Interactive Map Using Data Visualization and Machine Learning

This project aims to build a smart map, named VAWMap (Violence Against Women Map), that displays the intensity of various crimes against women across the states and districts of India in efforts to inspire action to combat this prevalent violence. The data set to be depicted on the map consists of the number of victims of rape, dowry deaths, kidnapping, cruelty by husbands, insult to modesty, and assault for each district of every state in India through the years between 2001-2013. Depicted states and their respective districts include Rajasthan, Punjab, and Haryana. Two algorithms, QR Decomposition with Column Pivoting and the Projected Clustering Algorithm, are leveraged to reveal prominent crimes and their locations-effectively yielding certain hot spot crime areas of North India. Two novel strategies to depict the intricate statistics obtained from these ML algorithms are proposed using a map-making platform, Mapbox. The result is two maps of India that display the intensity of the most prevalent crimes through a color gradient. The effectiveness, in terms of data reduction and visualization, between the two algorithms are compared and discussed.