Skip to content

Latest commit

 

History

History
7 lines (6 loc) · 282 Bytes

README.md

File metadata and controls

7 lines (6 loc) · 282 Bytes

industry-clusters

Final project for CS 505 - Computational Tools for Data Science.

Overview

This project uses document clustering technique TfidfVectorizer and k-means to identify trends of job descriptions within industries.

Data

Scraping indeed.com and Glassdoor API.