Index

A

add_exclusion() (dataforge_ml.config.PipelineConfig method) add_indicator_column() (dataforge_ml.imputation._config.ImputationConfig method) add_indicator_columns (dataforge_ml.imputation._config.ImputationConfig property) add_mnar_column() (dataforge_ml.imputation._config.ImputationConfig method) add_phase_exclusion() (dataforge_ml.config.PipelineConfig method)

annotations (dataforge_ml.evaluation.imputation._records.ColumnC2STResult attribute) apply_exclusions() (dataforge_ml.imputation._fitted_imputer.FittedImputer method) ArtifactPythonVersionWarning (class in dataforge_ml._serialization) author() (in module dataforge_ml.imputation._authoring) AuthoredColumn (class in dataforge_ml.imputation._authoring)

B

base_max_iter (dataforge_ml.imputation._config.NumericImputationConfig attribute) BayesianRidge (dataforge_ml.imputation._config.ModelChoice attribute) BelowSampleFloor (dataforge_ml.evaluation.imputation._records.C2STOutcome attribute) bimodal_correlation_threshold (dataforge_ml.imputation._config.NumericImputationConfig attribute) bimodal_dip_p_value_threshold (dataforge_ml.profiling._numeric_config.NumericProfileConfig attribute) bimodal_grouping_variables (dataforge_ml.imputation._config.NumericImputationConfig property)

bimodal_min_component_weight (dataforge_ml.profiling._numeric_config.NumericProfileConfig attribute) bimodal_min_correlated_features (dataforge_ml.imputation._config.NumericImputationConfig attribute) bimodal_min_separation_threshold (dataforge_ml.profiling._numeric_config.NumericProfileConfig attribute) Boolean (dataforge_ml.config.SemanticType attribute) boolean_minority_threshold (dataforge_ml.splitting._config.SplitConfig attribute) bootstrap_sample_size (dataforge_ml.profiling._numeric_config.NonlinearityProfileConfig attribute) BoundedDiscrete (dataforge_ml.profiling._config.NumericKind attribute)

C

c2st (dataforge_ml.evaluation._config.EvaluationConfig attribute) C2ST (dataforge_ml.evaluation._config.EvaluationMetric attribute) c2st (dataforge_ml.evaluation.imputation._records.EvaluationReport attribute) C2STAnnotation (class in dataforge_ml.evaluation.imputation._records) C2STConfig (class in dataforge_ml.evaluation._config) C2STOutcome (class in dataforge_ml.evaluation.imputation._records) C2STProvenance (class in dataforge_ml.evaluation.imputation._records) C2STReport (class in dataforge_ml.evaluation.imputation._records) C2STResult (class in dataforge_ml.evaluation._c2st) C2STScheme (class in dataforge_ml.evaluation._c2st) C2STScore (class in dataforge_ml.evaluation.imputation._records) C2STVerdict (class in dataforge_ml.evaluation.imputation._records) Categorical (dataforge_ml.config.SemanticType attribute) categorical (dataforge_ml.profiling._config.ProfileConfig attribute) CategoricalProfileConfig (class in dataforge_ml.profiling._categorical_config) center1 (dataforge_ml.imputation._authoring.AuthoredColumn attribute) (dataforge_ml.imputation._config.ColumnImputationDecision attribute) center2 (dataforge_ml.imputation._authoring.AuthoredColumn attribute) (dataforge_ml.imputation._config.ColumnImputationDecision attribute) chunk_size (dataforge_ml.profiling._config.ProfileConfig attribute) classifier (dataforge_ml.evaluation._config.C2STConfig attribute) classifier_class (dataforge_ml.evaluation.imputation._records.C2STProvenance attribute) classifier_injected (dataforge_ml.evaluation.imputation._records.C2STProvenance attribute) classifier_params (dataforge_ml.evaluation.imputation._records.C2STProvenance attribute) ClusterConditional (dataforge_ml.imputation._config.ImputationStrategy attribute) col_drop_threshold (dataforge_ml.profiling._missingness_config.MissingnessProfileConfig attribute) column (dataforge_ml.evaluation.imputation._records.ColumnC2STResult attribute) (dataforge_ml.imputation._config.ColumnImputationDecision attribute) (dataforge_ml.observability.PipelineEvent attribute)

