| |
|
EVENT DETAILS |
Make NLP data easier to understand with Pandas Data Frames.
Register on Crowdcast: https://www.crowdcast.io/e/text-extensions
This is a good webinar for you if you are:
- An aspiring data scientist
- Frequently working with large pieces of text data and want another approach to dissect data
- Someone who is interested in Natural Language Processing
- Curious about data in general!
Introduction to Text Extension for Pandas
This workshop will introduce you to Text Extensions for Pandas. Text Extensions for Pandas lets you use Pandas DataFrames for representing and manipulating the complex data structures that flow through modern natural language processing (NLP) applications. We provide Pandas extension types to cover common data structures for representing natural language data, plus library integrations that turn the outputs of popular NLP libraries into easy-to-understand DataFrames.
What will you learn?
- TensorArray extension type
- SpanArray extension type
- Natural Language Processing basics
- How to manipulate NLP data types with standard Pandas DataFrames operations
- How to use Pandas DataFrames to train a machine learning model
For the hands-on lab, you will learn how to analyze some Wikipedia text data with the Text Extensions for Pandas API. Sounds interesting - join us!
Learn more at https://codait.github.io/text-extensions-for-pandas/
Who should attend?
All Developers are welcome to attend the webinar!
Prerequisites
Register for a free IBM Cloud Account: https://ibm.biz/text-extension prior to the event to get the most out of our workshop.
Speakers
Frederick Reiss, Chief Architect, Center for Open-Source Data and AI Technologies (CODAIT)
Pooja Mistry, IBM Developer Advocate
Register on Crowdcast: https://www.crowdcast.io/e/text-extensions
|
|
|
|
|
|
