We get a little further on the azml_02 but it seems to fail still

azuremlpythonsdk-v2/azml_02_hyperparameters_tuning.py

@@ -23,17 +23,19 @@ best_model_name = "best_diabetes_model"
 
 def main():
     # 1. Create or Load a ML client
-    ml_client = XXXX()
+    ml_client = create_or_load_ml_client()
 
     # 2. Create compute resources
-    XXXX()
+    create_or_load_aml()
 
     # 3. Create and register a File Dataset
-    XXXX()
-    latest_version_dataset =  XXXX()
+    create_tabular_dataset()
+    latest_version_dataset = max(
+        [int(d.version) for d in ml_client.data.list(name=name_dataset)]
+    )
 
     # 4. Environment
-    environment_names = [env.name for XXXX in ml_client.environments.list()]
+    environment_names = [env.name for env in ml_client.environments.list()]
     if custom_env_name not in environment_names:
         create_docker_environment()
 
@@ -47,25 +49,25 @@ def main():
                 path=f"azureml:{name_dataset}:{latest_version_dataset}",
             ),
             registered_model_name=registered_model_name,
-            learning_rate=XXXX(values= XXXX),
-            n_estimators=XXXX(values=XXXX),
+            learning_rate=Choice(values= [0.01, 0.1, 1.0]),
+            n_estimators=Choice(values=[10, 100]),
         ),
         code=experiment_folder,
         command=(
-            "python XXXX"
-            + " --data XXXX"
-            + " --registered_model_name XXXX"
-            + " --learning_rate XXXX"
-            + " --n_estimators XXXX"
+            "python ${{inputs.script_name}}"
+            + " --data ${{inputs.data}}"
+            + " --registered_model_name ${{inputs.registered_model_name}}"
+            + " --learning_rate ${{inputs.learning_rate}}"
+            + " --n_estimators ${{inputs.n_estimators}}"
         ),
-        environment=XXXX,
+        environment=f"{custom_env_name}@latest",
         compute=AML_COMPUTE_NAME,
         experiment_name=experiment_name,
         display_name=experiment_name,
     )
 
     # Configure hyperdrive settings
-    sweep_job = job_for_sweep.XXXX(
+    sweep_job = job_for_sweep.sweep(
         compute=AML_COMPUTE_NAME,
         sampling_algorithm="grid",
         primary_metric="AUC",
@@ -106,7 +108,7 @@ def main():
 
     # Register best model
     print(f"Registering Model {best_model_name}")
-    ml_client.models.XXXX(model=model)
+    ml_client.models.register(model=model)
 
 
 if __name__ == "__main__":

azuremlpythonsdk-v2/diabetes_hyperdrive/diabetes_training.py

@@ -17,28 +17,28 @@ def main():
     # Input and output arguments
 
     # Get script arguments
-    parser = XXXX()
+    parser = argparse()
 
     # Input dataset
     parser.add_argument(
-        "XXXX",
+        "--data",
         type=str,
         help="path to input data",
     )
 
     # Model name
-    parser.add_argument("XXXX", type=str, help="model name")
+    parser.add_argument("--registered_model_name", type=str, help="model name")
 
     # Hyperparameters
     parser.add_argument(
-        "XXXX",
+        "--learning_rate",
         type=float,
         dest="learning_rate",
         default=0.1,
         help="learning rate",
     )
     parser.add_argument(
-        "XXXX",
+        "--n_estimators",
         type=int,
         dest="n_estimators",
         default=100,
@@ -50,10 +50,10 @@ def main():
     print(" ".join(f"{k}={v}" for k, v in vars(args).items()))
 
     # Start Logging
-    mlflow.XXXX()
+    mlflow.start_run()
 
     # enable autologging
-    mlflow.XXXX()
+    mlflow.sklearn.autolog()
 
     # load the diabetes data (passed as an input dataset)
     print("input data:", args.data)
@@ -78,32 +78,32 @@ def main():
     )
 
     # Split data into training set and test set
-    X_train, X_test, y_train, y_test = XXXX(
+    X_train, X_test, y_train, y_test = train_test_split(
         X, y, test_size=0.30, random_state=0
     )
 
     # Train a Gradient Boosting classification model
     # with the specified hyperparameters
     print("Training a classification model")
-    model = XXXX(
-        learning_rate=XXXX, n_estimators=XXXX
+    model = GradientBoostingClassifier(
+        learning_rate=args.learning_rate, n_estimators=args.n_estimators
     ).fit(X_train, y_train)
 
     # calculate accuracy
-    y_hat = model.XXXX(X_test)
+    y_hat = model.predict(X_test)
     accuracy = np.average(y_hat == y_test)
     print("Accuracy:", accuracy)
     mlflow.log_metric("Accuracy", float(accuracy))
 
     # calculate AUC
-    y_scores = model.XXXX(X_test)
+    y_scores = model.predict_proba(X_test)
     auc = roc_auc_score(y_test, y_scores[:, 1])
     print("AUC: " + str(auc))
     mlflow.log_metric("AUC", float(auc))
 
     # Registering the model to the workspace
     print("Registering the model via MLFlow")
-    mlflow.XXXX(
+    mlflow.sklearn.log_model(
         sk_model=model,
         registered_model_name=args.registered_model_name,
         artifact_path=args.registered_model_name,
@@ -116,7 +116,7 @@ def main():
     )
 
     # Stop Logging
-    mlflow.XXXX()
+    mlflow.end_run()
 
 
 if __name__ == "__main__":