NLP Demo & Tutorial

NLP Demo & Tutorial for Data Science Seminar (CS 396/496, Fall 2019)

For a better in browser viewing experience (than the one provided on github) use the NBViewer Links for Jupyter Notebooks:

• Introduction to spaCy.ipynb
  • crash course on spaCy functionality for NLP in Python
  • tokenization
  • lemmatization
  • stopwords
  • parts-of-speech tagging
  • word vectors
  • token matching
  • phrase matching
• ML for NLP.ipynb
  • Naive Bayes Classifier
  • preprocessing data sets
  • logistic regression
• Applying NLP to CPDB.ipynb
  • actually applying all the concepts to document_tags table of Chicago Police Database for document tagging of allegations
  • how to run sql queries directly in Python (using psycopg2)
  • document tagging for cpdb

To install dependencies:

pip3 install -r requirements.txt