---
swagger: "2.0"
info:
description: REST API for sharing, organizing and reusing machine learning datasets, code, and experiments. Follows a predictive URL scheme from endpoint https://www.openml.org/api/v1/json (or /xml). You need to add your `api_key` to every call (see your account settings), or simply log in. See https://www.openml.org/api_data_docs for the file server API.
version: 1.0.0
title: OpenML API
basePath: /api/v1/json
schemes:
- https
produces:
- application/json
paths:
/data/{id}:
get:
tags:
- data
summary: Get dataset description
description: |
Returns information about a dataset. The information includes the name, information about the creator, URL to download it and more.
parameters:
- name: id
in: path
description: Id of the dataset.
required: true
type: number
format: integer
- name: api_key
in: query
description: Api key to authenticate the user
required: false
type: string
responses:
200:
description: A dataset description
examples:
application/json: |-
{
"data_set_description": {
"id": "1",
"name": "anneal",
"version": "2",
"description": "...",
"format": "ARFF",
"upload_date": "2014-04-06 23:19:20",
"licence": "Public",
"url": "https://www.openml.org/data/download/1/dataset_1_anneal.arff",
"file_id": "1",
"default_target_attribute": "class",
"version_label": "2",
"tag": [
"study_1",
"uci"
],
"visibility": "public",
"original_data_url": "https://www.openml.org/d/2",
"status": "active",
"md5_checksum": "d01f6ccd68c88b749b20bbe897de3713"
}
}
schema:
$ref: '#/definitions/Data'
412:
description: |
Precondition failed. An error code and message are returned
110 - Please provide data_id.
111 - Unknown dataset. Data set description with data_id was not found in the database.
112 - No access granted. This dataset is not shared with you.
schema:
$ref: '#/definitions/Error'
delete:
tags:
- data
summary: Delete dataset
description: |
Deletes a dataset. Upon success, it returns the ID of the deleted dataset.
parameters:
- name: id
in: path
description: Id of the dataset.
required: true
type: number
format: integer
- name: api_key
in: query
description: Api key to authenticate the user
required: true
type: string
responses:
200:
description: ID of the deleted dataset
examples:
application/json: |-
{
"data_delete": {
"id": "4328"
}
}
schema:
type: object
properties:
data_delete:
$ref: '#/definitions/inline_response_200_data_delete'
412:
description: |
Precondition failed. An error code and message are returned
350 - Please provide API key. In order to remove your content, please authenticate.
351 - Authentication failed. The API key was not valid. Please try to login again, or contact api administrators.
352 - Dataset does not exists. The data ID could not be linked to an existing dataset.
353 - Dataset is not owned by you. The dataset is owned by another user. Hence you cannot delete it.
354 - Dataset is in use by other content. Can not be deleted. The data is used in tasks or runs. Delete other content before deleting this dataset.
355 - Deleting dataset failed. Deleting the dataset failed. Please contact
support team.
schema:
$ref: '#/definitions/Error'
/data:
post:
tags:
- data
summary: Upload dataset
description: |
Uploads a dataset. Upon success, it returns the data id.
consumes:
- multipart/form-data
parameters:
- name: description
in: formData
description: An XML file describing the dataset. Only name, description, and data format are required. Also see the [XSD schema](https://www.openml.org/api/v1/xsd/openml.data.upload) and an [XML example](https://www.openml.org/api/v1/xml_example/data).
required: true
type: file
- name: dataset
in: formData
description: The actual dataset, being an ARFF file.
required: true
type: file
- name: api_key
in: query
description: Api key to authenticate the user
required: true
type: string
responses:
200:
description: Id of the uploaded dataset
examples:
application/json: |-
{
"upload_data_set": {
"id": "4328"
}
}
schema:
type: object
properties:
upload_data_set:
$ref: '#/definitions/inline_response_200_1_upload_data_set'
412:
description: |
Precondition failed. An error code and message are returned.
130 - Problem with file uploading. There was a problem with the file upload.
131 - Problem validating uploaded description file. The XML description format does not meet the standards.
132 - Failed to move the files. Internal server error, please contact API administrators.
133 - Failed to make checksum of datafile. Internal server error, please contact API administrators.
134 - Failed to insert record in database. Internal server error, please contact API administrators.
135 - Please provide description xml.
136 - File failed format verification. The uploaded file is not valid according to the selected file format. Please check the file format specification and try again.
137 - Please provide API key. In order to share content, please log in or provide your API key.
138 - Authentication failed. The API key was not valid. Please try to login again, or contact API administrators
139 - Combination name / version already exists. Leave version out for auto increment
140 - Both dataset file and dataset url provided. The system is confused since both a dataset file (post) and a dataset url (xml) are provided. Please remove one.
141 - Neither dataset file or dataset url are provided. Please provide either a dataset file as POST variable, or a dataset url in the description XML.
142 - Error in processing arff file. Can be a syntax error, or the specified target feature does not exists. For now, we only check on arff files. If a dataset is claimed to be in such a format, and it can not be parsed, this error is returned.
143 - Suggested target feature not legal. It is possible to suggest a default target feature (for predictive tasks). However, it should be provided in the data.
144 - Unable to update dataset. The dataset with id could not be found in the database. If you upload a new dataset, unset the id.
schema:
$ref: '#/definitions/Error'
/data/qualities/list:
get:
tags:
- data
summary: List all data qualities
description: |
Returns a list of all data qualities in the system.
parameters:
- name: api_key
in: query
description: API key to authenticate the user
required: false
type: string
responses:
200:
description: A list of data qualities
examples:
application/json: |-
{
"data_qualities_list":{
"quality":[
"NumberOfClasses",
"NumberOfFeatures",
"NumberOfInstances",
"NumberOfInstancesWithMissingValues",
"NumberOfMissingValues",
"NumberOfNumericFeatures",
"NumberOfSymbolicFeatures"
]
}
}
schema:
$ref: '#/definitions/DataQualityList'
412:
description: |
Precondition failed. An error code and message are returned
370 - No data qualities available. There are no data qualities in the system.
schema:
$ref: '#/definitions/Error'
/data/qualities:
post:
tags:
- data
summary: Upload dataset qualities
description: |
Uploads dataset qualities. Upon success, it returns the data id.
consumes:
- multipart/form-data
parameters:
- name: description
in: formData
description: An XML file describing the dataset. Only name, description, and data format are required. Also see the [XSD schema](https://www.openml.org/api/v1/xsd/openml.data.qualities) and an [XML example](https://www.openml.org/api/v1/xml_example/data.qualities).
required: true
type: file
- name: api_key
in: query
description: Api key to authenticate the user
required: true
type: string
responses:
412:
description: |
Precondition failed. An error code and message are returned.
381 - Something wrong with XML, please check did and evaluation_engine_id
382 - Please provide description xml
383 - Problem validating uploaded description file
384 - Dataset not processed yet
schema:
$ref: '#/definitions/Error'
/data/status/update/:
post:
tags:
- data
summary: Change the status of a dataset
description: |
Change the status of a dataset, either 'active' or 'deactivated'
consumes:
- multipart/form-data
parameters:
- name: data_id
in: formData
description: Id of the dataset.
required: true
type: number
format: integer
- name: status
in: formData
description: The status on which to filter the results, either 'active' or 'deactivated'.
required: true
type: string
- name: api_key
in: formData
description: Api key to authenticate the user
required: true
type: string
responses:
412:
description: |
Precondition failed. An error code and message are returned.
691 - Illegal status
692 - Dataset does not exists
693 - Dataset is not owned by you
694 - Illegal status transition
695 - Status update failed
schema:
$ref: '#/definitions/Error'
/data/features:
post:
tags:
- data
summary: Upload dataset feature description
description: |
Uploads dataset feature description. Upon success, it returns the data id.
consumes:
- multipart/form-data
parameters:
- name: description
in: formData
description: An XML file describing the dataset. Only name, description, and data format are required. Also see the [XSD schema](https://www.openml.org/api/v1/xsd/openml.data.features) and an [XML example](https://www.openml.org/api/v1/xml_example/data.features).
required: true
type: file
- name: api_key
in: query
description: Api key to authenticate the user
required: true
type: string
responses:
412:
description: |
Precondition failed. An error code and message are returned.
431 - Dataset already processed
432 - Please provide description xml
433 - Problem validating uploaded description file
434 - Could not find dataset
436 - Something wrong with XML, check data id and evaluation engine id
schema:
$ref: '#/definitions/Error'
/data/features/{id}:
get:
tags:
- data
summary: Get data features
description: |
Returns the features of a dataset.
parameters:
- name: id
in: path
description: Id of the dataset.
required: true
type: number
format: integer
- name: api_key
in: query
description: Api key to authenticate the user
required: false
type: string
responses:
200:
description: All the features of the dataset
examples:
application/json: |-
{
"data_features": {
"feature": [
{
"index": "0",
"name": "sepallength",
"data_type": "numeric",
"is_target": "false",
"is_ignore": "false",
"is_row_identifier": "false"
},
{
"index": "1",
"name": "sepalwidth",
"data_type": "numeric",
"is_target": "false",
"is_ignore": "false",
"is_row_identifier": "false"
},
{
"index": "2",
"name": "petallength",
"data_type": "numeric",
"is_target": "false",
"is_ignore": "false",
"is_row_identifier": "false"
},
{
"index": "3",
"name": "petalwidth",
"data_type": "numeric",
"is_target": "false",
"is_ignore": "false",
"is_row_identifier": "false"
},
{
"index": "4",
"name": "class",
"data_type": "nominal",
"is_target": "true",
"is_ignore": "false",
"is_row_identifier": "false"
}
]
}
}
schema:
$ref: '#/definitions/DataFeatures'
412:
description: |
Precondition failed. An error code and message are returned.
270 - Please provide dataset ID.
271 - Unknown dataset. Data set with the given data ID was not found (or is not shared with you).
272 - No features found. The dataset did not contain any features, or we could not extract them.
273 - Dataset not processed yet. The dataset was not processed yet, features are not yet available. Please wait for a few minutes.
274 - Dataset processed with error. The feature extractor has run into an error while processing the dataset. Please check whether it is a valid supported file. If so, please contact the API admins.
schema:
$ref: '#/definitions/Error'
/data/qualities/{id}:
get:
tags:
- data
summary: Get data qualities
description: |
Returns the qualities of a dataset.
parameters:
- name: id
in: path
description: Id of the dataset.
required: true
type: number
format: integer
- name: api_key
in: query
description: Api key to authenticate the user
required: false
type: string
responses:
200:
description: All the qualities of the dataset
examples:
application/json: |-
{
"data_qualities": {
"quality": [
{
"name": "ClassCount",
"value": "3.0"
},
{
"name": "ClassEntropy",
"value": "1.584962500721156"
},
{
"name": "NumberOfClasses",
"value": "3"
},
{
"name": "NumberOfFeatures",
"value": "5"
},
{
"name": "NumberOfInstances",
"value": "150"
},
{
"name": "NumberOfInstancesWithMissingValues",
"value": "0"
},
{
"name": "NumberOfMissingValues",
"value": "0"
},
{
"name": "NumberOfNumericFeatures",
"value": "4"
},
{
"name": "NumberOfSymbolicFeatures",
"value": "0"
}
]
}
}
schema:
$ref: '#/definitions/DataQualities'
412:
description: |
Precondition failed. An error code and message are returned.
360 - Please provide data set ID
361 - Unknown dataset. The data set with the given ID was not found in the database, or is not shared with you.
362 - No qualities found. The registered dataset did not contain any calculated qualities.
363 - Dataset not processed yet. The dataset was not processed yet, no qualities are available. Please wait for a few minutes.
364 - Dataset processed with error. The quality calculator has run into an error while processing the dataset. Please check whether it is a valid supported file. If so, contact the support team.
365 - Interval start or end illegal. There was a problem with the interval
start or end.
schema:
$ref: '#/definitions/Error'
/data/list/{filters}:
get:
tags:
- data
summary: List and filter datasets
description: |
List datasets, possibly filtered by a range of properties. Any number of properties can be combined by listing them one after the other in the form '/data/list/{filter}/{value}/{filter}/{value}/...' Returns an array with all datasets that match the constraints.
parameters:
- name: filters
in: path
description: |
Any combination of these filters
/limit/{limit}/offset/{offset} - returns only {limit} results starting from result number {offset}. Useful for paginating results. With /limit/5/offset/10, results 11..15 will be returned. Both limit and offset need to be specified.
