This repo houses EDA, small data science projects and other experiments
Projects Contained in this repo are:
The themes viz generator file is used to generate the files needed for the fact checking sites dashboards. After generating the files, the files need to be pushed to the website. Please see: instructions on Push to Website to make the dashboard visible on the khoj page
The Bigram Clustering file can be used to generate bigrams of headlines of articles. The bigrams can be used to identify similar or identical stories by different groups.
The whatsapp_groups_analysis folder contains the code used to analyze conversations in WhatsApp groups Tattle tracked during the second Covid-19 wave in India. See the 'Crowdsourcing Aid' report here: https://tattle.co.in/articles/covid-whatsapp-public-groups/
This code groups a set of images based on visual and semantic similarity. It was used to generate the visualization for the report on Covid-19 Relief Groups on WhatsApp. But it is generalized code that can be used to group any images.
When you submit code changes, your submissions are understood to be under the same licence that covers the project - GPL-3. Feel free to contact the maintainers if that's a concern.
Have a proposal for an experiment? Please see instructions for contributing here.