Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
209 changes: 209 additions & 0 deletions tests/mock_data/clustering_tasks.xml
Original file line number Diff line number Diff line change
@@ -0,0 +1,209 @@
<oml:tasks xmlns:oml="http://openml.org/openml">
<oml:task>
<oml:task_id>126033</oml:task_id>
<oml:task_type_id>5</oml:task_type_id>
<oml:task_type>Clustering</oml:task_type>
<oml:did>2</oml:did>
<oml:name>anneal</oml:name>
<oml:status>active</oml:status>
<oml:format>ARFF</oml:format>
<oml:input name="estimation_procedure">17</oml:input>
<oml:input name="source_data">2</oml:input>
<oml:quality name="MajorityClassSize">684.0</oml:quality>
<oml:quality name="MaxNominalAttDistinctValues">7.0</oml:quality>
<oml:quality name="MinorityClassSize">8.0</oml:quality>
<oml:quality name="NumberOfClasses">5.0</oml:quality>
<oml:quality name="NumberOfFeatures">39.0</oml:quality>
<oml:quality name="NumberOfInstances">898.0</oml:quality>
<oml:quality name="NumberOfInstancesWithMissingValues">898.0</oml:quality>
<oml:quality name="NumberOfMissingValues">22175.0</oml:quality>
<oml:quality name="NumberOfNumericFeatures">6.0</oml:quality>
<oml:quality name="NumberOfSymbolicFeatures">33.0</oml:quality>
</oml:task>
<oml:task>
<oml:task_id>126034</oml:task_id>
<oml:task_type_id>5</oml:task_type_id>
<oml:task_type>Clustering</oml:task_type>
<oml:did>3</oml:did>
<oml:name>kr-vs-kp</oml:name>
<oml:status>active</oml:status>
<oml:format>ARFF</oml:format>
<oml:input name="estimation_procedure">17</oml:input>
<oml:input name="source_data">3</oml:input>
<oml:quality name="MajorityClassSize">1669.0</oml:quality>
<oml:quality name="MaxNominalAttDistinctValues">3.0</oml:quality>
<oml:quality name="MinorityClassSize">1527.0</oml:quality>
<oml:quality name="NumberOfClasses">2.0</oml:quality>
<oml:quality name="NumberOfFeatures">37.0</oml:quality>
<oml:quality name="NumberOfInstances">3196.0</oml:quality>
<oml:quality name="NumberOfInstancesWithMissingValues">0.0</oml:quality>
<oml:quality name="NumberOfMissingValues">0.0</oml:quality>
<oml:quality name="NumberOfNumericFeatures">0.0</oml:quality>
<oml:quality name="NumberOfSymbolicFeatures">37.0</oml:quality>
</oml:task>
<oml:task>
<oml:task_id>126035</oml:task_id>
<oml:task_type_id>5</oml:task_type_id>
<oml:task_type>Clustering</oml:task_type>
<oml:did>4</oml:did>
<oml:name>labor</oml:name>
<oml:status>active</oml:status>
<oml:format>ARFF</oml:format>
<oml:input name="estimation_procedure">17</oml:input>
<oml:input name="source_data">4</oml:input>
<oml:quality name="MajorityClassSize">37.0</oml:quality>
<oml:quality name="MaxNominalAttDistinctValues">3.0</oml:quality>
<oml:quality name="MinorityClassSize">20.0</oml:quality>
<oml:quality name="NumberOfClasses">2.0</oml:quality>
<oml:quality name="NumberOfFeatures">17.0</oml:quality>
<oml:quality name="NumberOfInstances">57.0</oml:quality>
<oml:quality name="NumberOfInstancesWithMissingValues">56.0</oml:quality>
<oml:quality name="NumberOfMissingValues">326.0</oml:quality>
<oml:quality name="NumberOfNumericFeatures">8.0</oml:quality>
<oml:quality name="NumberOfSymbolicFeatures">9.0</oml:quality>
</oml:task>
<oml:task>
<oml:task_id>126036</oml:task_id>
<oml:task_type_id>5</oml:task_type_id>
<oml:task_type>Clustering</oml:task_type>
<oml:did>5</oml:did>
<oml:name>arrhythmia</oml:name>
<oml:status>active</oml:status>
<oml:format>ARFF</oml:format>
<oml:input name="estimation_procedure">17</oml:input>
<oml:input name="source_data">5</oml:input>
<oml:quality name="MajorityClassSize">245.0</oml:quality>
