Course Outline
Introduction
- Spark NLP vs NLTK vs spaCy
- Overview of Spark NLP features and architecture
Getting Started
- Setup requirements
- Installing Spark NLP
- General concepts
Using Pre-trained Pipelines
- Importing required modules
- Default annotators
- Loading a pipeline model
- Transforming texts
Building NLP Pipelines
- Understanding the pipeline API
- Implementing NER models
- Choosing embeddings
- Using word, sentence, and universal embeddings
Classification and Inference
- Document classification use cases
- Sentiment analysis models
- Training a document classifier
- Using other machine learning frameworks
- Managing NLP models
- Optimizing models for low-latency inference
Troubleshooting
Summary and Next Steps
Requirements
- Familiarity with Apache Spark
- Python programming experience
Audience
- Data scientists
- Developers
Testimonials (5)
A lot of practical examples, different ways to approach the same problem, and sometimes not so obvious tricks how to improve the current solution
Rafał - Nordea
Course - Apache Spark MLlib
Sufficient hands on, trainer is knowledgable
Chris Tan
Course - A Practical Introduction to Stream Processing
practice tasks
Pawel Kozikowski - GE Medical Systems Polska Sp. Zoo
Course - Python and Spark for Big Data (PySpark)
The VM I liked very much The Teacher was very knowledgeable regarding the topic as well as other topics, he was very nice and friendly I liked the facility in Dubai.
Safar Alqahtani - Elm Information Security
Course - Big Data Analytics in Health
This is one of the best hands-on with exercises programming courses I have ever taken.