From f13ed30f42440552e4a912372abcb7c3023fc9c0 Mon Sep 17 00:00:00 2001 From: Chris Trevino Date: Fri, 28 Oct 2022 15:46:08 -0700 Subject: [PATCH] Restore some key tests into the regular CI pipeline (#725) * restore some key notebook tests Signed-off-by: Chris Trevino * remove advanced marks from unit tests Signed-off-by: Chris Trevino * remove advanced mark from test_validation.py Signed-off-by: Chris Trevino * apply formatting Signed-off-by: Chris Trevino * update test durations, restore some test notebooks Signed-off-by: Chris Trevino * bump the test splits Signed-off-by: Chris Trevino * restore main notebook tests, take a more piecemeal approach Signed-off-by: Chris Trevino Signed-off-by: Chris Trevino --- .github/workflows/ci.yml | 4 +- .test_durations | 744 ++++++++++-------- .../test_data_subset_refuter.py | 2 - tests/gcm/test_anomaly_attribution.py | 3 +- tests/gcm/test_feature.py | 3 +- tests/gcm/test_intrinsic_influence.py | 6 +- tests/gcm/test_stats.py | 3 +- tests/gcm/test_validation.py | 3 - tests/test_notebooks.py | 3 +- 9 files changed, 411 insertions(+), 360 deletions(-) diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index 038589543..380627783 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -15,7 +15,7 @@ jobs: matrix: python-version: [3.8, 3.9] poetry-version: [1.2.0] - test-group: [1, 2, 3, 4] + test-group: [1, 2, 3, 4, 5, 6] steps: - uses: actions/checkout@v2 @@ -47,7 +47,7 @@ jobs: run: poetry run poe format_check - name: Test - run: poetry run poe test --splits 4 --group ${{ matrix.test-group }} + run: poetry run poe test --splits 6 --group ${{ matrix.test-group }} - uses: fateyan/action-discord-notifier@v1 if: failure() && github.ref == 'refs/heads/main' diff --git a/.test_durations b/.test_durations index 7ea3a390e..f202bd6c7 100644 --- a/.test_durations +++ b/.test_durations @@ -1,240 +1,287 @@ { - "tests/causal_estimators/test_causalml_estimator.py::TestCausalmlEstimator::test_causalml_LRSRegressor": 1.8709904220013414, - "tests/causal_estimators/test_causalml_estimator.py::TestCausalmlEstimator::test_causalml_MLPTRegressor": 0.3396745189966168, - "tests/causal_estimators/test_causalml_estimator.py::TestCausalmlEstimator::test_causalml_RLearner": 2.3262762230042426, - "tests/causal_estimators/test_causalml_estimator.py::TestCausalmlEstimator::test_causalml_XGBTRegressor": 0.473878592998517, - "tests/causal_estimators/test_causalml_estimator.py::TestCausalmlEstimator::test_causalml_XLearner": 0.9274584140002844, - "tests/causal_estimators/test_econml_estimator.py::TestEconMLEstimator::test_backdoor_estimators": 28.61218002500027, - "tests/causal_estimators/test_econml_estimator.py::TestEconMLEstimator::test_iv_estimators": 31.404631056000653, - "tests/causal_estimators/test_generalized_linear_model_estimator.py::TestGeneralizedLinearModelEstimator::test_average_treatment_effect[0.1-GeneralizedLinearModelEstimator-num_common_causes0-num_instruments0-num_effect_modifiers0-num_treatments0-treatment_is_binary0-outcome_is_binary0-backdoor]": 8.239595178001764, - "tests/causal_estimators/test_instrumental_variable_estimator.py::TestInstrumentalVariableEstimator::test_average_treatment_effect[0.4-InstrumentalVariableEstimator-num_common_causes0-num_instruments0-num_effect_modifiers0-num_treatments0-treatment_is_binary0-outcome_is_binary0-iv]": 19.130412003003585, - "tests/causal_estimators/test_linear_regression_estimator.py::TestLinearRegressionEstimator::test_average_treatment_effect[0.1-LinearRegressionEstimator-num_common_causes0-num_instruments0-num_effect_modifiers0-num_treatments0-treatment_is_binary0-treatment_is_category0-outcome_is_binary0]": 26.658716234000167, - "tests/causal_estimators/test_linear_regression_estimator.py::TestLinearRegressionEstimator::test_average_treatment_effect[0.1-LinearRegressionEstimator-num_common_causes1-num_instruments1-num_effect_modifiers1-num_treatments1-treatment_is_binary1-treatment_is_category1-outcome_is_binary1]": 31.03801075100273, - "tests/causal_estimators/test_linear_regression_estimator.py::TestLinearRegressionEstimator::test_average_treatment_effect[0.1-LinearRegressionEstimator-num_common_causes2-num_instruments2-num_effect_modifiers2-num_treatments2-treatment_is_binary2-treatment_is_category2-outcome_is_binary2]": 9.276061235999805, - "tests/causal_estimators/test_propensity_score_matching_estimator.py::TestPropensityScoreMatchingEstimator::test_average_treatment_effect[0.3-PropensityScoreMatchingEstimator-num_common_causes0-num_instruments0-num_effect_modifiers0-num_treatments0-treatment_is_binary0-outcome_is_binary0]": 31.91888126900085, - "tests/causal_estimators/test_propensity_score_stratification_estimator.py::TestPropensityScoreStratificationEstimator::test_average_treatment_effect[0.1-PropensityScoreStratificationEstimator-num_common_causes0-num_instruments0-num_effect_modifiers0-num_treatments0-treatment_is_binary0-outcome_is_binary0]": 138.48159910100003, - "tests/causal_estimators/test_propensity_score_weighting_estimator.py::TestPropensityScoreWeightingEstimator::test_average_treatment_effect[0.4-PropensityScoreWeightingEstimator-num_common_causes0-num_instruments0-num_effect_modifiers0-num_treatments0-treatment_is_binary0-outcome_is_binary0]": 4.26221863000319, - "tests/causal_estimators/test_regression_discontinuity_estimator.py::TestRegressionDiscontinuityEstimator::test_average_treatment_effect[0.2-RegressionDiscontinuityEstimator-num_common_causes0-num_instruments0-num_effect_modifiers0-num_treatments0-treatment_is_binary0-outcome_is_binary0-iv]": 1.4388477979991876, - "tests/causal_estimators/test_two_stage_regression_estimator.py::TestTwoStageRegressionEstimator::test_average_treatment_effect[0.1-TwoStageRegressionEstimator-num_common_causes0-num_instruments0-num_effect_modifiers0-num_treatments0-num_frontdoor_variables0-treatment_is_binary0-outcome_is_binary0]": 0.9643940740024846, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[book_of_why_game2]": 0.0014306690027297009, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[book_of_why_game5]": 0.0012191680034447927, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[book_of_why_game5_C_is_unobserved]": 0.0009748299999046139, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[common_cause_of_mediator1]": 0.0008750499982852489, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[common_cause_of_mediator2]": 0.0008238410009653307, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[iv]": 0.0008677469995745923, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[mbias_with_unobserved]": 0.001158308001322439, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[no_treatment_but_valid_maximal_set]": 0.0009303000006184448, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[pearl_backdoor_example_graph]": 0.0015849739975237753, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[pearl_simpsons_machine_lvl1]": 0.0014502840022032615, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[pearl_simpsons_paradox_1c]": 0.0008510210027452558, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[pearl_simpsons_paradox_1d]": 0.0007988319957803469, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[pearl_simpsons_paradox_2a]": 0.0007327519961108919, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[pearl_simpsons_paradox_2b]": 0.0008152410009643063, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[pearl_simpsons_paradox_2b_L_observed]": 0.0009078209986910224, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[simple_no_confounder_graph]": 0.0008009720004338305, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[simple_selection_bias_graph]": 0.0006262339993554633, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[book_of_why_game2]": 0.0007835610049369279, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[book_of_why_game5]": 0.0013942850018793251, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[book_of_why_game5_C_is_unobserved]": 0.0010989290021825582, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[common_cause_of_mediator1]": 0.0012708910035144072, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[common_cause_of_mediator2]": 0.0008613020036136732, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[iv]": 0.0007903810001153033, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[mbias_with_unobserved]": 0.0007522919986513443, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[no_treatment_but_valid_maximal_set]": 0.0006968919988139533, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[pearl_backdoor_example_graph]": 0.0027513909990375396, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[pearl_simpsons_machine_lvl1]": 0.0007191530021373183, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[pearl_simpsons_paradox_1c]": 0.000729311999748461, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[pearl_simpsons_paradox_1d]": 0.0008954100012488198, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[pearl_simpsons_paradox_2a]": 0.0006999129946052562, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[pearl_simpsons_paradox_2b]": 0.0008020609966479242, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[pearl_simpsons_paradox_2b_L_observed]": 0.0010208290004811715, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[simple_no_confounder_graph]": 0.0006257239947444759, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[simple_selection_bias_graph]": 0.0007188820018200204, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[book_of_why_game2]": 0.0038469469982373994, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[book_of_why_game5]": 0.0031662459987273905, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[book_of_why_game5_C_is_unobserved]": 0.00308589699852746, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[common_cause_of_mediator1]": 0.0011341090030327905, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[common_cause_of_mediator2]": 0.003449792999163037, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[iv]": 0.0015098440017027315, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[mbias_with_unobserved]": 0.001752481002768036, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[no_treatment_but_valid_maximal_set]": 0.0012205960010760464, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[pearl_backdoor_example_graph]": 0.011672910997731378, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[pearl_simpsons_machine_lvl1]": 0.002395045001321705, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[pearl_simpsons_paradox_1c]": 0.0011582170009205583, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[pearl_simpsons_paradox_1d]": 0.001117357998737134, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[pearl_simpsons_paradox_2a]": 0.000866992002556799, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[pearl_simpsons_paradox_2b]": 0.0010696089993871283, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[pearl_simpsons_paradox_2b_L_observed]": 0.0013814560006721877, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[simple_no_confounder_graph]": 0.0010535480032558553, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[simple_selection_bias_graph]": 0.001052767998771742, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[book_of_why_game2]": 0.0026418130000820383, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[book_of_why_game5]": 0.0016909120022319257, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[book_of_why_game5_C_is_unobserved]": 0.0011231769967707805, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[common_cause_of_mediator1]": 0.0008846720011206344, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[common_cause_of_mediator2]": 0.0008662520012876485, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[iv]": 0.00082448000102886, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[mbias_with_unobserved]": 0.0014589849997719284, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[no_treatment_but_valid_maximal_set]": 0.0008935509977163747, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[pearl_backdoor_example_graph]": 0.004645663000701461, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[pearl_simpsons_machine_lvl1]": 0.0015170339975156821, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[pearl_simpsons_paradox_1c]": 0.0009246910012734588, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[pearl_simpsons_paradox_1d]": 0.0008557020009902772, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[pearl_simpsons_paradox_2a]": 0.0006576430023415014, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[pearl_simpsons_paradox_2b]": 0.0007975809967319947, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[pearl_simpsons_paradox_2b_L_observed]": 0.0010628490017552394, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[simple_no_confounder_graph]": 0.0007228830036183354, - "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[simple_selection_bias_graph]": 0.0006180359996506013, - "tests/causal_identifiers/test_efficient_backdoor_identifier.py::test_fail_multivar_outcome_efficient_backdoor_algorithms": 0.0007458220025000628, - "tests/causal_identifiers/test_efficient_backdoor_identifier.py::test_fail_multivar_treat_efficient_backdoor_algorithms": 0.0007435719962813891, - "tests/causal_identifiers/test_efficient_backdoor_identifier.py::test_fail_negative_costs_efficient_backdoor_algorithms": 0.0009358400056953542, - "tests/causal_identifiers/test_efficient_backdoor_identifier.py::test_fail_unobserved_cond_vars_efficient_backdoor_algorithms": 0.0007732110025244765, - "tests/causal_identifiers/test_efficient_backdoor_identifier.py::test_identify_efficient_backdoor_algorithms": 0.6694562520024192, - "tests/causal_identifiers/test_id_identifier.py::TestIDIdentifier::test_1": 0.0017407909981557168, - "tests/causal_identifiers/test_id_identifier.py::TestIDIdentifier::test_2": 0.001019930001348257, - "tests/causal_identifiers/test_id_identifier.py::TestIDIdentifier::test_3": 0.0014090740005485713, - "tests/causal_identifiers/test_id_identifier.py::TestIDIdentifier::test_4": 0.0013240250009403098, - "tests/causal_identifiers/test_id_identifier.py::TestIDIdentifier::test_5": 0.0013728450030612294, - "tests/causal_identifiers/test_id_identifier.py::TestIDIdentifier::test_6": 