Skip to content

task

openml.tasks.task #

OpenMLClassificationTask #

OpenMLClassificationTask(task_type_id: TaskType, task_type: str, data_set_id: int, target_name: str, estimation_procedure_id: int = 1, estimation_procedure_type: str | None = None, estimation_parameters: dict[str, str] | None = None, evaluation_measure: str | None = None, data_splits_url: str | None = None, task_id: int | None = None, class_labels: list[str] | None = None, cost_matrix: ndarray | None = None)

Bases: OpenMLSupervisedTask

OpenML Classification object.

Parameters#

task_type_id : TaskType ID of the Classification task type. task_type : str Name of the Classification task type. data_set_id : int ID of the OpenML dataset associated with the Classification task. target_name : str Name of the target variable. estimation_procedure_id : int, default=None ID of the estimation procedure for the Classification task. estimation_procedure_type : str, default=None Type of the estimation procedure. estimation_parameters : dict, default=None Estimation parameters for the Classification task. evaluation_measure : str, default=None Name of the evaluation measure. data_splits_url : str, default=None URL of the data splits for the Classification task. task_id : Union[int, None] ID of the Classification task (if it already exists on OpenML). class_labels : List of str, default=None A list of class labels (for classification tasks). cost_matrix : array, default=None A cost matrix (for classification tasks).

Source code in openml/tasks/task.py 
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
def __init__(  # noqa: PLR0913
    self,
    task_type_id: TaskType,
    task_type: str,
    data_set_id: int,
    target_name: str,
    estimation_procedure_id: int = 1,
    estimation_procedure_type: str | None = None,
    estimation_parameters: dict[str, str] | None = None,
    evaluation_measure: str | None = None,
    data_splits_url: str | None = None,
    task_id: int | None = None,
    class_labels: list[str] | None = None,
    cost_matrix: np.ndarray | None = None,
):
    super().__init__(
        task_id=task_id,
        task_type_id=task_type_id,
        task_type=task_type,
        data_set_id=data_set_id,
        estimation_procedure_id=estimation_procedure_id,
        estimation_procedure_type=estimation_procedure_type,
        estimation_parameters=estimation_parameters,
        evaluation_measure=evaluation_measure,
        target_name=target_name,
        data_splits_url=data_splits_url,
    )
    self.class_labels = class_labels
    self.cost_matrix = cost_matrix

    if cost_matrix is not None:
        raise NotImplementedError("Costmatrix")

estimation_parameters property writable #

estimation_parameters: dict[str, str] | None

Return the estimation parameters for the task.

id property #

id: int | None

Return the OpenML ID of this task.

openml_url property #

openml_url: str | None

The URL of the object on the server, if it was uploaded, else None.

download_split #

download_split() -> OpenMLSplit

Download the OpenML split for a given task.

Source code in openml/tasks/task.py 
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
def download_split(self) -> OpenMLSplit:
    """Download the OpenML split for a given task."""
    # TODO(eddiebergman): Can this every be `None`?
    assert self.task_id is not None
    cache_dir = _create_cache_directory_for_id("tasks", self.task_id)
    cached_split_file = cache_dir / "datasplits.arff"

    try:
        split = OpenMLSplit._from_arff_file(cached_split_file)
    except OSError:
        # Next, download and cache the associated split file
        self._download_split(cached_split_file)
        split = OpenMLSplit._from_arff_file(cached_split_file)

    return split

get_X_and_y #

get_X_and_y() -> tuple[DataFrame, Series | DataFrame | None]

Get data associated with the current task.

Returns#

tuple - X and y

Source code in openml/tasks/task.py 
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
def get_X_and_y(self) -> tuple[pd.DataFrame, pd.Series | pd.DataFrame | None]:
    """Get data associated with the current task.

    Returns
    -------
    tuple - X and y

    """
    dataset = self.get_dataset()
    if self.task_type_id not in (
        TaskType.SUPERVISED_CLASSIFICATION,
        TaskType.SUPERVISED_REGRESSION,
        TaskType.LEARNING_CURVE,
    ):
        raise NotImplementedError(self.task_type)

    X, y, _, _ = dataset.get_data(target=self.target_name)
    return X, y

get_dataset #

get_dataset(**kwargs: Any) -> OpenMLDataset

Download dataset associated with task.

Accepts the same keyword arguments as the openml.datasets.get_dataset.

Source code in openml/tasks/task.py 
147
148
149
150
151
152
def get_dataset(self, **kwargs: Any) -> datasets.OpenMLDataset:
    """Download dataset associated with task.

    Accepts the same keyword arguments as the `openml.datasets.get_dataset`.
    """
    return datasets.get_dataset(self.dataset_id, **kwargs)

get_split_dimensions #

get_split_dimensions() -> tuple[int, int, int]

Get the (repeats, folds, samples) of the split for a given task.

Source code in openml/tasks/task.py 
195
196
197
198
199
200
def get_split_dimensions(self) -> tuple[int, int, int]:
    """Get the (repeats, folds, samples) of the split for a given task."""
    if self.split is None:
        self.split = self.download_split()

    return self.split.repeats, self.split.folds, self.split.samples

get_train_test_split_indices #

get_train_test_split_indices(fold: int = 0, repeat: int = 0, sample: int = 0) -> tuple[ndarray, ndarray]

Get the indices of the train and test splits for a given task.

Source code in openml/tasks/task.py 
154
155
156
157
158
159
160
161
162
163
164
165
def get_train_test_split_indices(
    self,
    fold: int = 0,
    repeat: int = 0,
    sample: int = 0,
) -> tuple[np.ndarray, np.ndarray]:
    """Get the indices of the train and test splits for a given task."""
    # Replace with retrieve from cache
    if self.split is None:
        self.split = self.download_split()

    return self.split.get(repeat=repeat, fold=fold, sample=sample)

open_in_browser #

open_in_browser() -> None

Opens the OpenML web page corresponding to this object in your default browser.

