JamesMcGuigan / elasticsearch-nlp-classifier

ElasticSearch NLP Naive Bayes Classifier

ElasticSearch NLP Classifier

Java data streaming pipeline for ElasticSearch.

Enables NLP Naive Bayes classification with k-fold cross-validation on existing datasets.

Inspiration is taken from the following python Kaggle Notebooks:

• https://www.kaggle.com/jamesmcguigan/nlp-naive-bayes
• https://www.kaggle.com/jamesmcguigan/nlp-tf-idf-classifier
• https://www.kaggle.com/jamesmcguigan/nlp-logistic-regression
• https://www.kaggle.com/jamesmcguigan/nlp-laser-embeddings-keras

Initialization of the ElasticSearch database is handled in this repository:

• https://github.com/JamesMcGuigan/elasticsearch-tweets

For local installation instructions see:

• INSTALL.md