column_count (dataforge_ml.profiling._config.DatasetStats attribute) column_decisions (dataforge_ml.imputation._config.ImputationDecision attribute) column_overrides (dataforge_ml.config.PipelineConfig property) ColumnC2STResult (class in dataforge_ml.evaluation.imputation._records) ColumnImputationDecision (class in dataforge_ml.imputation._config) ColumnImputationRecord (class in dataforge_ml.imputation._config) ColumnProfile (class in dataforge_ml.profiling._config) columns (dataforge_ml.evaluation.imputation._records.C2STReport attribute) (dataforge_ml.imputation._config.ImputationUnit attribute) (dataforge_ml.imputation._unit_fit.UnitFitResult attribute) (dataforge_ml.imputation._unit_fit.UnitNotTrainableError attribute) (dataforge_ml.profiling._config.StructuralProfileResult attribute) compose() (dataforge_ml.imputation._fitted_imputer.FittedImputer class method) compute_correlation (dataforge_ml.profiling._config.ProfileConfig attribute) compute_nonlinearity (dataforge_ml.profiling._config.ProfileConfig attribute) config (dataforge_ml.evaluation.imputation._records.C2STProvenance attribute) config_snapshot (dataforge_ml.imputation._config.ImputationDecision attribute) Constant (dataforge_ml.imputation._config.ImputationStrategy attribute) constant_fill (dataforge_ml.imputation._authoring.AuthoredColumn attribute) (dataforge_ml.imputation._config.ColumnImputationDecision attribute) Continuous (dataforge_ml.profiling._config.NumericKind attribute) converged (dataforge_ml.imputation._fit_signals.FitSignals attribute) core_budget() (in module dataforge_ml.imputation._unit_fit) correlation (dataforge_ml.profiling._config.ProfileConfig attribute) correlation_target_column (dataforge_ml.profiling._config.ProfileConfig attribute) CorrelationProfileConfig (class in dataforge_ml.profiling._correlation_config) CrossValidation (dataforge_ml.evaluation._c2st.C2STScheme attribute) Custom (dataforge_ml.imputation._config.ModelChoice attribute) custom_estimators (dataforge_ml.imputation._config.ImputationDecision attribute)

D

dataframe (dataforge_ml.imputation._config.ImputationResult attribute) DataLoader (class in dataforge_ml.utils.data_loader) dataset (dataforge_ml.profiling._config.StructuralProfileResult attribute) DatasetStats (class in dataforge_ml.profiling._config) DataSplitter (class in dataforge_ml.splitting._splitter) Datetime (dataforge_ml.config.SemanticType attribute) datetime_ (dataforge_ml.profiling._config.ProfileConfig attribute) datetime_coerce_threshold (dataforge_ml.profiling._type_detection_config.TypeDetectionConfig attribute) datetime_epoch_units (dataforge_ml.profiling._config.ProfileConfig property) datetime_formats (dataforge_ml.profiling._config.ProfileConfig property) DatetimeProfileConfig (class in dataforge_ml.profiling._datetime_config) decide() (in module dataforge_ml.imputation._decision_assembler) decided_hyperparameters (dataforge_ml.imputation._config.ImputationDecision attribute) decision (dataforge_ml.imputation._config.ColumnImputationRecord attribute) (dataforge_ml.observability.EventType attribute)

degenerate (dataforge_ml.evaluation._c2st.C2STResult attribute) Degenerate (dataforge_ml.evaluation.imputation._records.C2STAnnotation attribute) deserialize() (in module dataforge_ml._serialization) domain_snap_bounds (dataforge_ml.imputation._authoring.AuthoredColumn attribute) (dataforge_ml.imputation._config.ColumnImputationDecision attribute) drop (dataforge_ml.imputation._config.ColumnImputationDecision attribute) Dropped (dataforge_ml.imputation._config.ImputationStrategy attribute) dropped_columns (dataforge_ml.imputation._config.ImputationDecision attribute) (dataforge_ml.imputation._config.ImputationResult attribute) DroppedColumnAbsentWarning (class in dataforge_ml.imputation._fitted_imputer) duplicate_count (dataforge_ml.profiling._config.DatasetStats attribute) duplicate_ratio (dataforge_ml.profiling._config.DatasetStats attribute) duration_s (dataforge_ml.imputation._fit_signals.FitSignals attribute)

E

encoded_category_max_ratio (dataforge_ml.profiling._type_detection_config.TypeDetectionConfig attribute) encoded_category_max_unique (dataforge_ml.profiling._type_detection_config.TypeDetectionConfig attribute) Encoding (dataforge_ml.config.PipelinePhase attribute) estimator (dataforge_ml.imputation._fit_signals.FitSignals attribute) evaluate_imputation() (in module dataforge_ml.evaluation.imputation._adapter)

