Real data issues in Machine Learning, and how to handle them

Instructor: Giovane Cesar da Silva (IBM)

Typically, when someone learns Machine Learning methods, the example data sets are pre-processed and cleaned. When working in professional projects, the state of the data is unknown and requires effort to make it usable even for simple statistics.

In this hands-on workshop, you will:

• practice data understanding,
• ingest data with bad format,
• apply standard data quality tests,
• apply data specific quality tests, and
• use some data patching algorithms.

Target audience: general

Duration: 3 hours

Level: beginner to intermediate

Prerequisites: Knowledge of Python language, package management, and Pandas data processing.

Laptop software: All attendees will need to bring laptops with wireless access with Anaconda 2019.03 installed and updated and configured in your preferred IDE.