Exploring Data in Azure Machine Learning looks at using Jupyter Notebooks to interactively explore and manipulate data prior to model training. In this lesson, we learn how to get a basic statistical summary of data and then how to resolve missing data values. The lesson’s demonstrations cover two scenarios: data sourced from a storage account and data from an attached Spark pool.
Learning Objectives
- Learn how to use the AzCopy utility to copy files to blob storage
- Learn how to use the Python SDK within a notebook to query and manipulate the data
Intended Audience
- Those interested in learning how to set up Azure Machine Learning Studio for interactive data wrangling
Prerequisites
- General understanding of the data store and data asset topics covered in the Accessing Data in Azure Machine Learning Lesson