Source code in openml/base.py 
145
146
147
148
149
150
151
152
def open_in_browser(self) -> None:
    """Opens the OpenML web page corresponding to this object in your default browser."""
    if self.openml_url is None:
        raise ValueError(
            "Cannot open element on OpenML.org when attribute `openml_url` is `None`",
        )

    webbrowser.open(self.openml_url)

publish #

publish() -> OpenMLBase

Publish the object on the OpenML server.

Source code in openml/base.py 
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
def publish(self) -> OpenMLBase:
    """Publish the object on the OpenML server."""
    file_elements = self._get_file_elements()

    if "description" not in file_elements:
        file_elements["description"] = self._to_xml()

    call = f"{_get_rest_api_type_alias(self)}/"
    response_text = openml._api_calls._perform_api_call(
        call,
        "post",
        file_elements=file_elements,
    )
    xml_response = xmltodict.parse(response_text)

    self._parse_publish_response(xml_response)
    return self

push_tag #

push_tag(tag: str) -> None

Annotates this entity with a tag on the server.

Parameters#

tag : str Tag to attach to the flow.

Source code in openml/base.py 
154
155
156
157
158
159
160
161
162
def push_tag(self, tag: str) -> None:
    """Annotates this entity with a tag on the server.

    Parameters
    ----------
    tag : str
        Tag to attach to the flow.
    """
    _tag_openml_base(self, tag)

remove_tag #

remove_tag(tag: str) -> None

Removes a tag from this entity on the server.

Parameters#

tag : str Tag to attach to the flow.

Source code in openml/base.py 
164
165
166
167
168
169
170
171
172
def remove_tag(self, tag: str) -> None:
    """Removes a tag from this entity on the server.

    Parameters
    ----------
    tag : str
        Tag to attach to the flow.
    """
    _tag_openml_base(self, tag, untag=True)

url_for_id classmethod #

url_for_id(id_: int) -> str

Return the OpenML URL for the object of the class entity with the given id.

Source code in openml/base.py 
36
37
38
39
40
@classmethod
def url_for_id(cls, id_: int) -> str:
    """Return the OpenML URL for the object of the class entity with the given id."""
    # Sample url for a flow: openml.org/f/123
    return f"{openml.config.get_server_base_url()}/{cls._entity_letter()}/{id_}"

OpenMLClusteringTask #

OpenMLClusteringTask(task_type_id: TaskType, task_type: str, data_set_id: int, estimation_procedure_id: int = 17, task_id: int | None = None, estimation_procedure_type: str | None = None, estimation_parameters: dict[str, str] | None = None, data_splits_url: str | None = None, evaluation_measure: str | None = None, target_name: str | None = None)

Bases: OpenMLTask

OpenML Clustering object.

Parameters#

task_type_id : TaskType Task type ID of the OpenML clustering task. task_type : str Task type of the OpenML clustering task. data_set_id : int ID of the OpenML dataset used in clustering the task. estimation_procedure_id : int, default=None ID of the OpenML estimation procedure. task_id : Union[int, None] ID of the OpenML clustering task. estimation_procedure_type : str, default=None Type of the OpenML estimation procedure used in the clustering task. estimation_parameters : dict, default=None Parameters used by the OpenML estimation procedure. data_splits_url : str, default=None URL of the OpenML data splits for the clustering task. evaluation_measure : str, default=None Evaluation measure used in the clustering task. target_name : str, default=None Name of the target feature (class) that is not part of the feature set for the clustering task.

Source code in openml/tasks/task.py 
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
def __init__(  # noqa: PLR0913
    self,
    task_type_id: TaskType,
    task_type: str,
    data_set_id: int,
    estimation_procedure_id: int = 17,
    task_id: int | None = None,
    estimation_procedure_type: str | None = None,
    estimation_parameters: dict[str, str] | None = None,
    data_splits_url: str | None = None,
    evaluation_measure: str | None = None,
    target_name: str | None = None,
):
    super().__init__(
        task_id=task_id,
        task_type_id=task_type_id,
        task_type=task_type,
        data_set_id=data_set_id,
        evaluation_measure=evaluation_measure,
        estimation_procedure_id=estimation_procedure_id,
        estimation_procedure_type=estimation_procedure_type,
        estimation_parameters=estimation_parameters,
        data_splits_url=data_splits_url,
    )

    self.target_name = target_name

id property #

id: int | None

Return the OpenML ID of this task.

openml_url property #

openml_url: str | None

The URL of the object on the server, if it was uploaded, else None.

download_split #

download_split() -> OpenMLSplit

Download the OpenML split for a given task.

Source code in openml/tasks/task.py 
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
def download_split(self) -> OpenMLSplit:
    """Download the OpenML split for a given task."""
    # TODO(eddiebergman): Can this every be `None`?
    assert self.task_id is not None
    cache_dir = _create_cache_directory_for_id("tasks", self.task_id)
    cached_split_file = cache_dir / "datasplits.arff"

    try:
        split = OpenMLSplit._from_arff_file(cached_split_file)
    except OSError:
        # Next, download and cache the associated split file
        self._download_split(cached_split_file)
        split = OpenMLSplit._from_arff_file(cached_split_file)

    return split

get_X #

get_X() -> DataFrame

Get data associated with the current task.

Returns#

The X data as a dataframe

Source code in openml/tasks/task.py 
497
498
499
500
501
502
503
504
505
506
def get_X(self) -> pd.DataFrame:
    """Get data associated with the current task.

    Returns
    -------
    The X data as a dataframe
    """
    dataset = self.get_dataset()
    data, *_ = dataset.get_data(target=None)
    return data

get_dataset #

get_dataset(**kwargs: Any) -> OpenMLDataset

Download dataset associated with task.

