Skip to content

replace live server calls in tests/test_datasets/test_dataset.py #1678

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
omkar-334 wants to merge 2 commits into
base: main
Choose a base branch
from
Draft

replace live server calls in tests/test_datasets/test_dataset.py #1678

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
104aa9e
replace live server calls in `tests/test_datasets/test_dataset.py`
omkar-334 Feb 20, 2026
df9ea42
Merge branch 'main' into test-ds
omkar-334 Feb 20, 2026
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
335 changes: 335 additions & 0 deletions mock_issue.md
View file
Open in desktop

Large diffs are not rendered by default.

32 changes: 32 additions & 0 deletions test.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,32 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": null,
"id": "62f2f535",
"metadata": {},
"outputs": [],
"source": [
"from __future__ import annotations\n",
"\n",
"import openml\n",
"\n",
"openml.config.server = \"https://www.openml.org/api/v1/xml\"\n",
"setups = openml.setups.list_setups(flow=5873)\n"
]
}
],
"metadata": {
"kernelspec": {
"display_name": ".venv (3.12.12)",
"language": "python",
"name": "python3"
},
"language_info": {
"name": "python",
"version": "3.12.12"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
9 changes: 9 additions & 0 deletions test.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,9 @@
from __future__ import annotations

import openml

openml.config.server = "https://www.openml.org/api/v1/xml"
setups = openml.setups.list_setups(flow=5873)

print(len(setups))
print(setups)
15 changes: 15 additions & 0 deletions tests/files/mock_responses/datasets/data_description_11.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,15 @@
<oml:data_set_description xmlns:oml="http://openml.org/openml">
<oml:id>11</oml:id>
<oml:name>car</oml:name>
<oml:version>1</oml:version>
<oml:description>Car Evaluation Database</oml:description>
<oml:format>ARFF</oml:format>
<oml:upload_date>2014-04-06T23:19:24</oml:upload_date>
<oml:licence>Public</oml:licence>
<oml:url>https://test.openml.org/data/v1/download/11/car.arff</oml:url>
<oml:file_id>11</oml:file_id>
<oml:default_target_attribute>class</oml:default_target_attribute>
<oml:version_label>1</oml:version_label>
<oml:visibility>public</oml:visibility>
<oml:status>active</oml:status>
</oml:data_set_description>
15 changes: 15 additions & 0 deletions tests/files/mock_responses/datasets/data_description_125.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,15 @@
<oml:data_set_description xmlns:oml="http://openml.org/openml">
<oml:id>125</oml:id>
<oml:name>kdd_internet_usage</oml:name>
<oml:version>1</oml:version>
<oml:description>KDD internet usage dataset</oml:description>
<oml:format>ARFF</oml:format>
<oml:upload_date>2014-10-06T23:19:24</oml:upload_date>
<oml:licence>Public</oml:licence>
<oml:url>https://test.openml.org/data/v1/download/125/kdd_internet_usage.arff</oml:url>
<oml:file_id>125</oml:file_id>
<oml:default_target_attribute>Who_Pays_for_Access_Work</oml:default_target_attribute>
<oml:version_label>1</oml:version_label>
<oml:visibility>public</oml:visibility>
<oml:status>active</oml:status>
</oml:data_set_description>
15 changes: 15 additions & 0 deletions tests/files/mock_responses/datasets/data_description_2.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,15 @@
<oml:data_set_description xmlns:oml="http://openml.org/openml">
<oml:id>2</oml:id>
<oml:name>anneal</oml:name>
<oml:version>1</oml:version>
<oml:description>Annealing Data</oml:description>
<oml:format>ARFF</oml:format>
<oml:upload_date>2014-04-06T23:19:24</oml:upload_date>
<oml:licence>Public</oml:licence>
<oml:url>https://test.openml.org/data/v1/download/2/anneal.arff</oml:url>
<oml:file_id>2</oml:file_id>
<oml:default_target_attribute>class</oml:default_target_attribute>
<oml:version_label>1</oml:version_label>
<oml:visibility>public</oml:visibility>
<oml:status>active</oml:status>
</oml:data_set_description>
15 changes: 15 additions & 0 deletions tests/files/mock_responses/datasets/data_description_40945.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,15 @@
<oml:data_set_description xmlns:oml="http://openml.org/openml">
<oml:id>40945</oml:id>
<oml:name>titanic</oml:name>
<oml:version>1</oml:version>
<oml:description>Titanic dataset</oml:description>
<oml:format>ARFF</oml:format>
<oml:upload_date>2018-01-01T00:00:00</oml:upload_date>
<oml:licence>Public</oml:licence>
<oml:url>https://test.openml.org/data/v1/download/40945/titanic.arff</oml:url>
<oml:file_id>40945</oml:file_id>
<oml:default_target_attribute>survived</oml:default_target_attribute>
<oml:version_label>1</oml:version_label>
<oml:visibility>public</oml:visibility>
<oml:status>active</oml:status>
</oml:data_set_description>
33 changes: 9 additions & 24 deletions tests/files/mock_responses/datasets/data_description_61.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,29 +2,14 @@
<oml:id>61</oml:id>
<oml:name>iris</oml:name>
<oml:version>1</oml:version>
<oml:description>**Author**: R.A. Fisher
**Source**: [UCI](https://archive.ics.uci.edu/ml/datasets/Iris) - 1936 - Donated by Michael Marshall
**Please cite**:

**Iris Plants Database**
This is perhaps the best known database to be found in the pattern recognition literature. Fisher's paper is a classic in the field and is referenced frequently to this day. (See Duda &amp; Hart, for example.) The data set contains 3 classes of 50 instances each, where each class refers to a type of iris plant. One class is linearly separable from the other 2; the latter are NOT linearly separable from each other.

Predicted attribute: class of iris plant.
This is an exceedingly simple domain.

### Attribute Information:
1. sepal length in cm
2. sepal width in cm
3. petal length in cm
4. petal width in cm
5. class:
-- Iris Setosa
-- Iris Versicolour
-- Iris Virginica</oml:description>
<oml:description_version>4</oml:description_version>
<oml:description>Iris Plants Database</oml:description>
<oml:format>ARFF</oml:format>
<oml:creator>R.A. Fisher</oml:creator> <oml:collection_date>1936</oml:collection_date> <oml:upload_date>2014-04-06T23:23:39</oml:upload_date>
<oml:language>English</oml:language> <oml:licence>Public</oml:licence> <oml:url>https://api.openml.org/data/v1/download/61/iris.arff</oml:url>
<oml:parquet_url>https://data.openml.org/datasets/0000/0061/dataset_61.pq</oml:parquet_url> <oml:file_id>61</oml:file_id> <oml:default_target_attribute>class</oml:default_target_attribute> <oml:version_label>1</oml:version_label> <oml:citation>https://archive.ics.uci.edu/ml/citation_policy.html</oml:citation> <oml:tag>Botany</oml:tag><oml:tag>Ecology</oml:tag><oml:tag>Kaggle</oml:tag><oml:tag>Machine Learning</oml:tag><oml:tag>study_1</oml:tag><oml:tag>study_25</oml:tag><oml:tag>study_4</oml:tag><oml:tag>study_41</oml:tag><oml:tag>study_50</oml:tag><oml:tag>study_52</oml:tag><oml:tag>study_7</oml:tag><oml:tag>study_86</oml:tag><oml:tag>study_88</oml:tag><oml:tag>study_89</oml:tag><oml:tag>uci</oml:tag> <oml:visibility>public</oml:visibility> <oml:original_data_url>https://archive.ics.uci.edu/ml/datasets/Iris</oml:original_data_url> <oml:paper_url>http://digital.library.adelaide.edu.au/dspace/handle/2440/15227</oml:paper_url> <oml:minio_url>https://data.openml.org/datasets/0000/0061/dataset_61.pq</oml:minio_url> <oml:status>active</oml:status>
<oml:processing_date>2020-11-20 19:02:18</oml:processing_date> <oml:md5_checksum>ad484452702105cbf3d30f8deaba39a9</oml:md5_checksum>
<oml:upload_date>2014-04-06T23:23:39</oml:upload_date>
<oml:licence>Public</oml:licence>
<oml:url>https://test.openml.org/data/v1/download/61/iris.arff</oml:url>
<oml:file_id>61</oml:file_id>
<oml:default_target_attribute>class</oml:default_target_attribute>
<oml:version_label>1</oml:version_label>
<oml:visibility>public</oml:visibility>
<oml:status>active</oml:status>
</oml:data_set_description>
4 changes: 4 additions & 0 deletions tests/files/mock_responses/datasets/data_feature_ontology_error_1105.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
<oml:error xmlns:oml="http://openml.org/openml">
<oml:code>1105</oml:code>
<oml:message>Ontology URL too long (max 256 characters)</oml:message>
</oml:error>