/status/{status} - returns only datasets with a given status, either 'active', 'deactivated', or 'in_preparation'.
/tag/{tag} - returns only datasets tagged with the given tag.
/{data_quality}/{range} - returns only tasks for which the underlying datasets have certain qualities. {data_quality} can be data_id, data_name, data_version, number_instances, number_features, number_classes, number_missing_values. {range} can be a specific value or a range in the form 'low..high'. Multiple qualities can be combined, as in 'number_instances/0..50/number_features/0..10'.
required: true
type: string
- name: api_key
in: query
description: API key to authenticate the user
required: false
type: string
responses:
200:
description: A list of datasets with the given task
examples:
application/json: |-
{
"data": {
"dataset": [
{
"did":"1",
"name":"anneal",
"status":"active",
"format":"ARFF",
"quality":[
{
"name":"MajorityClassSize",
"value":"684"
},
{
"name":"MaxNominalAttDistinctValues",
"value":"10.0"
},
{
"name":"MinorityClassSize"
,"value":"0"
},
{
"name":"NumBinaryAtts",
"value":"14.0"
},
{
"name":"NumberOfClasses",
"value":"6"
},
{
"name":"NumberOfFeatures",
"value":"39"
},
{
"name":"NumberOfInstances",
"value":"898"
},
{
"name":"NumberOfInstancesWithMissingValues",
"value":"0"
},
{
"name":"NumberOfMissingValues",
"value":"0"
},
{
"name":"NumberOfNumericFeatures",
"value":"6"
},
{
"name":"NumberOfSymbolicFeatures",
"value":"32"
}
]
}
]
}
}
schema:
$ref: '#/definitions/DataList'
412:
description: |
Precondition failed. An error code and message are returned.
370 - Illegal filter specified.
371 - Filter values/ranges not properly specified.
372 - No results. There where no matches for the given constraints.
373 - Can not specify an offset without a limit.
schema:
$ref: '#/definitions/Error'
/data/tag:
post:
tags:
- data
summary: Tag a dataset
description: Tags a dataset.
consumes:
- application/x-www-form-urlencoded
parameters:
- name: data_id
in: formData
description: Id of the dataset.
required: true
type: number
format: integer
- name: tag
in: formData
description: Tag name
required: true
type: string
- name: api_key
in: formData
description: Api key to authenticate the user
required: true
type: string
responses:
200:
description: The id of the tagged dataset
examples:
application/json: |-
{
"data_tag": {
"id": "2"
}
}
schema:
type: object
properties:
data_tag:
$ref: '#/definitions/inline_response_200_2_data_tag'
412:
description: |
Precondition failed. An error code and message are returned.
470 - In order to add a tag, please upload the entity id (either data_id, flow_id, run_id) and tag (the name of the tag).
471 - Entity not found. The provided entity_id {data_id, flow_id, run_id} does not correspond to an existing entity.
472 - Entity already tagged by this tag. The entity {dataset, flow, run} already had this tag.
473 - Something went wrong inserting the tag. Please contact OpenML Team.
474 - Internal error tagging the entity. Please contact OpenML Team.
schema:
$ref: '#/definitions/Error'
/data/untag:
post:
tags:
- data
summary: Untag a dataset
description: Untags a dataset.
consumes:
- application/x-www-form-urlencoded
parameters:
- name: data_id
in: formData
description: Id of the dataset.
required: true
type: number
- name: tag
in: formData
description: Tag name
required: true
type: string
- name: api_key
in: formData
description: Api key to authenticate the user
required: true
type: string
responses:
200:
description: The ID of the untagged dataset
examples:
application/json: |-
{
"data_untag": {
"id": "2"
}
}
schema:
type: object
properties:
data_untag:
$ref: '#/definitions/inline_response_200_3_data_untag'
412:
description: |
Precondition failed. An error code and message are returned.
475 - Please give entity_id {data_id, flow_id, run_id} and tag. In order to remove a tag, please upload the entity id (either data_id, flow_id, run_id) and tag (the name of the tag).
476 - Entity {dataset, flow, run} not found. The provided entity_id {data_id, flow_id, run_id} does not correspond to an existing entity.
477 - Tag not found. The provided tag is not associated with the entity {dataset, flow, run}.
478 - Tag is not owned by you. The entity {dataset, flow, run} was tagged by another user. Hence you cannot delete it.
479 - Internal error removing the tag. Please contact OpenML Team.
schema:
$ref: '#/definitions/Error'
/data/unprocessed/{data_engine_id}/{order}:
get:
tags:
- evaluation
summary: Get a list of unprocessed datasets
description: |
This call is for people running their own dataset processing engines. It returns the details of datasets that are not yet processed by the given processing engine. It doesn't process the datasets, it just returns the dataset info.
parameters:
- name: data_engine_id
in: path
description: The ID of the data processing engine. You get this ID when you register a new data processing engine with OpenML. The ID of the main data processing engine is 1.
required: true
type: string
- name: order
in: path
description: When there are multiple datasets still to process, this defines which ones to return. Options are 'normal' - the oldest datasets, or 'random'.
required: true
type: string
- name: api_key
in: query
description: API key to authenticate the user
required: false
type: string
responses:
200:
description: A list of unprocessed datasets
examples:
application/json:
data_unprocessed:
run:
- did: "1"
name: anneal
version: "2"
status: deactivated
format: ARFF
schema:
$ref: '#/definitions/DataUnprocessed'
412:
description: |
Precondition failed. An error code and message are returned.
681 - No unprocessed datasets.
schema:
$ref: '#/definitions/Error'
/data/qualities/unprocessed/{data_engine_id}/{order}:
post:
tags:
- data
summary: |
Get a list of datasets with unprocessed qualities
description: |
This call is for people running their own dataset processing engines. It returns the details of datasets for which certain qualities are not yet processed by the given processing engine. It doesn't process the datasets, it just returns the dataset info.
consumes:
- application/x-www-form-urlencoded
parameters:
- name: data_engine_id
in: path
description: The ID of the data processing engine. You get this ID when you register a new data processing engine with OpenML. The ID of the main data processing engine is 1.
required: true
type: string
- name: order
in: path
description: When there are multiple datasets still to process, this defines which ones to return. Options are 'normal' - the oldest datasets, or 'random'.
required: true
type: string
- name: api_key
in: query
description: API key to authenticate the user
required: false
type: string
- name: qualities
in: formData
description: Comma-separated list of (at least two) quality names, e.g. 'NumberOfInstances,NumberOfFeatures'.
required: true
type: string
responses:
200:
description: A list of unprocessed datasets
examples:
application/json:
data_unprocessed:
run:
- did: "1"
name: anneal
version: "2"
status: deactivated
format: ARFF
schema:
$ref: '#/definitions/DataUnprocessed'
412:
description: |
Precondition failed. An error code and message are returned.
686 - Please specify the features the evaluation engine wants to calculate (at least 2).
687 - No unprocessed datasets according to the given set of meta-features.
688 - Illegal qualities.
schema:
$ref: '#/definitions/Error'
/task/{id}:
get:
tags:
- task
summary: Get task description
description: |
Returns information about a task. The information includes the task type, input data, train/test sets, and more.
parameters:
- name: id
in: path
description: ID of the task.
required: true
type: number
format: integer
- name: api_key
in: query
description: Api key to authenticate the user
required: false
type: string
responses:
200:
description: A task description
examples:
application/json: |-
{
"task": {
"task_id":"1",
"task_type":"Supervised Classification",
"input":[
{
"name":"source_data",
"data_set":{
"data_set_id":"1",
"target_feature":"class"
}
},
{
"name":"estimation_procedure",
"estimation_procedure":{
"type":"crossvalidation",
"data_splits_url":"https://www.openml.org/api_splits/get/1/Task_1_splits.arff",
"parameter":[
{
"name":"number_repeats",
"value":"1"
},
{
"name":"number_folds",
"value":"10"
},
{
"name":"percentage"
},
{
"name":"stratified_sampling",
"value":"true"
}
]
}
},
{
"name":"cost_matrix",
"cost_matrix":[]
},
{
"name":"evaluation_measures",
"evaluation_measures":
{
"evaluation_measure":"predictive_accuracy"
}
}
],
"output":{
"name":"predictions",
"predictions":{
"format":"ARFF",
"feature":[
{
"name":"repeat",
"type":"integer"
},
{
"name":"fold",
"type":"integer"
},
{
"name":"row_id",
"type":"integer"
},
{
"name":"confidence.classname",
"type":"numeric"
},
{
"name":"prediction",
"type":"string"
}
]
}
},
"tag":["basic","study_1","under100k","under1m"]
}
}
schema:
$ref: '#/definitions/Task'
412:
description: |
Precondition failed. An error code and message are returned.
150 - Please provide task_id.
151 - Unknown task. The task with the given id was not found in the database
schema:
$ref: '#/definitions/Error'
delete:
tags:
- task
summary: Delete task
description: |
Deletes a task. Upon success, it returns the ID of the deleted task.
parameters:
- name: id
in: path
description: Id of the task.
required: true
type: number
format: integer
- name: api_key
in: query
description: Api key to authenticate the user
required: true
type: string
responses:
200:
description: ID of the deleted task
examples:
application/json: |-
{
"task_delete": {
"id": "4328"
}
}
schema:
type: object
properties:
task_delete:
$ref: '#/definitions/inline_response_200_4_task_delete'
412:
description: |
Precondition failed. An error code and message are returned.
450 - Please provide API key. In order to remove your content, please authenticate.
451 - Authentication failed. The API key was not valid. Please try to login again, or contact api administrators.
452 - Task does not exists. The task ID could not be linked to an existing task.
454 - Task is executed in some runs. Delete these first.
455 - Deleting the task failed. Please contact support team.
schema:
$ref: '#/definitions/Error'
/task:
post:
tags:
- task
summary: Upload task
description: |
Uploads a task. Upon success, it returns the task id.
consumes:
- multipart/form-data
parameters:
- name: description
in: formData
description: An XML file describing the task. Only name, description, and task format are required. Also see the [XSD schema](https://www.openml.org/api/v1/xsd/openml.task.upload) and an [XML example](https://www.openml.org/api/v1/xml_example/task).
required: true
type: file
- name: api_key
in: query
description: Api key to authenticate the user
required: true
type: string
responses:
200:
description: Id of the uploaded task
examples:
application/json: |-
{
"upload_task": {
"id": "4328"
}
}
schema:
type: object
properties:
upload_task:
$ref: '#/definitions/inline_response_200_5_upload_task'
412:
description: |
Precondition failed. An error code and message are returned.
530 - Description file not present. Please upload the task description.
531 - Internal error. Please contact api support team
532 - Problem validating uploaded description file. The XML description format does not meet the standards
533 - Task already exists.
534 - Error creating the task.
schema:
$ref: '#/definitions/Error'
/task/list/{filters}:
get:
tags:
- task
summary: List and filter tasks
description: |
List tasks, possibly filtered by a range of properties from the task itself or from the underlying dataset. Any number of properties can be combined by listing them one after the other in the form '/task/list/{filter}/{value}/{filter}/{value}/...' Returns an array with all tasks that match the constraints.
parameters:
- name: filters
in: path
description: |
Any combination of these filters
/limit/{limit}/offset/{offset} - returns only {limit} results starting from result number {offset}. Useful for paginating results. With /limit/5/offset/10, tasks 11..15 will be returned. Both limit and offset need to be specified.
/status/{status} - returns only tasks with a given status, either 'active', 'deactivated', or 'in_preparation'.
/type/{type_id} - returns only tasks with a given task type id. See the list of task types of the ID's (e.g. 1 = Supervised Classification).
/tag/{tag} - returns only tasks tagged with the given tag.
/data_tag/{tag} - returns only tasks for which the underlying dataset is tagged with the given tag.
