fix for tutorial-pipeline.ipynb

tutorials/get-started-notebooks/deploy/credit_defaults_model/conda.yaml

@@ -4,7 +4,7 @@ dependencies:
 - python=3.8.15
 - pip<=21.2.4
 - pip:
-  - mlflow
+  - mlflow==2.4.1
   - cloudpickle==2.2.0
   - psutil==5.8.0
   - scikit-learn==0.24.2

tutorials/get-started-notebooks/deploy/credit_defaults_model/requirements.txt

@@ -1,4 +1,4 @@
-mlflow
+mlflow==2.4.1
 cloudpickle==2.2.0
 psutil==5.8.0
-scikit-learn==0.24.2
+scikit-learn==0.24.2

tutorials/get-started-notebooks/pipeline.ipynb

@@ -275,7 +275,7 @@
     "    description=\"Custom environment for Credit Card Defaults pipeline\",\n",
     "    tags={\"scikit-learn\": \"0.24.2\"},\n",
     "    conda_file=os.path.join(dependencies_dir, \"conda.yaml\"),\n",
-    "    image=\"mcr.microsoft.com/azureml/openmpi4.1.0-ubuntu20.04:latest\",\n",
+    "    image=\"mcr.microsoft.com/azureml/openmpi4.1.0-ubuntu22.04:latest\",\n",
     "    version=\"0.2.0\",\n",
     ")\n",
     "pipeline_job_env = ml_client.environments.create_or_update(pipeline_job_env)\n",
@@ -536,97 +536,89 @@
    },
    "outputs": [],
    "source": [
+    "\n",
     "%%writefile {train_src_dir}/train.py\n",
     "import argparse\n",
-    "from sklearn.ensemble import GradientBoostingClassifier\n",
-    "from sklearn.metrics import classification_report\n",
     "import os\n",
     "import pandas as pd\n",
+    "import numpy as np\n",
     "import mlflow\n",
     "\n",
+    "from sklearn.ensemble import GradientBoostingClassifier\n",
+    "from sklearn.metrics import classification_report, accuracy_score, f1_score\n",
+    "\n",
     "\n",
     "def select_first_file(path):\n",
-    "    \"\"\"Selects first file in folder, use under assumption there is only one file in folder\n",
-    "    Args:\n",
-    "        path (str): path to directory or file to choose\n",
-    "    Returns:\n",
-    "        str: full path of selected file\n",
-    "    \"\"\"\n",
+    "    \"\"\"Selects first file in folder (assumes single file).\"\"\"\n",
     "    files = os.listdir(path)\n",
     "    return os.path.join(path, files[0])\n",
     "\n",
     "\n",
-    "# Start Logging\n",
-    "mlflow.start_run()\n",
-    "\n",
-    "# enable autologging\n",
-    "mlflow.sklearn.autolog()\n",
-    "\n",
-    "os.makedirs(\"./outputs\", exist_ok=True)\n",
-    "\n",
-    "\n",
     "def main():\n",
-    "    \"\"\"Main function of the script.\"\"\"\n",
-    "\n",
-    "    # input and output arguments\n",
     "    parser = argparse.ArgumentParser()\n",
     "    parser.add_argument(\"--train_data\", type=str, help=\"path to train data\")\n",
     "    parser.add_argument(\"--test_data\", type=str, help=\"path to test data\")\n",
     "    parser.add_argument(\"--n_estimators\", required=False, default=100, type=int)\n",
     "    parser.add_argument(\"--learning_rate\", required=False, default=0.1, type=float)\n",
-    "    parser.add_argument(\"--registered_model_name\", type=str, help=\"model name\")\n",
-    "    parser.add_argument(\"--model\", type=str, help=\"path to model file\")\n",
+    "\n",
+    "    # ✅ Keep this arg to avoid breaking existing job/pipeline definitions\n",
+    "    # Option A will NOT use it to register via MLflow.\n",
+    "    parser.add_argument(\"--registered_model_name\", type=str, required=False, help=\"model name (ignored in Option A)\")\n",
+    "\n",
+    "    parser.add_argument(\"--model\", type=str, help=\"path to model output folder\")\n",
     "    args = parser.parse_args()\n",
     "\n",
