How to create and use ML Notebook?

info

• Follow the steps mentioned below.
• Total time taken for this task: 60 Minutes.
• Pre-requisites: User registration is completed, logged in to Amorphic and role switched

Tidbits

• Amorphic's ML notebook is built on top of Amazon Sagemaker notebook instance.
• The notebook instance is a machine learning (ML) compute instance running the Jupyter Notebook app.
• SageMaker manages creating the instance and related resources.
• Use ML notebook instance to prepare and process data, write code to train models, deploy models to SageMaker hosting, and test or validate your models.

Create an ML notebook

• Click on 'MACHINE LEARNING' --> 'Notebooks' from left navigation-bar.
• Click on ➕ icon at the top right corner to create a new notebook.
• Enter the following information and click create.

Notebook Name: ml-notebook-<your_userid>
Description: This is an ML notebook for training a model.
Keywords: ML, Notebook
Instance Type: ml.c4.xlarge
Volume Size: 10
Datasets Write Access:
Datasets Read Access:
Enable Internet Access : Yes
Auto Terminate: Yes
Auto Termination Time: Choose the same time tomorrow.

• Click the 🔄 icon to refresh the status.
• Once the status turns to 'InService', you will see a link Notebook URL Link as shown below.

• Click on the link to go to the notebook.

Train a model in Jupyter Notebook

• Righ click here and click 'save link as' to download a notebook.

• Click on Upload button in the jupyter notebook.

• Select the above 'ChurnPredictionXGBoost.ipynb' and then click 'upload'.

• Click 'ChurnPredictionXGBoost.ipynb' to open it as shown below.

• Replace '9XXXXXXXXXXX' in the bucket variable with an account number from 'Dataset S3 Location' of the Dataset 'telecom_churn_prediction_metadata' or any other dataset created by you.
• Replace 'ankamv' with your userid in prefix variable.
• Run all cells of the notebook.
• Note the S3 path of the model from the output of the command print(model_data) as shown below.

• This model.tar.gz can be used to create an ML model in Amorphic.

tip

Check Creating an ML section for further learning.