0.0011200879998796154, - "tests/causal_identifiers/test_optimize_backdoor.py::TestOptimizeBackdoorIdentifier::test_1": 0.001310937001107959, - "tests/causal_identifiers/test_optimize_backdoor.py::TestOptimizeBackdoorIdentifier::test_2": 0.001268016996618826, - "tests/causal_identifiers/test_optimize_backdoor.py::TestOptimizeBackdoorIdentifier::test_3": 0.0015109139967535157, - "tests/causal_identifiers/test_optimize_backdoor.py::TestOptimizeBackdoorIdentifier::test_4": 0.0012465669969969895, - "tests/causal_identifiers/test_optimize_backdoor.py::TestOptimizeBackdoorIdentifier::test_5": 0.00135361599677708, - "tests/causal_identifiers/test_optimize_backdoor.py::TestOptimizeBackdoorIdentifier::test_6": 0.0013527060000342317, + "tests/causal_estimators/test_causalml_estimator.py::TestCausalmlEstimator::test_causalml_LRSRegressor": 0.3759101269988605, + "tests/causal_estimators/test_causalml_estimator.py::TestCausalmlEstimator::test_causalml_MLPTRegressor": 0.39586411700292956, + "tests/causal_estimators/test_causalml_estimator.py::TestCausalmlEstimator::test_causalml_RLearner": 3.5449028330003785, + "tests/causal_estimators/test_causalml_estimator.py::TestCausalmlEstimator::test_causalml_XGBTRegressor": 16.717251526999462, + "tests/causal_estimators/test_causalml_estimator.py::TestCausalmlEstimator::test_causalml_XLearner": 6.498728092999954, + "tests/causal_estimators/test_econml_estimator.py::TestEconMLEstimator::test_backdoor_estimators": 34.96089299800042, + "tests/causal_estimators/test_econml_estimator.py::TestEconMLEstimator::test_iv_estimators": 34.40518009199877, + "tests/causal_estimators/test_generalized_linear_model_estimator.py::TestGeneralizedLinearModelEstimator::test_average_treatment_effect[0.1-GeneralizedLinearModelEstimator-num_common_causes0-num_instruments0-num_effect_modifiers0-num_treatments0-treatment_is_binary0-outcome_is_binary0-backdoor]": 7.966845259001275, + "tests/causal_estimators/test_instrumental_variable_estimator.py::TestInstrumentalVariableEstimator::test_average_treatment_effect[0.4-InstrumentalVariableEstimator-num_common_causes0-num_instruments0-num_effect_modifiers0-num_treatments0-treatment_is_binary0-outcome_is_binary0-iv]": 19.22158048899837, + "tests/causal_estimators/test_linear_regression_estimator.py::TestLinearRegressionEstimator::test_average_treatment_effect[0.1-LinearRegressionEstimator-num_common_causes0-num_instruments0-num_effect_modifiers0-num_treatments0-treatment_is_binary0-treatment_is_category0-outcome_is_binary0]": 29.023863354997957, + "tests/causal_estimators/test_linear_regression_estimator.py::TestLinearRegressionEstimator::test_average_treatment_effect[0.1-LinearRegressionEstimator-num_common_causes1-num_instruments1-num_effect_modifiers1-num_treatments1-treatment_is_binary1-treatment_is_category1-outcome_is_binary1]": 31.650325972997962, + "tests/causal_estimators/test_linear_regression_estimator.py::TestLinearRegressionEstimator::test_average_treatment_effect[0.1-LinearRegressionEstimator-num_common_causes2-num_instruments2-num_effect_modifiers2-num_treatments2-treatment_is_binary2-treatment_is_category2-outcome_is_binary2]": 10.845288793998407, + "tests/causal_estimators/test_propensity_score_matching_estimator.py::TestPropensityScoreMatchingEstimator::test_average_treatment_effect[0.3-PropensityScoreMatchingEstimator-num_common_causes0-num_instruments0-num_effect_modifiers0-num_treatments0-treatment_is_binary0-outcome_is_binary0]": 30.789178972998343, + "tests/causal_estimators/test_propensity_score_stratification_estimator.py::TestPropensityScoreStratificationEstimator::test_average_treatment_effect[0.1-PropensityScoreStratificationEstimator-num_common_causes0-num_instruments0-num_effect_modifiers0-num_treatments0-treatment_is_binary0-outcome_is_binary0]": 160.28022117399996, + "tests/causal_estimators/test_propensity_score_weighting_estimator.py::TestPropensityScoreWeightingEstimator::test_average_treatment_effect[0.4-PropensityScoreWeightingEstimator-num_common_causes0-num_instruments0-num_effect_modifiers0-num_treatments0-treatment_is_binary0-outcome_is_binary0]": 4.023867720999988, + "tests/causal_estimators/test_regression_discontinuity_estimator.py::TestRegressionDiscontinuityEstimator::test_average_treatment_effect[0.2-RegressionDiscontinuityEstimator-num_common_causes0-num_instruments0-num_effect_modifiers0-num_treatments0-treatment_is_binary0-outcome_is_binary0-iv]": 1.5116642730008607, + "tests/causal_estimators/test_two_stage_regression_estimator.py::TestTwoStageRegressionEstimator::test_average_treatment_effect[0.1-TwoStageRegressionEstimator-num_common_causes0-num_instruments0-num_effect_modifiers0-num_treatments0-num_frontdoor_variables0-treatment_is_binary0-outcome_is_binary0]": 1.1414662810002483, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[book_of_why_game2]": 0.0018126160011888715, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[book_of_why_game5]": 0.0017006359994411469, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[book_of_why_game5_C_is_unobserved]": 0.001571333999891067, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[common_cause_of_mediator1]": 0.0010482779998710612, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[common_cause_of_mediator2]": 0.0012751069989462849, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[iv]": 0.0009463570004299982, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[mbias_with_unobserved]": 0.0017421259999537142, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[mediator-with-conf]": 0.0016782349994173273, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[mediator]": 0.0009926780003297608, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[no_treatment_but_valid_maximal_set]": 0.001140028000008897, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[pearl_backdoor_example_graph]": 0.0017095849980250932, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[pearl_simpsons_machine_lvl1]": 0.0017166450015793089, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[pearl_simpsons_paradox_1c]": 0.001360526001008111, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[pearl_simpsons_paradox_1d]": 0.0009135779982898384, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[pearl_simpsons_paradox_2a]": 0.001015068000924657, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[pearl_simpsons_paradox_2b]": 0.0014208780030458001, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[pearl_simpsons_paradox_2b_L_observed]": 0.001367434999338002, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[simple_no_confounder_graph]": 0.0008193280009436421, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_adjustment[simple_selection_bias_graph]": 0.0006739690015820088, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_direct_effect[book_of_why_game2]": 0.00189562599916826, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_direct_effect[book_of_why_game5]": 0.0019867740011250135, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_direct_effect[book_of_why_game5_C_is_unobserved]": 0.0011870069993165089, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_direct_effect[common_cause_of_mediator1]": 0.001332175001152791, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_direct_effect[common_cause_of_mediator2]": 0.0015398049999930663, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_direct_effect[iv]": 0.001466906001951429, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_direct_effect[mbias_with_unobserved]": 0.0013741579987254227, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_direct_effect[mediator-with-conf]": 0.001223986999320914, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_direct_effect[mediator]": 0.0011637180014076876, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_direct_effect[no_treatment_but_valid_maximal_set]": 0.001180844999908004, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_direct_effect[pearl_backdoor_example_graph]": 0.0019885229994542897, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_direct_effect[pearl_simpsons_machine_lvl1]": 0.0016714459998183884, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_direct_effect[pearl_simpsons_paradox_1c]": 0.0012556760011648294, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_direct_effect[pearl_simpsons_paradox_1d]": 0.0010645379989000503, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_direct_effect[pearl_simpsons_paradox_2a]": 0.001484447000621003, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_direct_effect[pearl_simpsons_paradox_2b]": 0.0011713570002029883, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_direct_effect[pearl_simpsons_paradox_2b_L_observed]": 0.0010907880005106563, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_direct_effect[simple_no_confounder_graph]": 0.0009234479985025246, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_maximal_direct_effect[simple_selection_bias_graph]": 0.000886957999682636, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[book_of_why_game2]": 0.000806748001195956, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[book_of_why_game5]": 0.0011636770013865316, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[book_of_why_game5_C_is_unobserved]": 0.0012951469998370158, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[common_cause_of_mediator1]": 0.0011018169989256421, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[common_cause_of_mediator2]": 0.0011450869988038903, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[iv]": 0.000854836998769315, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[mbias_with_unobserved]": 0.0007795979981892742, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[mediator-with-conf]": 0.0011874659994646208, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[mediator]": 0.001107837002564338, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[no_treatment_but_valid_maximal_set]": 0.0006330279993562726, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[pearl_backdoor_example_graph]": 0.002885192001485848, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[pearl_simpsons_machine_lvl1]": 0.000785227000960731, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[pearl_simpsons_paradox_1c]": 0.0007251780007209163, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[pearl_simpsons_paradox_1d]": 0.0008188480005628662, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[pearl_simpsons_paradox_2a]": 0.0007698690023971722, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[pearl_simpsons_paradox_2b]": 0.000812217002021498, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[pearl_simpsons_paradox_2b_L_observed]": 0.0009112580009968951, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[simple_no_confounder_graph]": 0.0005759289997513406, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_minimal_adjustment[simple_selection_bias_graph]": 0.0006972580013098195, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[book_of_why_game2]": 0.012994315000469214, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[book_of_why_game5]": 0.002812681999785127, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[book_of_why_game5_C_is_unobserved]": 0.0026856629992835224, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[common_cause_of_mediator1]": 0.0015318550013034837, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[common_cause_of_mediator2]": 0.0014273050019255606, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[iv]": 0.0009888179993140511, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[mbias_with_unobserved]": 0.001702436000414309, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[mediator-with-conf]": 0.001329264998275903, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[mediator]": 0.0010871759986912366, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[no_treatment_but_valid_maximal_set]": 0.001577997001732001, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[pearl_backdoor_example_graph]": 0.006493291000879253, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[pearl_simpsons_machine_lvl1]": 0.002696543997444678, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[pearl_simpsons_paradox_1c]": 0.0012809950003429549, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[pearl_simpsons_paradox_1d]": 0.0014350460005516652, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[pearl_simpsons_paradox_2a]": 0.0010957560007227585, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[pearl_simpsons_paradox_2b]": 0.011523588000272866, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[pearl_simpsons_paradox_2b_L_observed]": 0.0022056550023989985, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[simple_no_confounder_graph]": 0.001455075998819666, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_no_biased_sets[simple_selection_bias_graph]": 0.0018298760023753857, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[book_of_why_game2]": 0.002340043998628971, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[book_of_why_game5]": 0.002466014000674477, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[book_of_why_game5_C_is_unobserved]": 0.001431676000720472, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[common_cause_of_mediator1]": 0.0009155080006166827, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[common_cause_of_mediator2]": 0.0009229280003637541, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[iv]": 0.000789707999501843, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[mbias_with_unobserved]": 0.0012646070008486276, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[mediator-with-conf]": 0.0012902469989057863, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[mediator]": 0.000820707999082515, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[no_treatment_but_valid_maximal_set]": 0.001187568001114414, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[pearl_backdoor_example_graph]": 0.004794317999767372, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[pearl_simpsons_machine_lvl1]": 0.001530625000668806, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[pearl_simpsons_paradox_1c]": 0.0008735680003155721, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[pearl_simpsons_paradox_1d]": 