Update extension.py, flow.py, task.py and functions.py

openml/extensions/sklearn/extension.py

@@ -2109,6 +2109,19 @@ def instantiate_model_from_hpo_class(
         return base_estimator
 
     def _extract_trace_data(self, model, rep_no, fold_no):
+        """Extracts data from a machine learning model's cross-validation results and creates an ARFF (Attribute-Relation File Format) trace.
+        Parameters
+        ----------
+        model : Any
+            A fitted hyperparameter optimization model.
+        rep_no : int
+            The repetition number.
+        fold_no : int
+            The fold number.
+        Returns
+        -------
+            A list of ARFF tracecontent.
+        """
         arff_tracecontent = []
         for itt_no in range(0, len(model.cv_results_["mean_test_score"])):
             # we use the string values for True and False, as it is defined in

openml/flows/flow.py

@@ -523,6 +523,19 @@ def get_subflow(self, structure):
 
 
 def _copy_server_fields(source_flow, target_flow):
+    """ Recursively copies the fields added by the server from the `source_flow` to the `target_flow`.
+
+    Parameters
+    ----------
+    source_flow : OpenMLFlow
+        To copy the fields from.
+    target_flow : OpenMLFlow
+        To copy the fields to.
+
+    Returns
+    -------
+    None
+    """
     fields_added_by_the_server = ["flow_id", "uploader", "version", "upload_date"]
     for field in fields_added_by_the_server:
         setattr(target_flow, field, getattr(source_flow, field))
@@ -533,5 +546,20 @@ def _copy_server_fields(source_flow, target_flow):
 
 
 def _add_if_nonempty(dic, key, value):
+    """ Adds a key-value pair to a dictionary if the value is not None.
+
+    Parameters
+    ----------
+    dic : dict
+        To add the key-value pair to.
+    key : hashable
+        To add to the dictionary.
+    value : Any
+        To add to the dictionary.
+
+    Returns
+    -------
+    None
+    """
     if value is not None:
         dic[key] = value

openml/flows/functions.py

@@ -332,6 +332,20 @@ def get_flow_id(
 
 
 def __list_flows(api_call: str, output_format: str = "dict") -> Union[Dict, pd.DataFrame]:
+    """ Retrieve information about flows from OpenML API and parse it to a dictionary or a Pandas DataFrame.
+
+    Parameters
+    ----------
+    api_call : str
+        Retrieves the information about flows.
+    output_format : str
+        The output format. 
+
+    Returns
+    -------
+    Union[Dict, pd.DataFrame]
+        The flows information in the specified output format.
+    """
 
     xml_string = openml._api_calls._perform_api_call(api_call, "get")
     flows_dict = xmltodict.parse(xml_string, force_list=("oml:flow",))

openml/runs/run.py

@@ -31,36 +31,55 @@ class OpenMLRun(OpenMLBase):
     Parameters
     ----------
     task_id: int
+        The ID of the OpenML task associated with the run.
     flow_id: int
+        The ID of the OpenML flow associated with the run.
     dataset_id: int
+        The ID of the OpenML dataset used for the run.
     setup_string: str
+        The setup string of the run.
     output_files: Dict[str, str]
-        A dictionary that specifies where each related file can be found.
+        Specifies where each related file can be found. 
     setup_id: int
+        An integer representing the ID of the setup used for the run.
     tags: List[str]
+        Representing the tags associated with the run.
     uploader: int
-        User ID of the uploader.
+        User ID of the uploader. 
     uploader_name: str
+        The name of the person who uploaded the run.
     evaluations: Dict
+        Representing the evaluations of the run.
     fold_evaluations: Dict
+        The evaluations of the run for each fold.
     sample_evaluations: Dict
+        The evaluations of the run for each sample.
     data_content: List[List]
         The predictions generated from executing this run.
     trace: OpenMLRunTrace
+        The trace containing information on internal model evaluations of this run.
     model: object
+        The untrained model that was evaluated in the run.
     task_type: str
+        The type of the OpenML task associated with the run.
     task_evaluation_measure: str
+        The evaluation measure used for the task.
     flow_name: str
+        The name of the OpenML flow associated with the run.
     parameter_settings: List[OrderedDict]
+        Representing the parameter settings used for the run.
     predictions_url: str
+        The URL of the predictions file.
     task: OpenMLTask
+        An instance of the OpenMLTask class, representing the OpenML task associated with the run.
     flow: OpenMLFlow
+        An instance of the OpenMLFlow class, representing the OpenML flow associated with the run.
     run_id: int
+        The ID of the run.
     description_text: str, optional
-        Description text to add to the predictions file.
-        If left None, is set to the time the arff file is generated.
+        Description text to add to the predictions file. If left None, is set to the time the arff file is generated.
     run_details: str, optional (default=None)
-        Description of the run stored in the run meta-data.
+        Description of the run stored in the run meta-data. 
     """
 
     def __init__(

openml/tasks/task.py

@@ -36,6 +36,8 @@ class OpenMLTask(OpenMLBase):
 
     Parameters
     ----------
+    task_id : Optional[int]
+        Refers to the unique identifier of a task.
     task_type_id : TaskType
         Refers to the type of task.
     task_type : str
@@ -44,6 +46,14 @@ class OpenMLTask(OpenMLBase):
         Refers to the data.
     estimation_procedure_id: int
         Refers to the type of estimates used.
+    estimation_procedure_type : Optional[str] 
+        Refers to the type of estimation procedure used for the task.
+    estimation_parameters : Optional[Dict[str, str]]
+        Estimation parameters used for the task.
+    evaluation_measure : Optional[str]
+        Refers to the evaluation measure.
+    data_splits_url : Optional[str]
+        Refers to the URL of the data splits used for the task.
     """
 
     def __init__(