Accepts the same keyword arguments as the openml.datasets.get_dataset.

Source code in openml/tasks/task.py 
147
148
149
150
151
152
def get_dataset(self, **kwargs: Any) -> datasets.OpenMLDataset:
    """Download dataset associated with task.

    Accepts the same keyword arguments as the `openml.datasets.get_dataset`.
    """
    return datasets.get_dataset(self.dataset_id, **kwargs)

get_split_dimensions #

get_split_dimensions() -> tuple[int, int, int]

Get the (repeats, folds, samples) of the split for a given task.

Source code in openml/tasks/task.py 
195
196
197
198
199
200
def get_split_dimensions(self) -> tuple[int, int, int]:
    """Get the (repeats, folds, samples) of the split for a given task."""
    if self.split is None:
        self.split = self.download_split()

    return self.split.repeats, self.split.folds, self.split.samples

get_train_test_split_indices #

get_train_test_split_indices(fold: int = 0, repeat: int = 0, sample: int = 0) -> tuple[ndarray, ndarray]

Get the indices of the train and test splits for a given task.

Source code in openml/tasks/task.py 
154
155
156
157
158
159
160
161
162
163
164
165
def get_train_test_split_indices(
    self,
    fold: int = 0,
    repeat: int = 0,
    sample: int = 0,
) -> tuple[np.ndarray, np.ndarray]:
    """Get the indices of the train and test splits for a given task."""
    # Replace with retrieve from cache
    if self.split is None:
        self.split = self.download_split()

    return self.split.get(repeat=repeat, fold=fold, sample=sample)

open_in_browser #

open_in_browser() -> None

Opens the OpenML web page corresponding to this object in your default browser.

Source code in openml/base.py 
145
146
147
148
149
150
151
152
def open_in_browser(self) -> None:
    """Opens the OpenML web page corresponding to this object in your default browser."""
    if self.openml_url is None:
        raise ValueError(
            "Cannot open element on OpenML.org when attribute `openml_url` is `None`",
        )

    webbrowser.open(self.openml_url)

publish #

publish() -> OpenMLBase

Publish the object on the OpenML server.

Source code in openml/base.py 
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
def publish(self) -> OpenMLBase:
    """Publish the object on the OpenML server."""
    file_elements = self._get_file_elements()

    if "description" not in file_elements:
        file_elements["description"] = self._to_xml()

    call = f"{_get_rest_api_type_alias(self)}/"
    response_text = openml._api_calls._perform_api_call(
        call,
        "post",
        file_elements=file_elements,
    )
    xml_response = xmltodict.parse(response_text)

    self._parse_publish_response(xml_response)
    return self

push_tag #

push_tag(tag: str) -> None

Annotates this entity with a tag on the server.

Parameters#

tag : str Tag to attach to the flow.

Source code in openml/base.py 
154
155
156
157
158
159
160
161
162
def push_tag(self, tag: str) -> None:
    """Annotates this entity with a tag on the server.

    Parameters
    ----------
    tag : str
        Tag to attach to the flow.
    """
    _tag_openml_base(self, tag)

remove_tag #

remove_tag(tag: str) -> None

Removes a tag from this entity on the server.

Parameters#

tag : str Tag to attach to the flow.

Source code in openml/base.py 
164
165
166
167
168
169
170
171
172
def remove_tag(self, tag: str) -> None:
    """Removes a tag from this entity on the server.

    Parameters
    ----------
    tag : str
        Tag to attach to the flow.
    """
    _tag_openml_base(self, tag, untag=True)

url_for_id classmethod #

url_for_id(id_: int) -> str

Return the OpenML URL for the object of the class entity with the given id.

Source code in openml/base.py 
36
37
38
39
40
@classmethod
def url_for_id(cls, id_: int) -> str:
    """Return the OpenML URL for the object of the class entity with the given id."""
    # Sample url for a flow: openml.org/f/123
    return f"{openml.config.get_server_base_url()}/{cls._entity_letter()}/{id_}"

OpenMLLearningCurveTask #

OpenMLLearningCurveTask(task_type_id: TaskType, task_type: str, data_set_id: int, target_name: str, estimation_procedure_id: int = 13, estimation_procedure_type: str | None = None, estimation_parameters: dict[str, str] | None = None, data_splits_url: str | None = None, task_id: int | None = None, evaluation_measure: str | None = None, class_labels: list[str] | None = None, cost_matrix: ndarray | None = None)

Bases: OpenMLClassificationTask

OpenML Learning Curve object.

Parameters#

task_type_id : TaskType ID of the Learning Curve task. task_type : str Name of the Learning Curve task. data_set_id : int ID of the dataset that this task is associated with. target_name : str Name of the target feature in the dataset. estimation_procedure_id : int, default=None ID of the estimation procedure to use for evaluating models. estimation_procedure_type : str, default=None Type of the estimation procedure. estimation_parameters : dict, default=None Additional parameters for the estimation procedure. data_splits_url : str, default=None URL of the file containing the data splits for Learning Curve task. task_id : Union[int, None] ID of the Learning Curve task. evaluation_measure : str, default=None Name of the evaluation measure to use for evaluating models. class_labels : list of str, default=None Class labels for Learning Curve tasks. cost_matrix : numpy array, default=None Cost matrix for Learning Curve tasks.