0.0008980869988590712, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[pearl_simpsons_paradox_2a]": 0.0006939380018593511, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[pearl_simpsons_paradox_2b]": 0.0008037369989324361, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[pearl_simpsons_paradox_2b_L_observed]": 0.0010643670011631912, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[simple_no_confounder_graph]": 0.0007463379988621455, + "tests/causal_identifiers/test_backdoor_identifier.py::TestBackdoorIdentification::test_identify_backdoor_unobserved_not_in_backdoor_set[simple_selection_bias_graph]": 0.0007493590019294061, + "tests/causal_identifiers/test_efficient_backdoor_identifier.py::test_fail_multivar_outcome_efficient_backdoor_algorithms": 0.0008672480016684858, + "tests/causal_identifiers/test_efficient_backdoor_identifier.py::test_fail_multivar_treat_efficient_backdoor_algorithms": 0.0008551280006940942, + "tests/causal_identifiers/test_efficient_backdoor_identifier.py::test_fail_negative_costs_efficient_backdoor_algorithms": 0.0010978469999827212, + "tests/causal_identifiers/test_efficient_backdoor_identifier.py::test_fail_unobserved_cond_vars_efficient_backdoor_algorithms": 0.0009948770002665697, + "tests/causal_identifiers/test_efficient_backdoor_identifier.py::test_identify_efficient_backdoor_algorithms": 0.6932751590011321, + "tests/causal_identifiers/test_id_identifier.py::TestIDIdentifier::test_1": 0.002907263000452076, + "tests/causal_identifiers/test_id_identifier.py::TestIDIdentifier::test_2": 0.001736685999276233, + "tests/causal_identifiers/test_id_identifier.py::TestIDIdentifier::test_3": 0.002051943001788459, + "tests/causal_identifiers/test_id_identifier.py::TestIDIdentifier::test_4": 0.00194300499970268, + "tests/causal_identifiers/test_id_identifier.py::TestIDIdentifier::test_5": 0.001570145002915524, + "tests/causal_identifiers/test_id_identifier.py::TestIDIdentifier::test_6": 0.0012518270032160217, + "tests/causal_identifiers/test_optimize_backdoor.py::TestOptimizeBackdoorIdentifier::test_1": 0.001383537000947399, + "tests/causal_identifiers/test_optimize_backdoor.py::TestOptimizeBackdoorIdentifier::test_2": 0.0012244170011399547, + "tests/causal_identifiers/test_optimize_backdoor.py::TestOptimizeBackdoorIdentifier::test_3": 0.0015989059993444243, + "tests/causal_identifiers/test_optimize_backdoor.py::TestOptimizeBackdoorIdentifier::test_4": 0.0012727270004688762, + "tests/causal_identifiers/test_optimize_backdoor.py::TestOptimizeBackdoorIdentifier::test_5": 0.00143652699807717, + "tests/causal_identifiers/test_optimize_backdoor.py::TestOptimizeBackdoorIdentifier::test_6": 0.00155684499986819, + "tests/causal_refuters/test_add_unobserved_common_cause.py::TestAddUnobservedCommonCauseRefuter::test_evalue": 0.038604204999501235, + "tests/causal_refuters/test_add_unobserved_common_cause.py::TestAddUnobservedCommonCauseRefuter::test_evalue_linear_regression[backdoor.linear_regression]": 0.08990149099918199, + "tests/causal_refuters/test_add_unobserved_common_cause.py::TestAddUnobservedCommonCauseRefuter::test_evalue_logistic_regression[backdoor.generalized_linear_model]": 0.20605873000022257, + "tests/causal_refuters/test_add_unobserved_common_cause.py::TestAddUnobservedCommonCauseRefuter::test_linear_sensitivity_dataset_without_confounders[backdoor.linear_regression-effect_fraction_on_treatment0-benchmark_common_causes0-linear-partial-R2-0.95]": 3.2043318770010956, "tests/causal_refuters/test_add_unobserved_common_cause.py::TestAddUnobservedCommonCauseRefuter::test_linear_sensitivity_dataset_without_confounders[backdoor.linear_regression-effect_strength_on_t0-benchmark_common_causes0-linear-partial-R2-0.95]": 2.850189850996685, + "tests/causal_refuters/test_add_unobserved_common_cause.py::TestAddUnobservedCommonCauseRefuter::test_linear_sensitivity_given_strength_of_confounding[backdoor.linear_regression-effect_fraction_on_treatment0-benchmark_common_causes0-linear-partial-R2]": 3.153957377999177, "tests/causal_refuters/test_add_unobserved_common_cause.py::TestAddUnobservedCommonCauseRefuter::test_linear_sensitivity_given_strength_of_confounding[backdoor.linear_regression-effect_strength_on_t0-benchmark_common_causes0-linear-partial-R2]": 2.7763720100010687, + "tests/causal_refuters/test_add_unobserved_common_cause.py::TestAddUnobservedCommonCauseRefuter::test_linear_sensitivity_with_confounders[backdoor.linear_regression-effect_fraction_on_treatment0-benchmark_common_causes0-linear-partial-R2]": 3.195294589002515, "tests/causal_refuters/test_add_unobserved_common_cause.py::TestAddUnobservedCommonCauseRefuter::test_linear_sensitivity_with_confounders[backdoor.linear_regression-effect_strength_on_t0-benchmark_common_causes0-linear-partial-R2]": 2.8144416110008024, - "tests/causal_refuters/test_add_unobserved_common_cause.py::TestAddUnobservedCommonCauseRefuter::test_refutation_binary_treatment[0.01-backdoor.propensity_score_matching-0.01-0.02]": 43.11950718300068, - "tests/causal_refuters/test_add_unobserved_common_cause.py::TestAddUnobservedCommonCauseRefuter::test_refutation_continuous_treatment[0.01-iv.instrumental_variable-0.01-0.02]": 0.0784161240044341, - "tests/causal_refuters/test_add_unobserved_common_cause.py::TestAddUnobservedCommonCauseRefuter::test_refutation_continuous_treatment_range_both_treatment_outcome[0.01-iv.instrumental_variable-effect_strength_on_t0-effect_strength_on_y0]": 1.1829802219981502, - "tests/causal_refuters/test_add_unobserved_common_cause.py::TestAddUnobservedCommonCauseRefuter::test_refutation_continuous_treatment_range_outcome[0.01-iv.instrumental_variable-0.01-effect_strength_on_y0]": 0.18137515900525614, - "tests/causal_refuters/test_add_unobserved_common_cause.py::TestAddUnobservedCommonCauseRefuter::test_refutation_continuous_treatment_range_treatment[0.01-iv.instrumental_variable-effect_strength_on_t0-0.02]": 0.17905196800347767, - "tests/causal_refuters/test_bootstrap_refuter.py::TestDataSubsetRefuter::test_refutation_bootstrap_refuter_binary[0.05-backdoor.propensity_score_matching-1000]": 0.8577377189976687, - "tests/causal_refuters/test_bootstrap_refuter.py::TestDataSubsetRefuter::test_refutation_bootstrap_refuter_binary_integer_argument[0.1-backdoor.propensity_score_matching-5-3-5000]": 4.554001046999474, - "tests/causal_refuters/test_bootstrap_refuter.py::TestDataSubsetRefuter::test_refutation_bootstrap_refuter_binary_list_argument[0.1-backdoor.propensity_score_matching-5-required_variables0-5000]": 4.412829904998944, - "tests/causal_refuters/test_bootstrap_refuter.py::TestDataSubsetRefuter::test_refutation_bootstrap_refuter_binary_list_negative_argument[0.1-backdoor.propensity_score_matching-5-required_variables0-5000]": 4.431730446001893, - "tests/causal_refuters/test_bootstrap_refuter.py::TestDataSubsetRefuter::test_refutation_bootstrap_refuter_continuous[0.05-iv.instrumental_variable-1000]": 0.3983250860037515, - "tests/causal_refuters/test_bootstrap_refuter.py::TestDataSubsetRefuter::test_refutation_bootstrap_refuter_continuous_integer_argument[0.05-iv.instrumental_variable-5-3-1000]": 0.3220115190015349, - "tests/causal_refuters/test_bootstrap_refuter.py::TestDataSubsetRefuter::test_refutation_bootstrap_refuter_continuous_list_argument[0.05-iv.instrumental_variable-5-required_variables0-1000]": 0.3215620599949034, - "tests/causal_refuters/test_bootstrap_refuter.py::TestDataSubsetRefuter::test_refutation_bootstrap_refuter_continuous_list_negative_argument[0.1-iv.instrumental_variable-5-required_variables0-5000]": 0.5046643770001538, - "tests/causal_refuters/test_data_subset_refuter.py::TestDataSubsetRefuter::test_refutation_data_subset_refuter_binary[0.01-backdoor.propensity_score_matching]": 68.55800845900012, - "tests/causal_refuters/test_data_subset_refuter.py::TestDataSubsetRefuter::test_refutation_data_subset_refuter_continuous[0.01-iv.instrumental_variable]": 1.498870042996714, - "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_custom_function_linear_regression_with_noise_binary_treatment[0.2-backdoor.linear_regression-transformations0-1000]": 0.07436634000259801, - "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_custom_function_linear_regression_with_noise_continuous_treatment[0.2-iv.instrumental_variable-transformations0]": 0.3916881670047587, - "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_custom_function_linear_regression_with_permute_binary_treatment[0.2-backdoor.propensity_score_matching-transformations0-1000]": 0.49299202900147066, - "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_custom_function_linear_regression_with_permute_continuous_treatment[0.2-backdoor.linear_regression-transformations0]": 0.9126691839992418, - "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_default_binary_treatment[0.1-backdoor.propensity_score_matching-1000]": 0.4539793549993192, - "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_default_continuous_treatment[0.03-iv.instrumental_variable]": 2.1723163930000737, - "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_internal_knn_binary_treatment[0.2-backdoor.propensity_score_matching-transformations0-1000]": 0.46351385800517164, - "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_internal_knn_continuous_treatment[0.2-iv.instrumental_variable-transformations0]": 0.8979279530030908, - "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_internal_linear_regression_binary_treatment[0.2-backdoor.propensity_score_matching-transformations0-1000]": 0.47614499700284796, - "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_internal_linear_regression_continuous_treatment[0.01-iv.instrumental_variable-transformations0]": 0.6039230140013387, - "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_internal_neural_network_binary_treatment[0.1-backdoor.propensity_score_matching-transformations0-1000]": 0.5101833099979558, - "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_internal_neural_network_continuous_treatment[0.01-iv.instrumental_variable-transformations0]": 2.9238356690002547, - "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_internal_random_forest_binary_treatment[0.1-backdoor.propensity_score_matching-transformations0-1000]": 0.7357043550000526, - "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_internal_random_forest_continuous_treatment[0.01-iv.instrumental_variable-transformations0-10000]": 0.8158579579976504, - "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_internal_svm_binary_treatment[0.1-backdoor.propensity_score_matching-transformations0-1000]": 0.4558805480010051, - "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_internal_svm_continuous_treatment[0.01-iv.instrumental_variable-transformations0-10000]": 0.9708759800014377, - "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_permute_data_binary_treatment[0.1-backdoor.linear_regression-transformations0-1000]": 0.048296427994500846, - "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_permute_data_continuous_treatment[0.03-iv.instrumental_variable-transformations0]": 0.1175915969943162, - "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_randomly_generated_binary_treatment[0.05-backdoor.propensity_score_matching-transformations0-1000]": 0.4404820630006725, - "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_randomly_generated_continuous_treatment[0.05-iv.instrumental_variable-transformations0]": 0.11266090500066639, - "tests/causal_refuters/test_placebo_refuter.py::TestPlaceboRefuter::test_refutation_placebo_refuter_binary[0.1-backdoor.propensity_score_matching-5000]": 7.487174318997859, - "tests/causal_refuters/test_placebo_refuter.py::TestPlaceboRefuter::test_refutation_placebo_refuter_category[0.1-backdoor.linear_regression-5000]": 1.8801709030012717, - "tests/causal_refuters/test_placebo_refuter.py::TestPlaceboRefuter::test_refutation_placebo_refuter_category_non_consecutive_index[0.1-backdoor.linear_regression-5000]": 0.4805744439981936, - "tests/causal_refuters/test_placebo_refuter.py::TestPlaceboRefuter::test_refutation_placebo_refuter_continuous[0.03-backdoor.linear_regression-1000]": 1.4750072509996244, - "tests/data_transformers/test_pca_reducer.py::TestPCAReducer::test_reduce": 0.002902270993217826, - "tests/do_sampler/test_pandas_do_api.py::TestPandasDoAPI::test_pandas_api_continuous_cause_continuous_confounder[10000-0.1]": 3.5036639429999923, - "tests/do_sampler/test_pandas_do_api.py::TestPandasDoAPI::test_pandas_api_continuous_cause_discrete_confounder[10000-0.1]": 27.219203676999314, - "tests/do_sampler/test_pandas_do_api.py::TestPandasDoAPI::test_pandas_api_discrete_cause_continuous_confounder[10000-0.1]": 0.09374719999686931, - "tests/do_sampler/test_pandas_do_api.py::TestPandasDoAPI::test_pandas_api_discrete_cause_discrete_confounder[10000-0.1]": 0.2661919879974448, - "tests/do_sampler/test_pandas_do_api.py::TestPandasDoAPI::test_pandas_api_with_dummy_data[1-variable_types0]": 0.011210563003260177, - "tests/do_sampler/test_pandas_do_api.py::TestPandasDoAPI::test_pandas_api_with_full_specification_of_type[10000-variable_types0]": 0.026649983003153466, - "tests/do_sampler/test_pandas_do_api.py::TestPandasDoAPI::test_pandas_api_with_no_specification_of_type[10000-variable_types0]": 0.023502381998696364, - "tests/do_sampler/test_pandas_do_api.py::TestPandasDoAPI::test_pandas_api_with_partial_specification_of_type[10000-variable_types0]": 0.02382615099850227, - "tests/gcm/independence_test/test_kernel.py::test_given_categorical_conditionally_dependent_data_when_perform_approx_kernel_based_test_then_reject": 0.29915133899703505, - "tests/gcm/independence_test/test_kernel.py::test_given_categorical_conditionally_dependent_data_when_perform_kernel_based_test_then_reject": 1.1452262070015422, - "tests/gcm/independence_test/test_kernel.py::test_given_categorical_conditionally_independent_data_when_perform_approx_kernel_based_test_then_not_reject": 0.27699546300209477, - "tests/gcm/independence_test/test_kernel.py::test_given_categorical_conditionally_independent_data_when_perform_kernel_based_test_then_not_reject": 1.538889437000762, - "tests/gcm/independence_test/test_kernel.py::test_given_categorical_dependent_data_when_perform_approx_kernel_based_test_then_reject": 