The aim of the project is to predict the tags (a.k.a. keywords, topics, summaries) of a question, given only the question text and its title. The dataset consists of 6M+ of ‘Title’, ‘Body’ and ‘Tags’ of the questions posted on StackOverflow. From disparate stack exchange sites, containing a mix of both technical and non-technical questions. Using Binary Relevance Method with One vs Rest Classifier to achieve more than 94 % accuracy This repo contains my implementation of the Taxonomy Classification problem for TCS HumAIn Idea submission round
You will need to isntall the following modules to run this code successfully. The entire code is written in Python3
(1) Pandas
(2) Numpy
(3) Matplotlib
(4) Sqlite
(5) Seaborn
(6) Wordcloud
(7) Sqlalchemy
(8) NLTK libraries
(9) Sklearn packages