removed in Khiops 12. Use the to_dict method instead.

PARAMETER	DESCRIPTION
`writer`	Output writer. TYPE: `KhiopsOutputWriter`

`ModelingReport(json_data=None)`

Modeling report of all predictors created in a supervised analysis

PARAMETER	DESCRIPTION
`json_data`	JSON data of the `modelingReport` field of Khiops JSON report file. If not specified it returns an empty instance. TYPE: `dict` DEFAULT: `None`

ATTRIBUTE	DESCRIPTION
`report_type`	Report type. TYPE: `"Modeling" (only possible value)`
`dictionary`	Name of the training data table dictionary. TYPE: `str`
`database`	Path of the main training data table file. TYPE: `str`
`sample_percentage`	Percentage of instances used in training. TYPE: `int`
`sampling_mode`	Sampling mode used to split the train and datasets. TYPE: `'Include sample' or 'Exclude sample'`
`selection_variable`	Variable used to select instances for training. TYPE: `str`
`selection_value`	Value of `selection_variable` to select instances for training. TYPE: `str`
`learning_task`	Name of the associated learning task. TYPE: `'Classification analysis' or 'Regression analysis'`
`target_variable`	Name of the target variable. TYPE: `str`
`main_target_value`	Main value of the target variable. TYPE: `str`
`trained_predictors`	The predictors trained in the task. TYPE: `list of TrainedPredictor`

See class docstring

METHOD	DESCRIPTION
`get_predictor`	Returns the specified predictor
`get_snb_predictor`	Returns the Selective Naive Bayes predictor
`get_predictor_names`	Returns the names of the available predictor reports
`to_dict`	Transforms this instance to a dict with the Khiops JSON file structure
`write_report`	Writes the instance's TSV report into a writer object

Methods:

`get_predictor(predictor_name)`

Returns the specified predictor

PARAMETER	DESCRIPTION
`predictor_name`	Name of the predictor. TYPE: `str`

RETURNS	DESCRIPTION
`TrainedPredictor`	The predictor object for the specified name.

RAISES	DESCRIPTION
`KeyError`	If there is no predictor with the specified name.

`get_snb_predictor()`

Returns the Selective Naive Bayes predictor

RETURNS	DESCRIPTION
`TrainedPredictor`	The predictor object for "Selective Naive Bayes".

RAISES	DESCRIPTION
`KeyError`	If there is no predictor named "Selective Naive Bayes".

`get_predictor_names()`

Returns the names of the available predictor reports

RETURNS	DESCRIPTION
`list of str`	The names of the available predictor reports.

`to_dict()`

Transforms this instance to a dict with the Khiops JSON file structure

`write_report(writer)`

Writes the instance's TSV report into a writer object

Warning

This method is deprecated since Khiops 11.0.0 and will be removed in Khiops 12. Use the to_dict method instead.

PARAMETER	DESCRIPTION
`writer`	Output writer. TYPE: `KhiopsOutputWriter`

`EvaluationReport(json_data=None)`

Evaluation report for predictors

PARAMETER DESCRIPTION

json_data

JSON data of the fields: - trainEvaluationReport: predictor training - testEvaluationReport: predictor training & non-empty test split - evaluationReport: explicit evaluation

The first two fields are set when doing a supervised analysis: either with the "Train Model" feature of the Khiops app or the api.train_predictor function of the Khiops Python core API. The third field is set when doing an explicit evaluation: either with the Evaluate Predictor feature of the Khiops app or the api.evaluate_predictor function of the Khiops Python core API.

If not specified it returns an empty instance.

TYPE: dict DEFAULT: None

ATTRIBUTE	DESCRIPTION
`report_type`	Report type. TYPE: `"Evaluation" (only possible value)`
`evaluation_type`	Evaluation type. The value "" is set when the evaluation was explicit. TYPE: `(Train, Test or '')`
`dictionary`	Name of the training data table dictionary. TYPE: `str`
`database`	Path of the main training data table file. TYPE: `str`
`sample_percentage`	Percentage of instances used in training. TYPE: `int`
`sampling_mode`	Sampling mode used to split the train and datasets. TYPE: `str`
`selection_variable`	Variable used to select instances for training. TYPE: `str`
`selection_value`	Value of selection_variable to select instances for training. TYPE: `str`
`instance_number`	Number of training instances. TYPE: `int`
`learning_task`	Type of learning task. TYPE: `'Classification analysis' or 'Regression analysis'`
`target_variable`	Name of the target variable. TYPE: `str`
`main_target_value`	Main value of the target variable. TYPE: `str`
`predictors_performance`	Performance metrics for each predictor. TYPE: `list of PredictorPerformance`
`regression_rec_curves`	REC curves for each regressor. TYPE: `list of PredictorCurve`
`classification_target_values`	Target variable values for which a classifier lift curve was evaluated. TYPE: `list of str`
`classification_lift_curves`	Lift curves for each target value in `classification_target_values`. The lift curve for the optimal predictor is prepended to those of the target values. TYPE: `list of PredictorCurve`

See class docstring

METHOD	DESCRIPTION
`get_predictor_names`	Returns the names of the available predictors in the report
`get_predictor_performance`	Returns the performance metrics for the specified predictor
`get_snb_performance`	Returns the performance metrics for the Selective Naive Bayes predictor
`get_regressor_rec_curve`	Returns the REC curve for the specified regressor
`get_snb_rec_curve`	Returns the REC curve for the Selective Naive Bayes regressor
`get_classifier_lift_curve`	Returns the lift curve for the specified classifier and target value
`get_snb_lift_curve`	Returns lift curve for the Selective Naive Bayes clf. given a target value
`to_dict`	Transforms this instance to a dict with the Khiops JSON file structure
`write_report`	Writes the instance's TSV report into a writer object

Methods:

`get_predictor_names()`

Returns the names of the available predictors in the report

RETURNS	DESCRIPTION
`list of str`	The names of the available predictors.