/{data_quality}/{range} - returns only tasks for which the underlying datasets have certain qualities. {data_quality} can be data_id, data_name, number_instances, number_features, number_classes, number_missing_values. {range} can be a specific value or a range in the form 'low..high'. Multiple qualities can be combined, as in 'number_instances/0..50/number_features/0..10'.
required: true
type: string
- name: api_key
in: query
description: API key to authenticate the user
required: false
type: string
responses:
200:
description: A list of tasks with the given tag
examples:
application/json: |-
{
"task": {
"task": [
{
"task_id":"1",
"task_type":"Supervised Classification",
"did":"1",
"name":"anneal",
"status":"active",
"format":"ARFF",
"input":[
{
"name":"estimation_procedure",
"value":"1"
},
{
"name":"evaluation_measures",
"value":"predictive_accuracy"
},
{
"name":"source_data",
"value":"1"
},
{
"name":"target_feature",
"value":"class"
}
],
"quality":[
{
"name":"MajorityClassSize",
"value":"684"
},
{
"name":"MaxNominalAttDistinctValues",
"value":"10.0"
},
{
"name":"MinorityClassSize",
"value":"0"
},
{
"name":"NumBinaryAtts",
"value":"14.0"
},
{
"name":"NumberOfClasses",
"value":"6"
},
{
"name":"NumberOfFeatures",
"value":"39"
},
{
"name":"NumberOfInstances",
"value":"898"
},
{
"name":"NumberOfInstancesWithMissingValues",
"value":"0"
},
{
"name":"NumberOfMissingValues",
"value":"0"
},
{
"name":"NumberOfNumericFeatures",
"value":"6"
},
{
"name":"NumberOfSymbolicFeatures",
"value":"32"
}
],
"tag":[
"basic",
"study_1",
"study_7",
"under100k",
"under1m"
]
}
]
}
}
schema:
$ref: '#/definitions/TaskList'
412:
description: |
Precondition failed. An error code and message are returned.
480 - Illegal filter specified.
481 - Filter values/ranges not properly specified.
482 - No results. There where no matches for the given constraints.
483 - Can not specify an offset without a limit.
schema:
$ref: '#/definitions/Error'
/task/tag:
post:
tags:
- task
summary: Tag a task
description: Tags a task.
consumes:
- application/x-www-form-urlencoded
parameters:
- name: task_id
in: formData
description: Id of the task.
required: true
type: number
format: integer
- name: tag
in: formData
description: Tag name
required: true
type: string
- name: api_key
in: formData
description: Api key to authenticate the user
required: true
type: string
responses:
200:
description: The id of the tagged task
examples:
application/json: |-
{
"task_tag": {
"id": "2"
}
}
schema:
type: object
properties:
task_tag:
$ref: '#/definitions/inline_response_200_6_task_tag'
412:
description: |
Precondition failed. An error code and message are returned.
470 - In order to add a tag, please upload the entity id (either data_id, task_id, flow_id, run_id) and tag (the name of the tag).
471 - Entity not found. The provided entity_id {data_id, task_id, flow_id, run_id} does not correspond to an existing entity.
472 - Entity already tagged by this tag. The entity {dataset, task, flow, run} already had this tag.
473 - Something went wrong inserting the tag. Please contact OpenML Team.
474 - Internal error tagging the entity. Please contact OpenML Team.
schema:
$ref: '#/definitions/Error'
/task/untag:
post:
tags:
- task
summary: Untag a task
description: Untags a task.
consumes:
- application/x-www-form-urlencoded
parameters:
- name: task_id
in: formData
description: Id of the task.
required: true
type: number
- name: tag
in: formData
description: Tag name
required: true
type: string
- name: api_key
in: formData
description: Api key to authenticate the user
required: true
type: string
responses:
200:
description: A the features of the task
examples:
application/json: |-
{
"task_untag": {
"id": "2"
}
}
schema:
type: object
properties:
task_untag:
$ref: '#/definitions/inline_response_200_7_task_untag'
412:
description: |
Precondition failed. An error code and message are returned.
475 - Please give entity_id {data_id, flow_id, run_id} and tag. In order to remove a tag, please upload the entity id (either data_id, task_id, flow_id, run_id) and tag (the name of the tag).
476 - Entity {dataset, task, flow, run} not found. The provided entity_id {data_id, task_id, flow_id, run_id} does not correspond to an existing entity.
477 - Tag not found. The provided tag is not associated with the entity {dataset, task, flow, run}.
478 - Tag is not owned by you. The entity {dataset, flow, run} was tagged by another user. Hence you cannot delete it.
479 - Internal error removing the tag. Please contact OpenML Team.
schema:
$ref: '#/definitions/Error'
/tasktype/{id}:
get:
tags:
- tasktype
summary: Get task type description
description: |
Returns information about a task type. The information includes a description, the given inputs and the expected outputs.
parameters:
- name: id
in: path
description: ID of the task.
required: true
type: number
format: integer
- name: api_key
in: query
description: Api key to authenticate the user
required: false
type: string
responses:
200:
description: A task type description
examples:
application/json: |-
{
"task_type": {
"id": "1",
"name": "Supervised Classification",
"description": "In supervised classification, you are given an input dataset in which instances are labeled with a certain class. The goal is to build a model that predicts the class for future unlabeled instances. The model is evaluated using a train-test procedure, e.g. cross-validation.
\n\nTo make results by different users comparable, you are given the exact train-test folds to be used, and you need to return at least the predictions generated by your model for each of the test instances. OpenML will use these predictions to calculate a range of evaluation measures on the server.
\n\nYou can also upload your own evaluation measures, provided that the code for doing so is available from the implementation used. For extremely large datasets, it may be infeasible to upload all predictions. In those cases, you need to compute and provide the evaluations yourself.
\n\nOptionally, you can upload the model trained on all the input data. There is no restriction on the file format, but please use a well-known format or PMML.",
"creator": [
"Joaquin Vanschoren",
"Jan van Rijn",
"Luis Torgo",
"Bernd Bischl"
],
"contributor": [
"Bo Gao",
"Simon Fischer",
"Venkatesh Umaashankar",
"Michael Berthold",
"Bernd Wiswedel",
"Patrick Winter"
],
"creation_date": "2013-01-24 00:00:00",
"input": [
{
"name": "source_data",
"requirement": "required",
"data_type": "numeric"
},
{
"name": "target_feature",
"requirement": "required",
"data_type": "string"
},
{
"name": "estimation_procedure",
"requirement": "required",
"data_type": "numeric"
},
{
"name": "cost_matrix",
"data_type": "json"
},
{
"name": "custom_testset",
"data_type": "json"
},
{
"name": "evaluation_measures",
"data_type": "string"
}
]
}
}
schema:
$ref: '#/definitions/TaskType'
412:
description: |
Precondition failed. An error code and message are returned.
240 - Please provide task type ID.
241 - Unknown task type. The task type with the given id was not found in the database
schema:
$ref: '#/definitions/Error'
/tasktype/list:
get:
tags:
- tasktype
summary: List all task types
description: |
Returns an array with all task types in the system.
parameters:
- name: api_key
in: query
description: API key to authenticate the user
required: false
type: string
responses:
200:
description: A task description
examples:
application/json: |-
{
"task_types":{
"task_type":[
{
"id":"1",
"name":"Supervised Classification",
"description":"In supervised classification, you are given ...",
"creator":"Joaquin Vanschoren, Jan van Rijn, Luis Torgo, Bernd Bischl"
},
{
"id":"2",
"name":"Supervised Regression",
"description":"Given a dataset with a numeric target ...",
"creator":"Joaquin Vanschoren, Jan van Rijn, Luis Torgo, Bernd Bischl"
},{}
]
}
}
schema:
$ref: '#/definitions/TaskTypeList'
default:
description: Unexpected error
schema:
$ref: '#/definitions/Error'
/flow/{id}:
get:
tags:
- flow
summary: Get flow description
description: |
Returns information about a flow. The information includes the name, information about the creator, dependencies, parameters, run instructions and more.
parameters:
- name: id
in: path
description: ID of the flow.
required: true
type: number
format: integer
- name: api_key
in: query
description: API key to authenticate the user
required: false
type: string
responses:
200:
description: A flow description
examples:
application/json: |-
{
"flow": {
"id":"100",
"uploader":"1",
"name":"weka.J48",
"version":"2",
"external_version":"Weka_3.7.5_9117",
"description":"...",
"upload_date":"2014-04-23 18:00:36",
"language":"Java",
"dependencies":"Weka_3.7.5",
"parameter": [
{
"name":"A",
"data_type":"flag",
"default_value":[],
"description":"Laplace smoothing..."
},
{
"name":"C",
"data_type":"option",
"default_value":"0.25",
"description":"Set confidence threshold..."
}
]
}
}
schema:
$ref: '#/definitions/Flow'
412:
description: |
Precondition failed. An error code and message are returned.
180 - Please provide flow id.
181 - Unknown flow. The flow with the given ID was not found in the database.
schema:
$ref: '#/definitions/Error'
delete:
tags:
- flow
summary: Delete a flow
description: |
Deletes a flow. Upon success, it returns the ID of the deleted flow.
parameters:
- name: id
in: path
description: Id of the flow.
required: true
type: number
format: integer
- name: api_key
in: query
description: API key to authenticate the user
required: true
type: string
responses:
200:
description: ID of the deleted flow
examples:
application/json: |-
{
"flow_delete": {
"id": "4328"
}
}
schema:
type: object
properties:
flow_delete:
$ref: '#/definitions/inline_response_200_8_flow_delete'
412:
description: |
Precondition failed. An error code and message are returned.
320 - Please provide API key. In order to remove your content, please authenticate.
321 - Authentication failed. The API key was not valid. Please try to login again, or contact api administrators.
322 - Flow does not exists. The flow ID could not be linked to an existing flow.
323 - Flow is not owned by you. The flow is owned by another user. Hence you cannot delete it.
324 - Flow is in use by other content. Can not be deleted. The flow is used in runs, evaluations or as a component of another flow. Delete other content before deleting this flow.
325 - Deleting flow failed. Deleting the flow failed. Please contact
support team.
schema:
$ref: '#/definitions/Error'
/flow:
post:
tags:
- flow
summary: Upload a flow
description: |
Uploads a flow. Upon success, it returns the flow id.
consumes:
- multipart/form-data
parameters:
- name: description
in: formData
description: An XML file describing the flow. Only name and description are required. Also see the [XSD schema](https://www.openml.org/api/v1/xsd/openml.implementation.upload) and an [XML example](https://www.openml.org/api/v1/xml_example/flow).
required: true
type: file
- name: flow
in: formData
description: The actual flow, being a source (or binary) file.
required: false
type: file
- name: api_key
in: query
description: Api key to authenticate the user
required: true
type: string
responses:
200:
description: Id of the uploaded flow
examples:
application/json: |-
{
"upload_flow": {
"id": "2520"
}
}
schema:
type: object
properties:
upload_flow:
$ref: '#/definitions/inline_response_200_9_upload_flow'
412:
description: |
Precondition failed. An error code and message are returned.
160 - Error in file uploading. There was a problem with the file upload.
161 - Please provide description xml.
163 - Problem validating uploaded description file. The XML description format does not meet the standards.
164 - Flow already stored in database. Please change name or version number
165 - Failed to insert flow. There can be many causes for this error. If you included the implements field, it should be an existing entry in the algorithm or math_function table. Otherwise it could be an internal server error. Please contact API support team.
166 - Failed to add flow to database. Internal server error, please contact API administrators
167 - Illegal files uploaded. An non required file was uploaded.
168 - The provided md5 hash equals not the server generated md5 hash of the file.
169 - Please provide API key. In order to share content, please authenticate and provide API key.
170 - Authentication failed. The API key was not valid. Please try to login again, or contact API administrators
171 - Flow already exists. This flow is already in the database
172 - XSD not found. Please contact API support team
schema:
$ref: '#/definitions/Error'
/flow/exists/{name}/{version}:
get:
tags:
- flow
summary: Check whether flow exists
description: |
Checks whether a flow with the given name and (external) version exists.
parameters:
- name: name
in: path
description: The name of the flow.
required: true
type: string
- name: version
in: path
description: The external version of the flow
required: true
type: string
- name: api_key
in: query
description: API key to authenticate the user
required: false
type: string
responses:
200:
description: A list of flows
examples:
application/json: |-
{
"flow_exists": {
"exists": "true",
"id": "65"
}
}
schema:
type: object
properties:
flow_exists:
$ref: '#/definitions/inline_response_200_10_flow_exists'
412:
description: |
Precondition failed. An error code and message are returned.
330 - Mandatory fields not present. Please provide name and external_version.
schema:
$ref: '#/definitions/Error'
/flow/list/{filters}:
get:
tags:
- flow
summary: List and filter flows
description: |
List flows, possibly filtered by a range of properties. Any number of properties can be combined by listing them one after the other in the form '/task/list/{filter}/{value}/{filter}/{value}/...' Returns an array with all flows that match the constraints.
parameters:
- name: filters
in: path
description: |
Any combination of these filters
/limit/{limit}/offset/{offset} - returns only {limit} results starting from result number {offset}. Useful for paginating results. With /limit/5/offset/10, tasks 11..15 will be returned. Both limit and offset need to be specified.
/tag/{tag} - returns only tasks tagged with the given tag.
/uploader/{id} - return only evaluations uploaded by a specific user, specified by user ID.
required: true
type: string
- name: api_key
in: query
description: API key to authenticate the user
required: false
type: string
responses:
200:
description: A list of flows
examples:
application/json: |-
{
"flows":
{
"flow":[
{
"id":"65",
"full_name":"weka.RandomForest(1)",
"name":"weka.RandomForest",
"version":"1",
"external_version":"Weka_3.7.10_9186",
"uploader":"1"
},
{
"id":"66",
"full_name":"weka.IBk(1)",
"name":"weka.IBk",
"version":"1",
"external_version":"Weka_3.7.10_8034",
"uploader":"1"
},
{
"id":"67",
"full_name":"weka.BayesNet_K2(1)",
"name":"weka.BayesNet_K2",
"version":"1",
"external_version":"Weka_3.7.10_8034",
"uploader":"1"
}
]
}
}
schema:
$ref: '#/definitions/FlowList'
412:
description: |
Precondition failed. An error code and message are returned.
500 - No results. There where no matches for the given constraints.
501 - Illegal filter specified.
502 - Filter values/ranges not properly specified.
503 - Can not specify an offset without a limit.
schema:
$ref: '#/definitions/Error'
/flow/owned:
get:
tags:
- flow
summary: List flows owned by you
description: |
Returns an array with all flows owned by you.
parameters:
- name: api_key
in: query
description: API key to authenticate the user
required: false
type: string
responses:
200:
description: A list of flows
examples:
application/json: |-
{
"flow_owned": {
"id": [
"111",
"112",
"113",
"114",
"115",
"116",
"117"
]
}
}
schema:
type: object
properties:
flow_owned:
$ref: '#/definitions/inline_response_200_11_flow_owned'
412:
description: |
Precondition failed. An error code and message are returned.
310 - Please provide API key to authenticate.
311 - Authentication failed. The API key was not valid. Please try to login again, or contact api administrators.
312 - No flows owned by you.
schema:
$ref: '#/definitions/Error'
/flow/tag:
post:
tags:
- flow
summary: Tag a flow
description: Tags a flow.
consumes:
- application/x-www-form-urlencoded
parameters:
- name: flow_id
in: formData
description: Id of the flow.
required: true
type: number
format: integer
- name: tag
in: formData
description: Tag name
required: true
type: string
- name: api_key
in: formData
description: Api key to authenticate the user
required: true
type: string
responses:
200:
description: The id of the tagged flow
examples:
application/json: |-
{
"flow_tag": {
"id": "2"
}
}
schema:
type: object
properties:
flow_tag:
$ref: '#/definitions/inline_response_200_12_flow_tag'
412:
description: |
Precondition failed. An error code and message are returned.
470 - In order to add a tag, please upload the entity id (either data_id, flow_id, run_id) and tag (the name of the tag).
471 - Entity not found. The provided entity_id {data_id, flow_id, run_id} does not correspond to an existing entity.
472 - Entity already tagged by this tag. The entity {dataset, flow, run} already had this tag.
473 - Something went wrong inserting the tag. Please contact OpenML Team.
474 - Internal error tagging the entity. Please contact OpenML Team.
schema:
$ref: '#/definitions/Error'
/flow/untag:
post:
tags:
- flow
summary: Untag a flow
description: Untags a flow.
consumes:
- application/x-www-form-urlencoded
parameters:
- name: flow_id
in: formData
description: Id of the flow.
required: true
type: number
- name: tag
in: formData
description: Tag name
required: true
type: string
- name: api_key
in: formData
description: Api key to authenticate the user
required: true
type: string
responses:
200:
description: The id of the untagged flow
examples:
application/json: |-
{
"flow_untag": {
"id": "2"
}
}
schema:
type: object
properties:
flow_untag:
$ref: '#/definitions/inline_response_200_13_flow_untag'
412:
description: |
Precondition failed. An error code and message are returned.
475 - Please give entity_id {data_id, flow_id, run_id} and tag. In order to remove a tag, please upload the entity id (either data_id, flow_id, run_id) and tag (the name of the tag).
476 - Entity {dataset, flow, run} not found. The provided entity_id {data_id, flow_id, run_id} does not correspond to an existing entity.
477 - Tag not found. The provided tag is not associated with the entity {dataset, flow, run}.
478 - Tag is not owned by you. The entity {dataset, flow, run} was tagged
by another user. Hence you cannot delete it.
479 - Internal error removing the tag. Please contact OpenML Team.
schema:
$ref: '#/definitions/Error'
/setup/{id}:
get:
tags:
- setup
summary: Get a hyperparameter setup
description: |
Returns information about a setup. The information includes the list of hyperparameters, with name, value, and default value.
parameters:
- name: id
in: path
description: ID of the hyperparameter setup (configuration). These IDs are stated in run descriptions.
required: true
type: number
format: integer
- name: api_key
in: query
description: API key to authenticate the user
required: false
type: string
responses:
200:
description: A setup description
examples:
application/json: |-
{
"setup_parameters":{
"flow_id":"59",
"parameter":[
{
"full_name":"weka.JRip(1)_F",
"parameter_name":"F",
"data_type":"option",
"default_value":"3",
"value":"3"
},{
"full_name":"weka.JRip(1)_N",
"parameter_name":"N",
"data_type":"option",
"default_value":"2.0",
"value":"2.0"
},{
"full_name":"weka.JRip(1)_O",
"parameter_name":"O",
"data_type":"option",
"default_value":"2",
"value":"2"
},{
"full_name":"weka.JRip(1)_S",
"parameter_name":"S",
"data_type":"option",
"default_value":"1",
"value":"1"
}]
}
}
schema:
$ref: '#/definitions/Setup'
412:
description: |
Precondition failed. An error code and message are returned.
280 - Please provide setup ID. In order to view setup details, please provide the run ID
281 - Setup not found. The setup ID was invalid, or setup does not exist (anymore).
schema:
$ref: '#/definitions/Error'
/run/{id}:
get:
tags:
- run
summary: Get run description
description: |
Returns information about a run. The information includes the name, information about the creator, dependencies, parameters, run instructions and more.
parameters:
- name: id
in: path
description: ID of the run.
required: true
type: number
format: integer
- name: api_key
in: query
description: API key to authenticate the user
required: false
type: string
responses:
200:
description: A run description
examples:
application/json: |-
{
"run": {
"run_id":"100",
"uploader":"1",
"uploader_name":"Jan van Rijn",
"task_id":"28",
"task_type":"Supervised Classification",
"task_evaluation_measure":"predictive_accuracy",
"flow_id":"67",
"flow_name":"weka.BayesNet_K2(1)",
"setup_string":"weka.classifiers.bayes.BayesNet -- -D -Q weka.classifiers.bayes.net.search.local.K2 -- -P 1 -S BAYES -E weka.classifiers.bayes.net.estimate.SimpleEstimator -- -A 0.5",
"parameter_setting": [
{
"name":"D",
"value":"true"
},
{
"name":"Q",
"value":"weka.classifiers.bayes.net.search.local.K2"
},
{
"name":"P",
"value":"1"
},
{
"name":"S",
"value":"BAYES"
}
],
"input_data":
{
"dataset":
{
"did":"28",
"name":"optdigits",
"url":"https:\/\/www.openml.org\/data\/download\/28\/dataset_28_optdigits.arff"
}
},
"output_data":
{
"file": [
{
"did":"48838",
"file_id":"261",
"name":"description",
"url":"https:\/\/www.openml.org\/data\/download\/261\/weka_generated_run935374685998857626.xml"
},
{
"did":"48839",
"file_id":"262",
"name":"predictions",
"url":"https:\/\/www.openml.org\/data\/download\/262\/weka_generated_predictions576954524972002741.arff"
}
],
"evaluation": [
{
"name":"area_under_roc_curve",
"flow_id":"4",
"value":"0.990288",
"array_data":"[0.99724,0.989212,0.992776,0.994279,0.980578,0.98649,0.99422,0.99727,0.994858,0.976143]"
},
{
"name":"confusion_matrix",
"flow_id":"10",
"array_data":"[[544,1,0,0,7,0,1,0,0,1],[0,511,21,1,0,1,3,1,5,28],[0,7,511,1,0,1,0,3,23,11],[0,2,2,519,0,3,0,12,16,18],[0,3,0,0,528,0,4,21,6,6],[0,1,0,7,5,488,2,0,4,51],[1,7,0,0,2,0,548,0,0,0],[0,2,0,1,9,1,0,545,4,4],[1,25,2,2,3,6,2,1,503,9],[0,7,0,20,16,5,0,19,9,486]]"
},
{
"name":"f_measure",
"flow_id":"12",
"value":"0.922723",
"array_data":"[0.989091,0.898857,0.935041,0.92431,0.927944,0.918156,0.980322,0.933219,0.895018,0.826531]"
},
{
"name":"kappa",
"flow_id":"13",
"value":"0.913601"
}
]
}
}
}
schema:
$ref: '#/definitions/Run'
412:
description: |
Precondition failed. An error code and message are returned.
220 - Please provide run ID. In order to view run details, please provide the run ID.
221 - Run not found. The run ID was invalid, run does not exist (anymore).
schema:
$ref: '#/definitions/Error'
delete:
tags:
- run
summary: Delete run
description: |
Deletes a run. Upon success, it returns the ID of the deleted run.
parameters:
- name: id
in: path
description: Id of the run.
required: true
type: number
format: integer
- name: api_key
in: query
description: API key to authenticate the user
required: true
type: string
responses:
200:
description: ID of the deleted run
examples:
application/json: |-
{
"run_delete": {
"id": "2520"
}
}
schema:
type: object
properties:
data_delete:
$ref: '#/definitions/inline_response_200_14_data_delete'
412:
description: |
Precondition failed. An error code and message are returned.
390 - Please provide API key. In order to remove your content, please authenticate.
391 - Authentication failed. The API key was not valid. Please try to login again, or contact api administrators
392 - Run does not exists. The run ID could not be linked to an existing run.
393 - Run is not owned by you. The run was owned by another user. Hence you cannot delete it.
394 - Deleting run failed. Deleting the run failed. Please contact support team.
schema:
$ref: '#/definitions/Error'
/run:
post:
tags:
- run
summary: Upload run
description: |
Uploads a run. Upon success, it returns the run id.
consumes:
- multipart/form-data
parameters:
- name: description
in: formData
description: An XML file describing the dataset. Only name, description, and data format are required. Also see the [XSD schema](https://www.openml.org/api/v1/xsd/openml.run.upload) and an [XML example](https://www.openml.org/api/v1/xml_example/run).
required: true
type: file
- name: predictions
in: formData
description: The predictions generated by the run
required: true
type: file
- name: model_readable
in: formData
description: The human-readable model generated by the run
required: false
type: file
- name: model_serialized
in: formData
description: The serialized model generated by the run
required: false
type: file
- name: api_key
in: query
description: Api key to authenticate the user
required: true
type: string
responses:
200:
description: Id of the uploaded run
examples:
application/json: |-
{
"upload_run": {
"id": "2520"
}
}
schema:
type: object
properties:
upload_flow:
$ref: '#/definitions/inline_response_200_15_upload_flow'
412:
description: |
Precondition failed. An error code and message are returned.
201 - Authentication failed. The API key was not valid. Please try to login again, or contact api administrators.
202 - Please provide run XML.
203 - Could not validate run xml by XSD. Please double check that the xml is valid.
204 - Unknown task. The task with the given ID was not found in the database.
205 - Unknown flow. The flow with the given ID was not found in the database.
206 - Invalid number of files. The number of uploaded files did not match the number of files expected for the task type
207 - File upload failed. One of the files uploaded has a problem.
208 - Error inserting setup record. Please contact api administrators
210 - Unable to store run. Please contact api administrators.
211 - Dataset not in database. One of the datasets of the task was not included in database, please contact api administrators.
212 - Unable to store file. Please contact api administrators.
213 - Parameter in run xml unknown. One of the parameters provided in the run xml is not registered as parameter for the flow nor its components.
214 - Unable to store input setting. Please contact API support team.
215 - Unable to evaluate predictions. Please contact API support team.
216 - Error thrown by Java Application. Additional information field is provided.
217 - Error processing output data. Unknown or inconsistent evaluation measure. One of the provided evaluation measures could not be matched with a record in the math_function or flow table.
218 - Wrong flow associated with run. The flow implements a math_function, which is unable to generate predictions. Please select another flow.
219 - Error reading the XML document. The XML description file could not be verified.
schema:
$ref: '#/definitions/Error'
/run/list/{filters}:
get:
tags:
- run
summary: List and filter runs
description: "List runs, filtered by a range of properties. Any number of properties\
\ can be combined by listing them one after the other in the form '/run/list/{filter}/{value}/{filter}/{value}/...'\
\ Returns an array with all runs that match the constraints. A maximum of\
\ 10,000 results are returned, an error is returned if the result set is bigger.\
\ Use pagination (via limit and offset filters), or limit the results to certain\
\ tasks, flows, setups, or uploaders. \n"
parameters:
- name: filters
in: path
description: |
Any combination of these filters
/tag/{tag} - return only runs tagged with the given tag.
/run/{ids} - return only specific runs, specified as a comma-separated list of run IDs, e.g. ''1,2,3''
/task/{ids} - return only runs on specific tasks, specified as a comma-separated list of task IDs, e.g. ''1,2,3''
/flow/{ids} - return only runs on specific flows, specified as a comma-separated list of flow IDs, e.g. ''1,2,3''
/setup/{ids} - return only runs with specific setups, specified as a comma-separated list of setup IDs, e.g. ''1,2,3''
/uploader/{ids} - return only runs uploaded by specific users, specified as a comma-separated list of user IDs, e.g. ''1,2,3''
/limit/{limit}/offset/{offset} - returns only {limit} results starting from result number {offset}. Useful for paginating results. With /limit/5/offset/10, results 11..15 will be returned. Both limit and offset need to be specified.
required: true
type: string
- name: api_key
in: query
description: API key to authenticate the user
required: false
type: string
responses:
200:
description: A list of runs descriptions
examples:
application/json:
runs:
run:
- run_id: "100"
task_id: "28"
setup_id: "12"
flow_id: "67"
uploader: "1"
upload_time: 2014-04-06 23:30:40
error_message: []
- run_id: "101"
task_id: "48"
setup_id: "6"
flow_id: "61"
uploader: "1"
upload_time: 2014-04-06 23:30:40
error_message: []
- run_id: "102"
task_id: "41"
setup_id: "3"
flow_id: "58"
uploader: "1"
upload_time: 2014-04-06 23:30:40
error_message: []
schema:
$ref: '#/definitions/RunList'
412:
description: |
Precondition failed. An error code and message are returned.
510 - Please provide at least task, flow or setup, uploader or run, to filter results, or limit the number of responses. The number of runs is huge. Please limit the result space.
511 - Input not safe. The input parameters (task_id, setup_id, flow_id, run_id, uploader_id) did not meet the constraints (comma separated list of integers).
512 - There where no results. Check whether there are runs under the given constraint.
513 - Too many results. Given the constraints, there were still too many results. Please add filters to narrow down the list.
514 - Illegal filter specified.
515 - Offset specified without limit.
516 - Requested result limit too high.
schema:
$ref: '#/definitions/Error'
/run/tag:
post:
tags:
- run
summary: Tag a run
description: Tags a run.
consumes:
- application/x-www-form-urlencoded
parameters:
- name: run_id
in: formData
description: Id of the run.
required: true
type: number
format: integer
- name: tag
in: formData
description: Tag name
required: true
type: string
- name: api_key
in: formData
description: Api key to authenticate the user
required: true
type: string
responses:
200:
description: The id of the tagged run
examples:
application/json: |-
{
"run_tag": {
"id": "2"
}
}
schema:
type: object
properties:
run_tag:
$ref: '#/definitions/inline_response_200_16_run_tag'
412:
description: |
Precondition failed. An error code and message are returned.
470 - In order to add a tag, please upload the entity id (either data_id, flow_id, run_id) and tag (the name of the tag).
471 - Entity not found. The provided entity_id {data_id, flow_id, run_id} does not correspond to an existing entity.
472 - Entity already tagged by this tag. The entity {dataset, flow, run} already had this tag.
473 - Something went wrong inserting the tag. Please contact OpenML Team.
474 - Internal error tagging the entity. Please contact OpenML Team.
schema:
$ref: '#/definitions/Error'
/run/untag:
post:
tags:
- run
summary: Untag a run
description: Untags a run.
consumes:
- application/x-www-form-urlencoded
parameters:
- name: run_id
in: formData
description: Id of the run.
required: true
type: number
- name: tag
in: formData
description: Tag name
required: true
type: string
- name: api_key
in: formData
description: Api key to authenticate the user
required: true
type: string
responses:
200:
description: The id of the untagged run
examples:
application/json: |-
{
"run_untag": {
"id": "2"
}
}
schema:
type: object
properties:
run_untag:
$ref: '#/definitions/inline_response_200_17_run_untag'
412:
description: |
Precondition failed. An error code and message are returned.
475 - Please give entity_id {data_id, flow_id, run_id} and tag. In order to remove a tag, please upload the entity id (either data_id, flow_id, run_id) and tag (the name of the tag).
476 - Entity {dataset, flow, run} not found. The provided entity_id {data_id, flow_id, run_id} does not correspond to an existing entity.
477 - Tag not found. The provided tag is not associated with the entity {dataset, flow, run}.
478 - Tag is not owned by you. The entity {dataset, flow, run} was tagged by another user. Hence you cannot delete it.
479 - Internal error removing the tag. Please contact OpenML Team.
schema:
$ref: '#/definitions/Error'
/run/evaluate:
post:
tags:
- run
summary: Uploads a run evaluation
description: |
Uploads a run evaluation. When successful, it returns the run id.
consumes:
- multipart/form-data
parameters:
- name: description
in: formData
description: An XML file describing the run evaluation.Also see the [XSD schema](https://www.openml.org/api/v1/xsd/openml.run.evaluate) and an [XML example](https://www.openml.org/api/v1/xml_example/run.evaluate).
required: true
type: file
- name: api_key
in: query
description: Api key to authenticate the user
required: true
type: string
responses:
200:
description: Id of the evaluated run
examples:
application/json: |-
{
"run_evaluate": {
"id": "2520"
}
}
schema:
type: object
properties:
upload_flow:
$ref: '#/definitions/inline_response_200_18_upload_flow'
412:
description: |
Precondition failed. An error code and message are returned.
422 - Upload problem description XML
423 - Problem validating uploaded description file
424 - Problem opening description xml
schema:
$ref: '#/definitions/Error'
/run/reset/{id}:
get:
tags:
- run
summary: Resets a run.
description: |
Removes all run evaluations. When a run is reset, the runs will automatically be evaluated as soon as they are picked up by the evaluation engine again.
parameters:
- name: id
in: path
description: Run ID.
required: true
type: string
- name: api_key
in: query
description: API key to authenticate the user
required: false
type: string
responses:
200:
description: Id of the evaluated run
examples:
application/json: |-
{
"run_reset": {
"id": "2520"
}
}
schema:
type: object
properties:
run_reset:
$ref: '#/definitions/inline_response_200_18_upload_flow'
412:
description: |
Precondition failed. An error code and message are returned.
412 - Run does not exist
413 - Run is not owned by you
394 - Resetting run failed
schema:
$ref: '#/definitions/Error'
/run/trace/{id}:
get:
tags:
- run
summary: Get run trace
description: |
Returns the optimization trace of run. The trace contains every setup tried, its evaluation, and whether it was selected.
parameters:
- name: id
in: path
description: ID of the run.
required: true
type: number
format: integer
- name: api_key
in: query
description: API key to authenticate the user
required: false
type: string
responses:
200:
description: A run trace description
examples:
application/json: |-
{
"trace": {
"run_id":"573055",
"trace_iteration": {
"repeat":"0",
"fold":"0",
"repeat":"0",
"iteration":"0",
"setup_string":{"parameter_minNumObj": "1",
"parameter_confidenceFactor": "0.1"},
"evaluation":"94.814815",
"selected": "true"
},
"trace_iteration": {
"repeat":"0",
"fold":"0",
"repeat":"0",
"iteration":"1",
"setup_string":{"parameter_minNumObj": "1",
"parameter_confidenceFactor": "0.25"},
"evaluation": "94.074074",
"selected": "true"
}
}
}
schema:
$ref: '#/definitions/RunTrace'
412:
description: |
Precondition failed. An error code and message are returned.
570 - No successful trace associated with this run
schema:
$ref: '#/definitions/Error'
post:
tags:
- run
summary: Upload run
description: |
Uploads a run. Upon success, it returns the run id.
consumes:
- multipart/form-data
parameters:
- name: id
in: path
description: ID of the run.
required: true
type: number
format: integer
- name: description
in: formData
description: An XML file describing the trace. Also see the [XSD schema](https://www.openml.org/api/v1/xsd/openml.run.trace) and an [XML example](https://www.openml.org/api/v1/xml_example/run.trace).
required: true
type: file
- name: api_key
in: query
description: Api key to authenticate the user
required: true
type: string
responses:
200:
description: Id of the run with the trace
examples:
application/json: |-
{
"run_trace": {
"id": "2520"
}
}
schema:
type: object
properties:
upload_flow:
$ref: '#/definitions/inline_response_200_20_upload_flow'
412:
description: |
Precondition failed. An error code and message are returned.
561 - Problem with uploaded trace file.
562 - Problem validating xml trace file.
563 - Problem loading xml trace file.
schema:
$ref: '#/definitions/Error'
/evaluation/list/{filters}:
get:
tags:
- evaluation
summary: List and filter evaluations
description: "List evaluations, filtered by a range of properties. Any number\
\ of properties can be combined by listing them one after the other in the\
\ form '/evaluation/list/{filter}/{value}/{filter}/{value}/...' Returns an\
\ array with all evaluations that match the constraints. A maximum of 10,000\
\ results are returned, an error is returned if the result set is bigger.\
\ Use pagination (via limit and offset filters), or limit the results to certain\
\ tasks, flows, setups, uploaders or runs. \n"
parameters:
- name: filters
in: path
description: |
Any combination of these filters
/function/{name} - name of the evaluation measure, e.g. area_under_auc or predictive_accuracy. See the OpenML website for the complete list of measures.
/tag/{tag} - returns only evaluations of runs tagged with the given tag.
/run/{ids} - return only evaluations for specific runs, specified as a comma-separated list of run IDs, e.g. ''1,2,3''
/task/{ids} - return only evaluations for specific tasks, specified as a comma-separated list of task IDs, e.g. ''1,2,3''
/flow/{ids} - return only evaluations for specific flows, specified as a comma-separated list of flow IDs, e.g. ''1,2,3''
/setup/{ids} - return only evaluations for specific setups, specified as a comma-separated list of setup IDs, e.g. ''1,2,3''
/uploader/{ids} - return only evaluations uploaded by specific users, specified as a comma-separated list of user IDs, e.g. ''1,2,3''
/limit/{limit}/offset/{offset} - returns only {limit} results starting from result number {offset}. Useful for paginating results. With /limit/5/offset/10, results 11..15 will be returned. Both limit and offset need to be specified.