Source code in openml/tasks/task.py 
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
def __init__(  # noqa: PLR0913
    self,
    task_type_id: TaskType,
    task_type: str,
    data_set_id: int,
    target_name: str,
    estimation_procedure_id: int = 13,
    estimation_procedure_type: str | None = None,
    estimation_parameters: dict[str, str] | None = None,
    data_splits_url: str | None = None,
    task_id: int | None = None,
    evaluation_measure: str | None = None,
    class_labels: list[str] | None = None,
    cost_matrix: np.ndarray | None = None,
):
    super().__init__(
        task_id=task_id,
        task_type_id=task_type_id,
        task_type=task_type,
        data_set_id=data_set_id,
        estimation_procedure_id=estimation_procedure_id,
        estimation_procedure_type=estimation_procedure_type,
        estimation_parameters=estimation_parameters,
        evaluation_measure=evaluation_measure,
        target_name=target_name,
        data_splits_url=data_splits_url,
        class_labels=class_labels,
        cost_matrix=cost_matrix,
    )

estimation_parameters property writable #

estimation_parameters: dict[str, str] | None

Return the estimation parameters for the task.

id property #

id: int | None

Return the OpenML ID of this task.

openml_url property #

openml_url: str | None

The URL of the object on the server, if it was uploaded, else None.

download_split #

download_split() -> OpenMLSplit

Download the OpenML split for a given task.

Source code in openml/tasks/task.py 
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
def download_split(self) -> OpenMLSplit:
    """Download the OpenML split for a given task."""
    # TODO(eddiebergman): Can this every be `None`?
    assert self.task_id is not None
    cache_dir = _create_cache_directory_for_id("tasks", self.task_id)
    cached_split_file = cache_dir / "datasplits.arff"

    try:
        split = OpenMLSplit._from_arff_file(cached_split_file)
    except OSError:
        # Next, download and cache the associated split file
        self._download_split(cached_split_file)
        split = OpenMLSplit._from_arff_file(cached_split_file)

    return split

get_X_and_y #

get_X_and_y() -> tuple[DataFrame, Series | DataFrame | None]

Get data associated with the current task.

Returns#

tuple - X and y

Source code in openml/tasks/task.py 
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
def get_X_and_y(self) -> tuple[pd.DataFrame, pd.Series | pd.DataFrame | None]:
    """Get data associated with the current task.

    Returns
    -------
    tuple - X and y

    """
    dataset = self.get_dataset()
    if self.task_type_id not in (
        TaskType.SUPERVISED_CLASSIFICATION,
        TaskType.SUPERVISED_REGRESSION,
        TaskType.LEARNING_CURVE,
    ):
        raise NotImplementedError(self.task_type)

    X, y, _, _ = dataset.get_data(target=self.target_name)
    return X, y

get_dataset #

get_dataset(**kwargs: Any) -> OpenMLDataset

Download dataset associated with task.

Accepts the same keyword arguments as the openml.datasets.get_dataset.

Source code in openml/tasks/task.py 
147
148
149
150
151
152
def get_dataset(self, **kwargs: Any) -> datasets.OpenMLDataset:
    """Download dataset associated with task.

    Accepts the same keyword arguments as the `openml.datasets.get_dataset`.
    """
    return datasets.get_dataset(self.dataset_id, **kwargs)

get_split_dimensions #

get_split_dimensions() -> tuple[int, int, int]

Get the (repeats, folds, samples) of the split for a given task.

Source code in openml/tasks/task.py 
195
196
197
198
199
200
def get_split_dimensions(self) -> tuple[int, int, int]:
    """Get the (repeats, folds, samples) of the split for a given task."""
    if self.split is None:
        self.split = self.download_split()

    return self.split.repeats, self.split.folds, self.split.samples

get_train_test_split_indices #

get_train_test_split_indices(fold: int = 0, repeat: int = 0, sample: int = 0) -> tuple[ndarray, ndarray]

Get the indices of the train and test splits for a given task.

Source code in openml/tasks/task.py 
154
155
156
157
158
159
160
161
162
163
164
165
def get_train_test_split_indices(
    self,
    fold: int = 0,
    repeat: int = 0,
    sample: int = 0,
) -> tuple[np.ndarray, np.ndarray]:
    """Get the indices of the train and test splits for a given task."""
    # Replace with retrieve from cache
    if self.split is None:
        self.split = self.download_split()

    return self.split.get(repeat=repeat, fold=fold, sample=sample)

open_in_browser #

open_in_browser() -> None

Opens the OpenML web page corresponding to this object in your default browser.

Source code in openml/base.py 
145
146
147
148
149
150
151
152
def open_in_browser(self) -> None:
    """Opens the OpenML web page corresponding to this object in your default browser."""
    if self.openml_url is None:
        raise ValueError(
            "Cannot open element on OpenML.org when attribute `openml_url` is `None`",
        )

    webbrowser.open(self.openml_url)

publish #

publish() -> OpenMLBase

Publish the object on the OpenML server.

Source code in openml/base.py 
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
def publish(self) -> OpenMLBase:
    """Publish the object on the OpenML server."""
    file_elements = self._get_file_elements()

    if "description" not in file_elements:
        file_elements["description"] = self._to_xml()

    call = f"{_get_rest_api_type_alias(self)}/"
    response_text = openml._api_calls._perform_api_call(
        call,
        "post",
        file_elements=file_elements,
    )
    xml_response = xmltodict.parse(response_text)

    self._parse_publish_response(xml_response)
    return self

push_tag #

push_tag(tag: str) -> None

Annotates this entity with a tag on the server.

Parameters#

tag : str Tag to attach to the flow.

Source code in openml/base.py 
154
155
156
157
158
159
160
161
162
def push_tag(self, tag: str) -> None:
    """Annotates this entity with a tag on the server.

    Parameters
    ----------
    tag : str
        Tag to attach to the flow.
    """
    _tag_openml_base(self, tag)

remove_tag #

remove_tag(tag: str) -> None

Removes a tag from this entity on the server.

Parameters#

tag : str Tag to attach to the flow.

