This workshop provides a hands-on introduction to designing and building machine learning models on structured data on Google Cloud Platform. You will learn machine learning (ML) concepts and how to implement them using both BigQuery Machine Learning and TensorFlow/Keras. You will apply the lessons to a large out-of-memory dataset and develop hands-on skills in developing, evaluating, and productionizing ML models.

What you need

To complete this lab, you need:

What you learn

In this series of labs, you go from exploring a taxicab dataset to training and deploying a high-accuracy distributed model with BigQuery and with Keras on Cloud AI Platform.

To launch a notebook instance on GCP:

Step 1

Click the Navigation menu and scroll to AI Platform, then select Notebooks.

Step 2

Click New Instance and select TensorFlow 2.x > Without GPUs

Step 3

Once the instance has fully started, click Open JupyterLab to get a new notebook environment.

Step 4

Click on the Terminal icon and in the terminal, type:

git clone \
    https://github.com/GoogleCloudPlatform/training-data-analyst

In this lab, you will:

Step 1

In AI Platform Notebooks, navigate to training-data-analyst/quests/serverlessml/01_explore/solution and open explore_data.ipynb.

Step 2

Clear all the cells in the notebook (look for the Clear button on the notebook toolbar), change the region, project and bucket settings in the first cell, and then Run the cells one by one.

In this lab, you will:

Step 1

In AI Platform Notebooks, navigate to training-data-analyst/quests/serverlessml/02_bqml/solution and open first_model.ipynb.

Step 2

Clear all the cells in the notebook (look for the Clear button on the notebook toolbar), change the region, project and bucket settings in the first cell, and then Run the cells one by one.

In this lab, you will:

Step 1

In AI Platform Notebooks, navigate to training-data-analyst/quests/serverlessml/03_tfdata/solution and open input_pipeline.ipynb.

Step 2

Clear all the cells in the notebook (look for the Clear button on the notebook toolbar), change the region, project and bucket settings in the first cell, and then Run the cells one by one.

In this lab, you will:

Step 1

In AI Platform Notebooks, navigate to training-data-analyst/quests/serverlessml/04_keras/solution and open keras_dnn.ipynb.

Step 2

Clear all the cells in the notebook (look for the Clear button on the notebook toolbar), change the region, project and bucket settings in the first cell, and then Run the cells one by one.

In this lab, you will:

Step 1

In AI Platform Notebooks, navigate to training-data-analyst/quests/serverlessml/05_feateng/solution and open feateng_bqml.ipynb.

Step 2

Clear all the cells in the notebook (look for the Clear button on the notebook toolbar), change the region, project and bucket settings in the first cell, and then Run the cells one by one.

In this lab, you will:

Step 1

In AI Platform Notebooks, navigate to training-data-analyst/quests/serverlessml/06_feateng_keras/solution and open feateng_keras.ipynb.

Step 2

Clear all the cells in the notebook (look for the Clear button on the notebook toolbar), change the region, project and bucket settings in the first cell, and then Run the cells one by one.

In this lab, you will:

Step 1

In AI Platform Notebooks, navigate to training-data-analyst/quests/serverlessml/07_caip/solution and open export_data.ipynb.

Step 2

Clear all the cells in the notebook (look for the Clear button on the notebook toolbar), change the region, project and bucket settings in the first cell, and then Run the cells one by one.

Step 3

In AI Platform Notebooks, navigate to training-data-analyst/quests/serverlessml/07_caip/solution and open train_caip.ipynb.

Step 4

Clear all the cells in the notebook (look for the Clear button on the notebook toolbar), change the region, project and bucket settings in the first cell, and then Run the cells one by one.

┬ęGoogle, Inc. or its affiliates. All rights reserved. Do not distribute.