/nlp-text-analysis

Starter code for extracting keywords, bigrams, and trigrams from large collections of end-user comments.

Primary LanguageJupyter Notebook

Keyword Extraction Using NLP

This Jupyter Notebook contains a sequenced set of modular Python code blocks intended to help novices to natural language processing extract keywords and n-grams from unstructured user feedback. View the accomanying article for background and more detail around sources and specific steps.

Running Notebook

  1. From the command line, clone this repo
git clone https://github.com/andybywire/nlp-text-analysis.git
  1. Copy the two text files to your desktop
  • rfi-data.tsv
  • custom-stopwords.txt
  1. Then, from inside the repo directory, run
jupyter notebook
  1. Select text-analytics.ipynb and press "Run" to start executing the scripts