Skip to content

Update imports and model saving in quickstart notebook #3796

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
lavakumarrepala wants to merge 15 commits into
base: main
Choose a base branch
from
Open

Update imports and model saving in quickstart notebook #3796

Changes from all commits
Commits
Show all changes
15 commits
Select commit Hold shift + click to select a range
2a5d364
Update imports and model saving in quickstart notebook
lavakumarrepala Mar 10, 2026
fb6fafa
Update environment reference in quickstart notebook
lavakumarrepala Mar 10, 2026
7b96842
update quickstart.ipynb
lavakumarrepala Mar 10, 2026
4e1b73e
updated quickstart notebook to fix the broken links to the datasets a…
lavakumarrepala Mar 10, 2026
1dd676f
updated quickstart notebook to fix the broken links to the datasets a…
lavakumarrepala Mar 11, 2026
84d787a
updated image tag for sklearn environment to use the same custom envi…
lavakumarrepala Mar 11, 2026
81c1ecb
fic container crash
lavakumarrepala Mar 11, 2026
a2df510
Update Docker image for custom environment
lavakumarrepala Mar 11, 2026
a1666dd
update quickstart.ipynb
lavakumarrepala Mar 11, 2026
1940e17
update quickstart.ipynb
lavakumarrepala Mar 11, 2026
a3109c6
update quickstart.ipynb
lavakumarrepala Mar 11, 2026
9b0ed11
update quickstart.ipynb
lavakumarrepala Mar 11, 2026
45f8cce
update quickstart.ipynb
lavakumarrepala Mar 11, 2026
ed4a1d8
update quickstart.ipynb
lavakumarrepala Mar 11, 2026
84b7001
update quickstart.ipynb
lavakumarrepala Mar 11, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
98 changes: 60 additions & 38 deletions tutorials/get-started-notebooks/quickstart.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -178,6 +178,7 @@
"import pandas as pd\n",
"import mlflow\n",
"import mlflow.sklearn\n",
"import joblib\n",
"from sklearn.ensemble import GradientBoostingClassifier\n",
"from sklearn.metrics import classification_report\n",
"from sklearn.model_selection import train_test_split\n",
Expand All @@ -192,6 +193,7 @@
" 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 output folder\", default=\"./outputs\")\n",
" args = parser.parse_args()\n",
" \n",
" # Start Logging\n",
Expand Down Expand Up @@ -252,41 +254,28 @@
" ##########################\n",
" #<save and register model>\n",
" ##########################\n",
" # Registering the model to the workspace\n",
" print(\"Registering the model via MLFlow\")\n",
"\n",
" # pin numpy\n",
" conda_env = {\n",
" 'name': 'mlflow-env',\n",
" 'channels': ['conda-forge'],\n",
" 'dependencies': [\n",
" 'python=3.10.15',\n",
" 'pip<=21.3.1',\n",
" {\n",
" 'pip': [\n",
" 'mlflow==2.17.0',\n",
" 'cloudpickle==2.2.1',\n",
" 'pandas==1.5.3',\n",
" 'psutil==5.8.0',\n",
" 'scikit-learn==1.5.2',\n",
" 'numpy==1.26.4',\n",
" ]\n",
" }\n",
" ],\n",
" }\n",
"\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",
" conda_env=conda_env,\n",
" )\n",
"\n",
" # Saving the model to a file\n",
" mlflow.sklearn.save_model(\n",
" sk_model=clf,\n",
" path=os.path.join(args.registered_model_name, \"trained_model\"),\n",
" )\n",
" # Save the model to the component output folder first\n",
" print(\"Saving the model to the component output folder\")\n",
" os.makedirs(args.model, exist_ok=True)\n",
" model_path = os.path.join(args.model, \"model.pkl\")\n",
" joblib.dump(clf, model_path)\n",
" print(f\"Model saved to: {model_path}\")\n",
" \n",
" # Log model as artifact\n",
" mlflow.log_artifact(model_path, artifact_path=\"model\")\n",
" \n",
" # Log parameters manually to ensure they're captured\n",
" mlflow.log_param(\"n_estimators\", args.n_estimators)\n",
