Spark, Natural Language Processing, Machine Learning, Operationalize and Models

POT Hands on Labs

Hands on Introduction to Apache Spark, NLP, ML and Operationalizing Models for Data Engineers, Data Scientist and Developers

POT Summary

IBM is offering a no charge proof of technology for clients and practitioners on Apache Spark, Natural Language Processing, Watson Machine Learning and the Operationalizing of the Scoring Model.

This is a half day of education with hands on exercisesinstructed in person by Open Sourceexperts. The POT will provide a detail overview and the exercises will be performed on Jupyter notebooks with publiclyavailable datasets. Participants will use IBM’s fully managed free Cloud platform available for educational purposes.

Prerequisite:

A basic knowledge of Coding (Preferred Python and/or Scala) and SQL.

Agenda

Expect to spend a half day of lecture and hands on exercises attacking real-world data challenges using Apache Spark, NLP, ML and Models. In 4 hours, you will learn the essentials of why these solutions are important to your organization and data science process. This workshop will focus on data wrangling, machine learning, and operationalizing the model.

• 12:00 pm - 12:30pm Lunch, Socialize
• 12:30pm – 12:45pm Kickoff / Introductions/Account Setup
• 12:45pm – 1:15pm Intro to Watson Data Platform/Data Science Experience and Apache Spark
• 1:15pm – 2:00pm Lab 1, Hello Spark and Spark SQL (2 Parts)
• 2:00pm – 2:30pm Overview of Data Science & Machine Learning w/ Apache Spark
• 2:30pm - 3:00pm Lab 2, NLP and Machine Learning (2 Parts)
• 3:00pm – 3:30pm Lab 3, Data Science Scoring and Operationalizing the Model
• 3:30pm - 4:00pm Data Science Forum
• 4:00pm – onward Wrap up and Feedback

Data Science POT 2

To view the second POT assets click here; Data Science Experience POT 2