The Open Data Project aims to make socio-economic, school and crime data across multiple years available to the public in an easy-to-use manner. Data is gathered at the village, district, state and national level. This is primarily intended to make datasets available for predictive analysis and machine learning applications.

 

Solution

We combine multiple data sets from a wide variety of sources including data.gov.in, udise.in, ncrb.gov.in and Niti Aayog. We use a combination of scripts to clean, dedupe and merge the data to form yearly data sets.

 

Technology stack

• Python
• Jupyter Notebooks
• Wazimap
• CountingIndia.org

 

Hours spent: 1.5 months

Status: On going

Github URL’s:

https://github.com/kurund/aangan-data-analysis
https://github.com/kurund/janaganana

Screenshots: