We have the text data scraped from the websited of more than 70 thousand companies. Our task is to make clusters of similar companies, so we can analyse each group separately and approach the companies is similar groups with similar business proposals.
- Prashant_Jha_Company_Classification_Capstone_Project.ipynb: Python notebook with all the Data Preprocessing and Clustering code.
- Technical Documentation.pdf: Detailed documentation of the process used in code.
- presentation.pdf: Presentation of the project.