`get_predictor_performance(predictor_name)`

Returns the performance metrics for the specified predictor

PARAMETER	DESCRIPTION
`predictor_name`	A predictor name. TYPE: `str`

RETURNS	DESCRIPTION
`PredictorPerformance`	The performance metrics for the specified predictor.

RAISES	DESCRIPTION
`KeyError`	If no predictor with the specified name exists.

`get_snb_performance()`

Returns the performance metrics for the Selective Naive Bayes predictor

RETURNS	DESCRIPTION
`PredictorPerformance`	The performance metrics for the Selective Naive Bayes predictor.

RAISES	DESCRIPTION
`ValueError`	If the Selective Naive Bayes information is not available in the report.

`get_regressor_rec_curve(regressor_name)`

Returns the REC curve for the specified regressor

PARAMETER	DESCRIPTION
`regressor_name`	Name of a regressor. TYPE: `str`

RETURNS	DESCRIPTION
`PredictorCurve`	The REC curve for the specified regressor.

RAISES	DESCRIPTION
`ValueError`	If no regressor curves available. (
`KeyError`	If no regressor with the specified name exists.

`get_snb_rec_curve()`

Returns the REC curve for the Selective Naive Bayes regressor

RETURNS	DESCRIPTION
`PredictorCurve`	The REC curve for the Selective Naive Bayes regressor.

RAISES	DESCRIPTION
`ValueError`	If the Selective Naive Bayes information is not available in the report.

`get_classifier_lift_curve(classifier_name, target_value)`

Returns the lift curve for the specified classifier and target value

PARAMETER	DESCRIPTION
`classifier_name`	A name of a classifier. TYPE: `str`
`target_value`	A specific value of the target variable. TYPE: `str`

RETURNS	DESCRIPTION
`PredictorCurve`	The lift curve for the specified classifier and target value.

RAISES	DESCRIPTION
`KeyError`	If no classifier with the specified exists or no target value with the specified name exists.

`get_snb_lift_curve(target_value)`

Returns lift curve for the Selective Naive Bayes clf. given a target value

PARAMETER	DESCRIPTION
`target_value`	A specific value of the target variable. TYPE: `str`

RETURNS	DESCRIPTION
`PredictorCurve`	The lift curve of the Selective Naive Bayes classifier for the specified target value.

RAISES	DESCRIPTION
`ValueError`	If the Selective Naive Bayes classifier information is not available.
`KeyError`	If no target value with the specified name exists.

`to_dict()`

Transforms this instance to a dict with the Khiops JSON file structure

`write_report(writer)`

Writes the instance's TSV report into a writer object

Warning

This method is deprecated since Khiops 11.0.0 and will be removed in Khiops 12. Use the to_dict method instead.

PARAMETER	DESCRIPTION
`writer`	Output writer object. TYPE: `KhiopsOutputWriter`

`VariableStatistics(json_data=None)`

Variable information and statistics

Note

The statistics in this class are for both numerical and categorical data.

PARAMETER DESCRIPTION

json_data

JSON data of an element of the list found at the variablesStatistics field within the preparationReport field of a Khiops JSON report file. If not specified it returns an empty instance.

Note

The data_grid field is considered a "detail" and is not initialized in the constructor. Instead, it is initialized explicitly via the init_details method. This allows to make partial initializations for large reports. If not specified it returns an empty instance.

TYPE: dict DEFAULT: None

ATTRIBUTE	DESCRIPTION
`rank`	Variable rank with respect to its level. Lower Rank = Higher Level. TYPE: `str`
`name`	Variable name. TYPE: `str`
`type`	Variable type. There are only two valid values for a prepared variable : - "Numerical" - "Categorical" TYPE: `str`
`level`	Variable predictive importance. TYPE: `float`
`target_part_number`	In regression: Number of the target intervals In classification with target grouping: Number of target groups TYPE: `int`
`part_number`	Number of parts of the variable partition. TYPE: `int`
`value_number`	Number of distinct values of the variable. TYPE: `int`
`min`	Minimum value of the variable. TYPE: `float`
`max`	Maximum value of the variable. TYPE: `float`
`mean`	Mean value of the variable. TYPE: `float`
`std_dev`	Standard deviation of the variable. TYPE: `float`
`missing_number`	Number of missing values of the variable. TYPE: `int`
`sparse_missing_number`	Number of sparse missing values of the variable. TYPE: `int`
`mode`	Most common value. TYPE: `float`
`mode_frequency`	Frequency of the most common value. TYPE: `int`
`input_values`	Different values taken by the variable. If there are too many values only the more frequent will be available. TYPE: `list of str`
`input_value_frequencies`	The frequencies for each input value. Synchronized with `input_values`. TYPE: `list of int`
`construction_cost`	Construction cost of the variable. More complex variables cost more. TYPE: `float`
`preparation_cost`	Partition model cost. More complex partitions cost more. TYPE: `float`
`data_cost`	Negative log-likelihood of the variable given a preparation model and a construction model. TYPE: `float`
`derivation_rule`	If the variable is not native it is Khiops dictionary function to derive it. Otherwise is set to `None`. TYPE: `str`
`data_grid`	A density estimation of the partitioned variable with respect to the target. TYPE: `DataGrid`
`modl_histograms`	MODL optimal histograms for for numerical variables. Only for unsupervised analysis. TYPE: `ModlHistograms`

