regression        fit                importance_gain             keys feat_a: 224.34941560751759 -> 224.34939003142063, feat_b: 96.55650697741657 -> 96.5564900720492
regression        tune_fit           importance_gain             keys feat_a: 24083.933611996472 -> 24083.932853527367, feat_b: 338.41716367407935 -> 338.41718875296647
regression        tune_fit           tuning_table                frame shape (1, 14) -> (0, 0)
regression        tune_fit           params_table                rows validation_ratio: [0.45] -> [0.2]
regression        tune_fit           export_code                 keys validation_ratio: 0.45 -> 0.2
regression        tune_fit           tuning_plot                 value differs
regression        fit_tune           importance_gain             keys feat_a: 224.34941560751759 -> 224.34939003142063, feat_b: 96.55650697741657 -> 96.5564900720492
regression        fit_tune           tuning_table                frame shape (1, 14) -> (0, 0)
regression        fit_tune           tuning_plot                 value differs
regression        tune_fit_reexport  importance_gain             keys feat_a: 24083.933611996472 -> 24083.932853527367, feat_b: 338.41716367407935 -> 338.41718875296647
regression        tune_fit_reexport  tuning_table                frame shape (1, 14) -> (0, 0)
regression        tune_fit_reexport  params_table                rows validation_ratio: [0.45] -> [0.2]
regression        tune_fit_reexport  export_code                 keys validation_ratio: 0.45 -> 0.2
regression        tune_fit_reexport  tuning_plot                 value differs
regression        tune_resume_fit    importance_gain             keys feat_a: 24083.933611996472 -> 24083.932853527367, feat_b: 338.41716367407935 -> 338.41718875296647
regression        tune_resume_fit    tuning_table                frame shape (2, 14) -> (0, 0)
regression        tune_resume_fit    boundary_table              ok: -> raises:MODEL_NOT_FIT
regression        tune_resume_fit    params_table                rows validation_ratio: [0.45] -> [0.2]
regression        tune_resume_fit    export_code                 keys validation_ratio: 0.45 -> 0.2
regression        tune_resume_fit    tuning_plot                 value differs
binary            fit                importance_gain             keys feat_a: 177.38489106834788 -> 177.3849063271635, feat_b: 129.74501836299896 -> 129.74501839280128
binary            tune_fit           importance_gain             keys feat_a: 41.000022888183594 -> 41.00004959106445
binary            tune_fit           tuning_table                frame shape (1, 14) -> (0, 0)
binary            tune_fit           params_table                rows validation_ratio: [0.45] -> [0.2]
binary            tune_fit           export_code                 keys validation_ratio: 0.45 -> 0.2
binary            tune_fit           tuning_plot                 value differs
binary            fit_tune           importance_gain             keys feat_a: 177.38489106834788 -> 177.3849063271635, feat_b: 129.74501836299896 -> 129.74501839280128
binary            fit_tune           tuning_table                frame shape (1, 14) -> (0, 0)
binary            fit_tune           tuning_plot                 value differs
binary            tune_fit_reexport  importance_gain             keys feat_a: 41.000022888183594 -> 41.00004959106445
binary            tune_fit_reexport  tuning_table                frame shape (1, 14) -> (0, 0)
binary            tune_fit_reexport  params_table                rows validation_ratio: [0.45] -> [0.2]
binary            tune_fit_reexport  export_code                 keys validation_ratio: 0.45 -> 0.2
binary            tune_fit_reexport  tuning_plot                 value differs
binary            tune_resume_fit    importance_gain             keys feat_a: 41.000022888183594 -> 41.00004959106445
binary            tune_resume_fit    tuning_table                frame shape (2, 14) -> (0, 0)
binary            tune_resume_fit    boundary_table              ok: -> raises:MODEL_NOT_FIT
binary            tune_resume_fit    params_table                rows validation_ratio: [0.45] -> [0.2]
binary            tune_resume_fit    export_code                 keys validation_ratio: 0.45 -> 0.2
binary            tune_resume_fit    tuning_plot                 value differs
binary_calibrated fit                importance_gain             keys feat_a: 177.38489106834788 -> 177.3849063271635, feat_b: 129.74501836299896 -> 129.74501839280128
binary_calibrated tune_fit           importance_gain             keys feat_a: 41.000022888183594 -> 41.00004959106445