EvaluationConfig (class in dataforge_ml.evaluation._config) EvaluationMetric (class in dataforge_ml.evaluation._config) EvaluationReport (class in dataforge_ml.evaluation.imputation._records) event_type (dataforge_ml.observability.PipelineEvent attribute) EventType (class in dataforge_ml.observability) exclude_columns (dataforge_ml.config.PipelineConfig property)

F

fdr_alpha (dataforge_ml.evaluation._config.C2STConfig attribute) feature_cols (dataforge_ml.imputation._authoring.AuthoredColumn attribute) (dataforge_ml.imputation._config.ColumnImputationDecision attribute) feature_correlation (dataforge_ml.profiling._config.DatasetStats attribute) fill_value (dataforge_ml.imputation._config.ColumnImputationRecord attribute) fit_unit() (in module dataforge_ml.imputation._unit_fit) FitSignals (class in dataforge_ml.imputation._fit_signals) fitted (dataforge_ml.imputation._unit_fit.UnitFitResult attribute) FittedColumnAbsentError (class in dataforge_ml.imputation._fitted_imputer) FittedImputer (class in dataforge_ml.imputation._fitted_imputer) FittedUnit (class in dataforge_ml.imputation._fitted_imputer) Flagged (dataforge_ml.evaluation.imputation._records.C2STVerdict attribute) fold_index (dataforge_ml.splitting._config.FoldResult attribute) FoldResult (class in dataforge_ml.splitting._config) folds (dataforge_ml.splitting._config.HoldoutCVResult attribute) frame_z_spread (dataforge_ml.evaluation.imputation._records.C2STScore attribute) frames (dataforge_ml.evaluation.imputation._records.C2STScore attribute) free_text_avg_words (dataforge_ml.profiling._type_detection_config.TypeDetectionConfig attribute) free_text_high_unique_with_spaces (dataforge_ml.profiling._type_detection_config.TypeDetectionConfig attribute) free_text_median_chars (dataforge_ml.profiling._type_detection_config.TypeDetectionConfig attribute) free_text_min_unique_ratio (dataforge_ml.profiling._type_detection_config.TypeDetectionConfig attribute) free_text_p90_chars (dataforge_ml.profiling._type_detection_config.TypeDetectionConfig attribute)

from_dict() (dataforge_ml.config.PipelineConfig class method) (dataforge_ml.evaluation._config.C2STConfig class method) (dataforge_ml.evaluation._config.EvaluationConfig class method) (dataforge_ml.imputation._config.ColumnImputationDecision class method) (dataforge_ml.imputation._config.ColumnImputationRecord class method) (dataforge_ml.imputation._config.ImputationConfig class method) (dataforge_ml.imputation._config.ImputationDecision class method) (dataforge_ml.imputation._config.ImputationUnit class method) (dataforge_ml.imputation._config.NumericImputationConfig class method) (dataforge_ml.profiling._categorical_config.CategoricalProfileConfig class method) (dataforge_ml.profiling._config.ColumnProfile class method) (dataforge_ml.profiling._config.DatasetStats class method) (dataforge_ml.profiling._config.ProfileConfig class method) (dataforge_ml.profiling._config.StructuralProfileResult class method) (dataforge_ml.profiling._correlation_config.CorrelationProfileConfig class method) (dataforge_ml.profiling._datetime_config.DatetimeProfileConfig class method) (dataforge_ml.profiling._missingness_config.MissingnessProfileConfig class method) (dataforge_ml.profiling._numeric_config.NonlinearityProfileConfig class method) (dataforge_ml.profiling._numeric_config.NumericProfileConfig class method) (dataforge_ml.profiling._type_detection_config.TypeDetectionConfig class method) (dataforge_ml.splitting._config.SplitConfig class method) from_json() (dataforge_ml.config.PipelineConfig class method) (dataforge_ml.profiling._config.ProfileConfig class method)

G

GMMSampling (dataforge_ml.imputation._config.ImputationStrategy attribute) gradient_boost_min_rows (dataforge_ml.imputation._config.NumericImputationConfig attribute) GradientBoostingRegressor (dataforge_ml.imputation._config.ModelChoice attribute)

group_kfold() (dataforge_ml.splitting._splitter.DataSplitter method) group_split() (dataforge_ml.splitting._splitter.DataSplitter method) grouping_variable (dataforge_ml.imputation._authoring.AuthoredColumn attribute) (dataforge_ml.imputation._config.ColumnImputationDecision attribute)

H

heteroscedasticity_p_value_threshold (dataforge_ml.profiling._numeric_config.NonlinearityProfileConfig attribute) high_gap_cv_threshold (dataforge_ml.profiling._datetime_config.DatetimeProfileConfig attribute) high_outlier_density_threshold (dataforge_ml.profiling._numeric_config.NumericProfileConfig attribute)

holdout_cv() (dataforge_ml.splitting._splitter.DataSplitter method) HoldoutCVResult (class in dataforge_ml.splitting._config) hyperparameters (dataforge_ml.imputation._config.ImputationUnit attribute)