" mlflow.log_param(\"learning_rate\", args.learning_rate)\n",
" mlflow.log_param(\"test_train_ratio\", args.test_train_ratio)\n",
" \n",
" # Log additional metrics\n",
" from sklearn.metrics import accuracy_score\n",
" accuracy = accuracy_score(y_test, y_pred)\n",
" mlflow.log_metric(\"accuracy\", accuracy)\n",
" \n",
" print(f\"Model accuracy: {accuracy:.4f}\")\n",
" print(\"Model training completed and artifacts logged\")\n",
" ###########################\n",
" #</save and register model>\n",
" ###########################\n",
Expand Down Expand Up @@ -326,6 +315,33 @@
"* Since a compute resource was not specified, the script will be run on a [serverless compute cluster](https://learn.microsoft.com/azure/machine-learning/how-to-use-serverless-compute?view=azureml-api-2&tabs=python) that is automatically created."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Create a custom environment using the openmpi5.0-cuda12.4-ubuntu22.04 image\n",
"# This provides GPU support with CUDA 12.4 and updated Ubuntu 22.04\n",
"\n",
"from azure.ai.ml.entities import Environment\n",
"\n",
"# Create custom environment with the specified image\n",
"job_env = Environment(\n",
" name=\"openmpi5-cuda12-env\",\n",
" description=\"Custom environment with OpenMPI 5.0, CUDA 12.4, Ubuntu 22.04\",\n",
" image=\"mcr.microsoft.com/azureml/openmpi5.0-cuda12.4-ubuntu22.04:latest\",\n",
")\n",
"\n",
"# Register the environment\n",
"job_env = ml_client.environments.create_or_update(job_env)\n",
"\n",
"print(f\"✅ Custom environment created: {job_env.name}\")\n",
"print(f\" Environment version: {job_env.version}\")\n",
"print(\" Base image: openmpi5.0-cuda12.4-ubuntu22.04\")\n",
"print(\" This environment provides OpenMPI 5.0, CUDA 12.4 support, and Ubuntu 22.04\")"
]
},
{
"cell_type": "code",
"execution_count": null,
Expand All @@ -342,6 +358,7 @@
"\n",
"registered_model_name = \"credit_defaults_model\"\n",
"\n",
"# Use a stable curated environment for training\n",
"job = command(\n",
" inputs=dict(\n",
" data=Input(\n",
Expand All @@ -351,12 +368,15 @@
" test_train_ratio=0.2,\n",
" learning_rate=0.25,\n",
" registered_model_name=registered_model_name,\n",
" model=\"./outputs\",\n",
" ),\n",
" code=\"./src/\", # location of source code\n",
" command=\"python main.py --data ${{inputs.data}} --test_train_ratio ${{inputs.test_train_ratio}} --learning_rate ${{inputs.learning_rate}} --registered_model_name ${{inputs.registered_model_name}}\",\n",
" environment=\"azureml://registries/azureml/environments/sklearn-1.5/labels/latest\",\n",
" command=\"python main.py --data ${{inputs.data}} --test_train_ratio ${{inputs.test_train_ratio}} --learning_rate ${{inputs.learning_rate}} --registered_model_name ${{inputs.registered_model_name}} --model ${{inputs.model}}\",\n",
" environment=f\"{job_env.name}:{job_env.version}\", # Use our custom environment with openmpi5.0-cuda12.4-ubuntu22.04\n",
" display_name=\"credit_default_prediction\",\n",
")"
")\n",
"\n",
"print(f\"✅ Job configured with custom environment: {job_env.name}:{job_env.version}\")"
]
},
{
Expand Down Expand Up @@ -564,10 +584,12 @@
" name=\"blue\",\n",
" endpoint_name=online_endpoint_name,\n",
" model=model,\n",
" environment=f\"{job_env.name}:{job_env.version}\", # Use the same custom environment\n",
" instance_type=\"Standard_DS3_v2\",\n",
" instance_count=1,\n",
")\n",
"\n",
"print(f\"✅ Deployment configured with custom environment: {job_env.name}:{job_env.version}\")\n",
"blue_deployment = ml_client.begin_create_or_update(blue_deployment).result()"
]
},
Expand Down
Loading