See class docstring

METHOD	DESCRIPTION
`init_details`	Initializes the details' attributes from a Python JSON object
`is_detailed`	Returns True if the report contains any detailed information
`to_dict`	Transforms this instance to a dict with the Khiops JSON file structure
`write_report_header_line`	Writes the header line of a TSV report into a writer object
`write_report_line`	Writes a line of the TSV report into a writer object
`write_report_details`	Writes the details' attributes into a writer object

Methods:

`init_details(json_data=None)`

Initializes the details' attributes from a Python JSON object

PARAMETER	DESCRIPTION
`json_data`	JSON data of an element of the list found at the `variablesDetailedStatistics` field within the `preparationReport` field of a Khiops JSON report file. If not specified it leaves the object as-is. TYPE: `dict` DEFAULT: `None`

`is_detailed()`

Returns True if the report contains any detailed information

RETURNS	DESCRIPTION
`bool`	True if the report contains any detailed information.

`to_dict(details=False)`

Transforms this instance to a dict with the Khiops JSON file structure

`write_report_header_line(writer)`

Writes the header line of a TSV report into a writer object

The header is the same for all variable types.

Warning

This method is deprecated since Khiops 11.0.0 and will be removed in Khiops 12. Use the to_dict method instead.

PARAMETER	DESCRIPTION
`writer`	Output writer. TYPE: `KhiopsOutputWriter`

`write_report_line(writer)`

Writes a line of the TSV report into a writer object

Warning

This method is deprecated since Khiops 11.0.0 and will be removed in Khiops 12. Use the to_dict method instead.

PARAMETER	DESCRIPTION
`writer`	Output writer. TYPE: `KhiopsOutputWriter`

`write_report_details(writer)`

Writes the details' attributes into a writer object

Warning

This method is deprecated since Khiops 11.0.0 and will be removed in Khiops 12. Use the to_dict method instead.

PARAMETER	DESCRIPTION
`writer`	Output writer. TYPE: `KhiopsOutputWriter`

`VariablePairStatistics(json_data=None)`

Variable pair information and statistics

PARAMETER DESCRIPTION

json_data

JSON data of an element of the list found at the variablesPairStatistics field within the bivariatePreparationReport field of a Khiops JSON report file. If not specified it returns an empty instance.

Note

The data_grid field is considered as "detail" and is not initialized in the constructor. Instead, it is initialized explicitly via the init_details method. This allows to make partial initializations for large reports. If not specified it returns an empty instance.

TYPE: dict DEFAULT: None

ATTRIBUTE	DESCRIPTION
`rank`	Variable rank with respect to its level. Lower Rank = Higher Level. TYPE: `str`
`name1`	Name of the pair's first variable. TYPE: `str`
`name2`	Name of the pair's second variable. TYPE: `str`
`level`	Predictive importance of the pair. TYPE: `float`
`level1`	Predictive importance of the first variable. TYPE: `float`
`level2`	Predictive importance of the second variable. TYPE: `float`
`delta_level`	Difference between the pair's level and the sum of those of its components (`delta_level = level - level1 - level2`). TYPE: `float`
`variable_number`	Number of active variables in the pair: - 0 means that there is no information in any of the variables - 1 means that the pair information reduces to that of any of its components - 2 means that the two variables are jointly informative TYPE: `int`
`part_number1`	Number of parts of the first variable partition. TYPE: `int`
`part_number2`	Number of parts of the second variable partition. TYPE: `int`
`cell_number`	Number of cells generated of the pair grid. TYPE: `int`
`construction_cost`	Advanced: Construction cost of the variable. More complex variables cost more. TYPE: `float`
`preparation_cost`	Advanced: Partition model cost. More complex partitions cost more. TYPE: `float`
`data_cost`	Advanced: Negative log-likelihood of the variable given a preparation model and a construction model. TYPE: `float`
`data_grid`	A density estimation of the partitioned pair of variable with respect to the target. TYPE: `DataGrid`

See class docstring

METHOD	DESCRIPTION
`init_details`	Initializes the details' attributes from a Python JSON object
`is_detailed`	Returns True if the report contains any detailed information
`to_dict`	Transforms this instance to a dict with the Khiops JSON file structure
`write_report_header_line`	Writes the header line of a TSV report into a writer object
`write_report_line`	Writes a line of the TSV report into a writer object
`write_report_details`	Writes the details' attributes into a writer object

Methods:

`init_details(json_data=None)`

Initializes the details' attributes from a Python JSON object

PARAMETER	DESCRIPTION
`json_data`	JSON data of an element of the list found at the `variablesPairsDetailedStatistics` field within the `bivariatePreparationReport` field of a Khiops JSON report file. If not specified it leaves the object as-is. TYPE: `dict` DEFAULT: `None`

`is_detailed()`

Returns True if the report contains any detailed information

RETURNS	DESCRIPTION
`bool`	True if the report contains any detailed information.

`to_dict(details=False)`

Transforms this instance to a dict with the Khiops JSON file structure

`write_report_header_line(writer)`

Writes the header line of a TSV report into a writer object

The header is the same for all variable types.

