This document contains a list of all the Vertex AI Jupyter Notebook tutorials. They're end-to-end tutorials that show you how to preprocess data, train, deploy, and use the models for inference. If you're new to Vertex AI, we recommend you start with Introduction to Vertex AI.
There are many environments in which you can host Jupyter Notebooks. You can run them on your local machine, a Jupyter or JupyterLab server in your local network or in the cloud using a service like Colaboratory (Colab) or Vertex AI Workbench.
Running a Jupyter Notebook in Colab is an easy way to get started quickly. All you must do is click the Colab link in the following table. Colab spins up a VM instance with all needed dependencies, launches the Colab environment, and loads the Notebook. At this point, the notebook is ready to run.
You can also run the notebook using user-managed notebooks. When you create a user-managed notebooks instance with Vertex AI Workbench, you have full control over the hosting VM. You can specify the configuration and environment of the hosting VM. To open a notebook sample in a Vertex AI Workbench user-managed notebooks instance, click the Vertex AI Workbench link in the following table. The link opens the Vertex AI Workbench console. In the Deploy to notebook screen, type a name for your new notebook instance and select CREATE. After the notebook instance has started, a Ready to open notebook dialog is displayed. Select OPEN. On the Confirm deployment to notebook server page, select Confirm. Before running the notebook, select Kernel > Restart Kernel and Clear all Outputs. The notebook is now ready to run.
| Services | Notebook | Description | Open in |
|---|---|---|---|
| AutoML | Text classification model | Create, train, and deploy a text classification model on Vertex AI. | |
| AutoML | Time-series forecasting model | Create, train, and use an AutoML time-series forecasting model for batch prediction. | |
| BigQuery and Vertex AI Workbench | Perform exploratory analysis of BigQuery data | Explore and analyze BigQuery data in a Jupyter notebook environment. This notebook was written for Vertex AI Workbench but can also be run in Colab and elsewhere. | |
| BigQuery and Vertex AI Workbench | Train a multi-class classification model for ads-targeting | Build a machine learning model that uses BigQuery data to select ad campaigns based on user behavior. This notebook was written for Vertex AI Workbench but you can also run it in Colab and elsewhere. | |
| BigQuery, Vertex Explainable AI, and Vertex AI Workbench | Perform analysis, feature selection, model building, and deployment | Solve a taxi fare prediction problem by using Vertex Explainable AI and BigQuery data. This notebook was written for Vertex AI Workbench but you can also run it in Colab and elsewhere. | |
| BigQuery ML and Vertex AI Workbench | Forecast retail demand with Vertex AI and BigQuery ML | Train and evaluate a BigQuery ML model for demand forecasting on a retail dataset. This notebook was written for Vertex AI Workbench but you can also run it in Colab and elsewhere. | |
| BigQuery ML and Vertex AI Workbench | Build a pricing optimization model using BigQuery ML | Train a BigQuery ML model, generate sales forecasts, and analyze the results to optimize pricing. This notebook was written for Vertex AI Workbench but you can also run it in Colab and elsewhere. | |
| BigQuery ML, Google Analytics 4, and Vertex AI Workbench | Train and evaluate a propensity model in BigQuery ML | Use a real mobile app's raw event data that was gathered by Google Analytics 4 to predict user retention. This notebook was written for Vertex AI Workbench but you can also run it in Colab and elsewhere. | |
| BigQuery ML, Vertex AI Model Registry, and batch prediction | Train a BigQuery ML model and register it to the Vertex AI Model Registry | Train a BigQuery ML model and register it to the Vertex AI Model Registry before running batch predictions. | |
| BigQuery ML, Vertex AI Model Registry, and online prediction | Train and deploy a churn prediction model for real-time inference | Train a BigQuery ML model, register it to the Vertex AI Model Registry, and deploy the model to an endpoint on Vertex AI for online predictions. | |
| Custom training | Batch prediction | Use the Vertex AI SDK for Python to train and deploy a custom image classification model for batch prediction. | |
| Custom training | Online prediction | Use the Vertex AI SDK for Python to train and deploy a custom image classification model for online prediction. | |
| Custom training | Hyperparameter tuning | Use the Vertex AI SDK for Python to run a hyperparameter tuning job. | |
| Tabular data | Forecasting model comparison | Compare the performance of the Vertex AI Forecasting model and the BigQuery ML ARIMA_PLUS model on a synthetic dataset of product sales. | |
| Tabular data | Tabular Workflow: AutoML Tabular Pipeline | Run AutoML Tabular as a managed instance of Vertex AI Pipelines. Customize the workflow by overriding the search space, configuring hardware, and skipping the architecture search. | |
| Tabular data | Tabular Workflows: TabNet Pipeline | Run the TabNet algorithm as a managed instance of Vertex AI Pipelines. | |
| Tabular data | Tabular Workflows: Wide and Deep Pipeline | Run the Wide and Deep algorithm as a managed instance of Vertex AI Pipelines. | |
| Text data and Vertex AI Workbench | Build and deploy a sentiment analysis model on Vertex AI | Build a sentiment analysis model by using AutoML text classification and deploy the model on Vertex AI to get predictions This notebook was written for Vertex AI Workbench but you can also run it in Colab and elsewhere. | |
| Vertex AI TensorBoard | Vertex AI TensorBoard integration with Vertex AI Pipelines | Learn how to create a training pipeline using the KFP SDK, execute the pipeline in Vertex AI Pipelines, and monitor your training process on Vertex AI TensorBoard in near real time. | |
| Vertex AI Experiments | Compare pipeline runs | Log and compare different Pipeline Jobs in Vertex AI. | |
| Vertex AI Experiments | Model training with pre-built data pre-processing code | Use a Python data pre-processing library to clean up an in memory dataset and then train a model using Keras. | |