4 changes: 4 additions & 0 deletions tests/files/mock_responses/datasets/data_feature_ontology_error_1106.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
<oml:error xmlns:oml="http://openml.org/openml">
<oml:code>1106</oml:code>
<oml:message>Ontology URL is not a valid URL</oml:message>
</oml:error>
3 changes: 3 additions & 0 deletions tests/files/mock_responses/datasets/data_feature_ontology_success.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,3 @@
<oml:upload_data_feature_ontology xmlns:oml="http://openml.org/openml">
<oml:id>1</oml:id>
</oml:upload_data_feature_ontology>
94 changes: 94 additions & 0 deletions tests/files/mock_responses/datasets/data_features_11.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,94 @@
<oml:data_features xmlns:oml="http://openml.org/openml">
<oml:feature>
<oml:index>0</oml:index>
<oml:name>buying</oml:name>
<oml:data_type>nominal</oml:data_type>
<oml:nominal_value>vhigh</oml:nominal_value>
<oml:nominal_value>high</oml:nominal_value>
<oml:nominal_value>med</oml:nominal_value>
<oml:nominal_value>low</oml:nominal_value>
<oml:is_target>false</oml:is_target>
<oml:is_ignore>false</oml:is_ignore>
<oml:is_row_identifier>false</oml:is_row_identifier>
<oml:number_of_missing_values>0</oml:number_of_missing_values>
</oml:feature>
<oml:feature>
<oml:index>1</oml:index>
<oml:name>maint</oml:name>
<oml:data_type>nominal</oml:data_type>
<oml:nominal_value>vhigh</oml:nominal_value>
<oml:nominal_value>high</oml:nominal_value>
<oml:nominal_value>med</oml:nominal_value>
<oml:nominal_value>low</oml:nominal_value>
<oml:is_target>false</oml:is_target>
<oml:is_ignore>false</oml:is_ignore>
<oml:is_row_identifier>false</oml:is_row_identifier>
<oml:number_of_missing_values>0</oml:number_of_missing_values>
<oml:ontology>https://dbpedia.org/page/Maintenance</oml:ontology>
<oml:ontology>https://schema.org/maintenanceOrRepairNeeded</oml:ontology>
</oml:feature>
<oml:feature>
<oml:index>2</oml:index>
<oml:name>doors</oml:name>
<oml:data_type>nominal</oml:data_type>
<oml:nominal_value>2</oml:nominal_value>
<oml:nominal_value>3</oml:nominal_value>
<oml:nominal_value>4</oml:nominal_value>
<oml:nominal_value>5more</oml:nominal_value>
<oml:is_target>false</oml:is_target>
<oml:is_ignore>false</oml:is_ignore>
<oml:is_row_identifier>false</oml:is_row_identifier>
<oml:number_of_missing_values>0</oml:number_of_missing_values>
<oml:ontology>https://dbpedia.org/page/Car_door</oml:ontology>
</oml:feature>
<oml:feature>
<oml:index>3</oml:index>
<oml:name>persons</oml:name>
<oml:data_type>nominal</oml:data_type>
<oml:nominal_value>2</oml:nominal_value>
<oml:nominal_value>4</oml:nominal_value>
<oml:nominal_value>more</oml:nominal_value>
<oml:is_target>false</oml:is_target>
<oml:is_ignore>false</oml:is_ignore>
<oml:is_row_identifier>false</oml:is_row_identifier>
<oml:number_of_missing_values>0</oml:number_of_missing_values>
<oml:ontology>https://dbpedia.org/page/Passenger</oml:ontology>
</oml:feature>
<oml:feature>
<oml:index>4</oml:index>
<oml:name>lug_boot</oml:name>
<oml:data_type>nominal</oml:data_type>
<oml:nominal_value>small</oml:nominal_value>