Warning

This method is deprecated since Khiops 11.0.0 and will be removed in Khiops 12. Use the to_dict method instead.

PARAMETER	DESCRIPTION
`writer`	Output writer. TYPE: `KhiopsOutputWriter`

`write_report_line(writer)`

Writes a line of the TSV report into a writer object

Warning

This method is deprecated since Khiops 11.0.0 and will be removed in Khiops 12. Use the to_dict method instead.

PARAMETER	DESCRIPTION
`writer`	Output writer. TYPE: `KhiopsOutputWriter`

`write_report_details(writer)`

Writes the details' attributes into a writer object

Warning

This method is deprecated since Khiops 11.0.0 and will be removed in Khiops 12. Use the to_dict method instead.

PARAMETER	DESCRIPTION
`writer`	Output writer. TYPE: `KhiopsOutputWriter`

`Tree(json_data=None)`

A decision tree feature

PARAMETER	DESCRIPTION
`json_data`	JSON data of a value associated to the rank key in the object found at the `treeDetails` field within the `treePreparationReport` field of a Khiops JSON report file. If not specified, it returns an empty instance. TYPE: `dict` DEFAULT: `None`

ATTRIBUTE	DESCRIPTION
`name`	Name of the tree. TYPE: `str`
`variable_number`	Number of variables in the tree. TYPE: `int`
`depth`	Depth of the tree. TYPE: `int`
`target_partition`	Summary of the target partition. For regression only. TYPE: `TargetPartition`
`nodes`	Nodes of the tree. TYPE: `list of TreeNode`

"See class docstring

METHOD	DESCRIPTION
`to_dict`	Transforms this instance to a dict with the Khiops JSON file structure

Methods:

`to_dict()`

Transforms this instance to a dict with the Khiops JSON file structure

`TargetPartition(json_data=None)`

Target partition details (for regression trees only)

PARAMETER	DESCRIPTION
`json_data`	JSON data of the `targetPartition` field of the `treeDetails` field of the `treePreparationReport` field of a Khiops JSON report file. If not specified it returns an empty instance. TYPE: `dict` DEFAULT: `None`

ATTRIBUTE	DESCRIPTION
`variable`	Variable name. TYPE: `str`
`type`	Variable type. TYPE: `"Numerical" (only possible value)`
`partition_type`	Partition type. TYPE: `"Intervals" (only possible value)`
`partition`	The dimension parts. The list objects are of type PartInterval, as `partition_type` is "Intervals" TYPE: `list`
`frequencies`	Frequencies of the intervals in the target partition. TYPE: `list of int`

See class docstring

METHOD	DESCRIPTION
`to_dict`	Transforms this instance to a dict with the Khiops JSON file structure

Methods:

`to_dict()`

Transforms this instance to a dict with the Khiops JSON file structure

`TreeNode(json_data=None, parent_id=None)`

A decision tree node

PARAMETER	DESCRIPTION
`json_data`	JSON data of either: the `treeNodes` field of the `treeDetails` field of the `treePreparationReport` field of a Khiops JSON report file, or an element of the `childNodes` field of the `treeNodes` field of the `treeDetails` field of the `treePreparationReport` field of a Khiops JSON report file. If not specified it returns an empty instance TYPE: `dict` DEFAULT: `None`
`parent_id`	Identifier of the parent `TreeNode` instance. Not set for "root" nodes. TYPE: `str` DEFAULT: `None`

ATTRIBUTE	DESCRIPTION
`id`	Identifier of the `TreeNode` instance. TYPE: `str`
`parent_id`	Value of the `id` field of another `TreeNode` instance. Not set for "root" nodes. TYPE: `(str, optional)`
`variable`	Name of the tree variable. TYPE: `str`
`type`	Khiops type of the tree variable. TYPE: `str`
`partition`	The tree variable partition. TYPE: `list`
`default_group_index`	The index of the default variable group. TYPE: `int`
`target_values`	Values of a categorical tree target variable. TYPE: `list of str`
`target_value_frequencies`	Frequencies of each tree target value. Synchronized with `target_values`. TYPE: `list of int`

See class docstring

METHOD	DESCRIPTION
`to_dict`	Transforms this instance to a dict with the Khiops JSON file structure

Methods:

`to_dict()`

Transforms this instance to a dict with the Khiops JSON file structure

`ModlHistograms(json_data=None)`

A histogram density estimation for numerical data

A MODL histogram is a regularized piecewise-constant estimation of the probability density for numerical data. It has various refinement levels to ease exploratory analysis tasks.

PARAMETER	DESCRIPTION
`json_data`	JSON data at a `modlHistograms` field of an element of the list found at the `variablesDetailedStatistics` field within the `preparationReport` field of a Khiops JSON report file. If not specified, it returns an empty instance. TYPE: `dict` DEFAULT: `None`

