Lab13.md

Monitoring Data Drift

Changing trends in data over time can reduce the accuracy of the predictions made by a model. Monitoring for this data drift and retraining as necessary is an important way to ensure your machine learning solution continues to predict accurately.

Before You Start

Before you start this lab, ensure that you have completed the Create an Azure Machine Learning Workspace and Create a Compute Instance tasks in Getting Started with Azure Machine Learning. Then return to this lab.

Monitor Data Drift

In this task, you'll monitor datasets for data drift.

1. In Azure Machine Learning studio, view the Compute for the workspace you created in the Getting Started with Azure Machine Learning lab; and on the Compute Instances tab, ensure your compute instance is running. If not, start it.

2. When the compute instance is running, click the Jupyter link to open the Jupyter home page in a new browser tab.

3. In the Jupyter home page, in the Users/mslearn-aml-labs folder, open the 13-Monitoring_Data_Drift.ipynb notebook. Then read the notes in the notebook, running each code cell in turn.

   Tip: If you cloned the repository previously, and the notebook file is not in the Users/mslearn-aml-labs folder, open a new terminal in your Jupyter environment and run the following commands to refresh the lab files (overwriting any changes you have made):

   cd Users/mslearn-aml-labs
   git reset --hard HEAD
   git pull

Important: When you have finished the lab, close all Jupyter tabs and Stop your compute instance to avoid incurring unnecessary costs.