I

Identifier (dataforge_ml.config.SemanticType attribute) identifier_max_median_length (dataforge_ml.profiling._type_detection_config.TypeDetectionConfig attribute) identifier_unique_ratio (dataforge_ml.profiling._type_detection_config.TypeDetectionConfig attribute) imbalance_warn_ratio (dataforge_ml.evaluation._config.C2STConfig attribute) ImbalancedPiles (dataforge_ml.evaluation.imputation._records.C2STAnnotation attribute) imputation (dataforge_ml.config.PipelineConfig attribute) Imputation (dataforge_ml.config.PipelinePhase attribute) ImputationConfig (class in dataforge_ml.imputation._config) ImputationDecision (class in dataforge_ml.imputation._config) ImputationFitWarning (class in dataforge_ml.imputation._fit_signals) ImputationResult (class in dataforge_ml.imputation._config)

ImputationStrategy (class in dataforge_ml.imputation._config) ImputationUnit (class in dataforge_ml.imputation._config) IncompatibleArtifactError (class in dataforge_ml._serialization) index (dataforge_ml.observability.PipelineEvent attribute) Indicator (dataforge_ml.imputation._config.ImputationStrategy attribute) indicator_added (dataforge_ml.imputation._config.ColumnImputationRecord attribute) indicator_flag (dataforge_ml.imputation._config.ColumnImputationDecision attribute) inferred_dtype (dataforge_ml.profiling._config.ColumnProfile attribute) inspect() (in module dataforge_ml._serialization) is_block (dataforge_ml.imputation._config.ImputationUnit attribute) is_target (dataforge_ml.profiling._config.ColumnProfile attribute) item (dataforge_ml.observability.EventType attribute)

K

kfold() (dataforge_ml.splitting._splitter.DataSplitter method) KNN (dataforge_ml.imputation._config.ImputationStrategy attribute) knn_distance_weight_max_features (dataforge_ml.imputation._config.NumericImputationConfig attribute) knn_distance_weight_max_null_ratio (dataforge_ml.imputation._config.NumericImputationConfig attribute) knn_max_features (dataforge_ml.imputation._config.NumericImputationConfig attribute)

knn_max_neighbors (dataforge_ml.imputation._config.NumericImputationConfig attribute) knn_max_rows (dataforge_ml.imputation._config.NumericImputationConfig attribute) knn_min_neighbors (dataforge_ml.imputation._config.NumericImputationConfig attribute) kurt_leptokurtic_lower (dataforge_ml.profiling._numeric_config.NumericProfileConfig attribute) kurt_platykurtic_upper (dataforge_ml.profiling._numeric_config.NumericProfileConfig attribute)

L

load() (dataforge_ml.utils.data_loader.DataLoader method)

low_power_below (dataforge_ml.evaluation._config.C2STConfig attribute) LowPower (dataforge_ml.evaluation.imputation._records.C2STAnnotation attribute)

M

mar_correlation_threshold (dataforge_ml.profiling._missingness_config.MissingnessProfileConfig attribute) max_stratification_signals (dataforge_ml.splitting._config.SplitConfig attribute) max_workers (dataforge_ml.imputation._config.NumericImputationConfig attribute) mcar_feature_predictability_threshold (dataforge_ml.imputation._config.NumericImputationConfig attribute) Mean (dataforge_ml.imputation._config.ImputationStrategy attribute) mean_frame_z (dataforge_ml.evaluation.imputation._records.C2STScore attribute) mean_repeat_z (dataforge_ml.evaluation._c2st.C2STResult attribute) Median (dataforge_ml.imputation._config.ImputationStrategy attribute) memory_breakdown (dataforge_ml.profiling._config.DatasetStats attribute) memory_bytes (dataforge_ml.profiling._config.DatasetStats attribute) memory_threshold_mb (dataforge_ml.profiling._config.ProfileConfig attribute) message (dataforge_ml.observability.PipelineEvent attribute) mi_min_rows (dataforge_ml.profiling._correlation_config.CorrelationProfileConfig attribute) MICE (dataforge_ml.imputation._config.ImputationStrategy attribute) mice_correlation_threshold (dataforge_ml.imputation._config.NumericImputationConfig attribute) mice_max_nearest_features (dataforge_ml.imputation._config.NumericImputationConfig attribute) mice_min_rows (dataforge_ml.imputation._config.NumericImputationConfig attribute) mice_n_nearest_features_min_cols (dataforge_ml.imputation._config.NumericImputationConfig attribute)

