My work for the Google Summer of Code
This repository contains the reports from the data analysis conducted during the GSoC and carried on over team digitale's Dataportal.
Every report is written in HTML/Markdown and holds explicative informations regarding the subjects and links to other complementary resources such as Superset dashboards and IPython notebooks.
It provides the following datastories:
- ANAC
- ANAC competitor
- DSU - Alloggi e Mense
- DSU - Spese, Interventi e Dipendenti
Every datastory is placed inside a single folder and has its own image folder that holds the visualizations and the graphs.
-
ANAC is the anti-corruption institution of the italian government and I have completed 2 datastories that tell the analysis of their OpenData datasets and how it can help fight irregularities in the tenders. To fully appreciate this work one needs to know some basic python programming and possibly some machine learning, since they are both heavily used in the processing.
-
DSU is the agency of the italian ministry of education that implements the "right-to-study" on a regional basis. I have analyzed student residences, cafeterias, expenses, interventions and employees over different years, and presented this work using interactive visualizations and providing insights.
These analysis are based on true world-data and provide a good proof-of-concept on how to use OpenData to help the Public Administration in solving their tasks. Every sector of the state accumulates a lot of data, so much more work can be done, using the other thousands of datasets available on the team's dataportal!
I really appreciated this opportunity and I worked with very skilled menthors that were always available and never too pushy in my regards.
I would like to continue collaborating in this community providing my free-time expertise whenever possible, and possibly bring in the project other data-science-enthusiast colleagues.