Meet Rosie

Machine Intelligence against corruption

Transcript

1. 1 Rosie
2. So far 2 • 5 implemented classifiers • ~3k suspicious reimbursements found • 629 reports made • 216 congresspeople reported
3. How we get the data? 3 • Scrapping • APIs ◦ ReceitaWS ◦ Camara
4. I have the data, what do I do now? • Develop a hypothesis • Test it out • Implement a classifier • Report 4
5. Jupyter Notebooks 5
6. GitHub 6
7. Server 7
8. The irregular companies classifier
9. import data 9
10. data.format() 10
11. data.head(5) 11
12. 12 pd.merge
13. 13 data.query()
14. Fixtures • Sample data 14
15. Tests • Test first, code later 15
16. Show me the code • The classifier 16
17. What about Rosie? • import Classifier 17
18. 5222 18
19. github.com/datasciencebr @jesstemporal apoia.se/serenata 19