| Vertex AI Experiments | Compare trained and evaluated models | Compare local trained models. | |
| Vertex AI Feature Store | Manage sample ML features using Vertex AI Feature Store | Store, serve, manage, and share machine learning features at a large scale. | |
| Vertex AI Matching Engine | Use Matching Engine Approximate Nearest Neighbor (ANN) search. | Create an Approximate Nearest Neighbor (ANN) index, query against indexes, and validate the performance of the index. | |
| Model evaluation and Tabular data | AutoML tabular classification model evaluation | Evaluate batch prediction results for a trained AutoML tabular classification model. | |
| Model evaluation and Tabular data | AutoML tabular regression model evaluation | Evaluate batch prediction results for a trained AutoML tabular regression model. | |
| Model evaluation and Text data | AutoML text classification model evaluation | Evaluate batch prediction results for a trained AutoML text classification model. | |
| Model evaluation and Video data | AutoML video classification model evaluation | Evaluate batch prediction results for a trained AutoML video classification model. | |
| Model evaluation and Tabular data | Custom tabular classification model evaluation | Evaluate batch prediction results for a trained custom tabular classification model. | |
| Model evaluation and Tabular data | Custom tabular regression model evaluation | Evaluate batch prediction results for a trained custom tabular regression model. | |
| Vertex AI Model Monitoring | Use Model Monitoring to detect drift and training-prediction skew | Interpret statistics, visualizations, and other data reported by Model Monitoring. | |
| Vertex AI Pipelines | Create a pipeline with lightweight components based on Python functions | Use the Kubeflow Pipelines (KFP) SDK to build Vertex AI Pipelines. | |
| Vertex AI Pipelines | AutoML image classification model workflow | Build an AutoML image classification workflow on Vertex AI Pipelines. | |
| Vertex AI Pipelines | AutoML tabular classification model workflow | Build an AutoML tabular classification workflow on Vertex AI Pipelines. | |
| Vertex AI Pipelines | AutoML tabular regression model workflow | Build an AutoML tabular regression workflow on Vertex AI Pipelines. | |
| Vertex AI Pipelines | AutoML text classification model workflow | Build an AutoML text classification workflow on Vertex AI Pipelines. | |
| Vertex AI Pipelines | Custom training with pre-built Google Cloud Pipeline Components | Use Vertex AI Pipelines with pre-built Google Cloud Pipeline Components for custom training. | |
| Vertex AI Pipelines | Custom training workflow with pre-built Google Cloud Pipeline Components and custom components | Use custom components to build a Vertex AI Pipelines workflow. | |
| Vertex AI Pipelines | Pipelines with control structures | Use the Kubeflow Pipelines (KFP) SDK to build Vertex AI Pipelines that use control structures. | |
| Vertex AI Pipelines | Model metrics | Build Vertex AI Pipelines that generate model metrics and visualizations, and compare pipeline runs. | |
| Vertex AI Pipelines | Vertex AI Pipelines and the Kubeflow Pipelines SDK | Use Vertex AI Pipelines with the Kubeflow Pipelines (KFP) SDK. | |
| Vertex AI Vizier | Multi-objective optimization | Optimize multiple objective functions simultaneously. | |
| Vertex AI Workbench | Build a fraud detection model on Vertex AI | Build, deploy, and analyze predictions from a random forest model by using tools like scikit-learn, Vertex AI, and the What-If Tool (WIT) on a fraud transaction dataset. This notebook was written for Vertex AI Workbench but you can also run it in Colab and elsewhere. | |
| Vertex AI Workbench | Deploy an automated machine learning model using Vertex AI Workbench | Deploy a predictive maintenance machine learning model on Vertex AI, and automate the workflow by using the executor feature of Vertex AI Workbench. This notebook was written for Vertex AI Workbench but much of it can also be run in Colab and elsewhere. | |
| Vertex Explainable AI | Tabular binary classification for batch prediction | Use the Vertex AI SDK to create tabular binary classification models and perform batch prediction with explanation using a AutoML model. | |
| Vertex Explainable AI | Tabular binary classification for online prediction | Use the Vertex AI SDK to create tabular classification models and do online prediction with explanation using a AutoML model. | |
| Vertex Explainable AI | Custom training image classification model for batch prediction | Use the Vertex AI SDK to train and deploy a custom image classification model for batch prediction with explanation. | |
| Vertex Explainable AI | Custom training image classification model for online prediction | Use the Vertex AI SDK to train and deploy a custom image classification model for online prediction with explanation. | |
| Vertex Explainable AI | Training tabular regression models for batch prediction | Use the Vertex AI SDK to train and deploy a custom tabular regression model for batch prediction with explanation. | |
| Vertex Explainable AI | Custom training tabular regression model for online prediction | Use the Vertex AI SDK to train and deploy a custom tabular regression model for online prediction with explanation. | |
| Vertex Explainable AI and Vertex AI Workbench | Deploy and get predictions and explanations from a churn prediction model | Explore and preprocess data, train and deploy a customer churn model, and get predictions on a customer churn dataset. Get explanations by using Vertex Explainable AI. This notebook was written for Vertex AI Workbench but you can also run it in Colab and elsewhere. | |
| Vertex Explainable AI and Vertex AI Workbench | Inventory prediction on ecommerce data using Vertex AI | Build a machine learning model for inventory prediction on an ecommerce dataset using the Vertex AI SDK for Python. This notebook was written for Vertex AI Workbench but you can also run it in Colab and elsewhere. | |
| Vertex ML Metadata | Custom training job parameter and metric tracking | Track metrics and parameters for Vertex AI custom training jobs, and perform detailed analysis. |