<oml:nominal_value>med</oml:nominal_value>
<oml:nominal_value>big</oml:nominal_value>
<oml:is_target>false</oml:is_target>
<oml:is_ignore>false</oml:is_ignore>
<oml:is_row_identifier>false</oml:is_row_identifier>
<oml:number_of_missing_values>0</oml:number_of_missing_values>
</oml:feature>
<oml:feature>
<oml:index>5</oml:index>
<oml:name>safety</oml:name>
<oml:data_type>nominal</oml:data_type>
<oml:nominal_value>low</oml:nominal_value>
<oml:nominal_value>med</oml:nominal_value>
<oml:nominal_value>high</oml:nominal_value>
<oml:is_target>false</oml:is_target>
<oml:is_ignore>false</oml:is_ignore>
<oml:is_row_identifier>false</oml:is_row_identifier>
<oml:number_of_missing_values>0</oml:number_of_missing_values>
</oml:feature>
<oml:feature>
<oml:index>6</oml:index>
<oml:name>class</oml:name>
<oml:data_type>nominal</oml:data_type>
<oml:nominal_value>unacc</oml:nominal_value>
<oml:nominal_value>acc</oml:nominal_value>
<oml:nominal_value>good</oml:nominal_value>
<oml:nominal_value>vgood</oml:nominal_value>
<oml:is_target>true</oml:is_target>
<oml:is_ignore>false</oml:is_ignore>
<oml:is_row_identifier>false</oml:is_row_identifier>
<oml:number_of_missing_values>0</oml:number_of_missing_values>
</oml:feature>
</oml:data_features>
135 changes: 135 additions & 0 deletions tests/files/mock_responses/datasets/data_features_40945.xml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,135 @@
<oml:data_features xmlns:oml="http://openml.org/openml">
<oml:feature>
<oml:index>0</oml:index>
<oml:name>pclass</oml:name>
<oml:data_type>numeric</oml:data_type>
<oml:is_target>false</oml:is_target>
<oml:is_ignore>false</oml:is_ignore>
<oml:is_row_identifier>false</oml:is_row_identifier>
<oml:number_of_missing_values>0</oml:number_of_missing_values>
</oml:feature>
<oml:feature>
<oml:index>1</oml:index>
<oml:name>survived</oml:name>
<oml:data_type>nominal</oml:data_type>
<oml:nominal_value>0</oml:nominal_value>
<oml:nominal_value>1</oml:nominal_value>
<oml:is_target>true</oml:is_target>
<oml:is_ignore>false</oml:is_ignore>
<oml:is_row_identifier>false</oml:is_row_identifier>
<oml:number_of_missing_values>0</oml:number_of_missing_values>
</oml:feature>
<oml:feature>
<oml:index>2</oml:index>
<oml:name>name</oml:name>
<oml:data_type>string</oml:data_type>
<oml:is_target>false</oml:is_target>
<oml:is_ignore>false</oml:is_ignore>
<oml:is_row_identifier>false</oml:is_row_identifier>
<oml:number_of_missing_values>0</oml:number_of_missing_values>
</oml:feature>
<oml:feature>
<oml:index>3</oml:index>
<oml:name>sex</oml:name>
<oml:data_type>nominal</oml:data_type>
<oml:nominal_value>male</oml:nominal_value>
<oml:nominal_value>female</oml:nominal_value>
<oml:is_target>false</oml:is_target>
<oml:is_ignore>false</oml:is_ignore>
<oml:is_row_identifier>false</oml:is_row_identifier>
<oml:number_of_missing_values>0</oml:number_of_missing_values>
</oml:feature>
<oml:feature>
<oml:index>4</oml:index>
<oml:name>age</oml:name>
<oml:data_type>numeric</oml:data_type>
<oml:is_target>false</oml:is_target>
<oml:is_ignore>false</oml:is_ignore>