0.2287549439970462, - "tests/gcm/independence_test/test_kernel.py::test_given_categorical_dependent_data_when_perform_kernel_based_test_then_reject": 0.08614612100063823, - "tests/gcm/independence_test/test_kernel.py::test_given_categorical_independent_data_when_perform_approx_kernel_based_test_then_not_reject": 0.20994599200275843, - "tests/gcm/independence_test/test_kernel.py::test_given_categorical_independent_data_when_perform_kernel_based_test_then_not_reject": 0.08014346700292663, - "tests/gcm/independence_test/test_kernel.py::test_given_constant_data_when_perform_approx_kernel_based_test_then_returns_expected_result": 0.08669152299989946, - "tests/gcm/independence_test/test_kernel.py::test_given_constant_data_when_perform_kernel_based_test_then_returns_expected_result": 0.002242487000330584, - "tests/gcm/independence_test/test_kernel.py::test_given_constant_inputs_when_perform_kernel_based_test_then_returns_non_nan_value": 0.0007114549953257665, - "tests/gcm/independence_test/test_kernel.py::test_given_continuous_conditionally_dependent_data_when_perform_approx_kernel_based_test_then_reject": 0.26513264200184494, - "tests/gcm/independence_test/test_kernel.py::test_given_continuous_conditionally_dependent_data_when_perform_kernel_based_test_then_reject": 1.8727134019973164, - "tests/gcm/independence_test/test_kernel.py::test_given_continuous_conditionally_independent_data_when_perform_approx_kernel_based_test_then_not_reject": 0.2970279729925096, - "tests/gcm/independence_test/test_kernel.py::test_given_continuous_conditionally_independent_data_when_perform_kernel_based_test_then_not_reject": 1.007309553995583, - "tests/gcm/independence_test/test_kernel.py::test_given_continuous_dependent_data_when_perform_approx_kernel_based_test_then_reject": 0.22697504900133936, - "tests/gcm/independence_test/test_kernel.py::test_given_continuous_dependent_data_when_perform_kernel_based_test_then_reject": 0.07577386800039676, - "tests/gcm/independence_test/test_kernel.py::test_given_continuous_independent_data_when_perform_approx_kernel_based_test_then_not_reject": 0.21268876300018746, - "tests/gcm/independence_test/test_kernel.py::test_given_continuous_independent_data_when_perform_kernel_based_test_then_not_reject": 0.058165056001598714, - "tests/gcm/independence_test/test_kernel.py::test_given_random_seed_when_perform_conditional_approx_kernel_based_test_then_return_deterministic_result": 0.1216843800029892, - "tests/gcm/independence_test/test_kernel.py::test_given_random_seed_when_perform_conditional_kernel_based_test_then_return_deterministic_result": 0.03439881699887337, - "tests/gcm/independence_test/test_kernel.py::test_given_random_seed_when_perform_pairwise_approx_kernel_based_test_then_return_deterministic_result": 0.07384701699629659, - "tests/gcm/independence_test/test_kernel.py::test_given_random_seed_when_perform_pairwise_kernel_based_test_then_return_deterministic_result": 0.031348867003544, + "tests/causal_refuters/test_add_unobserved_common_cause.py::TestAddUnobservedCommonCauseRefuter::test_non_parametric_sensitivity_given_strength_of_confounding[backdoor.econml.dml.KernelDML-2-benchmark_common_causes0-non-parametric-partial-R2]": 11.274044722000326, + "tests/causal_refuters/test_add_unobserved_common_cause.py::TestAddUnobservedCommonCauseRefuter::test_partially_linear_sensitivity_given_strength_of_confounding[backdoor.econml.dml.LinearDML-2-benchmark_common_causes0-non-parametric-partial-R2]": 2.1124762050003483, + "tests/causal_refuters/test_add_unobserved_common_cause.py::TestAddUnobservedCommonCauseRefuter::test_refutation_binary_treatment[0.01-backdoor.propensity_score_matching-0.01-0.02]": 44.626613692998944, + "tests/causal_refuters/test_add_unobserved_common_cause.py::TestAddUnobservedCommonCauseRefuter::test_refutation_continuous_treatment[0.01-iv.instrumental_variable-0.01-0.02]": 0.08056703300098889, + "tests/causal_refuters/test_add_unobserved_common_cause.py::TestAddUnobservedCommonCauseRefuter::test_refutation_continuous_treatment_range_both_treatment_outcome[0.01-iv.instrumental_variable-effect_strength_on_t0-effect_strength_on_y0]": 1.3013563799995609, + "tests/causal_refuters/test_add_unobserved_common_cause.py::TestAddUnobservedCommonCauseRefuter::test_refutation_continuous_treatment_range_outcome[0.01-iv.instrumental_variable-0.01-effect_strength_on_y0]": 0.2020682439997472, + "tests/causal_refuters/test_add_unobserved_common_cause.py::TestAddUnobservedCommonCauseRefuter::test_refutation_continuous_treatment_range_treatment[0.01-iv.instrumental_variable-effect_strength_on_t0-0.02]": 0.20793321400014975, + "tests/causal_refuters/test_bootstrap_refuter.py::TestDataSubsetRefuter::test_refutation_bootstrap_refuter_binary[0.05-backdoor.propensity_score_matching-1000]": 0.8476695269982883, + "tests/causal_refuters/test_bootstrap_refuter.py::TestDataSubsetRefuter::test_refutation_bootstrap_refuter_binary_integer_argument[0.1-backdoor.propensity_score_matching-5-3-5000]": 4.607819500000915, + "tests/causal_refuters/test_bootstrap_refuter.py::TestDataSubsetRefuter::test_refutation_bootstrap_refuter_binary_list_argument[0.1-backdoor.propensity_score_matching-5-required_variables0-5000]": 4.454197867000403, + "tests/causal_refuters/test_bootstrap_refuter.py::TestDataSubsetRefuter::test_refutation_bootstrap_refuter_binary_list_negative_argument[0.1-backdoor.propensity_score_matching-5-required_variables0-5000]": 4.471698694002043, + "tests/causal_refuters/test_bootstrap_refuter.py::TestDataSubsetRefuter::test_refutation_bootstrap_refuter_continuous[0.05-iv.instrumental_variable-1000]": 0.4846738450014527, + "tests/causal_refuters/test_bootstrap_refuter.py::TestDataSubsetRefuter::test_refutation_bootstrap_refuter_continuous_integer_argument[0.05-iv.instrumental_variable-5-3-1000]": 0.4462375079965568, + "tests/causal_refuters/test_bootstrap_refuter.py::TestDataSubsetRefuter::test_refutation_bootstrap_refuter_continuous_list_argument[0.05-iv.instrumental_variable-5-required_variables0-1000]": 0.40095900500091375, + "tests/causal_refuters/test_bootstrap_refuter.py::TestDataSubsetRefuter::test_refutation_bootstrap_refuter_continuous_list_negative_argument[0.1-iv.instrumental_variable-5-required_variables0-5000]": 0.5441861099989183, + "tests/causal_refuters/test_data_subset_refuter.py::TestDataSubsetRefuter::test_refutation_data_subset_refuter_binary[0.01-backdoor.propensity_score_matching]": 68.9505145080002, + "tests/causal_refuters/test_data_subset_refuter.py::TestDataSubsetRefuter::test_refutation_data_subset_refuter_continuous[0.01-iv.instrumental_variable]": 1.811442590000297, + "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_custom_function_linear_regression_with_noise_binary_treatment[0.2-backdoor.linear_regression-transformations0-1000]": 0.08030410499850404, + "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_custom_function_linear_regression_with_noise_continuous_treatment[0.2-iv.instrumental_variable-transformations0]": 0.4127799799989589, + "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_custom_function_linear_regression_with_permute_binary_treatment[0.2-backdoor.propensity_score_matching-transformations0-1000]": 0.47684506999758014, + "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_custom_function_linear_regression_with_permute_continuous_treatment[0.2-backdoor.linear_regression-transformations0]": 0.9885844689979422, + "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_default_binary_treatment[0.1-backdoor.propensity_score_matching-1000]": 0.42835930500041286, + "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_default_continuous_treatment[0.03-iv.instrumental_variable]": 2.288028838000173, + "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_internal_knn_binary_treatment[0.2-backdoor.propensity_score_matching-transformations0-1000]": 0.4866959130013129, + "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_internal_knn_continuous_treatment[0.2-iv.instrumental_variable-transformations0]": 0.9384641270007705, + "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_internal_linear_regression_binary_treatment[0.2-backdoor.propensity_score_matching-transformations0-1000]": 0.5279801420001604, + "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_internal_linear_regression_continuous_treatment[0.01-iv.instrumental_variable-transformations0]": 0.7205875620002189, + "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_internal_neural_network_binary_treatment[0.1-backdoor.propensity_score_matching-transformations0-1000]": 0.5486997209991387, + "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_internal_neural_network_continuous_treatment[0.01-iv.instrumental_variable-transformations0]": 5.1585782559996005, + "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_internal_random_forest_binary_treatment[0.1-backdoor.propensity_score_matching-transformations0-1000]": 0.732061638002051, + "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_internal_random_forest_continuous_treatment[0.01-iv.instrumental_variable-transformations0-10000]": 0.8679392299982283, + "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_internal_svm_binary_treatment[0.1-backdoor.propensity_score_matching-transformations0-1000]": 0.46700796699769853, + "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_internal_svm_continuous_treatment[0.01-iv.instrumental_variable-transformations0-10000]": 1.0434644179986208, + "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_permute_data_binary_treatment[0.1-backdoor.linear_regression-transformations0-1000]": 0.056201067001893534, + "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_permute_data_continuous_treatment[0.03-iv.instrumental_variable-transformations0]": 0.1261690240007738, + "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_randomly_generated_binary_treatment[0.05-backdoor.propensity_score_matching-transformations0-1000]": 0.42547475500396104, + "tests/causal_refuters/test_dummy_outcome_refuter.py::TestDummyOutcomeRefuter::test_refutation_dummy_outcome_refuter_randomly_generated_continuous_treatment[0.05-iv.instrumental_variable-transformations0]": 0.11543983599767671, + "tests/causal_refuters/test_placebo_refuter.py::TestPlaceboRefuter::test_refutation_placebo_refuter_binary[0.1-backdoor.propensity_score_matching-5000]": 7.3666792690019065, + "tests/causal_refuters/test_placebo_refuter.py::TestPlaceboRefuter::test_refutation_placebo_refuter_category[0.1-backdoor.linear_regression-5000]": 2.8750521050023963, + "tests/causal_refuters/test_placebo_refuter.py::TestPlaceboRefuter::test_refutation_placebo_refuter_category_non_consecutive_index[0.1-backdoor.linear_regression-5000]": 0.47494545400149946, + "tests/causal_refuters/test_placebo_refuter.py::TestPlaceboRefuter::test_refutation_placebo_refuter_continuous[0.03-backdoor.linear_regression-1000]": 1.8235527470005763, + "tests/data_transformers/test_pca_reducer.py::TestPCAReducer::test_reduce": 0.002960286001325585, + "tests/do_sampler/test_pandas_do_api.py::TestPandasDoAPI::test_pandas_api_continuous_cause_continuous_confounder[10000-0.1]": 3.5447984439997526, + "tests/do_sampler/test_pandas_do_api.py::TestPandasDoAPI::test_pandas_api_continuous_cause_discrete_confounder[10000-0.1]": 27.0796278050002, + "tests/do_sampler/test_pandas_do_api.py::TestPandasDoAPI::test_pandas_api_discrete_cause_continuous_confounder[10000-0.1]": 0.09848521200001414, + "tests/do_sampler/test_pandas_do_api.py::TestPandasDoAPI::test_pandas_api_discrete_cause_discrete_confounder[10000-0.1]": 0.5648940689970914, + "tests/do_sampler/test_pandas_do_api.py::TestPandasDoAPI::test_pandas_api_with_dummy_data[1-variable_types0]": 0.012208598000142956, + "tests/do_sampler/test_pandas_do_api.py::TestPandasDoAPI::test_pandas_api_with_full_specification_of_type[10000-variable_types0]": 0.02463898299902212, + "tests/do_sampler/test_pandas_do_api.py::TestPandasDoAPI::test_pandas_api_with_no_specification_of_type[10000-variable_types0]": 0.024161270002878155, + "tests/do_sampler/test_pandas_do_api.py::TestPandasDoAPI::test_pandas_api_with_partial_specification_of_type[10000-variable_types0]": 0.024245782999059884, + "tests/gcm/independence_test/test_kernel.py::test_given_categorical_conditionally_dependent_data_when_perform_approx_kernel_based_test_then_reject": 0.2696055870019336, + "tests/gcm/independence_test/test_kernel.py::test_given_categorical_conditionally_dependent_data_when_perform_kernel_based_test_then_reject": 1.410417672001131, + "tests/gcm/independence_test/test_kernel.py::test_given_categorical_conditionally_independent_data_when_perform_approx_kernel_based_test_then_not_reject": 0.25542592800047714, + "tests/gcm/independence_test/test_kernel.py::test_given_categorical_conditionally_independent_data_when_perform_kernel_based_test_then_not_reject": 1.27113092700165, + "tests/gcm/independence_test/test_kernel.py::test_given_categorical_dependent_data_when_perform_approx_kernel_based_test_then_reject": 0.22055077500044717, + "tests/gcm/independence_test/test_kernel.py::test_given_categorical_dependent_data_when_perform_kernel_based_test_then_reject": 0.03890899799989711, + "tests/gcm/independence_test/test_kernel.py::test_given_categorical_independent_data_when_perform_approx_kernel_based_test_then_not_reject": 0.20551914299903729, + "tests/gcm/independence_test/test_kernel.py::test_given_categorical_independent_data_when_perform_kernel_based_test_then_not_reject": 0.03948311400017701, + "tests/gcm/independence_test/test_kernel.py::test_given_constant_data_when_perform_approx_kernel_based_test_then_returns_expected_result": 0.03382713999963016, + "tests/gcm/independence_test/test_kernel.py::test_given_constant_data_when_perform_kernel_based_test_then_returns_expected_result": 0.0017116209983214503, + "tests/gcm/independence_test/test_kernel.py::test_given_constant_inputs_when_perform_kernel_based_test_then_returns_non_nan_value": 0.0004904510005871998, + "tests/gcm/independence_test/test_kernel.py::test_given_continuous_conditionally_dependent_data_when_perform_approx_kernel_based_test_then_reject": 0.269351683997229, + "tests/gcm/independence_test/test_kernel.py::test_given_continuous_conditionally_dependent_data_when_perform_kernel_based_test_then_reject": 