min_filled_cells (dataforge_ml.evaluation._config.C2STConfig attribute) min_rows (dataforge_ml.profiling._numeric_config.NonlinearityProfileConfig attribute) min_samples_leaf (dataforge_ml.evaluation._config.C2STConfig attribute) missingness (dataforge_ml.profiling._config.ColumnProfile attribute) (dataforge_ml.profiling._config.ProfileConfig attribute) missingness_matrix (dataforge_ml.profiling._config.DatasetStats attribute) MissingnessProfileConfig (class in dataforge_ml.profiling._missingness_config) mixed_type_min_minor_pct (dataforge_ml.profiling._categorical_config.CategoricalProfileConfig attribute) mnar (dataforge_ml.imputation._config.ColumnImputationDecision attribute) MNAR (dataforge_ml.imputation._config.ImputationStrategy attribute) mnar_columns (dataforge_ml.imputation._config.ImputationConfig property) mnar_null_ratio_threshold (dataforge_ml.profiling._datetime_config.DatetimeProfileConfig attribute) Modality (class in dataforge_ml.config) modality (dataforge_ml.profiling._config.DatasetStats attribute) (dataforge_ml.profiling._config.ProfileConfig attribute) Mode (dataforge_ml.imputation._config.ImputationStrategy attribute) model_choice (dataforge_ml.imputation._config.ColumnImputationDecision attribute) ModelChoice (class in dataforge_ml.imputation._config) mutual_information_threshold (dataforge_ml.profiling._numeric_config.NonlinearityProfileConfig attribute)

N

n_filled (dataforge_ml.evaluation.imputation._records.ColumnC2STResult attribute) n_iter (dataforge_ml.imputation._fit_signals.FitSignals attribute) n_observed (dataforge_ml.evaluation.imputation._records.ColumnC2STResult attribute) n_test (dataforge_ml.evaluation._c2st.C2STResult attribute) name (dataforge_ml.profiling._config.ColumnProfile attribute) near_constant_threshold (dataforge_ml.profiling._categorical_config.CategoricalProfileConfig attribute) (dataforge_ml.profiling._numeric_config.NumericProfileConfig attribute) near_redundant_cramer_v_threshold (dataforge_ml.profiling._correlation_config.CorrelationProfileConfig attribute) near_redundant_eta_squared_threshold (dataforge_ml.profiling._correlation_config.CorrelationProfileConfig attribute) near_redundant_pearson_threshold (dataforge_ml.profiling._correlation_config.CorrelationProfileConfig attribute) NoFilledCells (dataforge_ml.evaluation.imputation._records.C2STOutcome attribute) nonlinearity (dataforge_ml.profiling._config.ProfileConfig attribute) NonlinearityProfileConfig (class in dataforge_ml.profiling._numeric_config) NoObservedCells (dataforge_ml.evaluation.imputation._records.C2STOutcome attribute) Normalization (dataforge_ml.config.PipelinePhase attribute)

notes (dataforge_ml.imputation._fit_signals.FitSignals attribute) NotFlagged (dataforge_ml.evaluation.imputation._records.C2STVerdict attribute) NoVerdict (dataforge_ml.evaluation.imputation._records.C2STVerdict attribute) Numeric (dataforge_ml.config.SemanticType attribute) numeric (dataforge_ml.imputation._config.ImputationConfig attribute) (dataforge_ml.profiling._config.ProfileConfig attribute) numeric_coerce_threshold (dataforge_ml.profiling._type_detection_config.TypeDetectionConfig attribute) numeric_kind (dataforge_ml.profiling._config.ColumnProfile attribute) numeric_kind_overrides (dataforge_ml.config.PipelineConfig property) numeric_sentinels (dataforge_ml.imputation._config.ImputationDecision attribute) (dataforge_ml.imputation._fitted_imputer.FittedImputer attribute) (dataforge_ml.profiling._config.ProfileConfig property) (dataforge_ml.profiling._config.StructuralProfileResult attribute) NumericImputationConfig (class in dataforge_ml.imputation._config) NumericKind (class in dataforge_ml.profiling._config) NumericProfileConfig (class in dataforge_ml.profiling._numeric_config)

O

original_dtype (dataforge_ml.profiling._config.ColumnProfile attribute) outcome (dataforge_ml.evaluation.imputation._records.ColumnC2STResult attribute) outlier_sigma_threshold (dataforge_ml.profiling._numeric_config.NumericProfileConfig attribute)