ATTRIBUTE	DESCRIPTION
`histogram_number`	Number of available histograms. TYPE: `int`
`interpretable_histogram_number`	Number of interpretable histograms. Can be equal to either `histogram_number` or `histogram_number - 1`. TYPE: `int`
`truncation_epsilon`	Truncation epsilon used by the truncation heuristic implemented in Khiops. Equals 0 if no truncation is detected in the input data. TYPE: `float`
`removed_singular_interval_number`	Number of singular intervals removed from the finest-grained histogram to obtain the first interpretable histogram. TYPE: `int`
`granularities`	Histogram granularities, sorted in increasing order. Synchronized with `histograms`. TYPE: `list of int`
`interval_numbers`	Histogram interval numbers, sorted in increasing order. Synchronized with `histograms`. TYPE: `list of int`
`peak_interval_numbers`	Histogram peak interval numbers, sorted in increasing order. Synchronized with `histograms`. TYPE: `list of int`
`spike_interval_numbers`	Histogram spike interval numbers, sorted in increasing order. Synchronized with `histograms`. TYPE: `list of int`
`empty_interval_numbers`	Histogram empty interval numbers, sorted in increasing order. Synchronized with `histograms`. TYPE: `list of int`
`levels`	List of histogram levels, sorted in increasing order. Synchronized with `histograms`. TYPE: `list of float`
`information_rates`	Histogram information rates, sorted in increasing order. Between 0 and 100 for interpretable histograms. Synchronized with `histograms`. TYPE: `list of float`
`histograms`	The MODL histograms. TYPE: `list of Histogram`

See class docstring

METHOD	DESCRIPTION
`to_dict`	Transforms this instance to a dict with the Khiops JSON file structure

Methods:

`to_dict()`

Transforms this instance to a dict with the Khiops JSON file structure

`Histogram(json_data=None)`

A histogram

Represents one of the refinement levels of a ModlHistograms object.

PARAMETER	DESCRIPTION
`json_data`	JSON data of an element at the `histograms` field of a `modlHistograms` field of an element of the list found at the `variablesDetailedStatistics` field within the `preparationReport` field of a Khiops JSON report file. If not specified it returns an empty instance. TYPE: `dict` DEFAULT: `None`

ATTRIBUTE	DESCRIPTION
`bounds`	Interval bounds. TYPE: `list of float`
`frequencies`	Interval frequencies. TYPE: `list of int`

See class docstring

METHOD	DESCRIPTION
`to_dict`	Transforms this instance to a dict with the Khiops JSON file structure

Methods:

`to_dict()`

Transforms this instance to a dict with the Khiops JSON file structure

`DataGrid(json_data=None)`

A piecewise constant probability density estimation

A data grid represents one or many variables referred to as "dimensions" to differentiate them from the original data variables. Each dimension can be partitioned by:

Intervals for numerical variables
Values (singletons) / Value groups for categorical variables

The Cartesian product of the unidimensional partitions provides a multivariate partition of cells whose frequencies allow to estimate the multivariate probability density.

In the univariate case, the data grid is simply an histogram. In the case of multiple variables, the data grid may be supervised or not. If supervised, the target variable is the last one, and the data grid represents the conditional density estimator of the source variable with respect to the target. Otherwise, it represents a joint density estimator.

In case of an unsupervised data grid, the cells are described by their index on the variable partitions, together with their frequencies. For a supervised data grid, the cells are described by their index on the input variables partitions, and a vector of target frequencies is associated to each cell.

PARAMETER	DESCRIPTION
`json_data`	JSON data at a `dataGrid` field of an element of the list found at the `variablesDetailedStatistics` field within the `preparationReport` field of a Khiops JSON report file. If not specified it returns an empty instance. TYPE: `dict` DEFAULT: `None`

ATTRIBUTE	DESCRIPTION
`is_supervised`	`True` if the data grid is supervised (there is a target). TYPE: `bool`
`dimensions`	The dimensions of the data grid. TYPE: `list of DataGridDimension`
`frequencies`	Unsupervised only: Frequencies for each part. TYPE: `list of int`
`part_interests`	Supervised univariate only: Prediction interests for each part of the input dimension. Synchronized with `dimensions[0].partition`. TYPE: `list of float`
`part_target_frequencies`	Supervised univariate only: List of frequencies per target value for each part of the input dimension. Synchronized with `dimensions[0].partition`. TYPE: `list`
`cell_ids`	Multivariate only: Unique identifiers of the grid's cells. TYPE: `list of str`
`cell_part_indexes`	Multivariate only: List of dimension indexes defining each cell. Synchronized with `cell_ids`. TYPE: `list`
`cell_frequencies`	Unsupervised multivariate only: Frequencies for each cell. Synchronized with `cell_ids`. TYPE: `list of int`
`cell_target_frequencies`	Supervised multivariate only: List of frequencies per target value for each cell. Synchronized with `cell_ids`. TYPE: `list`

See class docstring

METHOD	DESCRIPTION
`to_dict`	Transforms this instance to a dict with the Khiops JSON file structure
`write_report`	Writes the instance's TSV report into a writer object

Methods:

`to_dict()`

Transforms this instance to a dict with the Khiops JSON file structure

`write_report(writer)`

Writes the instance's TSV report into a writer object

Warning

This method is deprecated since Khiops 11.0.0 and will be removed in Khiops 12. Use the to_dict method instead.