1.4925917610016768, + "tests/gcm/independence_test/test_kernel.py::test_given_continuous_conditionally_independent_data_when_perform_approx_kernel_based_test_then_not_reject": 0.20362845199997537, + "tests/gcm/independence_test/test_kernel.py::test_given_continuous_conditionally_independent_data_when_perform_kernel_based_test_then_not_reject": 1.9381592869995075, + "tests/gcm/independence_test/test_kernel.py::test_given_continuous_dependent_data_when_perform_approx_kernel_based_test_then_reject": 0.20551107300161675, + "tests/gcm/independence_test/test_kernel.py::test_given_continuous_dependent_data_when_perform_kernel_based_test_then_reject": 0.04344868600128393, + "tests/gcm/independence_test/test_kernel.py::test_given_continuous_independent_data_when_perform_approx_kernel_based_test_then_not_reject": 0.20429461199819343, + "tests/gcm/independence_test/test_kernel.py::test_given_continuous_independent_data_when_perform_kernel_based_test_then_not_reject": 0.06942105699999956, + "tests/gcm/independence_test/test_kernel.py::test_given_random_seed_when_perform_conditional_approx_kernel_based_test_then_return_deterministic_result": 0.11785191600029066, + "tests/gcm/independence_test/test_kernel.py::test_given_random_seed_when_perform_conditional_kernel_based_test_then_return_deterministic_result": 0.01995912500024133, + "tests/gcm/independence_test/test_kernel.py::test_given_random_seed_when_perform_pairwise_approx_kernel_based_test_then_return_deterministic_result": 0.09124762999999803, + "tests/gcm/independence_test/test_kernel.py::test_given_random_seed_when_perform_pairwise_kernel_based_test_then_return_deterministic_result": 0.010564567000983516, "tests/gcm/independence_test/test_kernel.py::test_given_too_few_samples_when_perform_kernel_based_test_then_raise_error": 0.0005369960053940304, - "tests/gcm/independence_test/test_kernel.py::test_given_weak_dependency_when_perform_kernel_based_test_then_returns_expected_result": 6.355862268999772, + "tests/gcm/independence_test/test_kernel.py::test_given_weak_dependency_when_perform_kernel_based_test_then_returns_expected_result": 1.3359811050013377, "tests/gcm/independence_test/test_kernel.py::test_when_using_fast_centering_then_gives_expected_results": 0.05734733299686923, - "tests/gcm/independence_test/test_regression.py::test_regression_based_conditional_independence_parallelization": 0.8040251249985886, - "tests/gcm/independence_test/test_regression.py::test_regression_based_conditional_independence_test_categorical_dependent": 0.20517464200020186, - "tests/gcm/independence_test/test_regression.py::test_regression_based_conditional_independence_test_categorical_independent": 0.2127767899983155, - "tests/gcm/independence_test/test_regression.py::test_regression_based_conditional_independence_test_dependent": 0.3155361110002559, - "tests/gcm/independence_test/test_regression.py::test_regression_based_conditional_independence_test_independent": 0.1960459349975281, - "tests/gcm/independence_test/test_regression.py::test_regression_based_pairwise_independence_test_categorical_dependent": 0.2196950100005779, - "tests/gcm/independence_test/test_regression.py::test_regression_based_pairwise_independence_test_categorical_independent": 0.20847917899664026, - "tests/gcm/independence_test/test_regression.py::test_regression_based_pairwise_independence_test_dependent": 0.24657917199874646, - "tests/gcm/independence_test/test_regression.py::test_regression_based_pairwise_independence_test_independent": 0.24525637500119046, - "tests/gcm/test_anomaly.py::test_given_data_with_change_in_mechanism_when_estimate_distribution_change_score_then_returns_expected_result": 17.271205247998296, - "tests/gcm/test_anomaly.py::test_given_data_with_change_in_mechanism_when_estimate_distribution_change_score_using_difference_in_means_then_returns_expected_result": 18.573216941000283, - "tests/gcm/test_anomaly.py::test_given_data_with_change_in_mechanism_when_estimate_distribution_change_score_using_difference_in_variance_then_returns_expected_result": 30.12939289699716, - "tests/gcm/test_anomaly.py::test_given_data_with_change_in_root_node_when_estimate_distribution_change_score_using_difference_in_means_then_returns_expected_result": 17.02896168499865, - "tests/gcm/test_anomaly.py::test_given_graph_with_multiple_parents_when_estimate_distribution_change_scores_then_returns_expected_result": 6.83073560000048, - "tests/gcm/test_anomaly.py::test_given_multivariate_inputs_when_estimate_anomaly_scores_then_does_not_raise_error": 0.8354802380017645, - "tests/gcm/test_anomaly.py::test_given_outlier_observation_when_estimate_anomaly_scores_using_inverse_density_scorer_then_returns_expected_result": 14.157676802999049, - "tests/gcm/test_anomaly.py::test_given_outlier_observation_when_estimate_anomaly_scores_using_mean_deviation_scorer_then_returns_expected_result": 1.2811969299982593, - "tests/gcm/test_anomaly.py::test_given_outlier_observation_when_estimate_anomaly_scores_using_median_cdf_quantile_scorer_then_returns_expected_result": 1.3741463899968949, - "tests/gcm/test_anomaly.py::test_given_outlier_observation_when_estimate_anomaly_scores_using_median_deviation_scorer_then_returns_expected_result": 1.609633436997683, - "tests/gcm/test_anomaly.py::test_given_outlier_observation_when_estimate_anomaly_scores_using_rescaled_median_cdf_quantile_scorer_then_returns_expected_result": 1.4401765190013975, - "tests/gcm/test_anomaly.py::test_given_simple_linear_data_when_estimate_conditional_anomaly_scores_then_returns_expected_result": 0.0027797249967989046, - "tests/gcm/test_anomaly_attribution.py::test_given_non_trivial_graph_with_nonlinear_relationships_when_attribute_anomaly_scores_with_it_score_then_returns_qualitatively_correct_results": 2.0995102369997767, - "tests/gcm/test_anomaly_attribution.py::test_given_simple_causal_chain_with_linear_relationships_when_attribute_anomaly_scores_with_feature_relevance_then_returns_qualitatively_correct_results": 2.178279106003174, - "tests/gcm/test_anomaly_attribution.py::test_given_simple_causal_chain_with_linear_relationships_when_attribute_anomaly_scores_with_it_score_then_returns_qualitatively_correct_results": 1.3042352470038168, - "tests/gcm/test_anomaly_attribution.py::test_given_simple_gaussian_data_when_attribute_anomaly_scores_with_feature_relevance_then_returns_qualitatively_correct_results": 0.5284207230033644, - "tests/gcm/test_anomaly_attribution.py::test_given_simple_gaussian_data_when_attribute_anomaly_scores_with_it_score_then_returns_qualitatively_correct_results": 6.348568976001843, - "tests/gcm/test_anomaly_attribution.py::test_relative_frequency": 0.0002936099990620278, - "tests/gcm/test_anomaly_scorers.py::test_given_simple_toy_data_when_using_MedianCDFQuantileScorer_then_returns_expected_scores": 0.000498973997309804, - "tests/gcm/test_anomaly_scorers.py::test_given_simple_toy_data_when_using_MedianDeviationScorer_then_returns_expected_scores": 0.000577939998038346, - "tests/gcm/test_arrow_strength.py::test_given_categorical_target_node_when_estimate_arrow_strength_of_model_classifier_then_returns_expected_result": 1.073614480003016, - "tests/gcm/test_arrow_strength.py::test_given_continuous_data_with_default_attribution_func_when_estimate_arrow_strength_then_returns_expected_results": 0.10413893800432561, - "tests/gcm/test_arrow_strength.py::test_given_gcm_with_misspecified_mechanism_when_evaluate_arrow_strength_with__observational_data_then_gives_expected_results": 0.059819231002620654, - "tests/gcm/test_arrow_strength.py::test_given_kl_divergence_attribution_func_when_estimate_arrow_strength_then_returns_expected_results": 4.1209102970024105, - "tests/gcm/test_auto.py::test_given_linear_classification_problem_when_auto_assign_causal_models_with_better_quality_returns_linear_model": 0.5792933610027831, - "tests/gcm/test_auto.py::test_given_linear_classification_problem_when_auto_assign_causal_models_with_good_quality_returns_linear_model": 0.2876891730047646, - "tests/gcm/test_auto.py::test_given_linear_regression_problem_when_auto_assign_causal_models_with_better_quality_returns_linear_model": 0.8629348760005087, - "tests/gcm/test_auto.py::test_given_linear_regression_problem_when_auto_assign_causal_models_with_good_quality_returns_linear_model": 0.31510659000559826, - "tests/gcm/test_auto.py::test_given_non_linear_classification_problem_when_auto_assign_causal_models_with_better_quality_returns_non_linear_model": 0.5879168029969151, - "tests/gcm/test_auto.py::test_given_non_linear_classification_problem_when_auto_assign_causal_models_with_good_quality_returns_non_linear_model": 0.2784427689985023, - "tests/gcm/test_auto.py::test_given_non_linear_regression_problem_when_auto_assign_causal_models_with_better_quality_returns_non_linear_model": 1.1180348099951516, - "tests/gcm/test_auto.py::test_given_non_linear_regression_problem_when_auto_assign_causal_models_with_good_quality_returns_non_linear_model": 0.7233570249991317, - "tests/gcm/test_auto.py::test_when_auto_called_from_main_namespace_returns_no_attribute_error": 0.000274299003649503, - "tests/gcm/test_confidence_intervals.py::test_given_simple_counter_as_estimation_func_when_confidence_interval_then_returns_mean_and_interval_counter": 0.0018954930019390304, - "tests/gcm/test_confidence_intervals_cms.py::test_given_causal_graph_based_estimation_func_when_confidence_interval_then_can_use_bootstrap_training_and_sampling": 0.6973980469956587, - "tests/gcm/test_confidence_intervals_cms.py::test_given_parameterized_estimation_func_when_confidence_interval_then_can_use_bootstrap_sampling_to_bind_parameters": 0.0017940140023711137, + "tests/gcm/independence_test/test_regression.py::test_regression_based_conditional_independence_parallelization": 0.3592468739989272, + "tests/gcm/independence_test/test_regression.py::test_regression_based_conditional_independence_test_categorical_dependent": 0.26605106299939507, + "tests/gcm/independence_test/test_regression.py::test_regression_based_conditional_independence_test_categorical_independent": 0.31590158400103974, + "tests/gcm/independence_test/test_regression.py::test_regression_based_conditional_independence_test_dependent": 0.3428450259980309, + "tests/gcm/independence_test/test_regression.py::test_regression_based_conditional_independence_test_independent": 0.16104197300046508, + "tests/gcm/independence_test/test_regression.py::test_regression_based_pairwise_independence_test_categorical_dependent": 0.04541199199957191, + "tests/gcm/independence_test/test_regression.py::test_regression_based_pairwise_independence_test_categorical_independent": 0.10463475799951993, + "tests/gcm/independence_test/test_regression.py::test_regression_based_pairwise_independence_test_dependent": 0.10435450899785792, + "tests/gcm/independence_test/test_regression.py::test_regression_based_pairwise_independence_test_independent": 0.14417282299837098, + "tests/gcm/ml/test_regression.py::test_given_product_regressor_then_computes_correct_values": 0.001283600999158807, + "tests/gcm/test_anomaly.py::test_given_data_with_change_in_mechanism_when_estimate_distribution_change_score_then_returns_expected_result": 29.807445410000582, + "tests/gcm/test_anomaly.py::test_given_data_with_change_in_mechanism_when_estimate_distribution_change_score_using_difference_in_means_then_returns_expected_result": 25.35173482800019, + "tests/gcm/test_anomaly.py::test_given_data_with_change_in_mechanism_when_estimate_distribution_change_score_using_difference_in_variance_then_returns_expected_result": 34.873429462000786, + "tests/gcm/test_anomaly.py::test_given_data_with_change_in_root_node_when_estimate_distribution_change_score_using_difference_in_means_then_returns_expected_result": 24.64987556900269, + "tests/gcm/test_anomaly.py::test_given_graph_with_multiple_parents_when_estimate_distribution_change_scores_then_returns_expected_result": 13.599023269998725, + "tests/gcm/test_anomaly.py::test_given_multivariate_inputs_when_estimate_anomaly_scores_then_does_not_raise_error": 13.891689223999492, + "tests/gcm/test_anomaly.py::test_given_outlier_observation_when_estimate_anomaly_scores_using_inverse_density_scorer_then_returns_expected_result": 30.14598051699977, + "tests/gcm/test_anomaly.py::test_given_outlier_observation_when_estimate_anomaly_scores_using_mean_deviation_scorer_then_returns_expected_result": 17.030378150000615, + "tests/gcm/test_anomaly.py::test_given_outlier_observation_when_estimate_anomaly_scores_using_median_cdf_quantile_scorer_then_returns_expected_result": 24.73614000700036, + "tests/gcm/test_anomaly.py::test_given_outlier_observation_when_estimate_anomaly_scores_using_median_deviation_scorer_then_returns_expected_result": 16.054258019998088, + "tests/gcm/test_anomaly.py::test_given_outlier_observation_when_estimate_anomaly_scores_using_rescaled_median_cdf_quantile_scorer_then_returns_expected_result": 18.47946877600043, + "tests/gcm/test_anomaly.py::test_given_simple_linear_data_when_estimate_conditional_anomaly_scores_then_returns_expected_result": 0.0029044759994576452, + "tests/gcm/test_anomaly_attribution.py::test_given_non_trivial_graph_with_nonlinear_relationships_when_attribute_anomaly_scores_with_it_score_then_returns_qualitatively_correct_results": 2.1123664880014985, + "tests/gcm/test_anomaly_attribution.py::test_given_simple_causal_chain_with_linear_relationships_when_attribute_anomaly_scores_with_feature_relevance_then_returns_qualitatively_correct_results": 24.001711004000754, + "tests/gcm/test_anomaly_attribution.py::test_given_simple_causal_chain_with_linear_relationships_when_attribute_anomaly_scores_with_it_score_then_returns_qualitatively_correct_results": 29.369829627998115, + "tests/gcm/test_anomaly_attribution.py::test_given_simple_gaussian_data_when_attribute_anomaly_scores_with_feature_relevance_then_returns_qualitatively_correct_results": 0.6089531779998651, + "tests/gcm/test_anomaly_attribution.py::test_given_simple_gaussian_data_when_attribute_anomaly_scores_with_it_score_then_returns_qualitatively_correct_results": 4.976234596999348, + "tests/gcm/test_anomaly_attribution.py::test_relative_frequency": 0.00037885099845880177, + "tests/gcm/test_anomaly_scorers.py::test_given_simple_toy_data_when_using_MedianCDFQuantileScorer_then_returns_expected_scores": 