Source code in openml/base.py 
164
165
166
167
168
169
170
171
172
def remove_tag(self, tag: str) -> None:
    """Removes a tag from this entity on the server.

    Parameters
    ----------
    tag : str
        Tag to attach to the flow.
    """
    _tag_openml_base(self, tag, untag=True)

url_for_id classmethod #

url_for_id(id_: int) -> str

Return the OpenML URL for the object of the class entity with the given id.

Source code in openml/base.py 
36
37
38
39
40
@classmethod
def url_for_id(cls, id_: int) -> str:
    """Return the OpenML URL for the object of the class entity with the given id."""
    # Sample url for a flow: openml.org/f/123
    return f"{openml.config.get_server_base_url()}/{cls._entity_letter()}/{id_}"

OpenMLRegressionTask #

OpenMLRegressionTask(task_type_id: TaskType, task_type: str, data_set_id: int, target_name: str, estimation_procedure_id: int = 7, estimation_procedure_type: str | None = None, estimation_parameters: dict[str, str] | None = None, data_splits_url: str | None = None, task_id: int | None = None, evaluation_measure: str | None = None)

Bases: OpenMLSupervisedTask

OpenML Regression object.

Parameters#

task_type_id : TaskType Task type ID of the OpenML Regression task. task_type : str Task type of the OpenML Regression task. data_set_id : int ID of the OpenML dataset. target_name : str Name of the target feature used in the Regression task. estimation_procedure_id : int, default=None ID of the OpenML estimation procedure. estimation_procedure_type : str, default=None Type of the OpenML estimation procedure. estimation_parameters : dict, default=None Parameters used by the OpenML estimation procedure. data_splits_url : str, default=None URL of the OpenML data splits for the Regression task. task_id : Union[int, None] ID of the OpenML Regression task. evaluation_measure : str, default=None Evaluation measure used in the Regression task.

Source code in openml/tasks/task.py 
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
def __init__(  # noqa: PLR0913
    self,
    task_type_id: TaskType,
    task_type: str,
    data_set_id: int,
    target_name: str,
    estimation_procedure_id: int = 7,
    estimation_procedure_type: str | None = None,
    estimation_parameters: dict[str, str] | None = None,
    data_splits_url: str | None = None,
    task_id: int | None = None,
    evaluation_measure: str | None = None,
):
    super().__init__(
        task_id=task_id,
        task_type_id=task_type_id,
        task_type=task_type,
        data_set_id=data_set_id,
        estimation_procedure_id=estimation_procedure_id,
        estimation_procedure_type=estimation_procedure_type,
        estimation_parameters=estimation_parameters,
        evaluation_measure=evaluation_measure,
        target_name=target_name,
        data_splits_url=data_splits_url,
    )

estimation_parameters property writable #

estimation_parameters: dict[str, str] | None

Return the estimation parameters for the task.

id property #

id: int | None

Return the OpenML ID of this task.

openml_url property #

openml_url: str | None

The URL of the object on the server, if it was uploaded, else None.

download_split #

download_split() -> OpenMLSplit

Download the OpenML split for a given task.

Source code in openml/tasks/task.py 
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
def download_split(self) -> OpenMLSplit:
    """Download the OpenML split for a given task."""
    # TODO(eddiebergman): Can this every be `None`?
    assert self.task_id is not None
    cache_dir = _create_cache_directory_for_id("tasks", self.task_id)
    cached_split_file = cache_dir / "datasplits.arff"

    try:
        split = OpenMLSplit._from_arff_file(cached_split_file)
    except OSError:
        # Next, download and cache the associated split file
        self._download_split(cached_split_file)
        split = OpenMLSplit._from_arff_file(cached_split_file)

    return split

get_X_and_y #

get_X_and_y() -> tuple[DataFrame, Series | DataFrame | None]

Get data associated with the current task.

Returns#

tuple - X and y

Source code in openml/tasks/task.py 
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
def get_X_and_y(self) -> tuple[pd.DataFrame, pd.Series | pd.DataFrame | None]:
    """Get data associated with the current task.

    Returns
    -------
    tuple - X and y

    """
    dataset = self.get_dataset()
    if self.task_type_id not in (
        TaskType.SUPERVISED_CLASSIFICATION,
        TaskType.SUPERVISED_REGRESSION,
        TaskType.LEARNING_CURVE,
    ):
        raise NotImplementedError(self.task_type)

    X, y, _, _ = dataset.get_data(target=self.target_name)
    return X, y

get_dataset #

get_dataset(**kwargs: Any) -> OpenMLDataset

Download dataset associated with task.

Accepts the same keyword arguments as the openml.datasets.get_dataset.

Source code in openml/tasks/task.py 
147
148
149
150
151
152
def get_dataset(self, **kwargs: Any) -> datasets.OpenMLDataset:
    """Download dataset associated with task.

    Accepts the same keyword arguments as the `openml.datasets.get_dataset`.
    """
    return datasets.get_dataset(self.dataset_id, **kwargs)

get_split_dimensions #

get_split_dimensions() -> tuple[int, int, int]

Get the (repeats, folds, samples) of the split for a given task.

Source code in openml/tasks/task.py 
195
196
197
198
199
200
def get_split_dimensions(self) -> tuple[int, int, int]:
    """Get the (repeats, folds, samples) of the split for a given task."""
    if self.split is None:
        self.split = self.download_split()

    return self.split.repeats, self.split.folds, self.split.samples

get_train_test_split_indices #

get_train_test_split_indices(fold: int = 0, repeat: int = 0, sample: int = 0) -> tuple[ndarray, ndarray]

Get the indices of the train and test splits for a given task.

