docs: update flow tutorial to use SklearnExtension.model_to_flow

examples/Basics/simple_flows_and_runs_tutorial.py

@@ -1,12 +1,10 @@
 # %% [markdown]
 # A simple tutorial on how to upload results from a machine learning experiment to OpenML.
-
 # %%
 import sklearn
 from sklearn.neighbors import KNeighborsClassifier
-
 import openml
-
+from openml_sklearn import SklearnExtension
 # %% [markdown]
 # <div class="admonition warning">
 #     <p class="admonition-title">Warning</p>
@@ -20,68 +18,39 @@
 #         OpenML-Python API.
 #     </p>
 # </div>
-
 # %%
 openml.config.start_using_configuration_for_example()
-
 # %% [markdown]
 # ## Train a machine learning model and evaluate it
 # NOTE: We are using task 119 from the test server: https://test.openml.org/d/20
-
 # %%
 task = openml.tasks.get_task(119)
-
 # Get the data
 dataset = task.get_dataset()
 X, y, categorical_indicator, attribute_names = dataset.get_data(
     target=dataset.default_target_attribute
 )
-
 # Get the holdout split from the task
 train_indices, test_indices = task.get_train_test_split_indices(fold=0, repeat=0)
 X_train, X_test = X.iloc[train_indices], X.iloc[test_indices]
 y_train, y_test = y.iloc[train_indices], y.iloc[test_indices]
-
-knn_parameters = {
-    "n_neighbors": 3,
-}
-clf = KNeighborsClassifier(**knn_parameters)
+clf = KNeighborsClassifier(n_neighbors=3)
 clf.fit(X_train, y_train)
-
 # Get experiment results
 y_pred = clf.predict(X_test)
 y_pred_proba = clf.predict_proba(X_test)
-
 # %% [markdown]
 # ## Upload the machine learning experiments to OpenML
-# First, create a fow and fill it with metadata about the machine learning model.
-
+# Create a flow from the trained model using the sklearn extension.
+# This automatically extracts all metadata and hyperparameters.
 # %%
-knn_flow = openml.flows.OpenMLFlow(
-    # Metadata
-    model=clf,  # or None, if you do not want to upload the model object.
-    name="CustomKNeighborsClassifier",
-    description="A custom KNeighborsClassifier flow for OpenML.",
-    external_version=f"{sklearn.__version__}",
-    language="English",
-    tags=["openml_tutorial_knn"],
-    dependencies=f"{sklearn.__version__}",
-    # Hyperparameters
-    parameters={k: str(v) for k, v in knn_parameters.items()},
-    parameters_meta_info={
-        "n_neighbors": {"description": "number of neighbors to use", "data_type": "int"}
-    },
-    # If you have a pipeline with subcomponents, such as preprocessing, add them here.
-    components={},
-)
+extension = SklearnExtension()
+knn_flow = extension.model_to_flow(clf)
 knn_flow.publish()
 print(f"knn_flow was published with the ID {knn_flow.flow_id}")
-
 # %% [markdown]
 # Second, we create a run to store the results associated with the flow.
-
 # %%
-
 # Format the predictions for OpenML
 predictions = []
 for test_index, y_true_i, y_pred_i, y_pred_proba_i in zip(
@@ -98,13 +67,11 @@
             proba=dict(zip(task.class_labels, y_pred_proba_i)),
         )
     )
-
-# Format the parameters for OpenML
+# Get parameters from the flow
 oml_knn_parameters = [
     {"oml:name": k, "oml:value": v, "oml:component": knn_flow.flow_id}
-    for k, v in knn_parameters.items()
+    for k, v in knn_flow.parameters.items()
 ]
-
 knn_run = openml.runs.OpenMLRun(
     task_id=task.task_id,
     flow_id=knn_flow.flow_id,
@@ -117,6 +84,5 @@
 knn_run = knn_run.publish()
 print(f"Run was uploaded to {knn_run.openml_url}")
 print(f"The flow can be found at {knn_run.flow.openml_url}")
-
 # %%
-openml.config.stop_using_configuration_for_example()
+openml.config.stop_using_configuration_for_example()