This project has been undertaken as a part of our undergraduate coursework, to understand generation of datasets and classification algorithms.

1. Clone this repo

   $ git clone https://github.com/sdabhi23/people-occupations-classifier.git

2. Setup virtual environment (optional)

   $ virtualenv .venv
   # for windows
   $ .venv\Scripts\activate
   # for *nix
   $ .venv/Scripts/activate

3. Installing the required libraries

   $ pip install -r requirements.txt

4. Additional steps for nltk

   >>> import nltk
   >>> nltk.download('stopwords')

5. Steps to configure ipython kernel

   Required only if using virtual environment

   $ ipython kernel install --user --name=people_classifier

   Then change the kernel in the jupyter interface to people_classifier.

• Shrey Dabhi (sdabhi23)
• Kartavya Soni (kartavyasoni25)

• Classifying Wikipedia People Into Occupations by Aleksander Gabrovski (.pdf)
• Multi-Class Text Classification with Scikit-Learn (article)
• Using jupyter notebooks with a virtual environment (article)