0.0005814419982925756, + "tests/gcm/test_anomaly_scorers.py::test_given_simple_toy_data_when_using_MedianDeviationScorer_then_returns_expected_scores": 0.0006448339991038665, + "tests/gcm/test_arrow_strength.py::test_given_categorical_target_node_when_estimate_arrow_strength_of_model_classifier_then_returns_expected_result": 1.1652822319992993, + "tests/gcm/test_arrow_strength.py::test_given_continuous_data_with_default_attribution_func_when_estimate_arrow_strength_then_returns_expected_results": 0.12396619799983455, + "tests/gcm/test_arrow_strength.py::test_given_gcm_with_misspecified_mechanism_when_evaluate_arrow_strength_with__observational_data_then_gives_expected_results": 0.07071328300116875, + "tests/gcm/test_arrow_strength.py::test_given_kl_divergence_attribution_func_when_estimate_arrow_strength_then_returns_expected_results": 7.431842104999305, + "tests/gcm/test_auto.py::test_given_linear_classification_problem_when_auto_assign_causal_models_with_better_quality_returns_linear_model": 0.5956583260012849, + "tests/gcm/test_auto.py::test_given_linear_classification_problem_when_auto_assign_causal_models_with_good_quality_returns_linear_model": 5.7380634199980705, + "tests/gcm/test_auto.py::test_given_linear_regression_problem_when_auto_assign_causal_models_with_better_quality_returns_linear_model": 0.8294572150007298, + "tests/gcm/test_auto.py::test_given_linear_regression_problem_when_auto_assign_causal_models_with_good_quality_returns_linear_model": 7.128187996999259, + "tests/gcm/test_auto.py::test_given_non_linear_classification_problem_when_auto_assign_causal_models_with_better_quality_returns_non_linear_model": 0.5962440150015027, + "tests/gcm/test_auto.py::test_given_non_linear_classification_problem_when_auto_assign_causal_models_with_good_quality_returns_non_linear_model": 6.589439229999698, + "tests/gcm/test_auto.py::test_given_non_linear_regression_problem_when_auto_assign_causal_models_with_better_quality_returns_non_linear_model": 1.2263876689994504, + "tests/gcm/test_auto.py::test_given_non_linear_regression_problem_when_auto_assign_causal_models_with_good_quality_returns_non_linear_model": 9.161473943000601, + "tests/gcm/test_auto.py::test_when_auto_called_from_main_namespace_returns_no_attribute_error": 0.00029278099827934057, + "tests/gcm/test_confidence_intervals.py::test_given_simple_counter_as_estimation_func_when_confidence_interval_then_returns_mean_and_interval_counter": 0.0020715710015792865, + "tests/gcm/test_confidence_intervals_cms.py::test_given_causal_graph_based_estimation_func_when_confidence_interval_then_can_use_bootstrap_training_and_sampling": 5.556269120001161, + "tests/gcm/test_confidence_intervals_cms.py::test_given_parameterized_estimation_func_when_confidence_interval_then_can_use_bootstrap_sampling_to_bind_parameters": 0.0018258170002809493, "tests/gcm/test_density_estimators.py::test_gaussian_mixture_density_estimator": 0.00399742500303546, "tests/gcm/test_density_estimators.py::test_kernel_based_density_estimator_1d": 0.0006911870041221846, + "tests/gcm/test_density_estimators.py::test_when_fit_and_evaluate_gaussian_mixture_density_estimator_then_behaves_as_expected": 0.00461995500154444, + "tests/gcm/test_density_estimators.py::test_when_fit_and_evaluate_kernel_based_density_estimator_1d_then_behaves_as_expected": 0.0018513159975555027, "tests/gcm/test_distribution_change.py::test_distribution_change": 17.114309640997817, "tests/gcm/test_distribution_change.py::test_distribution_change_of_graphs": 0.04189897299875156, - "tests/gcm/test_distribution_change.py::test_when_using_distribution_change_with_return_additional_info_then_returns_additional_info": 14.030528078998032, - "tests/gcm/test_distribution_change.py::test_when_using_distribution_change_without_fdrc_then_returns_valid_results": 17.78734955999971, + "tests/gcm/test_distribution_change.py::test_given_non_linear_data_when_using_distribution_change_with_mean_difference_then_returns_expected_results": 65.09276458400018, + "tests/gcm/test_distribution_change.py::test_given_two_data_sets_with_different_mechanisms_when_evaluate_distribution_change_then_returns_expected_result": 28.554325112998413, + "tests/gcm/test_distribution_change.py::test_given_two_graphs_fitted_on_data_sets_with_different_mechanisms_when_evaluate_distribution_change_of_graphs_then_returns_expected_result": 0.04381045099944458, + "tests/gcm/test_distribution_change.py::test_when_using_distribution_change_with_return_additional_info_then_returns_additional_info": 31.143261340999743, + "tests/gcm/test_distribution_change.py::test_when_using_distribution_change_without_fdrc_then_returns_valid_results": 26.930980414999794, "tests/gcm/test_divergence.py::test_auto_estimate_kl_divergence_categorical": 0.0019550790020730346, "tests/gcm/test_divergence.py::test_auto_estimate_kl_divergence_continuous": 0.22346158000436844, "tests/gcm/test_divergence.py::test_auto_estimate_kl_divergence_probabilities": 0.0004078410020156298, "tests/gcm/test_divergence.py::test_estimate_kl_divergence_categorical": 0.0016859440002008341, "tests/gcm/test_divergence.py::test_estimate_kl_divergence_continuous": 0.23781509599939454, "tests/gcm/test_divergence.py::test_estimate_kl_divergence_of_probabilities": 0.00036038400139659643, + "tests/gcm/test_divergence.py::test_given_categorical_data_when_auto_estimate_kl_divergence_then_correctly_selects_categorical_version": 0.0018206149979960173, + "tests/gcm/test_divergence.py::test_given_probability_vectors_when_auto_estimate_kl_divergence_then_correctly_selects_probability_version": 0.0005056440004409524, + "tests/gcm/test_divergence.py::test_given_probability_vectors_when_estimate_kl_divergence_of_probabilities_then_returns_expected_result": 0.00048442400111525785, + "tests/gcm/test_divergence.py::test_given_simple_categorical_data_estimate_kl_divergence_categorical_then_returns_expected_result": 0.0017990949982049642, + "tests/gcm/test_divergence.py::test_given_simple_gaussian_data_when_auto_estimate_kl_divergence_then_correctly_selects_continuous_version": 0.22154908500124293, + "tests/gcm/test_divergence.py::test_given_simple_gaussian_data_when_estimate_kl_divergence_continuous_then_returns_expected_result": 0.22085172900006, "tests/gcm/test_fcms.py::test_classifier_sem_produces_strings": 0.0052253809953981545, "tests/gcm/test_fcms.py::test_classifier_sem_throws_error_when_non_string_targets": 0.0012314030027482659, "tests/gcm/test_fcms.py::test_classifier_sem_with_categorical_inputs": 0.008931514999858337, @@ -242,135 +289,150 @@ "tests/gcm/test_fcms.py::test_fit_causal_graph_using_additive_noise_model": 0.006898495001223637, "tests/gcm/test_fcms.py::test_fit_causal_graph_using_post_nonlinear_models": 0.006813561001763446, "tests/gcm/test_fcms.py::test_fit_causal_graph_using_post_nonlinear_models_with_categorical_features": 0.007516005000070436, + "tests/gcm/test_fcms.py::test_given_categorical_input_data_when_draw_from_fitted_causal_graph_with_linear_anm_then_generates_correct_marginal_distribution": 0.01656258800176147, + "tests/gcm/test_fcms.py::test_given_categorical_input_data_when_fit_causal_graph_with_linear_anm_then_learns_correct_coefficients": 0.005331156997272046, + "tests/gcm/test_fcms.py::test_given_exponential_data_when_fit_post_non_linear_sem_with_invertible_exponential_function_then_returns_expected_results": 0.003780343999096658, + "tests/gcm/test_fcms.py::test_given_linear_data_when_draw_samples_from_fitted_anm_then_generates_correct_marginal_distribution": 0.008520762001353432, + "tests/gcm/test_fcms.py::test_given_linear_data_when_fit_causal_graph_with_linear_anm_then_learns_correct_coefficients": 0.002319291001185775, + "tests/gcm/test_fcms.py::test_given_logarithmic_data_when_fit_post_non_linear_sem_with_invertible_logarithmic_function_then_returns_expected_results": 0.004063615999257308, + "tests/gcm/test_fcms.py::test_given_non_string_data_when_try_to_fit_classifier_fcm_then_throws_error": 0.0017007439982990036, + "tests/gcm/test_fcms.py::test_given_simple_linear_data_when_fit_post_non_linear_sem_with_invertible_identity_then_returns_expected_results": 0.004450587997780531, "tests/gcm/test_fcms.py::test_post_non_linear_sem_with_invertible_exponential": 0.0038756509966333397, "tests/gcm/test_fcms.py::test_post_non_linear_sem_with_invertible_identity": 0.0038736210008210037, "tests/gcm/test_fcms.py::test_post_non_linear_sem_with_invertible_logarithmic": 0.0035957540058007, - "tests/gcm/test_feature.py::test_feature_relevance_sample_mean_diff": 1.171173066002666, - "tests/gcm/test_feature.py::test_feature_relevance_sample_mean_diff_with_certain_batch_size": 0.1368202419980662, - "tests/gcm/test_feature.py::test_given_baseline_values_when_estimating_feature_relevance_sample_with_mean_diff_then_returns_expected_result": 0.3077509229951829, - "tests/gcm/test_feature.py::test_given_misspecified_graph_when_estimating_parent_relevance_with_observed_data_then_returns_correct_result": 3.776513219003391, - "tests/gcm/test_feature.py::test_when_using_feature_relevance_distribution_with_entropy_set_function_then_returns_correct_results": 0.8174488349977764, - "tests/gcm/test_feature.py::test_when_using_parent_relevance_with_categorical_data_then_returns_correct_results": 6.637920232002216, - "tests/gcm/test_feature.py::test_when_using_parent_relevance_with_confidence_intervals_then_returns_reasonable_bounds": 9.255171256001631, - "tests/gcm/test_feature.py::test_when_using_parent_relevance_with_continous_data_then_returns_correct_results": 0.9622846450001816, - "tests/gcm/test_graph.py::test_fit_and_draw_samples": 0.006282384998485213, - "tests/gcm/test_graph.py::test_is_root_node": 0.00025715499941725284, - "tests/gcm/test_graph.py::test_set_causal_model_raises_error": 0.00030884399529895745, - "tests/gcm/test_intrinsic_influence.py::test_given_only_categorical_data_when_estimate_icc_then_does_not_fail": 16.3624693510028, - "tests/gcm/test_intrinsic_influence.py::test_intrinsic_causal_influence_categorical": 10.063866736003547, - "tests/gcm/test_intrinsic_influence.py::test_intrinsic_causal_influence_categorical_2": 4.945753104999312, - "tests/gcm/test_intrinsic_influence.py::test_intrinsic_causal_influence_variance_linear": 8.015012635998573, - "tests/gcm/test_intrinsic_influence.py::test_when_calling_intrinsic_causal_influence_then_the_shape_of_inputs_in_the_attribution_function_should_be_equal": 1.692093040997861, - "tests/gcm/test_ml.py::test_categorical_features": 0.005635629004245857, - "tests/gcm/test_ml.py::test_categorical_inputs": 0.006445263999921735, - "tests/gcm/test_ml.py::test_when_cloning_sklearn_classification_model_then_returns_a_cloned_object": 0.0003863520032609813, - "tests/gcm/test_shapley.py::test_estimate_shapley_values_symmetry_approximation_via_early_stopping": 0.2916524889988068, - "tests/gcm/test_shapley.py::test_estimate_shapley_values_symmetry_approximation_via_early_stopping_with_random_seed": 2.206780909000372, - "tests/gcm/test_shapley.py::test_estimate_shapley_values_symmetry_approximation_via_permutation_with_random_seed": 3.5830478360003326, - "tests/gcm/test_shapley.py::test_estimate_shapley_values_symmetry_approximation_via_subset": 0.7485893240009318, - "tests/gcm/test_shapley.py::test_estimate_shapley_values_symmetry_approximation_via_subset_with_random_seed": 3.2098093750028056, - "tests/gcm/test_shapley.py::test_estimate_shapley_values_symmetry_exact": 8.105218070999399, - "tests/gcm/test_shapley.py::test_estimate_shapley_values_symmetry_exact_fast": 6.525596875999327, - "tests/gcm/test_shapley.py::test_evaluate_set_function_via_shapley_symmetry_approximation_via_permutation": 0.8665359029946558, - "tests/gcm/test_shapley.py::test_given_few_features_when_estimate_shapley_values_with_auto_approx_then_returns_correct_result": 0.003006461000040872, - "tests/gcm/test_shapley.py::test_given_many_features_when_estimate_shapley_values_with_auto_approx_then_returns_correct_result": 0.04127842900561518, - "tests/gcm/test_stats.py::test_estimate_geometric_median": 0.003749911000340944, - "tests/gcm/test_stats.py::test_given_different_batch_sizes_when_estimating_marginal_expectation_then_returns_expected_result": 0.12773612499950104, - "tests/gcm/test_stats.py::test_given_linear_dependent_data_when_estimate_ftest_pvalue_then_returns_expected_result": 0.0013709800005017314, - "tests/gcm/test_stats.py::test_given_multivariate_dependent_data_when_estimate_ftest_pvalue_then_returns_expected_result": 0.001504758998635225, - "tests/gcm/test_stats.py::test_given_p_values_with_nans_when_using_quantile_based_fwer_then_ignores_the_nan_values": 0.00038718799987691455, - "tests/gcm/test_stats.py::test_marginal_expectation_independent_categorical_linear": 0.19481896700017387, - "tests/gcm/test_stats.py::test_marginal_expectation_independent_categorical_nonlinear": 3.155934750004235, - "tests/gcm/test_stats.py::test_marginal_expectation_independent_continuous_linear": 0.229990669999097, - "tests/gcm/test_stats.py::test_marginal_expectation_independent_continuous_nonlinear": 3.869605367999611, - "tests/gcm/test_stats.py::test_marginal_expectation_returns_all_results": 0.016676576000463683, - "tests/gcm/test_stats.py::test_marginal_expectation_returns_reduced_results": 0.03466918100093608, - "tests/gcm/test_stats.py::test_quantile_based_fwer": 0.0008770439999352675, - "tests/gcm/test_stats.py::test_quantile_based_fwer_raises_error": 0.00033082900336012244, - "tests/gcm/test_stats.py::test_quantile_based_fwer_scaling": 0.0005289260006975383, - "tests/gcm/test_stochastic_models.py::test_bayesian_gaussian_mixture_distribution": 0.11869163300070795, - "tests/gcm/test_stochastic_models.py::test_bayesian_gaussian_mixture_distribution_runtime_error": 0.0005404119983722921, - "tests/gcm/test_stochastic_models.py::test_empirical_distribution": 0.3082659879983112, - "tests/gcm/test_stochastic_models.py::test_fitted_parameters_assigned_correctly_using_beta_distribution": 0.09166112499588053, - "tests/gcm/test_stochastic_models.py::test_fitted_parameters_assigned_correctly_using_normal_distribution": 0.000768283996876562, - "tests/gcm/test_stochastic_models.py::test_scipy_auto_select_continuous_parametric_distribution": 0.005523714000446489, - "tests/gcm/test_stochastic_models.py::test_scipy_fittable_parametric_distribution": 0.0005317560026014689, - "tests/gcm/test_stochastic_models.py::test_scipy_fixed_parametric_distribution": 