Source code in openml/tasks/task.py 
154
155
156
157
158
159
160
161
162
163
164
165
def get_train_test_split_indices(
    self,
    fold: int = 0,
    repeat: int = 0,
    sample: int = 0,
) -> tuple[np.ndarray, np.ndarray]:
    """Get the indices of the train and test splits for a given task."""
    # Replace with retrieve from cache
    if self.split is None:
        self.split = self.download_split()

    return self.split.get(repeat=repeat, fold=fold, sample=sample)

open_in_browser #

open_in_browser() -> None

Opens the OpenML web page corresponding to this object in your default browser.

Source code in openml/base.py 
145
146
147
148
149
150
151
152
def open_in_browser(self) -> None:
    """Opens the OpenML web page corresponding to this object in your default browser."""
    if self.openml_url is None:
        raise ValueError(
            "Cannot open element on OpenML.org when attribute `openml_url` is `None`",
        )

    webbrowser.open(self.openml_url)

publish #

publish() -> OpenMLBase

Publish the object on the OpenML server.

Source code in openml/base.py 
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
def publish(self) -> OpenMLBase:
    """Publish the object on the OpenML server."""
    file_elements = self._get_file_elements()

    if "description" not in file_elements:
        file_elements["description"] = self._to_xml()

    call = f"{_get_rest_api_type_alias(self)}/"
    response_text = openml._api_calls._perform_api_call(
        call,
        "post",
        file_elements=file_elements,
    )
    xml_response = xmltodict.parse(response_text)

    self._parse_publish_response(xml_response)
    return self

push_tag #

push_tag(tag: str) -> None

Annotates this entity with a tag on the server.

Parameters#

tag : str Tag to attach to the flow.

Source code in openml/base.py 
154
155
156
157
158
159
160
161
162
def push_tag(self, tag: str) -> None:
    """Annotates this entity with a tag on the server.

    Parameters
    ----------
    tag : str
        Tag to attach to the flow.
    """
    _tag_openml_base(self, tag)

remove_tag #

remove_tag(tag: str) -> None

Removes a tag from this entity on the server.

Parameters#

tag : str Tag to attach to the flow.

Source code in openml/base.py 
164
165
166
167
168
169
170
171
172
def remove_tag(self, tag: str) -> None:
    """Removes a tag from this entity on the server.

    Parameters
    ----------
    tag : str
        Tag to attach to the flow.
    """
    _tag_openml_base(self, tag, untag=True)

url_for_id classmethod #

url_for_id(id_: int) -> str

Return the OpenML URL for the object of the class entity with the given id.

Source code in openml/base.py 
36
37
38
39
40
@classmethod
def url_for_id(cls, id_: int) -> str:
    """Return the OpenML URL for the object of the class entity with the given id."""
    # Sample url for a flow: openml.org/f/123
    return f"{openml.config.get_server_base_url()}/{cls._entity_letter()}/{id_}"

OpenMLSupervisedTask #

OpenMLSupervisedTask(task_type_id: TaskType, task_type: str, data_set_id: int, target_name: str, estimation_procedure_id: int = 1, estimation_procedure_type: str | None = None, estimation_parameters: dict[str, str] | None = None, evaluation_measure: str | None = None, data_splits_url: str | None = None, task_id: int | None = None)

Bases: OpenMLTask, ABC

OpenML Supervised Classification object.

Parameters#

task_type_id : TaskType ID of the task type. task_type : str Name of the task type. data_set_id : int ID of the OpenML dataset associated with the task. target_name : str Name of the target feature (the class variable). estimation_procedure_id : int, default=None ID of the estimation procedure for the task. estimation_procedure_type : str, default=None Type of the estimation procedure for the task. estimation_parameters : dict, default=None Estimation parameters for the task. evaluation_measure : str, default=None Name of the evaluation measure for the task. data_splits_url : str, default=None URL of the data splits for the task. task_id: Union[int, None] Refers to the unique identifier of task.

Source code in openml/tasks/task.py 
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
def __init__(  # noqa: PLR0913
    self,
    task_type_id: TaskType,
    task_type: str,
    data_set_id: int,
    target_name: str,
    estimation_procedure_id: int = 1,
    estimation_procedure_type: str | None = None,
    estimation_parameters: dict[str, str] | None = None,
    evaluation_measure: str | None = None,
    data_splits_url: str | None = None,
    task_id: int | None = None,
):
    super().__init__(
        task_id=task_id,
        task_type_id=task_type_id,
        task_type=task_type,
        data_set_id=data_set_id,
        estimation_procedure_id=estimation_procedure_id,
        estimation_procedure_type=estimation_procedure_type,
        estimation_parameters=estimation_parameters,
        evaluation_measure=evaluation_measure,
        data_splits_url=data_splits_url,
    )

    self.target_name = target_name

estimation_parameters property writable #

estimation_parameters: dict[str, str] | None

Return the estimation parameters for the task.

id property #

id: int | None

Return the OpenML ID of this task.

openml_url property #

openml_url: str | None

The URL of the object on the server, if it was uploaded, else None.

download_split #

download_split() -> OpenMLSplit

Download the OpenML split for a given task.

Source code in openml/tasks/task.py 
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
def download_split(self) -> OpenMLSplit:
    """Download the OpenML split for a given task."""
    # TODO(eddiebergman): Can this every be `None`?
    assert self.task_id is not None
    cache_dir = _create_cache_directory_for_id("tasks", self.task_id)
    cached_split_file = cache_dir / "datasplits.arff"

    try:
        split = OpenMLSplit._from_arff_file(cached_split_file)
    except OSError:
        # Next, download and cache the associated split file
        self._download_split(cached_split_file)
        split = OpenMLSplit._from_arff_file(cached_split_file)

    return split

get_X_and_y #

get_X_and_y() -> tuple[DataFrame, Series | DataFrame | None]

Get data associated with the current task.