-    "    # paths are mounted as folder, therefore, we are selecting the file from folder\n",
-    "    train_df = pd.read_csv(select_first_file(args.train_data))\n",
+    "    # ✅ Option A: Disable autologging to avoid AML backend unsupported endpoints\n",
+    "    mlflow.sklearn.autolog(disable=True)\n",
     "\n",
-    "    # Extracting the label column\n",
-    "    y_train = train_df.pop(\"default payment next month\")\n",
+    "    os.makedirs(\"./outputs\", exist_ok=True)\n",
     "\n",
-    "    # convert the dataframe values to array\n",
-    "    X_train = train_df.values\n",
+    "    # Start run (Azure ML handles tracking URI)\n",
+    "    mlflow.start_run()\n",
     "\n",
-    "    # paths are mounted as folder, therefore, we are selecting the file from folder\n",
-    "    test_df = pd.read_csv(select_first_file(args.test_data))\n",
+    "    # Optional: record the intended model name as a tag for traceability\n",
+    "    if args.registered_model_name:\n",
+    "        mlflow.set_tag(\"registered_model_name_requested\", args.registered_model_name)\n",
     "\n",
-    "    # Extracting the label column\n",
-    "    y_test = test_df.pop(\"default payment next month\")\n",
+    "    # Load data\n",
+    "    train_df = pd.read_csv(select_first_file(args.train_data))\n",
+    "    y_train = train_df.pop(\"default payment next month\").to_numpy()\n",
+    "    X_train = train_df.values\n",
     "\n",
-    "    # convert the dataframe values to array\n",
+    "    test_df = pd.read_csv(select_first_file(args.test_data))\n",
+    "    y_test = test_df.pop(\"default payment next month\").to_numpy()\n",
     "    X_test = test_df.values\n",
     "\n",
     "    print(f\"Training with data of shape {X_train.shape}\")\n",
     "\n",
+    "    # Train\n",
     "    clf = GradientBoostingClassifier(\n",
-    "        n_estimators=args.n_estimators, learning_rate=args.learning_rate\n",
+    "        n_estimators=args.n_estimators,\n",
+    "        learning_rate=args.learning_rate\n",
     "    )\n",
     "    clf.fit(X_train, y_train)\n",
     "\n",
+    "    # Evaluate\n",
     "    y_pred = clf.predict(X_test)\n",
-    "\n",
     "    print(classification_report(y_test, y_pred))\n",
     "\n",
-    "    # Registering the model to the workspace\n",
-    "    print(\"Registering the model via MLFlow\")\n",
-    "    mlflow.sklearn.log_model(\n",
-    "        sk_model=clf,\n",
-    "        registered_model_name=args.registered_model_name,\n",
-    "        artifact_path=args.registered_model_name,\n",
-    "    )\n",
+    "    accuracy = accuracy_score(y_test, y_pred)\n",
+    "    f1 = f1_score(y_test, y_pred)\n",
     "\n",
-    "    # Saving the model to a file\n",
-    "    mlflow.sklearn.save_model(\n",
-    "        sk_model=clf,\n",
-    "        path=os.path.join(args.model, \"trained_model\"),\n",
-    "    )\n",
+    "    # Log metrics only (safe)\n",
+    "    mlflow.log_metric(\"accuracy\", accuracy)\n",
+    "    mlflow.log_metric(\"f1_score\", f1)\n",
     "\n",
-    "    # Stop Logging\n",
+    "    # ✅ Save model artifact (still using MLflow serialization, but NOT registering)\n",
+    "    model_output_path = os.path.join(args.model, \"trained_model\")\n",
+    "    mlflow.sklearn.save_model(sk_model=clf, path=model_output_path)\n",
+    "\n",
+    "    print(f\"Model saved to {model_output_path}\")\n",
     "    mlflow.end_run()\n",
     "\n",
     "\n",
     "if __name__ == \"__main__\":\n",
-    "    main()"
+    "    main()\n"
    ]
   },
   {