PARAMETER	DESCRIPTION
`writer`	Output writer. TYPE: `KhiopsOutputWriter`

`DataGridDimension(json_data=None)`

A dimension (variable) of a data grid

PARAMETER	DESCRIPTION
`json_data`	JSON data of an element at the `dimensions` field of a `dataGrid` field of an element of the list found at the `variablesDetailedStatistics` field within the `preparationReport` field of a Khiops JSON report file. If not specified it returns an empty instance. TYPE: `dict` DEFAULT: `None`

ATTRIBUTE	DESCRIPTION
`variable`	Variable name TYPE: `str`
`type`	Variable type. TYPE: `Numerical or Categorical`
`partition_type`	Partition type. TYPE: `(Intervals, Values or 'Value groups')`
`partition`	The dimension parts. The list objects are of type: - PartInterval: If `partition type` is "Intervals" - PartValue: If `partition_type` is "Values" - PartValueGroup: If `partition_type` is "Value groups" TYPE: `list`

See class docstring

METHOD	DESCRIPTION
`to_dict`	Transforms this instance to a dict with the Khiops JSON file structure
`write_report`	Writes the instance's TSV report into a writer object

Methods:

`to_dict()`

Transforms this instance to a dict with the Khiops JSON file structure

`write_report(writer)`

Writes the instance's TSV report into a writer object

Warning

This method is deprecated since Khiops 11.0.0 and will be removed in Khiops 12. Use the to_dict method instead.

PARAMETER	DESCRIPTION
`writer`	Output writer. TYPE: `KhiopsOutputWriter`

`PartInterval(json_data=None)`

Element of a numerical interval partition in a data grid

PARAMETER	DESCRIPTION
`json_data`	JSON data of the `partition` field of a `dataGrid` field of an element of the list found at the `variablesDetailedStatistics` field within the `preparationReport` field of a Khiops JSON report file. If not specified it returns an empty instance. TYPE: `list` DEFAULT: `None`

ATTRIBUTE	DESCRIPTION
`lower_bound`	The lower bound of the interval. TYPE: `float`
`upper_bound`	The upper bound of the interval. TYPE: `float`
`is_missing`	True if it is the missing values part (bounds are `None`). TYPE: `bool`
`is_left_open`	True if the interval has no minimum. `lower_bound` still contains the minimum value seen on data. TYPE: `bool`
`is_right_open`	True if the interval has no maximum. `upper_bound` still contains the minimum value seen on data. TYPE: `bool`

See class docstring

METHOD	DESCRIPTION
`__str__`	Returns a human readable string representation
`part_type`	Type of this part
`to_dict`	Transforms this instance to a dict with the Khiops JSON file structure
`write_report_line`	Writes a line of the TSV report into a writer object

Methods:

`str()`

Returns a human readable string representation

`part_type()`

Type of this part

RETURNS	DESCRIPTION
`str`	Only possible value: "Interval".

`to_dict()`

Transforms this instance to a dict with the Khiops JSON file structure

`write_report_line(writer)`

Writes a line of the TSV report into a writer object

Warning

This method is deprecated since Khiops 11.0.0 and will be removed in Khiops 12. Use the to_dict method instead.

PARAMETER	DESCRIPTION
`writer`	Output writer. TYPE: `KhiopsOutputWriter`

`PartValue(json_data=None)`

Element of a value partition (singletons) in a data grid

PARAMETER	DESCRIPTION
`json_data`	The value contained in this singleton part. If not specified it returns an empty object. TYPE: `str` DEFAULT: `None`

ATTRIBUTE	DESCRIPTION
`value`	A representation of the value defining the singleton. TYPE: `str`

See class docstring

METHOD	DESCRIPTION
`__str__`	Returns a readable string representation
`part_type`	Type of the instance
`to_dict`	Transforms this instance to a dict with the Khiops JSON file structure
`write_report_line`	Writes a line of the TSV report into a writer object

Methods:

`str()`

Returns a readable string representation

`part_type()`

Type of the instance

RETURNS	DESCRIPTION
`str`	Only possible value: "Value".

`to_dict()`

Transforms this instance to a dict with the Khiops JSON file structure

`write_report_line(writer)`

Writes a line of the TSV report into a writer object

Warning

This method is deprecated since Khiops 11.0.0 and will be removed in Khiops 12. Use the to_dict method instead.

PARAMETER	DESCRIPTION
`writer`	Output writer. TYPE: `KhiopsOutputWriter`

`PartValueGroup(json_data=None)`

Element of a categorical partition in a data grid

PARAMETER	DESCRIPTION
`json_data`	The list of values of the group. If not specified it returns an empty instance. TYPE: `list of str` DEFAULT: `None`

ATTRIBUTE	DESCRIPTION
`values`	The group's values. TYPE: `list of str`
`is_default_part`	True if this part is dedicated to all unknown values. TYPE: `bool`

See class docstring

METHOD	DESCRIPTION
`__str__`	Returns a human readable string representation
`part_type`	Type of the instance
`to_dict`	Transforms this instance to a dict with the Khiops JSON file structure
`write_report_line`	Writes a line of the TSV report into a writer object

Methods:

`str()`

Returns a human readable string representation

`part_type()`

Type of the instance

RETURNS	DESCRIPTION
`str`	Only possible value: "Value group".

`to_dict()`

Transforms this instance to a dict with the Khiops JSON file structure

`write_report_line(writer)`

Writes a line of the TSV report into a writer object

Warning

This method is deprecated since Khiops 11.0.0 and will be removed in Khiops 12. Use the to_dict method instead.

PARAMETER	DESCRIPTION
`writer`	Output writer. TYPE: `KhiopsOutputWriter`

`TrainedPredictor(json_data=None)`

Trained predictor information

PARAMETER DESCRIPTION

json_data

JSON data of an element of the list found at the trainedPredictors field within the modelingReport field of a Khiops JSON report file. If not specified it returns an empty instance.