Returns#

tuple - X and y

Source code in openml/tasks/task.py 
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
def get_X_and_y(self) -> tuple[pd.DataFrame, pd.Series | pd.DataFrame | None]:
    """Get data associated with the current task.

    Returns
    -------
    tuple - X and y

    """
    dataset = self.get_dataset()
    if self.task_type_id not in (
        TaskType.SUPERVISED_CLASSIFICATION,
        TaskType.SUPERVISED_REGRESSION,
        TaskType.LEARNING_CURVE,
    ):
        raise NotImplementedError(self.task_type)

    X, y, _, _ = dataset.get_data(target=self.target_name)
    return X, y

get_dataset #

get_dataset(**kwargs: Any) -> OpenMLDataset

Download dataset associated with task.

Accepts the same keyword arguments as the openml.datasets.get_dataset.

Source code in openml/tasks/task.py 
147
148
149
150
151
152
def get_dataset(self, **kwargs: Any) -> datasets.OpenMLDataset:
    """Download dataset associated with task.

    Accepts the same keyword arguments as the `openml.datasets.get_dataset`.
    """
    return datasets.get_dataset(self.dataset_id, **kwargs)

get_split_dimensions #

get_split_dimensions() -> tuple[int, int, int]

Get the (repeats, folds, samples) of the split for a given task.

Source code in openml/tasks/task.py 
195
196
197
198
199
200
def get_split_dimensions(self) -> tuple[int, int, int]:
    """Get the (repeats, folds, samples) of the split for a given task."""
    if self.split is None:
        self.split = self.download_split()

    return self.split.repeats, self.split.folds, self.split.samples

get_train_test_split_indices #

get_train_test_split_indices(fold: int = 0, repeat: int = 0, sample: int = 0) -> tuple[ndarray, ndarray]

Get the indices of the train and test splits for a given task.

Source code in openml/tasks/task.py 
154
155
156
157
158
159
160
161
162
163
164
165
def get_train_test_split_indices(
    self,
    fold: int = 0,
    repeat: int = 0,
    sample: int = 0,
) -> tuple[np.ndarray, np.ndarray]:
    """Get the indices of the train and test splits for a given task."""
    # Replace with retrieve from cache
    if self.split is None:
        self.split = self.download_split()

    return self.split.get(repeat=repeat, fold=fold, sample=sample)

open_in_browser #

open_in_browser() -> None

Opens the OpenML web page corresponding to this object in your default browser.

Source code in openml/base.py 
145
146
147
148
149
150
151
152
def open_in_browser(self) -> None:
    """Opens the OpenML web page corresponding to this object in your default browser."""
    if self.openml_url is None:
        raise ValueError(
            "Cannot open element on OpenML.org when attribute `openml_url` is `None`",
        )

    webbrowser.open(self.openml_url)

publish #

publish() -> OpenMLBase

Publish the object on the OpenML server.

Source code in openml/base.py 
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
def publish(self) -> OpenMLBase:
    """Publish the object on the OpenML server."""
    file_elements = self._get_file_elements()

    if "description" not in file_elements:
        file_elements["description"] = self._to_xml()

    call = f"{_get_rest_api_type_alias(self)}/"
    response_text = openml._api_calls._perform_api_call(
        call,
        "post",
        file_elements=file_elements,
    )
    xml_response = xmltodict.parse(response_text)

    self._parse_publish_response(xml_response)
    return self

push_tag #

push_tag(tag: str) -> None

Annotates this entity with a tag on the server.

Parameters#

tag : str Tag to attach to the flow.

Source code in openml/base.py 
154
155
156
157
158
159
160
161
162
def push_tag(self, tag: str) -> None:
    """Annotates this entity with a tag on the server.

    Parameters
    ----------
    tag : str
        Tag to attach to the flow.
    """
    _tag_openml_base(self, tag)

remove_tag #

remove_tag(tag: str) -> None

Removes a tag from this entity on the server.

Parameters#

tag : str Tag to attach to the flow.

Source code in openml/base.py 
164
165
166
167
168
169
170
171
172
def remove_tag(self, tag: str) -> None:
    """Removes a tag from this entity on the server.

    Parameters
    ----------
    tag : str
        Tag to attach to the flow.
    """
    _tag_openml_base(self, tag, untag=True)

url_for_id classmethod #

url_for_id(id_: int) -> str

Return the OpenML URL for the object of the class entity with the given id.

Source code in openml/base.py 
36
37
38
39
40
@classmethod
def url_for_id(cls, id_: int) -> str:
    """Return the OpenML URL for the object of the class entity with the given id."""
    # Sample url for a flow: openml.org/f/123
    return f"{openml.config.get_server_base_url()}/{cls._entity_letter()}/{id_}"

OpenMLTask #

OpenMLTask(task_id: int | None, task_type_id: TaskType, task_type: str, data_set_id: int, estimation_procedure_id: int = 1, estimation_procedure_type: str | None = None, estimation_parameters: dict[str, str] | None = None, evaluation_measure: str | None = None, data_splits_url: str | None = None)

Bases: OpenMLBase

OpenML Task object.

Parameters#

task_id: Union[int, None] Refers to the unique identifier of OpenML task. task_type_id: TaskType Refers to the type of OpenML task. task_type: str Refers to the OpenML task. data_set_id: int Refers to the data. estimation_procedure_id: int Refers to the type of estimates used. estimation_procedure_type: str, default=None Refers to the type of estimation procedure used for the OpenML task. estimation_parameters: [Dict[str, str]], default=None Estimation parameters used for the OpenML task. evaluation_measure: str, default=None Refers to the evaluation measure. data_splits_url: str, default=None Refers to the URL of the data splits used for the OpenML task.