OutlierDetection (dataforge_ml.config.PipelinePhase attribute) overall_sparsity (dataforge_ml.profiling._config.DatasetStats attribute) override_hyperparameters (dataforge_ml.imputation._config.ImputationDecision attribute) OverrideCoercionError (class in dataforge_ml.profiling._base)

P

p_adjusted (dataforge_ml.evaluation.imputation._records.C2STScore attribute) p_value (dataforge_ml.evaluation.imputation._records.C2STScore attribute) Passthrough (dataforge_ml.imputation._config.ImputationStrategy attribute) per_column_constant_fill (dataforge_ml.imputation._config.NumericImputationConfig property) per_column_strategy (dataforge_ml.imputation._config.NumericImputationConfig property) phase (dataforge_ml.observability.PipelineEvent attribute) phase_exclusions (dataforge_ml.config.PipelineConfig property) PipelineConfig (class in dataforge_ml.config)

PipelineEvent (class in dataforge_ml.observability) PipelinePhase (class in dataforge_ml.config) profile() (dataforge_ml.profiling.orchestrator.StructuralProfiler method) profile_stratified_kfold() (dataforge_ml.splitting._splitter.DataSplitter method) profile_stratified_split() (dataforge_ml.splitting._splitter.DataSplitter method) ProfileConfig (class in dataforge_ml.profiling._config) profiling (dataforge_ml.config.PipelineConfig attribute) Profiling (dataforge_ml.config.PipelinePhase attribute) provenance (dataforge_ml.evaluation.imputation._records.C2STReport attribute)

R

r2_gap_threshold (dataforge_ml.profiling._numeric_config.NonlinearityProfileConfig attribute) r2_rf_unpredictable_threshold (dataforge_ml.profiling._numeric_config.NonlinearityProfileConfig attribute) random_seed (dataforge_ml.config.PipelineConfig attribute) (dataforge_ml.imputation._fitted_imputer.FittedImputer attribute) random_split() (dataforge_ml.splitting._splitter.DataSplitter method) random_state (dataforge_ml.evaluation._config.C2STConfig attribute) (dataforge_ml.profiling._numeric_config.NonlinearityProfileConfig attribute) RandomForestRegressor (dataforge_ml.imputation._config.ModelChoice attribute) rare_threshold_pct (dataforge_ml.profiling._categorical_config.CategoricalProfileConfig attribute) reason (dataforge_ml.imputation._unit_fit.UnitNotTrainableError attribute) recent_window_fraction (dataforge_ml.profiling._datetime_config.DatetimeProfileConfig attribute) records (dataforge_ml.imputation._config.ImputationResult attribute) (dataforge_ml.imputation._fitted_imputer.FittedImputer attribute)

redundancy_correlation_threshold (dataforge_ml.splitting._config.SplitConfig attribute) repeat_index (dataforge_ml.splitting._config.FoldResult attribute) repeat_z (dataforge_ml.evaluation._c2st.C2STResult attribute) repeat_z_spread (dataforge_ml.evaluation._c2st.C2STResult attribute) repeated_kfold() (dataforge_ml.splitting._splitter.DataSplitter method) repeats (dataforge_ml.evaluation._config.C2STConfig attribute) resolve_active_columns() (dataforge_ml.config.PipelineConfig method) row_count (dataforge_ml.profiling._config.DatasetStats attribute) row_distribution (dataforge_ml.profiling._config.DatasetStats attribute) row_drop_threshold (dataforge_ml.profiling._config.ProfileConfig attribute) rows_per_signal (dataforge_ml.splitting._config.SplitConfig attribute)