<oml:is_row_identifier>false</oml:is_row_identifier>
<oml:number_of_missing_values>263</oml:number_of_missing_values>
</oml:feature>
<oml:feature>
<oml:index>5</oml:index>
<oml:name>sibsp</oml:name>
<oml:data_type>numeric</oml:data_type>
<oml:is_target>false</oml:is_target>
<oml:is_ignore>false</oml:is_ignore>
<oml:is_row_identifier>false</oml:is_row_identifier>
<oml:number_of_missing_values>0</oml:number_of_missing_values>
</oml:feature>
<oml:feature>
<oml:index>6</oml:index>
<oml:name>parch</oml:name>
<oml:data_type>numeric</oml:data_type>
<oml:is_target>false</oml:is_target>
<oml:is_ignore>false</oml:is_ignore>
<oml:is_row_identifier>false</oml:is_row_identifier>
<oml:number_of_missing_values>0</oml:number_of_missing_values>
</oml:feature>
<oml:feature>
<oml:index>7</oml:index>
<oml:name>ticket</oml:name>
<oml:data_type>string</oml:data_type>
<oml:is_target>false</oml:is_target>
<oml:is_ignore>false</oml:is_ignore>
<oml:is_row_identifier>false</oml:is_row_identifier>
<oml:number_of_missing_values>0</oml:number_of_missing_values>
</oml:feature>
<oml:feature>
<oml:index>8</oml:index>
<oml:name>fare</oml:name>
<oml:data_type>numeric</oml:data_type>
<oml:is_target>false</oml:is_target>
<oml:is_ignore>false</oml:is_ignore>
<oml:is_row_identifier>false</oml:is_row_identifier>
<oml:number_of_missing_values>1</oml:number_of_missing_values>
</oml:feature>
<oml:feature>
<oml:index>9</oml:index>
<oml:name>cabin</oml:name>
<oml:data_type>string</oml:data_type>
<oml:is_target>false</oml:is_target>
<oml:is_ignore>false</oml:is_ignore>
<oml:is_row_identifier>false</oml:is_row_identifier>
<oml:number_of_missing_values>1014</oml:number_of_missing_values>
</oml:feature>
<oml:feature>
<oml:index>10</oml:index>
<oml:name>embarked</oml:name>
<oml:data_type>nominal</oml:data_type>
<oml:nominal_value>S</oml:nominal_value>
<oml:nominal_value>C</oml:nominal_value>
<oml:nominal_value>Q</oml:nominal_value>
<oml:is_target>false</oml:is_target>
<oml:is_ignore>false</oml:is_ignore>
<oml:is_row_identifier>false</oml:is_row_identifier>
<oml:number_of_missing_values>2</oml:number_of_missing_values>
</oml:feature>
<oml:feature>
<oml:index>11</oml:index>
<oml:name>boat</oml:name>
<oml:data_type>string</oml:data_type>
<oml:is_target>false</oml:is_target>
<oml:is_ignore>false</oml:is_ignore>
<oml:is_row_identifier>false</oml:is_row_identifier>
<oml:number_of_missing_values>823</oml:number_of_missing_values>
</oml:feature>
<oml:feature>
<oml:index>12</oml:index>
<oml:name>body</oml:name>
<oml:data_type>numeric</oml:data_type>
<oml:is_target>false</oml:is_target>
<oml:is_ignore>false</oml:is_ignore>
<oml:is_row_identifier>false</oml:is_row_identifier>
<oml:number_of_missing_values>1188</oml:number_of_missing_values>
</oml:feature>
<oml:feature>
<oml:index>13</oml:index>
<oml:name>home.dest</oml:name>
<oml:data_type>string</oml:data_type>
<oml:is_target>false</oml:is_target>
<oml:is_ignore>false</oml:is_ignore>
<oml:is_row_identifier>false</oml:is_row_identifier>
<oml:number_of_missing_values>564</oml:number_of_missing_values>
</oml:feature>
</oml:data_features>
Loading