/per_fold/{true,false} - whether or not to return crossvalidation scores per fold. Defaults to 'false'. Setting it to 'true' leads to large numbers of results, use only for very specific sets of runs.
required: true
type: string
- name: api_key
in: query
description: API key to authenticate the user
required: false
type: string
responses:
200:
description: A list of evaluations descriptions
examples:
application/json:
evaluations:
evaluation:
- run_id: "1"
task_id: "68"
flow_id: "61"
function: area_under_roc_curve
upload_time: 2014-04-06 23:30:40
value: "0.839359"
array_data: '[0,0.99113,0.898048,0.874862,0.791282,0.807343,0.820674]'
- run_id: "1"
task_id: "68"
flow_id: "61"
function: f_measure
upload_time: 2014-04-06 23:30:40
value: "0.600026"
array_data: '[0,0,0.711934,0.735714,0.601363,0.435678,0.430913]'
- run_id: "1"
task_id: "68"
flow_id: "61"
function: predictive_accuracy
upload_time: 2014-04-06 23:30:40
value: "0.614634"
array_data: []
schema:
$ref: '#/definitions/EvaluationList'
412:
description: |
Precondition failed. An error code and message are returned.
540 - Please provide at least task, flow or setup, uploader or run, to
filter results, or limit the number of responses.
541 - The input parameters (task_id, setup_id, flow_id, run_id, uploader_id) did not meet the constraints (comma separated list of integers).
542 - There where no results. Check whether there are runs under the given constraint.
543 - Too many results. Given the constraints, there were still too many results. Please add filters to narrow down the list.
544 - Illegal filter specified.
545 - Offset specified without limit.
546 - Requested result limit too high.
547 - Per fold can only be set to value "true" or "false".
548 - Per fold queries are experimental and require a fair amount of filters on resulting run records to keep the query fast (use, e.g., flow, setup, task and uploader filter)
schema:
$ref: '#/definitions/Error'
/evaluation/request/{evaluation_engine_id}/{order}:
get:
tags:
- evaluation
summary: Get an unevaluated run
description: |
This call is for people running their own evaluation engines. It returns the details of a run that is not yet evaluated by the given evaluation engine. It doesn't evaluate the run, it just returns the run info.
parameters:
- name: evaluation_engine_id
in: path
description: The ID of the evaluation engine. You get this ID when you register a new evaluation engine with OpenML. The ID of the main evaluation engine is 1.
required: true
type: string
- name: order
in: path
description: When there are multiple runs still to evaluate, this defines which one to return. Options are 'normal' - the oldest run, 'reverse' - the newest run, or 'random' - a random run.
required: true
type: string
- name: api_key
in: query
description: API key to authenticate the user
required: false
type: string
responses:
200:
description: A list of evaluations descriptions
examples:
application/json:
evaluation_request:
run:
- run_id: "8943712"
task_id: "3021"
setup_id: "68799271"
uploader: "1935"
upload_time: 2018-04-03 21:05:38
schema:
$ref: '#/definitions/EvaluationRequest'
412:
description: |
Precondition failed. An error code and message are returned.
100 - Function not valid.
545 - No unevaluated runs according to the criteria.
546 - Illegal filter.
schema:
$ref: '#/definitions/Error'
/study/{id}:
get:
tags:
- study
summary: Get study description by study id or alias
description: "Returns information about the study with the given id or alias.\
\ \n"
parameters:
- name: id
in: path
description: ID or alias of the study.
required: true
type: string
- name: api_key
in: query
description: Api key to authenticate the user
required: false
type: string
responses:
200:
description: A study description
examples:
application/json: |-
{
"study": {
"id": "99",
"main_entity_type": "task",
"name": "CC18 benchmark suite",
"description": "CC18 benchmark suite",
"creation_date": "2019-02-16T17:35:58",
"creator": "1159",
"data": {"data_id": ["1","2","3"]},
"tasks": {"task_id": ["1","2","3"]}
}
}
schema:
$ref: '#/definitions/Study'
412:
description: |
Precondition failed. An error code and message are returned.
601 - Unknown study. The study with the given id or alias was not found in the database
schema:
$ref: '#/definitions/Error'
delete:
tags:
- study
summary: Delete study
description: |
Deletes a study. Upon success, it returns the ID of the deleted study.
parameters:
- name: id
in: path
description: Id of the study.
required: true
type: number
format: integer
- name: api_key
in: query
description: Api key to authenticate the user
required: true
type: string
responses:
200:
description: ID of the deleted study
examples:
application/json: |-
{
"study_delete": {
"id": "1"
}
}
schema:
type: object
properties:
study_delete:
$ref: '#/definitions/inline_response_200_21_study_delete'
412:
description: |
Precondition failed. An error code and message are returned.
591 - Please provide API key. In order to remove your content, please authenticate.
592 - Study does not exists. The study ID could not be linked to an existing study.
593 - Study deletion failed. Please try again later.
schema:
$ref: '#/definitions/Error'
/study:
post:
tags:
- study
summary: Create new study
description: |
Creates a new study. Upon success, it returns the study id.
consumes:
- multipart/form-data
parameters:
- name: description
in: formData
description: An XML file describing the study. Also see the [XSD schema](https://www.openml.org/api/v1/xsd/openml.study.upload) and an [XML example](https://www.openml.org/api/v1/xml_example/study).
required: true
type: file
- name: api_key
in: query
description: Api key to authenticate the user
required: true
type: string
responses:
200:
description: Id of the uploaded study
examples:
application/json: |-
{
"upload_study": {
"id": "4328"
}
}
schema:
type: object
properties:
upload_study:
$ref: '#/definitions/inline_response_200_22_upload_study'
412:
description: |
Precondition failed. An error code and message are returned.
1031 - Description file not present. Please upload the study description.
1032 - Problem validating uploaded description file. The XML description format does not meet the standards. See the XSD schema.
1033 - Illegal main entity type. Currently only collections of tasks and can be created.
1034 - Linked entities are not of the correct type fot this study.
1035 - Benchmark suites can only be linked to run studies.
1036 - Referred benchmark suite cannot be found.
1037 - Referred benchmark suite should be a task collection.
1038 - Study alias is not unique.
1039 - Dataset insertion problem. Please contact the administrators.
schema:
$ref: '#/definitions/Error'
/study/list/{filters}:
get:
tags:
- study
summary: List all studies (collections of items)
description: |
List studies, optionally filtered by a range of properties. Any number of properties can be combined by listing them one after the other in the form '/study/list/{filter}/{value}/{filter}/{value}/...' Returns an array with all studies that match the constraints.
parameters:
- name: filters
in: path
description: |
Any combination of these filters
/main_entity_type/{type} - only return studies collecting entities of a given type (e.g. 'task' or 'run').
/uploader/{ids} - return only evaluations uploaded by specific users, specified as a comma-separated list of user IDs, e.g. ''1,2,3''
/limit/{limit}/offset/{offset} - returns only {limit} results starting from result number {offset}. Useful for paginating results. With /limit/5/offset/10, results 11..15 will be returned. Both limit and offset need to be specified.
required: true
type: string
- name: api_key
in: query
description: API key to authenticate the user
required: false
type: string
responses:
200:
description: A list of studies
examples:
application/json: |-
{
"study_list":{
"study":[
{
"id":"1",
"alias":"Study_1",
"name":"A large-scale comparison of classification algorithms",
"creation_date":"2017-07-20 15:51:20",
"creator":"2"
},
{
"id":"2",
"alias":"Study_2",
"name":"Fast Algorithm Selection using Learning Curves",
"creation_date":"2017-07-20 15:51:20",
"creator":"2"
}
]
}
},
schema:
$ref: '#/definitions/StudyList'
412:
description: |
Precondition failed. An error code and message are returned.
schema:
$ref: '#/definitions/Error'
/study/{id}/attach:
post:
tags:
- study
summary: Attach a new entity to a study
description: |
Attach a new entity to an exising study. Upon success, it returns the study id, type, and linked entities.
consumes:
- multipart/form-data
parameters:
- name: id
in: path
description: Id of the study.
required: true
type: number
format: integer
- name: description
in: formData
description: An XML file describing the entities to be attached. Also see the [XSD schema](https://www.openml.org/api/v1/xsd/openml.study.attach) and an [XML example](https://www.openml.org/api/v1/xml_example/attach).
required: true
type: file
- name: api_key
in: query
description: Api key to authenticate the user
required: true
type: string
responses:
200:
description: Properties of the updated study
examples:
application/json: |-
{
"study_attach": {
"id": "1",
"main_entity_type": "task",
"linked_entities": "5"
}
}
schema:
type: object
properties:
study_attach:
$ref: '#/definitions/inline_response_200_23_study_attach'
412:
description: |
Precondition failed. An error code and message are returned.
1041 - Could not find study. Check the study ID in your request.
1042 - Cannnot attach entities to legacy studies.
1043 - Please provide POST field 'ids'.
1044 - Please ensure that the 'ids' in the POST field is a list of natural numbers.
1045 - Could not attach entities to the study. It appears as if the entity does not exist.
schema:
$ref: '#/definitions/Error'
/study/{id}/detach:
post:
tags:
- study
summary: Detach an entity from a study
description: |
Detach an entity from an exising study. Upon success, it returns the study id, type, and linked entities.
consumes:
- multipart/form-data
parameters:
- name: id
in: path
description: Id of the study.
required: true
type: number
format: integer
- name: description
in: formData
description: An XML file describing the entities to be detached. Also see the [XSD schema](https://www.openml.org/api/v1/xsd/openml.study.detach) and an [XML example](https://www.openml.org/api/v1/xml_example/detach).
required: true
type: file
- name: api_key
in: query
description: Api key to authenticate the user
required: true
type: string
responses:
200:
description: Properties of the updated study
examples:
application/json: |-
{
"study_detach": {
"id": "1",
"main_entity_type": "task",
"linked_entities": "5"
}
}
schema:
type: object
properties:
upload_study:
$ref: '#/definitions/inline_response_200_23_study_attach'
412:
description: "Precondition failed. An error code and message are returned.\n\
1041 - Could not find study. Check the study ID in your request.\n1042\
\ - Cannot attach entities to legacy studies.\n1043 - Please provide POST\
\ field 'ids'.\n1044 - Please ensure that the 'ids' in the POST field\
\ is a list of natural numbers.\n1046 - Could not detach entities from\
\ the study. It appears as if the entity does not exist. \n"
schema:
$ref: '#/definitions/Error'
/estimationprocedure/list:
get:
tags:
- estimationprocedure
summary: List all estimation procedures
description: |
Returns an array with all model performance estimation procedures in the system.
parameters:
- name: api_key
in: query
description: API key to authenticate the user
required: false
type: string
responses:
200:
description: A list of estimation procedures
examples:
application/json: |-
{
"estimationprocedures": {
"estimationprocedure": [
{
"id":"1",
"ttid":"1",
"name":"10-fold Crossvalidation",
"type":"crossvalidation",
"repeats":"1",
"folds":"10",
"stratified_sampling":"true"
},
{
"id":"2",
"ttid":"1",
"name":"5 times 2-fold Crossvalidation",
"type":"crossvalidation",
"repeats":"5",
"folds":"2",
"stratified_sampling":"true"
}
]
}
}
schema:
$ref: '#/definitions/EstimationProcedureList'
412:
description: |
Precondition failed. An error code and message are returned.
500 - No model performance estimation procedures available.
schema:
$ref: '#/definitions/Error'
definitions:
Flow:
type: object
properties:
flow_description:
$ref: '#/definitions/Flow_flow_description'
FlowList:
type: object
properties:
flows:
$ref: '#/definitions/FlowList_flows'
Task:
type: object
properties:
task_description:
$ref: '#/definitions/Task_task_description'
TaskList:
type: object
properties:
task:
$ref: '#/definitions/TaskList_task'
EstimationProcedureList:
type: object
properties:
estimationprocedures:
$ref: '#/definitions/EstimationProcedureList_estimationprocedures'
DataList:
type: object
properties:
data:
$ref: '#/definitions/DataList_data'
DataQualities:
type: object
properties:
data_qualities:
$ref: '#/definitions/DataQualities_data_qualities'
DataQualityList:
type: object
properties:
data_qualities_list:
$ref: '#/definitions/DataQualityList_data_qualities_list'
DataFeatures:
type: object
properties:
data_features:
$ref: '#/definitions/DataFeatures_data_features'
Data:
type: object
properties:
data_set_description:
$ref: '#/definitions/Data_data_set_description'
RunList:
type: object
properties:
runs:
$ref: '#/definitions/RunList_runs'
EvaluationList:
type: object
properties:
evaluations:
$ref: '#/definitions/EvaluationList_evaluations'
EvaluationRequest:
type: object
properties:
evaluation_request:
$ref: '#/definitions/EvaluationRequest_evaluation_request'
DataUnprocessed:
type: object
properties:
data_unprocessed:
$ref: '#/definitions/DataUnprocessed_data_unprocessed'
Setup:
type: object
properties:
setup_parameters:
$ref: '#/definitions/Setup_setup_parameters'
Run:
type: object
properties:
run_description:
$ref: '#/definitions/Run_run_description'
TaskType:
type: object
properties:
id:
type: string
description: ID of the task type, a positive integer
name:
type: string
description: The name of the task type, e.g. Supervised Classification
description:
type: string
description: A description of the task type
contributor:
type: array
items:
type: string
description: A list of people who defined the task type
date:
type: string
description: The date when the task type was created
input:
type: array
items:
$ref: '#/definitions/TaskType_input'
output:
type: array
items:
$ref: '#/definitions/TaskType_output'
TaskTypeList:
type: object
properties:
task_types:
$ref: '#/definitions/TaskTypeList_task_types'
Study:
type: object
properties:
study:
$ref: '#/definitions/Study_study'
StudyList:
type: object
properties:
study_list:
$ref: '#/definitions/StudyList_study_list'
RunTrace:
type: object
properties:
trace:
$ref: '#/definitions/RunTrace_trace'
Error:
type: object
properties:
code:
type: integer
format: int32
message:
type: string
additional_message:
type: string
inline_response_200_data_delete:
properties:
id:
type: string
description: ID of the deleted dataset, a positive integer
inline_response_200:
properties:
data_delete:
$ref: '#/definitions/inline_response_200_data_delete'
inline_response_200_1_upload_data_set:
properties:
id:
type: string
description: ID of the uploaded dataset, a positive integer
inline_response_200_1:
properties:
upload_data_set:
$ref: '#/definitions/inline_response_200_1_upload_data_set'
inline_response_200_2_data_tag:
properties:
id:
type: string
description: ID of the tagged dataset
inline_response_200_2:
properties:
data_tag:
$ref: '#/definitions/inline_response_200_2_data_tag'
inline_response_200_3_data_untag:
properties:
id:
type: string
description: ID of the untagged dataset
inline_response_200_3:
properties:
data_untag:
$ref: '#/definitions/inline_response_200_3_data_untag'
inline_response_200_4_task_delete:
properties:
id:
type: string
description: ID of the deleted task, a positive integer
inline_response_200_4:
properties:
task_delete:
$ref: '#/definitions/inline_response_200_4_task_delete'
inline_response_200_5_upload_task:
properties:
id:
type: string
description: ID of the uploaded task, a positive integer
inline_response_200_5:
properties:
upload_task:
$ref: '#/definitions/inline_response_200_5_upload_task'
inline_response_200_6_task_tag:
properties:
id:
type: string
description: ID of the tagged task
inline_response_200_6:
properties:
task_tag:
$ref: '#/definitions/inline_response_200_6_task_tag'
inline_response_200_7_task_untag:
properties:
id:
type: string
description: ID of the untagged task
inline_response_200_7:
properties:
task_untag:
$ref: '#/definitions/inline_response_200_7_task_untag'
inline_response_200_8_flow_delete:
properties:
id:
type: string
description: ID of the deleted flow, a positive integer
inline_response_200_8:
properties:
flow_delete:
$ref: '#/definitions/inline_response_200_8_flow_delete'
inline_response_200_9_upload_flow:
properties:
id:
type: string
description: ID of the uploaded flow, a positive integer
inline_response_200_9:
properties:
upload_flow:
$ref: '#/definitions/inline_response_200_9_upload_flow'
inline_response_200_10_flow_exists:
properties:
exists:
type: string
description: true or false
id:
type: string
description: The id of the flow with the given name and (external) version
inline_response_200_10:
properties:
flow_exists:
$ref: '#/definitions/inline_response_200_10_flow_exists'
inline_response_200_11_flow_owned:
properties:
id:
type: array
items:
type: string
inline_response_200_11:
properties:
flow_owned:
$ref: '#/definitions/inline_response_200_11_flow_owned'
inline_response_200_12_flow_tag:
properties:
id:
type: string
description: ID of the tagged flow
inline_response_200_12:
properties:
flow_tag:
$ref: '#/definitions/inline_response_200_12_flow_tag'
inline_response_200_13_flow_untag:
properties:
id:
type: string
description: ID of the untagged flow
inline_response_200_13:
properties:
flow_untag:
$ref: '#/definitions/inline_response_200_13_flow_untag'
inline_response_200_14_data_delete:
properties:
id:
type: string
description: ID of the deleted run, a positive integer
inline_response_200_14:
properties:
data_delete:
$ref: '#/definitions/inline_response_200_14_data_delete'
inline_response_200_15_upload_flow:
properties:
id:
type: string
description: ID of the uploaded run, a positive integer
inline_response_200_15:
properties:
upload_flow:
$ref: '#/definitions/inline_response_200_15_upload_flow'
inline_response_200_16_run_tag:
properties:
id:
type: string
description: ID of the tagged run
inline_response_200_16:
properties:
run_tag:
$ref: '#/definitions/inline_response_200_16_run_tag'
inline_response_200_17_run_untag:
properties:
id:
type: string
description: ID of the untagged run
inline_response_200_17:
properties:
run_untag:
$ref: '#/definitions/inline_response_200_17_run_untag'
inline_response_200_18_upload_flow:
properties:
id:
type: string
description: ID of the evaluated run, a positive integer
inline_response_200_18:
properties:
upload_flow:
$ref: '#/definitions/inline_response_200_18_upload_flow'
inline_response_200_19:
properties:
run_reset:
$ref: '#/definitions/inline_response_200_18_upload_flow'
inline_response_200_20_upload_flow:
properties:
id:
type: string
description: ID of the run with the trace, a positive integer
inline_response_200_20:
properties:
upload_flow:
$ref: '#/definitions/inline_response_200_20_upload_flow'
inline_response_200_21_study_delete:
properties:
id:
type: string
description: ID of the deleted study, a positive integer
inline_response_200_21:
properties:
study_delete:
$ref: '#/definitions/inline_response_200_21_study_delete'
inline_response_200_22_upload_study:
properties:
id:
type: string
description: ID of the uploaded study, a positive integer
inline_response_200_22:
properties:
upload_study:
$ref: '#/definitions/inline_response_200_22_upload_study'
inline_response_200_23_study_attach:
properties:
id:
type: string
description: ID of the study, a positive integer
main_entity_type:
type: string
description: Main entity type of the of the study
linked_entities:
type: string
description: The number of linked entities
inline_response_200_23:
properties:
study_attach:
$ref: '#/definitions/inline_response_200_23_study_attach'
inline_response_200_24:
properties:
upload_study:
$ref: '#/definitions/inline_response_200_23_study_attach'
Flow_flow_description_parameter:
properties:
name:
type: string
description: The name of the parameter
data_type:
type: string
description: The data type of the parameter
default_value:
type: string
description: The default value of the parameter
description:
type: string
description: A description of the parameter
Flow_flow_description:
properties:
id:
type: string
description: ID of the flow, a positive integer
uploader:
type: string
description: The uploader of the flow
name:
type: string
description: The name of the flow
version:
type: string
description: The version of the flow, set by OpenML. A positive integer
version_label:
type: string
description: The version of the flow, as defined by the uploader, for reference. Can be any format as long as it is unique.
description:
type: string
description: Wiki description of the flow, in (Git flavoured) markdown format
upload_date:
type: string
description: The datetime that the flow was uploaded, format yyyy-MM-dd HH:mm:ss
language:
type: string
description: The programming language the flow is written in.
dependencies:
type: string
description: The libraries that this flow depends on, and their version numbers.
tag:
type: array
description: Tags added by OpenML users. Includes study tags in the form `study_1`
items:
type: string
parameter:
type: array
items:
$ref: '#/definitions/Flow_flow_description_parameter'
FlowList_flows_flow:
properties:
id:
type: string
description: The flow ID
full_name:
type: string
description: The full flow name (name + internal version number)
name:
type: string
description: The flow name
version:
type: string
description: The internal flow version
external_version:
type: string
description: The external flow version
uploader:
type: string
description: The ID of the person who uploaded the flow
FlowList_flows:
properties:
flow:
type: array
items:
$ref: '#/definitions/FlowList_flows_flow'
Task_task_description_data_set:
properties:
data_set_id:
type: string
description: The id of the dataset
target_feature:
type: string
description: The name of the target feature for this task
Task_task_description_estimation_procedure_parameter:
properties:
name:
type: string
description: The name of the parameter
value:
type: string
description: The value of the parameter
Task_task_description_estimation_procedure:
properties:
type:
type: string
description: The type of procedure, e.g. crossvalidation
data_splits_url:
type: string
description: The url where the data splits can be downloaded
parameter:
type: array
items:
$ref: '#/definitions/Task_task_description_estimation_procedure_parameter'
Task_task_description_evaluation_measures:
properties:
evaluation_measure:
type: string
description: The evaluation measure to optimize in this task
Task_task_description_input:
properties:
name:
type: string
description: The name of the input, e.g. source_data
data_set:
$ref: '#/definitions/Task_task_description_data_set'
estimation_procedure:
$ref: '#/definitions/Task_task_description_estimation_procedure'
cost_matrix:
type: array
description: The cost matrix, indicating the costs for each type of misclassification
items:
type: array
items:
type: integer
format: int64
evaluation_measures:
$ref: '#/definitions/Task_task_description_evaluation_measures'
Task_task_description_predictions_feature:
properties:
name:
type: string
description: The name of the prediction feature, e.g. row_id
type:
type: string
description: The type of the prediction feature, e.g. integer
Task_task_description_predictions:
properties:
format:
type: string
description: The fromat of the predictions, e.g. ARFF
feature:
type: array
items:
$ref: '#/definitions/Task_task_description_predictions_feature'
Task_task_description_output:
properties:
name:
type: string
description: The name of the output, e.g. predictions
predictions:
$ref: '#/definitions/Task_task_description_predictions'
Task_task_description:
properties:
task_id:
type: string
description: ID of the task, a positive integer
task_type:
type: string
description: The type of the task, e.g. Supervised Classification
input:
type: array
items:
$ref: '#/definitions/Task_task_description_input'
output:
type: array
items:
$ref: '#/definitions/Task_task_description_output'
tag:
type: array
items:
type: string
description: Tags added by OpenML users. Includes study tags in the form `study_1`
TaskList_task_input:
properties:
name:
type: string
description: The name of the input
value:
type: string
description: The value of the input
TaskList_task_quality:
properties:
name:
type: string
description: The name of the quality
value:
type: string
description: The value of the quality
TaskList_task_task:
properties:
task_id:
type: string
description: The ID of the task
task_type:
type: string
description: The type of task (e.g. Supervised Classificationr)
did:
type: string
description: The id of the source dataset
name:
type: string
description: The name of the source dataset
status:
type: string
description: The status of the source dataset, active, in_preparation, or deactivated
format:
type: string
description: The format of the source dataset
input:
type: array
items:
$ref: '#/definitions/TaskList_task_input'
quality:
type: array
items:
$ref: '#/definitions/TaskList_task_quality'
tag:
type: array
items:
type: string
description: Tags added by OpenML users. Includes study tags in the form `study_1`
TaskList_task:
properties:
task:
type: array
items:
$ref: '#/definitions/TaskList_task_task'
EstimationProcedureList_estimationprocedures_estimationprocedure:
properties:
id:
type: string
description: The estimation procedure ID
ttid:
type: string
description: The task type ID
name:
type: string
description: The estimation procedure name, e.g. '10 fold Crossvalidation'
type:
type: string
description: The estimation procedure type, e.g. 'crossvalidation'
repeats:
type: string
description: The number of repeats, e.g. '10'
folds:
type: string
description: The number of cross-validation folds, e.g. '10'
stratified_sampling:
type: string
description: Whether or not the sampling is stratified, 'true' or 'false'
EstimationProcedureList_estimationprocedures:
properties:
estimationprocedure:
type: array
items:
$ref: '#/definitions/EstimationProcedureList_estimationprocedures_estimationprocedure'
DataList_data_quality:
properties:
name:
type: string
description: The name of the property
value:
type: string
description: The value of the property
DataList_data_dataset:
properties:
did:
type: string
description: The dataset ID
name:
type: string
description: The dataset name
status:
type: string
description: The dataset status, either in_preparation, active, or deactivated
format:
type: string
description: The data format of the dataset, e.g. ARFF
quality:
type: array
items:
$ref: '#/definitions/DataList_data_quality'
DataList_data:
properties:
dataset:
type: array
items:
$ref: '#/definitions/DataList_data_dataset'
DataQualities_data_qualities_quality:
properties:
name:
type: string
description: The name of the dataset quality measures
value:
type: string
description: The value for this dataset
DataQualities_data_qualities:
properties:
quality:
type: array
items:
$ref: '#/definitions/DataQualities_data_qualities_quality'
DataQualityList_data_qualities_list:
properties:
quality:
type: array
items:
type: string
DataFeatures_data_features_feature:
properties:
index:
type: string
description: Feature index
name:
type: string
description: Feature name
data_type:
type: string
description: Feature data type
is_target:
type: string
description: Whether this feature is seen as a target feature
is_ignore:
type: string
description: Whether this feature should be ignored in modelling (e.g. every value is unique)
is_row_identifier:
type: string
description: Whether this feature is a row identifier
DataFeatures_data_features:
properties:
feature:
type: array
items:
$ref: '#/definitions/DataFeatures_data_features_feature'
Data_data_set_description:
required:
- description
- format
- name
properties:
id:
type: string
description: ID of the dataset, a positive integer
name:
type: string
description: The name of the dataset
version:
type: string
description: The version of the dataset, set by OpenML. A positive integer
description:
type: string
description: Wiki description of the dataset, in (Git flavoured) markdown format
format:
type: string
description: Data format, for instance ARFF
upload_date:
type: string
description: The datetime that the dataset was uploaded, format yyyy-MM-dd HH:mm:ss
licence:
type: string
description: The licence granted for using the dataset, for instance Public or CC-BY
url:
type: string
description: The URL where the data can be downloaded
file_id:
type: string
description: The ID of the dataset file stored on the OpenML server
default_target_attribute:
type: string
description: For tabular data, the name of the column that is typically used as the target attribute for that data set
version_label:
type: string
description: The version of the dataset, as defined by the uploader, for reference. Can be any format as long as it is unique.