<oml:quality name="MaxNominalAttDistinctValues">13.0</oml:quality>
<oml:quality name="MinorityClassSize">2.0</oml:quality>
<oml:quality name="NumberOfClasses">13.0</oml:quality>
<oml:quality name="NumberOfFeatures">280.0</oml:quality>
<oml:quality name="NumberOfInstances">452.0</oml:quality>
<oml:quality name="NumberOfInstancesWithMissingValues">384.0</oml:quality>
<oml:quality name="NumberOfMissingValues">408.0</oml:quality>
<oml:quality name="NumberOfNumericFeatures">206.0</oml:quality>
<oml:quality name="NumberOfSymbolicFeatures">74.0</oml:quality>
</oml:task>
<oml:task>
<oml:task_id>126037</oml:task_id>
<oml:task_type_id>5</oml:task_type_id>
<oml:task_type>Clustering</oml:task_type>
<oml:did>6</oml:did>
<oml:name>letter</oml:name>
<oml:status>active</oml:status>
<oml:format>ARFF</oml:format>
<oml:input name="estimation_procedure">17</oml:input>
<oml:input name="source_data">6</oml:input>
<oml:quality name="MajorityClassSize">813.0</oml:quality>
<oml:quality name="MaxNominalAttDistinctValues">26.0</oml:quality>
<oml:quality name="MinorityClassSize">734.0</oml:quality>
<oml:quality name="NumberOfClasses">26.0</oml:quality>
<oml:quality name="NumberOfFeatures">17.0</oml:quality>
<oml:quality name="NumberOfInstances">20000.0</oml:quality>
<oml:quality name="NumberOfInstancesWithMissingValues">0.0</oml:quality>
<oml:quality name="NumberOfMissingValues">0.0</oml:quality>
<oml:quality name="NumberOfNumericFeatures">16.0</oml:quality>
<oml:quality name="NumberOfSymbolicFeatures">1.0</oml:quality>
</oml:task>
<oml:task>
<oml:task_id>126038</oml:task_id>
<oml:task_type_id>5</oml:task_type_id>
<oml:task_type>Clustering</oml:task_type>
<oml:did>7</oml:did>
<oml:name>audiology</oml:name>
<oml:status>active</oml:status>
<oml:format>ARFF</oml:format>
<oml:input name="estimation_procedure">17</oml:input>
<oml:input name="source_data">7</oml:input>
<oml:quality name="MajorityClassSize">57.0</oml:quality>
<oml:quality name="MaxNominalAttDistinctValues">24.0</oml:quality>
<oml:quality name="MinorityClassSize">1.0</oml:quality>
<oml:quality name="NumberOfClasses">24.0</oml:quality>
<oml:quality name="NumberOfFeatures">70.0</oml:quality>
<oml:quality name="NumberOfInstances">226.0</oml:quality>
<oml:quality name="NumberOfInstancesWithMissingValues">222.0</oml:quality>
<oml:quality name="NumberOfMissingValues">317.0</oml:quality>
<oml:quality name="NumberOfNumericFeatures">0.0</oml:quality>
<oml:quality name="NumberOfSymbolicFeatures">70.0</oml:quality>
</oml:task>
<oml:task>
<oml:task_id>126039</oml:task_id>
<oml:task_type_id>5</oml:task_type_id>
<oml:task_type>Clustering</oml:task_type>
<oml:did>8</oml:did>
<oml:name>liver-disorders</oml:name>
<oml:status>active</oml:status>
<oml:format>ARFF</oml:format>
<oml:input name="estimation_procedure">17</oml:input>
<oml:input name="source_data">8</oml:input>
<oml:quality name="NumberOfClasses">0.0</oml:quality>
<oml:quality name="NumberOfFeatures">6.0</oml:quality>
<oml:quality name="NumberOfInstances">345.0</oml:quality>
<oml:quality name="NumberOfInstancesWithMissingValues">0.0</oml:quality>
<oml:quality name="NumberOfMissingValues">0.0</oml:quality>
<oml:quality name="NumberOfNumericFeatures">6.0</oml:quality>
<oml:quality name="NumberOfSymbolicFeatures">0.0</oml:quality>
</oml:task>
<oml:task>
<oml:task_id>126040</oml:task_id>
<oml:task_type_id>5</oml:task_type_id>
<oml:task_type>Clustering</oml:task_type>
<oml:did>9</oml:did>
<oml:name>autos</oml:name>
<oml:status>active</oml:status>
<oml:format>ARFF</oml:format>
<oml:input name="estimation_procedure">17</oml:input>
<oml:input name="source_data">9</oml:input>
