def test_combine_experiments_wrong_multiple():
"""Test the combination of experimental results for different
datasets, oversamplers and classifiers and scoring."""
# Clone and fit experiments
experiment1 = (clone(EXPERIMENT).set_params(
oversamplers=[('bsmote', BorderlineSMOTE(), {
'k_neighbors': [2, 5]
})],
classifiers=[('gbc', GradientBoostingClassifier(), {})],
scoring='f1',
).fit(DATASETS[:-1]))
experiment2 = clone(EXPERIMENT).fit(DATASETS[-1:])
with pytest.raises(ValueError):
combine_results(experiment1.results_, experiment2.results_)
def test_combine_results_multiple():
"""Test the combination of experimental results for different
datasets, oversamplers and classifiers."""
# Clone and fit experiments
experiment1 = (clone(EXPERIMENT).set_params(
oversamplers=[('bsmote', BorderlineSMOTE(), {
'k_neighbors': [2, 5]
})],
classifiers=[('gbc', GradientBoostingClassifier(), {})],
scoring=['accuracy', 'f1'],
).fit(DATASETS[:-1]))
experiment2 = (clone(EXPERIMENT).set_params(
scoring=['accuracy', 'f1']).fit(DATASETS[-1:]))
# Extract combined results
combined_results = combine_results(experiment1.results_,
experiment2.results_)
results = combined_results.reset_index()
# Assertions
assert set(results.Dataset) == {'A', 'B', 'C'}
assert set(results.Oversampler) == {'random', 'smote', 'bsmote'}
assert set(results.Classifier) == {'dtc', 'knc', 'gbc'}
assert set([scorer[0] for scorer in combined_results.columns
]) == set(['accuracy', 'f1'])
pd.testing.assert_frame_equal(
combined_results,
pd.concat([experiment1.results_, experiment2.results_]).sort_index(),
)
def test_combine_results_datasets():
"""Test the combination of experimental results for different datasets."""
# Clone and fit experiments
experiment1 = clone(EXPERIMENT).fit(DATASETS[:-1])
experiment2 = clone(EXPERIMENT).fit(DATASETS[-1:])
# Extract combined results
combined_results = combine_results(experiment1.results_,
experiment2.results_)
results = combined_results.reset_index()
# Assertions
assert set(results.Dataset) == {'A', 'B', 'C'}
assert set(results.Oversampler) == {'random', 'smote'}
assert set(results.Classifier) == {'dtc', 'knc'}
assert set([scorer[0]
for scorer in combined_results.columns]) == set(['accuracy'])
pd.testing.assert_frame_equal(
combined_results,
pd.concat([experiment1.results_, experiment2.results_]).sort_index(),
)