0.0003344569995533675, - "tests/gcm/test_uncertainty.py::test_estimate_entropy_discrete": 0.0010040130036941264, - "tests/gcm/test_uncertainty.py::test_estimate_entropy_kmeans": 0.11172045399507624, - "tests/gcm/test_uncertainty.py::test_estimate_entropy_of_probabilities": 0.00047356600043713115, - "tests/gcm/test_uncertainty.py::test_estimate_entropy_using_discretization": 0.0017287959999521263, - "tests/gcm/test_uncertainty.py::test_estimate_gaussian_entropy": 0.0007188839954324067, - "tests/gcm/test_uncertainty.py::test_estimate_variance": 0.1497926180018112, - "tests/gcm/test_validation.py::test_given_non_linear_data_and_correct_dag_when_refute_invertible_model_then_not_reject_model": 5.803969453001628, - "tests/gcm/test_validation.py::test_given_non_linear_data_and_incorrect_dag_when_refute_invertible_model_then_reject_model": 5.037821076999535, - "tests/gcm/test_validation.py::test_given_non_linear_data_and_incorrect_dag_with_collider_when_refute_invertible_model_then_reject_model": 6.595124856998154, - "tests/gcm/test_validation.py::test_refute_causal_structure_adjusted_p_values": 0.9631542310016812, - "tests/gcm/test_validation.py::test_refute_causal_structure_chain": 0.20382860899917432, - "tests/gcm/test_validation.py::test_refute_causal_structure_collider": 0.029991837000125088, - "tests/gcm/test_validation.py::test_refute_causal_structure_fork": 0.5995468189976236, - "tests/gcm/test_validation.py::test_refute_causal_structure_general": 0.04577041499942425, - "tests/gcm/test_validation.py::test_when_using_refute_causal_structure_without_fdrc_then_nans_for_adjusted_p_values_are_returned": 0.33601710599759826, - "tests/gcm/test_whatif.py::test_counterfactual_samples_raises_error_all_parameter_none": 0.003792122002778342, - "tests/gcm/test_whatif.py::test_counterfactual_samples_raises_error_both_parameter_given": 0.0040026999995461665, - "tests/gcm/test_whatif.py::test_counterfactual_samples_with_noise_samples": 0.0053520000001299195, - "tests/gcm/test_whatif.py::test_counterfactual_samples_with_observed_samples": 0.007056922004267108, - "tests/gcm/test_whatif.py::test_given_binary_target_when_estimate_average_causal_effect_then_return_expected_result": 0.42823138600215316, - "tests/gcm/test_whatif.py::test_given_continuous_target_when_estimate_average_causal_effect_then_return_expected_result": 0.812088416001643, - "tests/gcm/test_whatif.py::test_interventional_samples_atomic": 0.008358578001207206, - "tests/gcm/test_whatif.py::test_interventional_samples_atomic_draw": 0.0109674770028505, - "tests/gcm/test_whatif.py::test_interventional_samples_atomic_multiple_interventions": 0.0057828280005196575, - "tests/gcm/test_whatif.py::test_interventional_samples_conditional": 0.008653826003865106, - "tests/gcm/test_whatif.py::test_interventional_samples_conditional_draw": 0.010875829004362458, - "tests/gcm/test_whatif.py::test_interventional_samples_raise_error_all_parameter_none": 0.003524371000821702, - "tests/gcm/test_whatif.py::test_interventional_samples_raise_error_both_parameter_given": 0.003893631997925695, - "tests/gcm/test_whatif.py::test_interventional_samples_with_categorical_variables_draw": 0.018410912998660933, - "tests/gcm/util/test_plotting.py::test_plot_adjacency_matrix": 0.017139122002845397, - "tests/gcm/util/test_plotting.py::test_when_plot_does_not_raise_exception": 0.06699552199643222, - "tests/gcm/util/test_pygraphviz.py::test_calc_arrow_width": 0.00036200900285621174, - "tests/test_causal_estimator.py::test_causal_estimator_placeholder_methods": 0.00047312800234067254, - "tests/test_causal_model.py::TestCausalModel::test_external_estimator[10-100-1]": 0.8277756619972934, - "tests/test_causal_model.py::TestCausalModel::test_graph_input2[10-1-100-1]": 0.004107875000045169, - "tests/test_causal_model.py::TestCausalModel::test_graph_input3[10-1-100-1]": 0.004984627998055657, - "tests/test_causal_model.py::TestCausalModel::test_graph_input4[10-1-100-1]": 0.004323232999013271, - "tests/test_causal_model.py::TestCausalModel::test_graph_input[10-1-100-1]": 0.00443547199756722, - "tests/test_causal_model.py::TestCausalModel::test_graph_refutation2[10-5000]": 2.546336801999132, - "tests/test_causal_model.py::TestCausalModel::test_graph_refutation[10-5000]": 0.38944244000231265, - "tests/test_causal_refuter.py::test_causal_refuter_bootstrap_test": 0.0005493779972312041, - "tests/test_causal_refuter.py::test_causal_refuter_placeholder_method": 0.00032829900010256097, - "tests/test_data_transformer.py::test_dimensionality_reducer_placeholder_methods": 0.00022748899937141687, + "tests/gcm/test_fcms.py::test_when_clone_additive_noise_models_with_scipy_distribution_then_clone_has_correct_models": 0.0022859580003569135, + "tests/gcm/test_fcms.py::test_when_draw_from_classifier_fcm_then_returns_string_samples": 0.00800903900017147, + "tests/gcm/test_fcms.py::test_when_fit_classifier_fcm_with_categorical_inputs_then_returns_expected_results": 0.011222037999687018, + "tests/gcm/test_feature.py::test_feature_relevance_sample_mean_diff": 0.9340454179982771, + "tests/gcm/test_feature.py::test_feature_relevance_sample_mean_diff_with_certain_batch_size": 0.1313322430014523, + "tests/gcm/test_feature.py::test_given_baseline_values_when_estimating_feature_relevance_sample_with_mean_diff_then_returns_expected_result": 0.3403174660015793, + "tests/gcm/test_feature.py::test_given_misspecified_graph_when_estimating_parent_relevance_with_observed_data_then_returns_correct_result": 22.445173250998778, + "tests/gcm/test_feature.py::test_when_using_feature_relevance_distribution_with_entropy_set_function_then_returns_correct_results": 0.7777337800016539, + "tests/gcm/test_feature.py::test_when_using_parent_relevance_with_categorical_data_then_returns_correct_results": 19.896863140002097, + "tests/gcm/test_feature.py::test_when_using_parent_relevance_with_confidence_intervals_then_returns_reasonable_bounds": 9.796963109998615, + "tests/gcm/test_feature.py::test_when_using_parent_relevance_with_continous_data_then_returns_correct_results": 0.9760240809991956, + "tests/gcm/test_graph.py::test_fit_and_draw_samples": 0.006999461998930201, + "tests/gcm/test_graph.py::test_is_root_node": 0.0003289969990873942, + "tests/gcm/test_graph.py::test_set_causal_model_raises_error": 0.00037695599894504994, + "tests/gcm/test_intrinsic_influence.py::test_given_only_categorical_data_when_estimate_icc_then_does_not_fail": 57.989755541000704, + "tests/gcm/test_intrinsic_influence.py::test_intrinsic_causal_influence_categorical": 53.30633696399855, + "tests/gcm/test_intrinsic_influence.py::test_intrinsic_causal_influence_categorical_2": 39.327678016999926, + "tests/gcm/test_intrinsic_influence.py::test_intrinsic_causal_influence_variance_linear": 38.00465657899986, + "tests/gcm/test_intrinsic_influence.py::test_when_calling_intrinsic_causal_influence_then_the_shape_of_inputs_in_the_attribution_function_should_be_equal": 18.991308744998605, + "tests/gcm/test_ml.py::test_categorical_features": 0.006344903002172941, + "tests/gcm/test_ml.py::test_categorical_inputs": 0.007466925000699121, + "tests/gcm/test_ml.py::test_when_cloning_sklearn_classification_model_then_returns_a_cloned_object": 0.0004838210006710142, + "tests/gcm/test_shapley.py::test_estimate_shapley_values_symmetry_approximation_via_early_stopping": 0.675727908999761, + "tests/gcm/test_shapley.py::test_estimate_shapley_values_symmetry_approximation_via_early_stopping_with_random_seed": 2.5750011860000086, + "tests/gcm/test_shapley.py::test_estimate_shapley_values_symmetry_approximation_via_permutation_with_random_seed": 3.466346587998487, + "tests/gcm/test_shapley.py::test_estimate_shapley_values_symmetry_approximation_via_subset": 0.7537785750009789, + "tests/gcm/test_shapley.py::test_estimate_shapley_values_symmetry_approximation_via_subset_with_random_seed": 3.07799904499916, + "tests/gcm/test_shapley.py::test_estimate_shapley_values_symmetry_exact": 8.23336829300024, + "tests/gcm/test_shapley.py::test_estimate_shapley_values_symmetry_exact_fast": 6.592175635998501, + "tests/gcm/test_shapley.py::test_evaluate_set_function_via_shapley_symmetry_approximation_via_permutation": 0.8430921929993929, + "tests/gcm/test_shapley.py::test_given_few_features_when_estimate_shapley_values_with_auto_approx_then_returns_correct_result": 0.0038017719980416587, + "tests/gcm/test_shapley.py::test_given_many_features_when_estimate_shapley_values_with_auto_approx_then_returns_correct_result": 0.10425491199930548, + "tests/gcm/test_stats.py::test_estimate_geometric_median": 0.004048476999741979, + "tests/gcm/test_stats.py::test_given_different_batch_sizes_when_estimating_marginal_expectation_then_returns_expected_result": 0.12518689300122787, + "tests/gcm/test_stats.py::test_given_linear_dependent_data_when_estimate_ftest_pvalue_then_returns_expected_result": 0.0015984810015652329, + "tests/gcm/test_stats.py::test_given_multivariate_dependent_data_when_estimate_ftest_pvalue_then_returns_expected_result": 0.0016053010022005765, + "tests/gcm/test_stats.py::test_given_p_values_with_nans_when_using_quantile_based_fwer_then_ignores_the_nan_values": 0.00037483099913515616, + "tests/gcm/test_stats.py::test_marginal_expectation_independent_categorical_linear": 0.18587543800094863, + "tests/gcm/test_stats.py::test_marginal_expectation_independent_categorical_nonlinear": 56.26012143300068, + "tests/gcm/test_stats.py::test_marginal_expectation_independent_continuous_linear": 0.2658739599992259, + "tests/gcm/test_stats.py::test_marginal_expectation_independent_continuous_nonlinear": 40.81410756399964, + "tests/gcm/test_stats.py::test_marginal_expectation_returns_all_results": 0.01936461700097425, + "tests/gcm/test_stats.py::test_marginal_expectation_returns_reduced_results": 0.029648808000274585, + "tests/gcm/test_stats.py::test_quantile_based_fwer": 0.0008437809992756229, + "tests/gcm/test_stats.py::test_quantile_based_fwer_raises_error": 0.0003298399988125311, + "tests/gcm/test_stats.py::test_quantile_based_fwer_scaling": 0.000547830999494181, + "tests/gcm/test_stochastic_models.py::test_bayesian_gaussian_mixture_distribution": 0.07944374699945911, + "tests/gcm/test_stochastic_models.py::test_bayesian_gaussian_mixture_distribution_runtime_error": 0.00045383999713521916, + "tests/gcm/test_stochastic_models.py::test_empirical_distribution": 0.30704421600057685, + "tests/gcm/test_stochastic_models.py::test_fitted_parameters_assigned_correctly_using_beta_distribution": 0.12220136099858792, + "tests/gcm/test_stochastic_models.py::test_fitted_parameters_assigned_correctly_using_normal_distribution": 0.0007490899988624733, + "tests/gcm/test_stochastic_models.py::test_scipy_auto_select_continuous_parametric_distribution": 0.32287205799912044, + "tests/gcm/test_stochastic_models.py::test_scipy_fittable_parametric_distribution": 0.000533110001924797, + "tests/gcm/test_stochastic_models.py::test_scipy_fixed_parametric_distribution": 0.0003421000019443454, + "tests/gcm/test_uncertainty.py::test_estimate_entropy_discrete": 0.0011733400006050942, + "tests/gcm/test_uncertainty.py::test_estimate_entropy_kmeans": 0.11020228700181178, + "tests/gcm/test_uncertainty.py::test_estimate_entropy_of_probabilities": 0.0005798410002171295, + "tests/gcm/test_uncertainty.py::test_estimate_entropy_using_discretization": 0.0018264999980601715, + "tests/gcm/test_uncertainty.py::test_estimate_gaussian_entropy": 0.0007306910010811407, + "tests/gcm/test_uncertainty.py::test_estimate_variance": 0.1536971050009015, + "tests/gcm/test_validation.py::test_given_non_linear_data_and_correct_dag_when_refute_invertible_model_then_not_reject_model": 30.215193159998307, + "tests/gcm/test_validation.py::test_given_non_linear_data_and_incorrect_dag_when_refute_invertible_model_then_reject_model": 16.495497463998618, + "tests/gcm/test_validation.py::test_given_non_linear_data_and_incorrect_dag_with_collider_when_refute_invertible_model_then_reject_model": 14.271690126999601, + "tests/gcm/test_validation.py::test_refute_causal_structure_adjusted_p_values": 0.8805916279980011, + "tests/gcm/test_validation.py::test_refute_causal_structure_chain": 0.35697386999891023, + "tests/gcm/test_validation.py::test_refute_causal_structure_collider": 0.023211495001305593, + "tests/gcm/test_validation.py::test_refute_causal_structure_fork": 1.0799866790039232, + "tests/gcm/test_validation.py::test_refute_causal_structure_general": 0.04712397700131987, + "tests/gcm/test_validation.py::test_when_using_refute_causal_structure_without_fdrc_then_nans_for_adjusted_p_values_are_returned": 0.7557343110020156, + "tests/gcm/test_whatif.py::test_counterfactual_samples_raises_error_all_parameter_none": 0.005386669001381961, + "tests/gcm/test_whatif.py::test_counterfactual_samples_raises_error_both_parameter_given": 0.0040787509988149395, + "tests/gcm/test_whatif.py::test_counterfactual_samples_with_noise_samples": 0.00703999400138855, + "tests/gcm/test_whatif.py::test_counterfactual_samples_with_observed_samples": 0.00909313500051212, + "tests/gcm/test_whatif.py::test_given_binary_target_when_estimate_average_causal_effect_then_return_expected_result": 5.736080510998363, + "tests/gcm/test_whatif.py::test_given_continuous_target_when_estimate_average_causal_effect_then_return_expected_result": 7.400701212001877, + "tests/gcm/test_whatif.py::test_interventional_samples_atomic": 0.005556936001084978, + "tests/gcm/test_whatif.py::test_interventional_samples_atomic_draw": 0.006262816999878851, + "tests/gcm/test_whatif.py::test_interventional_samples_atomic_multiple_interventions": 0.009842175000812858, + "tests/gcm/test_whatif.py::test_interventional_samples_conditional": 0.0048610239991830895, + "tests/gcm/test_whatif.py::test_interventional_samples_conditional_draw": 0.006809946999055683, + "tests/gcm/test_whatif.py::test_interventional_samples_raise_error_all_parameter_none": 0.004740374997709296, + "tests/gcm/test_whatif.py::test_interventional_samples_raise_error_both_parameter_given": 0.006484949999503442, + "tests/gcm/test_whatif.py::test_interventional_samples_with_categorical_variables_draw": 0.06180697300260363, + "tests/gcm/util/test_general.py::test_given_categorical_data_when_evaluating_has_categorical_then_returns_expected_result": 