Source code in openml/tasks/task.py 
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
def __init__(  # noqa: PLR0913
    self,
    task_id: int | None,
    task_type_id: TaskType,
    task_type: str,
    data_set_id: int,
    estimation_procedure_id: int = 1,
    estimation_procedure_type: str | None = None,
    estimation_parameters: dict[str, str] | None = None,
    evaluation_measure: str | None = None,
    data_splits_url: str | None = None,
):
    self.task_id = int(task_id) if task_id is not None else None
    self.task_type_id = task_type_id
    self.task_type = task_type
    self.dataset_id = int(data_set_id)
    self.evaluation_measure = evaluation_measure
    self.estimation_procedure: _EstimationProcedure = {
        "type": estimation_procedure_type,
        "parameters": estimation_parameters,
        "data_splits_url": data_splits_url,
    }
    self.estimation_procedure_id = estimation_procedure_id
    self.split: OpenMLSplit | None = None

id property #

id: int | None

Return the OpenML ID of this task.

openml_url property #

openml_url: str | None

The URL of the object on the server, if it was uploaded, else None.

download_split #

download_split() -> OpenMLSplit

Download the OpenML split for a given task.

Source code in openml/tasks/task.py 
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
def download_split(self) -> OpenMLSplit:
    """Download the OpenML split for a given task."""
    # TODO(eddiebergman): Can this every be `None`?
    assert self.task_id is not None
    cache_dir = _create_cache_directory_for_id("tasks", self.task_id)
    cached_split_file = cache_dir / "datasplits.arff"

    try:
        split = OpenMLSplit._from_arff_file(cached_split_file)
    except OSError:
        # Next, download and cache the associated split file
        self._download_split(cached_split_file)
        split = OpenMLSplit._from_arff_file(cached_split_file)

    return split

get_dataset #

get_dataset(**kwargs: Any) -> OpenMLDataset

Download dataset associated with task.

Accepts the same keyword arguments as the openml.datasets.get_dataset.

Source code in openml/tasks/task.py 
147
148
149
150
151
152
def get_dataset(self, **kwargs: Any) -> datasets.OpenMLDataset:
    """Download dataset associated with task.

    Accepts the same keyword arguments as the `openml.datasets.get_dataset`.
    """
    return datasets.get_dataset(self.dataset_id, **kwargs)

get_split_dimensions #

get_split_dimensions() -> tuple[int, int, int]

Get the (repeats, folds, samples) of the split for a given task.

Source code in openml/tasks/task.py 
195
196
197
198
199
200
def get_split_dimensions(self) -> tuple[int, int, int]:
    """Get the (repeats, folds, samples) of the split for a given task."""
    if self.split is None:
        self.split = self.download_split()

    return self.split.repeats, self.split.folds, self.split.samples

get_train_test_split_indices #

get_train_test_split_indices(fold: int = 0, repeat: int = 0, sample: int = 0) -> tuple[ndarray, ndarray]

Get the indices of the train and test splits for a given task.

Source code in openml/tasks/task.py 
154
155
156
157
158
159
160
161
162
163
164
165
def get_train_test_split_indices(
    self,
    fold: int = 0,
    repeat: int = 0,
    sample: int = 0,
) -> tuple[np.ndarray, np.ndarray]:
    """Get the indices of the train and test splits for a given task."""
    # Replace with retrieve from cache
    if self.split is None:
        self.split = self.download_split()

    return self.split.get(repeat=repeat, fold=fold, sample=sample)

open_in_browser #

open_in_browser() -> None

Opens the OpenML web page corresponding to this object in your default browser.

Source code in openml/base.py 
145
146
147
148
149
150
151
152
def open_in_browser(self) -> None:
    """Opens the OpenML web page corresponding to this object in your default browser."""
    if self.openml_url is None:
        raise ValueError(
            "Cannot open element on OpenML.org when attribute `openml_url` is `None`",
        )

    webbrowser.open(self.openml_url)

publish #

publish() -> OpenMLBase

Publish the object on the OpenML server.

Source code in openml/base.py 
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
def publish(self) -> OpenMLBase:
    """Publish the object on the OpenML server."""
    file_elements = self._get_file_elements()

    if "description" not in file_elements:
        file_elements["description"] = self._to_xml()

    call = f"{_get_rest_api_type_alias(self)}/"
    response_text = openml._api_calls._perform_api_call(
        call,
        "post",
        file_elements=file_elements,
    )
    xml_response = xmltodict.parse(response_text)

    self._parse_publish_response(xml_response)
    return self

push_tag #

push_tag(tag: str) -> None

Annotates this entity with a tag on the server.

Parameters#

tag : str Tag to attach to the flow.

Source code in openml/base.py 
154
155
156
157
158
159
160
161
162
def push_tag(self, tag: str) -> None:
    """Annotates this entity with a tag on the server.

    Parameters
    ----------
    tag : str
        Tag to attach to the flow.
    """
    _tag_openml_base(self, tag)

remove_tag #

remove_tag(tag: str) -> None

Removes a tag from this entity on the server.

Parameters#

tag : str Tag to attach to the flow.

Source code in openml/base.py 
164
165
166
167
168
169
170
171
172
def remove_tag(self, tag: str) -> None:
    """Removes a tag from this entity on the server.

    Parameters
    ----------
    tag : str
        Tag to attach to the flow.
    """
    _tag_openml_base(self, tag, untag=True)

url_for_id classmethod #

url_for_id(id_: int) -> str

Return the OpenML URL for the object of the class entity with the given id.

Source code in openml/base.py 
36
37
38
39
40
@classmethod
def url_for_id(cls, id_: int) -> str:
    """Return the OpenML URL for the object of the class entity with the given id."""
    # Sample url for a flow: openml.org/f/123
    return f"{openml.config.get_server_base_url()}/{cls._entity_letter()}/{id_}"

TaskType #

Bases: Enum

Possible task types as defined in OpenML.