Note

The selected_variables field is considered a "detail" and is not initialized in the constructor. Instead, it is initialized explicitly via the init_details method. This allows to make partial initializations for large reports.

TYPE: dict DEFAULT: None

ATTRIBUTE	DESCRIPTION
`family`	Predictor family name. Valid values are found in the `predictor_families` class variable. They are: "Baseline": for regression only, "Selective Naive Bayes": in all other cases. TYPE: `str`
`type`	Predictor type. Valid values are found in the `predictor_types` class attribute. TYPE: `Classifier or Regressor`
`name`	Human readable predictor name. TYPE: `str`
`variable_number`	Number of variables used by the predictor. TYPE: `int`
`selected_variables`	Variables used by the predictor. Only for type "Selective Naive Bayes". TYPE: `list of SelectedVariable`

See class docstring

METHOD	DESCRIPTION
`init_details`	Initializes the details' attributes from a Python JSON object
`is_detailed`	Returns True if the report contains any detailed information
`to_dict`	Transforms this instance to a dict with the Khiops JSON file structure
`write_report_header_line`	Writes the header line of a TSV report into a writer object
`write_report_line`	Writes a line of the TSV report into a writer object
`write_report_details`	Writes the details of the TSV report into a writer object

Methods:

`init_details(json_data=None)`

Initializes the details' attributes from a Python JSON object

PARAMETER	DESCRIPTION
`json_data`	JSON data of the dictionary found at the `trainedPredictorsDetails` field within the `modelingReport` field of a Khiops JSON report file. If not specified it leaves the object as-is. TYPE: `dict` DEFAULT: `None`

`is_detailed()`

Returns True if the report contains any detailed information

RETURNS	DESCRIPTION
`bool`	True if the report contains any detailed information.

`to_dict(details=False)`

Transforms this instance to a dict with the Khiops JSON file structure

`write_report_header_line(writer)`

Writes the header line of a TSV report into a writer object

Warning

This method is deprecated since Khiops 11.0.0 and will be removed in Khiops 12. Use the to_dict method instead.

The header is the same for all variable types.

PARAMETER	DESCRIPTION
`writer`	Output writer. TYPE: `KhiopsOutputWriter`

`write_report_line(writer)`

Writes a line of the TSV report into a writer object

Warning

This method is deprecated since Khiops 11.0.0 and will be removed in Khiops 12. Use the to_dict method instead.

PARAMETER	DESCRIPTION
`writer`	Output writer. TYPE: `KhiopsOutputWriter`

`write_report_details(writer)`

Writes the details of the TSV report into a writer object

Warning

This method is deprecated since Khiops 11.0.0 and will be removed in Khiops 12. Use the to_dict method instead.

PARAMETER	DESCRIPTION
`writer`	Output writer. TYPE: `KhiopsOutputWriter`

`SelectedVariable(json_data=None)`

Information about a selected variable in a predictor

PARAMETER	DESCRIPTION
`json_data`	JSON data representing an element of the `selectedVariables` list in the `trainedPredictorsDetails` field within the `modelingReport` field of a Khiops JSON report file. If not specified it returns an empty instance. TYPE: `dict` DEFAULT: `None`

ATTRIBUTE	DESCRIPTION
`name`	Human readable variable name. TYPE: `str`
`prepared_name`	Internal variable name. TYPE: `str`
`level`	Variable level. TYPE: `float`
`weight`	Variable weight in the model. TYPE: `float`
`importance`	A measure of overall importance of the variable in the model. It is the geometric mean of the level and weight. TYPE: `float`

See class docstring

METHOD	DESCRIPTION
`to_dict`	Transforms this instance to a dict with the Khiops JSON file structure
`write_report_header_line`	Writes the header line of a TSV report into a writer object
`write_report_line`	Writes a line of the TSV report into a writer object

Methods:

`to_dict()`

Transforms this instance to a dict with the Khiops JSON file structure

`write_report_header_line(writer)`

Writes the header line of a TSV report into a writer object

The header is the same for all variable types.

Warning

This method is deprecated since Khiops 11.0.0 and will be removed in Khiops 12. Use the to_dict method instead.

PARAMETER	DESCRIPTION
`writer`	Output writer. TYPE: `KhiopsOutputWriter`

`write_report_line(writer)`

Writes a line of the TSV report into a writer object

Warning

This method is deprecated since Khiops 11.0.0 and will be removed in Khiops 12. Use the to_dict method instead.

PARAMETER	DESCRIPTION
`writer`	Output writer. TYPE: `KhiopsOutputWriter`

`PredictorPerformance(json_data=None)`

A predictor's performance evaluation

This class describes the performance of a predictor (classifier or regressor).

PARAMETER DESCRIPTION

json_data

JSON data of an element of the dictionary found at the predictorPerformances field within the one of the evaluation report fields of a Khiops JSON report file. If not specified it returns an empty instance.

Note

The confusion_matrix field is considered as "detail" and is not initialized in the constructor. Instead, it is initialized explicitly via the init_details method. This allows to make partial initializations for large reports.