0.0008290509995276807, + "tests/gcm/util/test_general.py::test_given_categorical_data_when_evaluating_is_categorical_then_returns_expected_result": 0.0012246000005688984, + "tests/gcm/util/test_plotting.py::test_plot_adjacency_matrix": 0.017390742999850772, + "tests/gcm/util/test_plotting.py::test_when_plot_does_not_raise_exception": 0.07301370699860854, + "tests/gcm/util/test_pygraphviz.py::test_calc_arrow_width": 0.0003234109990444267, + "tests/test_causal_estimator.py::test_causal_estimator_placeholder_methods": 0.0004471669981285231, + "tests/test_causal_model.py::TestCausalModel::test_external_estimator[10-100-1]": 0.8948007010003494, + "tests/test_causal_model.py::TestCausalModel::test_graph_input2[10-1-100-1]": 0.0038136530019983184, + "tests/test_causal_model.py::TestCausalModel::test_graph_input3[10-1-100-1]": 0.004221674000291387, + "tests/test_causal_model.py::TestCausalModel::test_graph_input4[10-1-100-1]": 0.0038689320026605856, + "tests/test_causal_model.py::TestCausalModel::test_graph_input[10-1-100-1]": 0.004279080003470881, + "tests/test_causal_model.py::TestCausalModel::test_graph_refutation2[10-5000]": 2.5579186659997504, + "tests/test_causal_model.py::TestCausalModel::test_graph_refutation[10-5000]": 0.38690518799921847, + "tests/test_causal_refuter.py::test_causal_refuter_bootstrap_test": 0.0005826579981658142, + "tests/test_causal_refuter.py::test_causal_refuter_placeholder_method": 0.0003741770015039947, + "tests/test_data_transformer.py::test_dimensionality_reducer_placeholder_methods": 0.00023744900136080105, "tests/test_notebooks.py::test_notebook[DoWhy-The Causal Story Behind Hotel Booking Cancellations.ipynb]": 269.5888159609967, "tests/test_notebooks.py::test_notebook[do_sampler_demo.ipynb]": 3.0448386579955695, - "tests/test_notebooks.py::test_notebook[dowhy-conditional-treatment-effects.ipynb]": 333.77691264999885, - "tests/test_notebooks.py::test_notebook[dowhy-simple-iv-example.ipynb]": 4.564906564999546, - "tests/test_notebooks.py::test_notebook[dowhy_causal_api.ipynb]": 3.4215711319993716, + "tests/test_notebooks.py::test_notebook[dowhy-conditional-treatment-effects.ipynb]": 330.1932206170004, + "tests/test_notebooks.py::test_notebook[dowhy-simple-iv-example.ipynb]": 5.2607425800015335, + "tests/test_notebooks.py::test_notebook[dowhy_causal_api.ipynb]": 3.450208180000118, "tests/test_notebooks.py::test_notebook[dowhy_causal_discovery_example.ipynb]": 3.559609330997773, - "tests/test_notebooks.py::test_notebook[dowhy_confounder_example.ipynb]": 9.348463070993603, - "tests/test_notebooks.py::test_notebook[dowhy_demo_dummy_outcome_refuter.ipynb]": 5.399920256997575, - "tests/test_notebooks.py::test_notebook[dowhy_efficient_backdoor_example.ipynb]": 2.960695682999358, - "tests/test_notebooks.py::test_notebook[dowhy_estimation_methods.ipynb]": 6.683948532001523, - "tests/test_notebooks.py::test_notebook[dowhy_example_effect_of_memberrewards_program.ipynb]": 21.221713907005324, - "tests/test_notebooks.py::test_notebook[dowhy_ihdp_data_example.ipynb]": 14.597732170997915, - "tests/test_notebooks.py::test_notebook[dowhy_interpreter.ipynb]": 6.791981726000813, + "tests/test_notebooks.py::test_notebook[dowhy_confounder_example.ipynb]": 8.938289206002082, + "tests/test_notebooks.py::test_notebook[dowhy_demo_dummy_outcome_refuter.ipynb]": 5.1057545250005205, + "tests/test_notebooks.py::test_notebook[dowhy_efficient_backdoor_example.ipynb]": 3.6536705840007926, + "tests/test_notebooks.py::test_notebook[dowhy_estimation_methods.ipynb]": 6.895480563000092, + "tests/test_notebooks.py::test_notebook[dowhy_example_effect_of_memberrewards_program.ipynb]": 20.268174654001996, + "tests/test_notebooks.py::test_notebook[dowhy_functional_api.ipynb]": 39.91400131500268, + "tests/test_notebooks.py::test_notebook[dowhy_ihdp_data_example.ipynb]": 16.125613112000792, + "tests/test_notebooks.py::test_notebook[dowhy_interpreter.ipynb]": 6.770195254999635, "tests/test_notebooks.py::test_notebook[dowhy_lalonde_example.ipynb]": 3.583001503997366, - "tests/test_notebooks.py::test_notebook[dowhy_mediation_analysis.ipynb]": 3.145783426003618, - "tests/test_notebooks.py::test_notebook[dowhy_multiple_treatments.ipynb]": 2.924541534997843, + "tests/test_notebooks.py::test_notebook[dowhy_mediation_analysis.ipynb]": 3.3798217410003417, + "tests/test_notebooks.py::test_notebook[dowhy_multiple_treatments.ipynb]": 4.499033778000012, "tests/test_notebooks.py::test_notebook[dowhy_optimize_backdoor_example.ipynb]": 2.357267290004529, "tests/test_notebooks.py::test_notebook[dowhy_ranking_methods.ipynb]": 0.6213478449972172, "tests/test_notebooks.py::test_notebook[dowhy_refutation_testing.ipynb]": 60.58798760599893, - "tests/test_notebooks.py::test_notebook[dowhy_refuter_notebook.ipynb]": 410.8002465810023, - "tests/test_notebooks.py::test_notebook[dowhy_simple_example.ipynb]": 107.64207525600068, - "tests/test_notebooks.py::test_notebook[dowhy_twins_example.ipynb]": 514.2033587900005, - "tests/test_notebooks.py::test_notebook[gcm_401k_analysis.ipynb]": 38.251963464001165, - "tests/test_notebooks.py::test_notebook[gcm_basic_example.ipynb]": 3.863724312999693, - "tests/test_notebooks.py::test_notebook[gcm_counterfactual_medical_dry_eyes.ipynb]": 3.8575890449974395, - "tests/test_notebooks.py::test_notebook[gcm_draw_samples.ipynb]": 3.8037730070027465, - "tests/test_notebooks.py::test_notebook[gcm_rca_microservice_architecture.ipynb]": 153.4997832049994, - "tests/test_notebooks.py::test_notebook[gcm_supply_chain_dist_change.ipynb]": 178.38158313500026, - "tests/test_notebooks.py::test_notebook[graph_conditional_independence_refuter.ipynb]": 4.069151714997133, - "tests/test_notebooks.py::test_notebook[identifying_effects_using_id_algorithm.ipynb]": 2.658960433000175, + "tests/test_notebooks.py::test_notebook[dowhy_refuter_notebook.ipynb]": 386.7324736619976, + "tests/test_notebooks.py::test_notebook[dowhy_simple_example.ipynb]": 108.74308741299865, + "tests/test_notebooks.py::test_notebook[dowhy_twins_example.ipynb]": 497.4862356700014, + "tests/test_notebooks.py::test_notebook[gcm_401k_analysis.ipynb]": 39.396144726000784, + "tests/test_notebooks.py::test_notebook[gcm_basic_example.ipynb]": 8.232354712001325, + "tests/test_notebooks.py::test_notebook[gcm_counterfactual_medical_dry_eyes.ipynb]": 7.381902852001076, + "tests/test_notebooks.py::test_notebook[gcm_draw_samples.ipynb]": 8.667402456001582, + "tests/test_notebooks.py::test_notebook[gcm_rca_microservice_architecture.ipynb]": 100.56638710100015, + "tests/test_notebooks.py::test_notebook[gcm_supply_chain_dist_change.ipynb]": 197.49963043499883, + "tests/test_notebooks.py::test_notebook[graph_conditional_independence_refuter.ipynb]": 4.700006441998994, + "tests/test_notebooks.py::test_notebook[identifying_effects_using_id_algorithm.ipynb]": 3.2308513859989034, "tests/test_notebooks.py::test_notebook[lalonde_pandas_api.ipynb]": 3.8229689540021354, - "tests/test_notebooks.py::test_notebook[load_graph_example.ipynb]": 2.4960804089969315, - "tests/test_notebooks.py::test_notebook[sensitivity_analysis_testing.ipynb]": 14.854635226998653, - "tests/test_notebooks.py::test_notebook[tutorial-causalinference-machinelearning-using-dowhy-econml.ipynb]": 196.1131719360019 + "tests/test_notebooks.py::test_notebook[load_graph_example.ipynb]": 3.1312964820008347, + "tests/test_notebooks.py::test_notebook[sensitivity_analysis_nonparametric_estimators.ipynb]": 28.16567199399833, + "tests/test_notebooks.py::test_notebook[sensitivity_analysis_testing.ipynb]": 15.355559879000793, + "tests/test_notebooks.py::test_notebook[tutorial-causalinference-machinelearning-using-dowhy-econml.ipynb]": 195.6636093420002 } \ No newline at end of file diff --git a/tests/causal_refuters/test_data_subset_refuter.py b/tests/causal_refuters/test_data_subset_refuter.py index fb1f34d47..a7bc7a1ff 100644 --- a/tests/causal_refuters/test_data_subset_refuter.py +++ b/tests/causal_refuters/test_data_subset_refuter.py @@ -1,5 +1,4 @@ import numpy as np -import pytest from pytest import mark from .base import TestRefuter @@ -12,7 +11,6 @@ class TestDataSubsetRefuter(object): refuter_tester = TestRefuter(error_tolerance, estimator_method, "data_subset_refuter") refuter_tester.continuous_treatment_testsuite() # Run both - @mark.advanced @mark.parametrize(["error_tolerance", "estimator_method"], [(0.01, "backdoor.propensity_score_matching")]) def test_refutation_data_subset_refuter_binary(self, error_tolerance, estimator_method): refuter_tester = TestRefuter(error_tolerance, estimator_method, "data_subset_refuter") diff --git a/tests/gcm/test_anomaly_attribution.py b/tests/gcm/test_anomaly_attribution.py index 81840c66d..c7c99bf90 100644 --- a/tests/gcm/test_anomaly_attribution.py +++ b/tests/gcm/test_anomaly_attribution.py @@ -2,7 +2,7 @@ import networkx as nx import numpy as np import pandas as pd from flaky import flaky -from pytest import approx, mark +from pytest import approx from dowhy.gcm import ( AdditiveNoiseModel, @@ -120,7 +120,6 @@ def test_given_simple_gaussian_data_when_attribute_anomaly_scores_with_feature_r ) -@mark.advanced @flaky(max_runs=3) def test_given_simple_causal_chain_with_linear_relationships_when_attribute_anomaly_scores_with_it_score_then_returns_qualitatively_correct_results(): num_training_samples = 5000 diff --git a/tests/gcm/test_feature.py b/tests/gcm/test_feature.py index 2dca440cc..56dd09331 100644 --- a/tests/gcm/test_feature.py +++ b/tests/gcm/test_feature.py @@ -2,7 +2,7 @@ import networkx as nx import numpy as np import pandas as pd from flaky import flaky -from pytest import approx, mark +from pytest import approx from scipy import stats from dowhy.gcm import ( @@ -44,7 +44,6 @@ def test_when_using_parent_relevance_with_continous_data_then_returns_correct_re assert noise == approx(0, abs=0.5) -@mark.advanced @flaky(max_runs=5) def test_when_using_parent_relevance_with_categorical_data_then_returns_correct_results(): causal_model = StructuralCausalModel(nx.DiGraph([("X0", "Y"), ("X1", "Y"), ("X2", "Y"), ("X3", "Y"), ("X4", "Y")])) diff --git a/tests/gcm/test_intrinsic_influence.py b/tests/gcm/test_intrinsic_influence.py index 1d31a8639..689d83994 100644 --- a/tests/gcm/test_intrinsic_influence.py +++ b/tests/gcm/test_intrinsic_influence.py @@ -2,7 +2,7 @@ import networkx as nx import numpy as np import pandas as pd from flaky import flaky -from pytest import approx, mark +from pytest import approx from sklearn.linear_model import LogisticRegression from dowhy.gcm import StructuralCausalModel, auto, fit, intrinsic_causal_influence @@ -13,7 +13,6 @@ from dowhy.gcm.uncertainty import estimate_entropy_of_probabilities, estimate_va from dowhy.gcm.util.general import apply_one_hot_encoding, fit_one_hot_encoders -@mark.advanced @flaky(max_runs=3) def test_intrinsic_causal_influence_variance_linear(): causal_model = StructuralCausalModel(nx.DiGraph([("X0", "X1"), ("X1", "X2"), ("X2", "X3")])) @@ -42,7 +41,6 @@ def test_intrinsic_causal_influence_variance_linear(): assert np.sum([iccs[key] for key in iccs]) == approx(estimate_variance(X3), abs=0.5) -@mark.advanced @flaky(max_runs=3) def test_intrinsic_causal_influence_categorical(): causal_model = StructuralCausalModel(nx.DiGraph([("X0", "X1"), ("X1", "X2"), ("X2", "X3")])) @@ -86,7 +84,6 @@ def test_intrinsic_causal_influence_categorical(): assert np.sum([iccs[key] for key in iccs]) == approx(-expected_output_empty_subset, abs=0.05) -@mark.advanced @flaky(max_runs=3) def test_intrinsic_causal_influence_categorical_2(): causal_model = StructuralCausalModel(nx.DiGraph([("X0", "X1"), ("X1", "X2"), ("X2", "X3")])) @@ -142,7 +139,6 @@ def test_intrinsic_causal_influence_categorical_2(): assert np.sum([iccs[key] for key in iccs]) == approx(-expected_output_empty_subset, abs=0.05) -@mark.advanced @flaky(max_runs=3) def test_given_only_categorical_data_when_estimate_icc_then_does_not_fail(): causal_model = StructuralCausalModel(nx.DiGraph([("X0", "X1"), ("X1", "X2"), ("X2", "X3")])) diff --git a/tests/gcm/test_stats.py b/tests/gcm/test_stats.py index 7293c9179..e86e42233 100644 --- a/tests/gcm/test_stats.py +++ b/tests/gcm/test_stats.py @@ -2,7 +2,7 @@ import numpy as np import pytest from flaky import flaky from numpy.matlib import repmat -from pytest import approx, mark +from pytest import approx from dowhy.gcm.ml import ( create_hist_gradient_boost_classifier, @@ -97,7 +97,6 @@ def test_marginal_expectation_returns_reduced_results(): assert results.shape[1] == 1 -@mark.advanced @flaky(max_runs=5) def test_marginal_expectation_independent_continuous_linear(): X = np.random.normal(0, 1, (1000, 3)) diff --git a/tests/gcm/test_validation.py b/tests/gcm/test_validation.py index 26ce3cd98..5d9162ad3 100644 --- a/tests/gcm/test_validation.py +++ b/tests/gcm/test_validation.py @@ -2,7 +2,6 @@ import networkx as nx import numpy as np import pandas as pd from flaky import flaky -from pytest import mark from dowhy.gcm import ( InvertibleStructuralCausalModel, @@ -174,7 +173,6 @@ def test_given_non_linear_data_and_correct_dag_when_refute_invertible_model_then ) -@mark.advanced @flaky(max_runs=2) def test_given_non_linear_data_and_incorrect_dag_when_refute_invertible_model_then_reject_model(): data = _generate_simple_non_linear_data() @@ -201,7 +199,6 @@ def test_given_non_linear_data_and_incorrect_dag_when_refute_invertible_model_th ) -@mark.advanced @flaky(max_runs=3) def test_given_non_linear_data_and_incorrect_dag_with_collider_when_refute_invertible_model_then_reject_model(): data = _generate_simple_non_linear_data() diff --git a/tests/test_notebooks.py b/tests/test_notebooks.py index 9a39b7cf3..024293e7a 100644 --- a/tests/test_notebooks.py +++ b/tests/test_notebooks.py @@ -19,13 +19,14 @@ advanced_notebooks = [ "dowhy_optimize_backdoor_example.ipynb", # applied notebook, not necessary to test each time "dowhy_ranking_methods.ipynb", + # needs xgboost too + "DoWhy-The Causal Story Behind Hotel Booking Cancellations.ipynb", # # Slow Notebooks # "tutorial-causalinference-machinelearning-using-dowhy-econml.ipynb", "dowhy-conditional-treatment-effects.ipynb", "dowhy_refuter_notebook.ipynb", - "DoWhy-The Causal Story Behind Hotel Booking Cancellations.ipynb", # needs xgboost too "dowhy_twins_example.ipynb", "gcm_rca_microservice_architecture.ipynb", "gcm_supply_chain_dist_change.ipynb",