bluecast.tests.test_error_analysis_base_classes

Module Contents

Classes

ConcreteDataReader	Abstract class to define error reading out of fold datasets from BlueCast pipelines.
ConcreteErrorPreprocessor	Abstract class to define analysing prediction errors on out of fold datasets
ConcreteErrorAnalyser	Abstract class to define the analysis of prediction errors on out of fold datasets
ConcreteErrorDistributionPlotter	Abstract class to define the plots for error analysis

Functions

test_base_class_datareader_notimplemented_error()
test_base_class_erroranalyser_notimplemented_error()
test_base_class_errorpreprocessor_notimplemented_error()
test_data_reader_not_implemented()
test_error_preprocessor_not_implemented()
test_error_analyser_not_implemented()
test_error_distribution_plotter_not_implemented()
test_plot_error_distributions_with_splits()
test_plot_error_distributions_no_split()

bluecast.tests.test_error_analysis_base_classes.test_base_class_datareader_notimplemented_error()

bluecast.tests.test_error_analysis_base_classes.test_base_class_erroranalyser_notimplemented_error()

bluecast.tests.test_error_analysis_base_classes.test_base_class_errorpreprocessor_notimplemented_error()

class bluecast.tests.test_error_analysis_base_classes.ConcreteDataReader

Bases: bluecast.evaluation.base_classes.DataReader

Abstract class to define error reading out of fold datasets from BlueCast pipelines.

read_data_from_bluecast_instance() → polars.DataFrame

read_data_from_bluecast_cv_instance() → polars.DataFrame

class bluecast.tests.test_error_analysis_base_classes.ConcreteErrorPreprocessor

Bases: bluecast.evaluation.base_classes.ErrorPreprocessor

Abstract class to define analysing prediction errors on out of fold datasets

stack_predictions_by_class(df: polars.DataFrame) → polars.DataFrame

calculate_errors(df: polars.DataFrame) → polars.DataFrame

class bluecast.tests.test_error_analysis_base_classes.ConcreteErrorAnalyser

Bases: bluecast.evaluation.base_classes.ErrorAnalyser

Abstract class to define the analysis of prediction errors on out of fold datasets

analyse_errors(df: polars.DataFrame, descending: bool = True) → None

class bluecast.tests.test_error_analysis_base_classes.ConcreteErrorDistributionPlotter

Bases: bluecast.evaluation.base_classes.ErrorDistributionPlotter

Abstract class to define the plots for error analysis

plot_error_distributions(df: polars.DataFrame, hue_column: str = 'target_class') → None

bluecast.tests.test_error_analysis_base_classes.test_data_reader_not_implemented()

bluecast.tests.test_error_analysis_base_classes.test_error_preprocessor_not_implemented()

bluecast.tests.test_error_analysis_base_classes.test_error_analyser_not_implemented()

bluecast.tests.test_error_analysis_base_classes.test_error_distribution_plotter_not_implemented()

bluecast.tests.test_error_analysis_base_classes.test_plot_error_distributions_with_splits()

bluecast.tests.test_error_analysis_base_classes.test_plot_error_distributions_no_split()