A large amount of time for machine learning tasks is spent understanding the data and getting it into the proper configuration to train the model. This is the data wrangling, exploration, and cleaning phase of the machine learning life cycle. In Azure Machine Learning designer, many common data-changing operations are provided as transform modules. In this lab, you will explore the *Clean Missing Data* module to gain a deeper understanding of the tools at your disposal.
Learning Objectives
Successfully complete this lab by achieving the following learning objectives:
- Set Up the Workspace
Log in and go to the Azure Machine Learning Studio workspace provided in the lab.
Create a Training Cluster of
Standard_DS1_v2instances.Create a new blank Pipeline in the Azure Machine Learning Studio Designer.
- Explore Clean Missing Data
Add an Adult Census Income Binary Classification dataset node to the pipeline. Visualize this raw data to see what data is missing.
Find a column that is only missing a value in under 5% of the data. You will need to find the total row count and how many values are missing in each column. All of this information is provided on the Visualize popup.
Using a Clean Missing Data transformation, remove the rows which are missing data in the chosen column.
Submit the pipeline to perform the transformation.
- Visualize the Transformed Data
When the pipeline finishes, inspect the output of the Clean Missing Data node. How have the column statistics changed?
You can continue to chain the Clean Missing Data nodes to clean other columns. You can also select multiple columns to clean at the same time if you want to apply the same operation with the same threshold values on those columns.