binary_calibrated tune_fit           tuning_table                frame shape (1, 14) -> (0, 0)
binary_calibrated tune_fit           params_table                rows validation_ratio: [0.45] -> [0.2]
binary_calibrated tune_fit           export_code                 keys validation_ratio: 0.45 -> 0.2
binary_calibrated tune_fit           tuning_plot                 value differs
binary_calibrated fit_tune           importance_gain             keys feat_a: 177.38489106834788 -> 177.3849063271635, feat_b: 129.74501836299896 -> 129.74501839280128
binary_calibrated fit_tune           tuning_table                frame shape (1, 14) -> (0, 0)
binary_calibrated fit_tune           tuning_plot                 value differs
binary_calibrated tune_fit_reexport  importance_gain             keys feat_a: 41.000022888183594 -> 41.00004959106445
binary_calibrated tune_fit_reexport  tuning_table                frame shape (1, 14) -> (0, 0)
binary_calibrated tune_fit_reexport  params_table                rows validation_ratio: [0.45] -> [0.2]
binary_calibrated tune_fit_reexport  export_code                 keys validation_ratio: 0.45 -> 0.2
binary_calibrated tune_fit_reexport  tuning_plot                 value differs
binary_calibrated tune_resume_fit    importance_gain             keys feat_a: 41.000022888183594 -> 41.00004959106445
binary_calibrated tune_resume_fit    tuning_table                frame shape (2, 14) -> (0, 0)
binary_calibrated tune_resume_fit    boundary_table              ok: -> raises:MODEL_NOT_FIT
binary_calibrated tune_resume_fit    params_table                rows validation_ratio: [0.45] -> [0.2]
binary_calibrated tune_resume_fit    export_code                 keys validation_ratio: 0.45 -> 0.2
binary_calibrated tune_resume_fit    tuning_plot                 value differs
multiclass        fit                importance_gain             keys feat_a: 120.95295190811157 -> 120.95300006866455, feat_b: 59.539635576307774 -> 59.539634205400944
multiclass        tune_fit           importance_gain             keys feat_a: 126.5014181137085 -> 126.50149869918823
multiclass        tune_fit           tuning_table                frame shape (1, 14) -> (0, 0)
multiclass        tune_fit           params_table                rows validation_ratio: [0.45] -> [0.2]
multiclass        tune_fit           export_code                 keys validation_ratio: 0.45 -> 0.2
multiclass        tune_fit           tuning_plot                 value differs
multiclass        fit_tune           importance_gain             keys feat_a: 120.95295190811157 -> 120.95300006866455, feat_b: 59.539635576307774 -> 59.539634205400944
multiclass        fit_tune           tuning_table                frame shape (1, 14) -> (0, 0)
multiclass        fit_tune           tuning_plot                 value differs
multiclass        tune_fit_reexport  importance_gain             keys feat_a: 126.5014181137085 -> 126.50149869918823
multiclass        tune_fit_reexport  tuning_table                frame shape (1, 14) -> (0, 0)
multiclass        tune_fit_reexport  params_table                rows validation_ratio: [0.45] -> [0.2]
multiclass        tune_fit_reexport  export_code                 keys validation_ratio: 0.45 -> 0.2
multiclass        tune_fit_reexport  tuning_plot                 value differs
multiclass        tune_resume_fit    importance_gain             keys feat_a: 126.5014181137085 -> 126.50149869918823
multiclass        tune_resume_fit    tuning_table                frame shape (2, 14) -> (0, 0)
multiclass        tune_resume_fit    boundary_table              ok: -> raises:MODEL_NOT_FIT
multiclass        tune_resume_fit    params_table                rows validation_ratio: [0.45] -> [0.2]
multiclass        tune_resume_fit    export_code                 keys validation_ratio: 0.45 -> 0.2
multiclass        tune_resume_fit    tuning_plot                 value differs

cells: 440 (4 configurations x 5 lifecycles x 22 surfaces); differing: 80
  boundary_table: 4
  export_code: 12
  importance_gain: 20
  params_table: 12
  tuning_plot: 16
  tuning_table: 16
largest relative importance_gain error: 6.513e-07 (declared bound 5.1e-06)
cells where the fitted model returned a reading (exercised):
  evaluate: 20
  evaluate_table: 20
  fit_result: 20
  predict: 20
  residuals: 5
  confusion_matrix: 15
  importance_split: 20
  importance_gain: 20
  importance_shap: 20
  tuning_table: 16
  boundary_table: 4
  params_table: 20
  split_summary: 20
  export_code: 20
  residuals_plot: 5
  roc_curve_plot: 15
  calibration_plot: 5
  probability_histogram_plot: 5
  importance_plot: 20
  plot_learning_curve: 20
  plot_oof_distribution: 20
  tuning_plot: 16