TYPE: dict DEFAULT: None

ATTRIBUTE	DESCRIPTION
`rank`	An string index representing the order in the report. TYPE: `str`
`type`	Type of the predictor. TYPE: `Classifier or Regressor`
`name`	Human readable name. TYPE: `str`
`data_grid`	Data grid representing the distribution of the target values per part of the descriptive variable in the evaluated dataset. TYPE: `DataGrid`
`accuracy`	Classifier only: Accuracy. TYPE: `float`
`compression`	Classifier only: Compression rate. TYPE: `float`
`auc`	Classifier only: Area under the ROC curve. TYPE: `float`
`confusion_matrix`	Classifier only: Confusion matrix. TYPE: `ConfusionMatrix`
`rmse`	Regressor only: Root mean square error. TYPE: `float`
`mae`	Regressor only: Mean absolute error. TYPE: `float`
`nlpd`	Regressor only: Negative log predictive density. TYPE: `float`
`rank_rmse`	Regressor only: Root mean square error on the target's value rank. TYPE: `float`
`rank_mae`	Regressor only: Mean absolute error on the target's value rank. TYPE: `float`
`rank_nlpd`	Regressor only: Negative log predictive density on the target's value rank. TYPE: `float`

See class docstring

METHOD	DESCRIPTION
`init_details`	Initializes the details' attributes from a python JSON object
`is_detailed`	Returns True if the report contains any detailed information
`get_metric_names`	Returns the available univariate metrics
`get_metric`	Returns the value of the specified metric
`to_dict`	Transforms this instance to a dict with the Khiops JSON file structure
`write_report_header_line`	Writes the header line of a TSV report into a writer object
`write_report_line`	Writes a line of the TSV report into a writer object
`write_report_details`	Writes the details of the TSV report into a writer object

Methods:

`init_details(json_data=None)`

Initializes the details' attributes from a python JSON object

`is_detailed()`

Returns True if the report contains any detailed information

RETURNS	DESCRIPTION
`bool`	True if the report contains any detailed information.

`get_metric_names()`

Returns the available univariate metrics

RETURNS	DESCRIPTION
`list of str`	The names of the available metrics.

`get_metric(metric_name)`

Returns the value of the specified metric

Note

The available metrics is available via the method get_metric_names.

PARAMETER	DESCRIPTION
`metric_name`	A metric name (case insensitive). TYPE: `str`

RETURNS	DESCRIPTION
`float`	The value of the specified metric.

`to_dict(details=False)`

Transforms this instance to a dict with the Khiops JSON file structure

`write_report_header_line(writer)`

Writes the header line of a TSV report into a writer object

The header is the same for all variable types.

Warning

This method is deprecated since Khiops 11.0.0 and will be removed in Khiops 12. Use the to_dict method instead.

PARAMETER	DESCRIPTION
`writer`	Output writer. TYPE: `KhiopsOutputWriter`

`write_report_line(writer)`

Writes a line of the TSV report into a writer object

Warning

This method is deprecated since Khiops 11.0.0 and will be removed in Khiops 12. Use the to_dict method instead.

PARAMETER	DESCRIPTION
`writer`	Output writer. TYPE: `KhiopsOutputWriter`

`write_report_details(writer)`

Writes the details of the TSV report into a writer object

Warning

This method is deprecated since Khiops 11.0.0 and will be removed in Khiops 12. Use the to_dict method instead.

PARAMETER	DESCRIPTION
`writer`	Output writer. TYPE: `KhiopsOutputWriter`

`ConfusionMatrix(json_data=None)`

A classifier's confusion matrix

PARAMETER	DESCRIPTION
`json_data`	JSON data of the `confusionMatrix` field of an element of the dictionary found at the `predictorsDetailedPerformances` field within one of the evaluation report fields of a Khiops JSON report file. If not specified it returns an empty object. TYPE: `dict` DEFAULT: `None`

ATTRIBUTE	DESCRIPTION
`values`	Values of the target variable. TYPE: `list of str`
`matrix`	Matrix of predicted frequencies vs target frequencies. This list is synchornized with `values`. Each list element represents a row of the confusion matrix, that is, the target frequencies for a fixed predicted target value. TYPE: `list`

See class docstring

METHOD	DESCRIPTION
`to_dict`	Transforms this instance to a dict with the Khiops JSON file structure
`write_report`	Writes the instance's TSV report into a writer object

Methods:

`to_dict()`

Transforms this instance to a dict with the Khiops JSON file structure

`write_report(writer)`

Writes the instance's TSV report into a writer object

Warning

This method is deprecated since Khiops 11.0.0 and will be removed in Khiops 12. Use the to_dict method instead.

PARAMETER	DESCRIPTION
`writer`	Output writer. TYPE: `KhiopsOutputWriter`

`PredictorCurve(json_data=None)`

A lift curve for a classifier or a REC curve for a regressor

PARAMETER	DESCRIPTION
`json_data`	JSON data of an element of the `liftCurves` or `recCurves` field of one of the evaluation report fields of a Khiops JSON report file. If not specified it returns an empty instance. TYPE: `dict` DEFAULT: `None`

ATTRIBUTE	DESCRIPTION
`type`	Type of predictor curve. TYPE: `Lift(classifier) or REC(regressor)`
`name`	Name of evaluated predictor. TYPE: `str`
`values`	The curve's y-axis values. TYPE: `list of float`

See class docstring

Methods:

Functions:

`read_analysis_results_file(json_file_path)`

Reads a Khiops JSON report

PARAMETER	DESCRIPTION
`json_file_path`	Path of the JSON report file. TYPE: `str`

RETURNS	DESCRIPTION
`AnalysisResults`	An instance of AnalysisResults containing the report's information.

Examples:

See the following functions of the samples.py documentation script: - samples.access_predictor_evaluation_report() - samples.train_predictor_with_cross_validation() - samples.multiple_train_predictor()