/spark-nlp-book

Primary LanguageJupyter Notebook

Natural Language Processing with Spark NLP

This the repo for the book Natural Language Processing with Spark NLP: Learning to Understand Text at Scale

I have two folders for the notebooks

  • colab is the folder containing the notebooks to be run on google colab
  • jupyter is the folder to run the notebooks locally

I'm am working on a docker deployment, and it should be done soon.

There are a couple chapters where you may run into problems

  • Chapter 9: I've had some problems running the Core NLP server
  • Chapter 13: Uploading the data to Neo4j takes a very long time
  • Chapter 14: I've had some problems with spark-elasticsearch interface, also I have not been able to run elasticsearch on colab