Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Meet Rosie
Search
Jessica Temporal
March 27, 2017
Programming
0
71
Meet Rosie
Machine Intelligence against corruption
Jessica Temporal
March 27, 2017
Tweet
Share
More Decks by Jessica Temporal
See All by Jessica Temporal
Tips for Writing Great Technical Content
jtemporal
0
240
Traveling Through a Secure API with Python and Auth0
jtemporal
0
130
Rosie, Robot
jtemporal
0
440
Serenata de Amor's data science
jtemporal
1
170
Final Graduation Project
jtemporal
0
230
Other Decks in Programming
See All in Programming
なぜGoのジェネリクスはこの形なのか? Featherweight Goが明かす設計の核心
ryotaros
7
1.1k
After go func(): Goroutines Through a Beginner’s Eye
97vaibhav
0
350
CSC305 Lecture 04
javiergs
PRO
0
260
2分台で1500examples完走!爆速CIを支える環境構築術 - Kaigi on Rails 2025
falcon8823
3
3.5k
Writing Better Go: Lessons from 10 Code Reviews
konradreiche
0
110
Cloudflare AgentsとAI SDKでAIエージェントを作ってみた
briete
0
140
CSC509 Lecture 05
javiergs
PRO
0
300
Advance Your Career with Open Source
ivargrimstad
0
460
iOSエンジニア向けの英語学習アプリを作る!
yukawashouhei
0
190
オープンソースソフトウェアへの解像度🔬
utam0k
12
2.5k
開発生産性を上げるための生成AI活用術
starfish719
3
420
Things You Thought You Didn’t Need To Care About That Have a Big Impact On Your Job
hollycummins
0
210
Featured
See All Featured
Building Applications with DynamoDB
mza
96
6.7k
The Invisible Side of Design
smashingmag
301
51k
Mobile First: as difficult as doing things right
swwweet
224
10k
Building a Scalable Design System with Sketch
lauravandoore
462
33k
It's Worth the Effort
3n
187
28k
A better future with KSS
kneath
239
18k
RailsConf 2023
tenderlove
30
1.2k
Fight the Zombie Pattern Library - RWD Summit 2016
marcelosomers
234
17k
Performance Is Good for Brains [We Love Speed 2024]
tammyeverts
12
1.2k
Visualizing Your Data: Incorporating Mongo into Loggly Infrastructure
mongodb
48
9.7k
Build your cross-platform service in a week with App Engine
jlugia
232
18k
How to train your dragon (web standard)
notwaldorf
96
6.3k
Transcript
1 Rosie
So far 2 • 5 implemented classifiers • ~3k suspicious
reimbursements found • 629 reports made • 216 congresspeople reported
How we get the data? 3 • Scrapping • APIs
◦ ReceitaWS ◦ Camara
I have the data, what do I do now? •
Develop a hypothesis • Test it out • Implement a classifier • Report 4
Jupyter Notebooks 5
GitHub 6
Server 7
The irregular companies classifier
import data 9
data.format() 10
data.head(5) 11
12 pd.merge
13 data.query()
Fixtures • Sample data 14
Tests • Test first, code later 15
Show me the code • The classifier 16
What about Rosie? • import Classifier 17
5222 18
github.com/datasciencebr @jesstemporal apoia.se/serenata 19