tag:
type: array
description: Tags added by OpenML users. Includes study tags in the form `study_1`
items:
type: string
visibility:
type: string
description: Who can see the dataset. For instance `public`.
original_data_url:
type: string
description: The URL where the original data is hosted.
status:
type: string
description: active, in_preparation, or deactivated
md5_checksum:
type: string
description: Checksum to verify downloads of the dataset
RunList_runs_run:
properties:
run_id:
type: string
description: The run ID
task_id:
type: string
description: The ID of the task solved by this run
setup_id:
type: string
description: Ignore (internal representation of the parameter setting)
flow_id:
type: string
description: The ID of the flow used in this run
uploader:
type: string
description: The ID of the person uploading this run
error_message:
type: string
description: Error message generated by the run (if any)
RunList_runs:
properties:
run:
type: array
items:
$ref: '#/definitions/RunList_runs_run'
EvaluationList_evaluations_evaluation:
properties:
run_id:
type: string
description: The run ID
task_id:
type: string
description: The ID of the tasks solved by this run
flow_id:
type: string
description: The ID of the flow used by this run
function:
type: string
description: The name of the evaluation function
value:
type: string
description: The outcome of the evaluation
array_data:
type: string
description: For structured evaluation measures, an array of evaluation values (e.g. per-class predictions, evaluation matrices,...)
EvaluationList_evaluations:
properties:
evaluation:
type: array
items:
$ref: '#/definitions/EvaluationList_evaluations_evaluation'
EvaluationRequest_evaluation_request_run:
properties:
run_id:
type: string
description: ID of the run, a positive integer
task_id:
type: string
description: ID of the task, a positive integer
setup_id:
type: string
description: ID of the setup, a positive integer
uploader:
type: string
description: ID of the uploader, a positive integer
upload_time:
type: string
description: The datetime that the dataset was uploaded, format yyyy-MM-dd HH:mm:ss
EvaluationRequest_evaluation_request:
properties:
run:
$ref: '#/definitions/EvaluationRequest_evaluation_request_run'
DataUnprocessed_data_unprocessed_dataset:
properties:
did:
type: string
description: ID of the dataset a positive integer
name:
type: string
description: The name of the dataset
version:
type: string
description: Version of the dataset, a positive integer
status:
type: string
description: Status of the dataset
format:
type: string
description: The dataset format, e.g. ARFF
DataUnprocessed_data_unprocessed:
properties:
dataset:
$ref: '#/definitions/DataUnprocessed_data_unprocessed_dataset'
Setup_setup_parameters_parameter_setting:
properties:
full_name:
type: string
description: The full name of the hyperparameter
parameter_name:
type: string
description: The short name of the hyperparameter
data_type:
type: string
description: The data type of the hyperparameter value
default_value:
type: string
description: The default value of the parameter used
value:
type: string
description: The value of the parameter used
description: Hyperparameter settings. Can be multiple.
Setup_setup_parameters:
properties:
flow_id:
type: string
description: ID of the flow, a positive integer
parameter_setting:
type: array
items:
$ref: '#/definitions/Setup_setup_parameters_parameter_setting'
Run_run_description_parameter_setting:
properties:
name:
type: string
description: The name of the parameter
value:
type: string
description: The value of the parameter used
description: Parameter settings used in this run. Can be multiple.
Run_run_description_input_data_dataset:
properties:
did:
type: string
description: The id of the dataset
name:
type: string
description: The name of the dataset
url:
type: string
description: The download url of the dataset
Run_run_description_input_data:
properties:
dataset:
$ref: '#/definitions/Run_run_description_input_data_dataset'
description: The input data for this run.
Run_run_description_output_data_file:
properties:
did:
type: string
description: The id of the uploaded file
file_id:
type: string
description: The reference id of the uploaded file, for downloading afterward
name:
type: string
description: The name of the uploaded file (e.g., description, predictions, model,...)
description: Files uploaded by the user, e.g. run description, predictions. Can be multiple.
Run_run_description_output_data_evaluation:
properties:
name:
type: string
description: The name of the evaluation measure
flow_id:
type: string
description: The id of the code used to compute this evaluation method
value:
type: string
description: The result of the evaluation
array_data:
type: string
description: For composite evaluation measures (e.g. per-class measures, confusion matrix), a string (JSON) representation of the evaluation.
description: Evaluations uploaded by the user, e.g. runtimes, or computed by the server (after run upload). Can be multiple.
Run_run_description_output_data:
properties:
file:
type: array
items:
$ref: '#/definitions/Run_run_description_output_data_file'
evaluation:
type: array
items:
$ref: '#/definitions/Run_run_description_output_data_evaluation'
description: The data generated by this run.
Run_run_description:
properties:
id:
type: string
description: ID of the run, a positive integer
uploader:
type: string
description: The uploader of the run
uploader_name:
type: string
description: The name of the uploader of the run
task_id:
type: string
description: The id of the task solved by this run
task_type:
type: string
description: The type of task solved by this run (e.g., classification)
task_evaluation_measure:
type: string
description: The evaluation measure that is supposed to be optimized in the task, if any
flow_id:
type: string
description: The id of the flow used in this run
flow_name:
type: string
description: The name of the flow used in this run
setup_string:
type: string
description: Configuration of the flow as a string, to be interpreted by the flow, its library, or command line interface.
tag:
type: array
description: Tags added by OpenML users. Includes study tags in the form `study_1`
items:
type: string
parameter_setting:
type: array
items:
$ref: '#/definitions/Run_run_description_parameter_setting'
input_data:
$ref: '#/definitions/Run_run_description_input_data'
output_data:
$ref: '#/definitions/Run_run_description_output_data'
TaskType_input:
properties:
name:
type: string
description: The name of the input, e.g. source_data
data_set:
$ref: '#/definitions/Task_task_description_data_set'
estimation_procedure:
$ref: '#/definitions/Task_task_description_estimation_procedure'
cost_matrix:
type: array
items:
type: array
description: The cost matrix, indicating the costs for each type of misclassification
items:
type: integer
format: int64
evaluation_measures:
$ref: '#/definitions/Task_task_description_evaluation_measures'
TaskType_predictions:
properties:
format:
type: string
description: The format of the predictions, e.g. ARFF
feature:
type: array
items:
$ref: '#/definitions/Task_task_description_predictions_feature'
TaskType_output:
properties:
name:
type: string
description: The name of the output, e.g. predictions
predictions:
$ref: '#/definitions/TaskType_predictions'
TaskTypeList_task_types_task_type:
properties:
id:
type: string
description: The ID of the task type
name:
type: string
description: The name of the task type
description:
type: string
description: A description of the task type
creator:
type: string
description: A comma-separated list of the task type creators
TaskTypeList_task_types:
properties:
task_type:
type: array
items:
$ref: '#/definitions/TaskTypeList_task_types_task_type'
Study_study_tag:
properties:
name:
type: string
description: The name of the study (e.g. study_1)
write_access:
type: string
description: The write access level of the study (e.g. public)
Study_study_data:
properties:
data_id:
type: array
items:
type: string
description: The IDs of the datasets that are directly or indirectly linked to the study (e.g. because it is part of a task that belongs to the study)
Study_study_tasks:
properties:
task_id:
type: array
items:
type: string
description: The IDs of the tasks that are directly or indirectly linked to the study (e.g. because it is part of a run that belongs to the study)
Study_study_flows:
properties:
flow_id:
type: array
items:
type: string
description: The IDs of the flows that are directly or indirectly linked to the study (e.g. because it is part of a run that belongs to the study)
Study_study_runs:
properties:
run_id:
type: array
items:
type: string
description: The IDs of the runs attached to this study
Study_study:
properties:
id:
type: string
description: The ID of the study
alias:
type: string
description: The alias of the study
main_entity_type:
type: string
description: The type of entity collected in the study (e.g. task or run)
name:
type: string
description: The name of the study
creation_date:
type: string
description: The datetime that the dataset was uploaded, format yyyy-MM-dd HH:mm:ss
creator:
type: string
description: A comma-separated list of the study creators
tag:
$ref: '#/definitions/Study_study_tag'
data:
$ref: '#/definitions/Study_study_data'
tasks:
$ref: '#/definitions/Study_study_tasks'
flows:
$ref: '#/definitions/Study_study_flows'
runs:
$ref: '#/definitions/Study_study_runs'
StudyList_study_list_study:
properties:
id:
type: string
description: The ID of the study
alias:
type: string
description: The alias of the study
name:
type: string
description: The name of the study
creation_date:
type: string
description: The datetime that the dataset was uploaded, format yyyy-MM-dd HH:mm:ss
creator:
type: string
description: A comma-separated list of the study creators
StudyList_study_list:
properties:
study:
type: array
items:
$ref: '#/definitions/StudyList_study_list_study'
RunTrace_trace_trace_iteration:
properties:
repeat:
type: string
description: The number of the repeat in the outer cross-valudation
fold:
type: string
description: The number of the fold in the inner cross-validation
iteration:
type: string
description: A number of the optimization iteration
setup_string:
type: string
description: A JSON representation of the setup (configuration)
evaluation:
type: string
description: The evaluation score of the setup
selected:
type: string
description: Whether this setup was selected as the best one (true or false)
RunTrace_trace:
properties:
run_id:
type: string
description: run ID
trace_iteration:
type: array
items:
$ref: '#/definitions/RunTrace_trace_trace_iteration'