/SAIM-IntroductionToNLP

Labs for session 1 of the Intro to NLP meetup

Primary LanguageJupyter Notebook

Introduction to NLP

Overview In this workshop, we'll learn different Natural Language Techniques needed to start building different models. Python3 is the preferred language for the labs. Some pre-requisites before getting started are listed below.


Pre-requisites

  • Python >3.0
  • NLTK package
  • Spacy
  • Pandas
  • iPython
  • iPython Notebook
  • virtualenv

Once python3 is installed, create and activate a virtualenv

pip install virtualenv
virtualenv -p python3 venv
source activate venv/bin/activate
pip install --upgrade pip

This activates a virtualenv where you can install the required packages

Install nltk models

python -m nltk.downloader stopwords

Install spacy models

python -m spacy download en

Labs

  1. Preprocessing
  2. Part of speech tagging
  3. BOW/TF-IDF