S

scale_orders_of_magnitude (dataforge_ml.profiling._numeric_config.NumericProfileConfig attribute) Scaling (dataforge_ml.config.PipelinePhase attribute) scheme (dataforge_ml.evaluation._config.C2STConfig attribute) score (dataforge_ml.evaluation.imputation._records.ColumnC2STResult attribute) semantic_type (dataforge_ml.imputation._config.ColumnImputationDecision attribute) (dataforge_ml.profiling._config.ColumnProfile attribute) SemanticType (class in dataforge_ml.config) serialize() (in module dataforge_ml._serialization) set_bimodal_grouping_variable() (dataforge_ml.imputation._config.NumericImputationConfig method) set_column_type() (dataforge_ml.config.PipelineConfig method) set_datetime_epoch_unit() (dataforge_ml.profiling._config.ProfileConfig method) set_datetime_format() (dataforge_ml.profiling._config.ProfileConfig method) set_numeric_kind() (dataforge_ml.config.PipelineConfig method) set_numeric_sentinel() (dataforge_ml.profiling._config.ProfileConfig method) set_per_column_constant_fill() (dataforge_ml.imputation._config.NumericImputationConfig method) set_per_column_strategy() (dataforge_ml.imputation._config.NumericImputationConfig method) set_string_sentinel() (dataforge_ml.profiling._config.ProfileConfig method) severity_high (dataforge_ml.profiling._missingness_config.MissingnessProfileConfig attribute) severity_minor (dataforge_ml.profiling._missingness_config.MissingnessProfileConfig attribute) severity_moderate (dataforge_ml.profiling._missingness_config.MissingnessProfileConfig attribute) signals (dataforge_ml.imputation._config.ColumnImputationDecision attribute) (dataforge_ml.imputation._unit_fit.UnitFitResult attribute) skew_high (dataforge_ml.profiling._numeric_config.NumericProfileConfig attribute) skew_moderate (dataforge_ml.profiling._numeric_config.NumericProfileConfig attribute) skew_normal (dataforge_ml.profiling._numeric_config.NumericProfileConfig attribute)

sklearn_version (dataforge_ml.evaluation.imputation._records.C2STProvenance attribute) spearman_pearson_discrepancy_threshold (dataforge_ml.profiling._numeric_config.NonlinearityProfileConfig attribute) split (dataforge_ml.config.PipelineConfig attribute) Split (dataforge_ml.evaluation._c2st.C2STScheme attribute) SplitConfig (class in dataforge_ml.splitting._config) SplitResult (class in dataforge_ml.splitting._config) stage (dataforge_ml.observability.PipelineEvent attribute) stage_end (dataforge_ml.observability.EventType attribute) stage_start (dataforge_ml.observability.EventType attribute) stats (dataforge_ml.profiling._config.ColumnProfile attribute) stderr_observer() (in module dataforge_ml.observability) strategy (dataforge_ml.imputation._authoring.AuthoredColumn attribute) (dataforge_ml.imputation._config.ColumnImputationDecision attribute) (dataforge_ml.imputation._config.ImputationUnit attribute) (dataforge_ml.imputation._fit_signals.FitSignals attribute) (dataforge_ml.imputation._unit_fit.UnitFitResult attribute) (dataforge_ml.imputation._unit_fit.UnitNotTrainableError attribute) stratification_rare_threshold_pct (dataforge_ml.profiling._categorical_config.CategoricalProfileConfig attribute) string_sentinels (dataforge_ml.imputation._config.ImputationDecision attribute) (dataforge_ml.imputation._fitted_imputer.FittedImputer attribute) (dataforge_ml.profiling._config.ProfileConfig property) (dataforge_ml.profiling._config.StructuralProfileResult attribute) StructuralProfiler (class in dataforge_ml.profiling.orchestrator) StructuralProfileResult (class in dataforge_ml.profiling._config) substep (dataforge_ml.observability.EventType attribute)

T

Tabular (dataforge_ml.config.Modality attribute) tail_asymmetry_left_share_threshold (dataforge_ml.profiling._numeric_config.NumericProfileConfig attribute) tail_asymmetry_right_share_threshold (dataforge_ml.profiling._numeric_config.NumericProfileConfig attribute) target_columns (dataforge_ml.imputation._fitted_imputer.FittedUnit property) (dataforge_ml.profiling._config.ProfileConfig attribute) target_correlations (dataforge_ml.profiling._config.DatasetStats attribute) targets (dataforge_ml.profiling._config.StructuralProfileResult attribute) test (dataforge_ml.splitting._config.HoldoutCVResult attribute) (dataforge_ml.splitting._config.SplitResult attribute) test_accuracy (dataforge_ml.evaluation._c2st.C2STResult attribute) test_ratio (dataforge_ml.splitting._config.SplitResult attribute) test_size (dataforge_ml.splitting._config.SplitResult attribute) Tested (dataforge_ml.evaluation.imputation._records.C2STOutcome attribute) Text (dataforge_ml.config.SemanticType attribute) time_split() (dataforge_ml.splitting._splitter.DataSplitter method) to_dict() (dataforge_ml.config.PipelineConfig method) (dataforge_ml.evaluation._config.C2STConfig method) (dataforge_ml.evaluation._config.EvaluationConfig method) (dataforge_ml.imputation._config.ColumnImputationDecision method) (dataforge_ml.imputation._config.ColumnImputationRecord method) (dataforge_ml.imputation._config.ImputationConfig method) (dataforge_ml.imputation._config.ImputationDecision method) (dataforge_ml.imputation._config.ImputationUnit method) (dataforge_ml.imputation._config.NumericImputationConfig method) (dataforge_ml.profiling._categorical_config.CategoricalProfileConfig method) (dataforge_ml.profiling._config.ColumnProfile method) (dataforge_ml.profiling._config.DatasetStats method) (dataforge_ml.profiling._config.ProfileConfig method) (dataforge_ml.profiling._config.StructuralProfileResult method) (dataforge_ml.profiling._correlation_config.CorrelationProfileConfig method) (dataforge_ml.profiling._datetime_config.DatetimeProfileConfig method) (dataforge_ml.profiling._missingness_config.MissingnessProfileConfig method) (dataforge_ml.profiling._numeric_config.NonlinearityProfileConfig method) (dataforge_ml.profiling._numeric_config.NumericProfileConfig method) (dataforge_ml.profiling._type_detection_config.TypeDetectionConfig method) (dataforge_ml.splitting._config.SplitConfig method)