<oml:quality name="MajorityClassSize">67.0</oml:quality>
<oml:quality name="MaxNominalAttDistinctValues">22.0</oml:quality>
<oml:quality name="MinorityClassSize">3.0</oml:quality>
<oml:quality name="NumberOfClasses">6.0</oml:quality>
<oml:quality name="NumberOfFeatures">26.0</oml:quality>
<oml:quality name="NumberOfInstances">205.0</oml:quality>
<oml:quality name="NumberOfInstancesWithMissingValues">46.0</oml:quality>
<oml:quality name="NumberOfMissingValues">59.0</oml:quality>
<oml:quality name="NumberOfNumericFeatures">15.0</oml:quality>
<oml:quality name="NumberOfSymbolicFeatures">11.0</oml:quality>
</oml:task>
<oml:task>
<oml:task_id>126041</oml:task_id>
<oml:task_type_id>5</oml:task_type_id>
<oml:task_type>Clustering</oml:task_type>
<oml:did>10</oml:did>
<oml:name>lymph</oml:name>
<oml:status>active</oml:status>
<oml:format>ARFF</oml:format>
<oml:input name="estimation_procedure">17</oml:input>
<oml:input name="source_data">10</oml:input>
<oml:quality name="MajorityClassSize">81.0</oml:quality>
<oml:quality name="MaxNominalAttDistinctValues">8.0</oml:quality>
<oml:quality name="MinorityClassSize">2.0</oml:quality>
<oml:quality name="NumberOfClasses">4.0</oml:quality>
<oml:quality name="NumberOfFeatures">19.0</oml:quality>
<oml:quality name="NumberOfInstances">148.0</oml:quality>
<oml:quality name="NumberOfInstancesWithMissingValues">0.0</oml:quality>
<oml:quality name="NumberOfMissingValues">0.0</oml:quality>
<oml:quality name="NumberOfNumericFeatures">3.0</oml:quality>
<oml:quality name="NumberOfSymbolicFeatures">16.0</oml:quality>
</oml:task>
<oml:task>
<oml:task_id>126042</oml:task_id>
<oml:task_type_id>5</oml:task_type_id>
<oml:task_type>Clustering</oml:task_type>
<oml:did>11</oml:did>
<oml:name>balance-scale</oml:name>
<oml:status>active</oml:status>
<oml:format>ARFF</oml:format>
<oml:input name="estimation_procedure">17</oml:input>
<oml:input name="source_data">11</oml:input>
<oml:quality name="MajorityClassSize">288.0</oml:quality>
<oml:quality name="MaxNominalAttDistinctValues">3.0</oml:quality>
<oml:quality name="MinorityClassSize">49.0</oml:quality>
<oml:quality name="NumberOfClasses">3.0</oml:quality>
<oml:quality name="NumberOfFeatures">5.0</oml:quality>
<oml:quality name="NumberOfInstances">625.0</oml:quality>
<oml:quality name="NumberOfInstancesWithMissingValues">0.0</oml:quality>
<oml:quality name="NumberOfMissingValues">0.0</oml:quality>
<oml:quality name="NumberOfNumericFeatures">4.0</oml:quality>
<oml:quality name="NumberOfSymbolicFeatures">1.0</oml:quality>
</oml:task>
</oml:tasks>
13 changes: 9 additions & 4 deletions tests/test_tasks/test_task_functions.py
Original file line number Diff line number Diff line change
Expand Up @@ -56,10 +56,15 @@ def test__get_estimation_procedure_list(self):
assert isinstance(estimation_procedures[0], dict)
assert estimation_procedures[0]["task_type_id"] == TaskType.SUPERVISED_CLASSIFICATION

@pytest.mark.production_server()
@pytest.mark.xfail(reason="failures_issue_1544", strict=False)
def test_list_clustering_task(self):
self.use_production_server()
@mock.patch("requests.Session.request")
def test_list_clustering_task(self, mock_request):
import pathlib
mock_request.return_value = create_request_response(
status_code=200,
content_filepath=pathlib.Path(__file__).parent.parent
/ "mock_data"
/ "clustering_tasks.xml",
)
# as shown by #383, clustering tasks can give list/dict casting problems
openml.tasks.list_tasks(task_type=TaskType.CLUSTERING, size=10)
# the expected outcome is that it doesn't crash. No assertions.
Expand Down