to_json() (dataforge_ml.config.PipelineConfig method) (dataforge_ml.profiling._config.ProfileConfig method) (dataforge_ml.profiling._config.StructuralProfileResult method) to_markdown() (dataforge_ml.evaluation._c2st.C2STResult method) (dataforge_ml.evaluation.imputation._records.C2STProvenance method) (dataforge_ml.evaluation.imputation._records.C2STReport method) (dataforge_ml.evaluation.imputation._records.C2STScore method) (dataforge_ml.evaluation.imputation._records.ColumnC2STResult method) (dataforge_ml.evaluation.imputation._records.EvaluationReport method) (dataforge_ml.imputation._config.ColumnImputationDecision method) (dataforge_ml.imputation._config.ColumnImputationRecord method) (dataforge_ml.imputation._config.ImputationDecision method) (dataforge_ml.imputation._config.ImputationResult method) (dataforge_ml.imputation._config.ImputationUnit method) (dataforge_ml.profiling._config.StructuralProfileResult method) total (dataforge_ml.observability.PipelineEvent attribute) train (dataforge_ml.splitting._config.FoldResult attribute) (dataforge_ml.splitting._config.SplitResult attribute) train_accuracy (dataforge_ml.evaluation._c2st.C2STResult attribute) train_ratio (dataforge_ml.splitting._config.SplitResult attribute) train_size (dataforge_ml.splitting._config.FoldResult attribute) (dataforge_ml.splitting._config.SplitResult attribute) transform() (dataforge_ml.imputation._fitted_imputer.FittedImputer method) (dataforge_ml.imputation._fitted_imputer.FittedUnit method) type_detection (dataforge_ml.profiling._config.ProfileConfig attribute) type_flags (dataforge_ml.profiling._config.ColumnProfile attribute) TypeDetectionConfig (class in dataforge_ml.profiling._type_detection_config) TypeNotTestable (dataforge_ml.evaluation.imputation._records.C2STOutcome attribute)

U

Uninformative (dataforge_ml.evaluation.imputation._records.C2STOutcome attribute) unit_id (dataforge_ml.imputation._config.ImputationUnit attribute) (dataforge_ml.imputation._fit_signals.FitSignals attribute) (dataforge_ml.imputation._unit_fit.UnitFitResult attribute) (dataforge_ml.imputation._unit_fit.UnitNotTrainableError attribute) UnitFitResult (class in dataforge_ml.imputation._unit_fit) UnitNotTrainableError (class in dataforge_ml.imputation._unit_fit)

units (dataforge_ml.imputation._config.ImputationDecision attribute) (dataforge_ml.imputation._fitted_imputer.FittedImputer attribute) units_for() (dataforge_ml.imputation._config.ImputationDecision method) unseen_category (dataforge_ml.evaluation._c2st.C2STResult attribute) UnseenCategory (dataforge_ml.evaluation.imputation._records.C2STAnnotation attribute) UnseenColumnError (class in dataforge_ml.imputation._fitted_imputer) UnsupportedFormatError (class in dataforge_ml.utils.data_loader)

V

val (dataforge_ml.splitting._config.FoldResult attribute) val_size (dataforge_ml.splitting._config.FoldResult attribute)

validate() (dataforge_ml.imputation._config.ImputationConfig method) verdict (dataforge_ml.evaluation.imputation._records.ColumnC2STResult attribute)

W

warning (dataforge_ml.observability.EventType attribute) warnings (dataforge_ml.imputation._fit_signals.FitSignals attribute)

was_chunked (dataforge_ml.profiling._config.DatasetStats attribute) with_hyperparameters() (dataforge_ml.imputation._config.ImputationDecision method) with_model_choice() (dataforge_ml.imputation._config.ImputationDecision method)