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
Python Floripa - Teste A/B
Search
Larissa Lautert
January 26, 2017
Technology
0
97
Python Floripa - Teste A/B
Avaliação de testes A/B com Pandas.
Larissa Lautert
January 26, 2017
Tweet
Share
More Decks by Larissa Lautert
See All by Larissa Lautert
Aplicações de Inteligência Artificial no Direito
llautert
0
66
Avaliação de testes A/B com Pandas
llautert
0
77
Data Science e visualização de dados na Chaordic
llautert
1
140
Other Decks in Technology
See All in Technology
We Built for Predictability; The Workloads Didn’t Care
stahnma
0
130
コスト削減から「セキュリティと利便性」を担うプラットフォームへ
sansantech
PRO
3
1.4k
2026年、サーバーレスの現在地 -「制約と戦う技術」から「当たり前の実行基盤」へ- /serverless2026
slsops
2
220
ファインディの横断SREがTakumi byGMOと取り組む、セキュリティと開発スピードの両立
rvirus0817
1
1.2k
All About Sansan – for New Global Engineers
sansan33
PRO
1
1.3k
M&A 後の統合をどう進めるか ─ ナレッジワーク × Poetics が実践した組織とシステムの融合
kworkdev
PRO
1
420
モダンUIでフルサーバーレスなAIエージェントをAmplifyとCDKでサクッとデプロイしよう
minorun365
4
170
Bedrock PolicyでAmazon Bedrock Guardrails利用を強制してみた
yuu551
0
180
ブロックテーマ、WordPress でウェブサイトをつくるということ / 2026.02.07 Gifu WordPress Meetup
torounit
0
160
10Xにおける品質保証活動の全体像と改善 #no_more_wait_for_test
nihonbuson
PRO
2
220
SREじゃなかった僕らがenablingを通じて「SRE実践者」になるまでのリアル / SRE Kaigi 2026
aeonpeople
6
2.2k
プロポーザルに込める段取り八分
shoheimitani
1
180
Featured
See All Featured
How to train your dragon (web standard)
notwaldorf
97
6.5k
Money Talks: Using Revenue to Get Sh*t Done
nikkihalliwell
0
150
Facilitating Awesome Meetings
lara
57
6.7k
Large-scale JavaScript Application Architecture
addyosmani
515
110k
Applied NLP in the Age of Generative AI
inesmontani
PRO
4
2k
Fireside Chat
paigeccino
41
3.8k
Evolution of real-time – Irina Nazarova, EuRuKo, 2024
irinanazarova
9
1.2k
Lightning talk: Run Django tests with GitHub Actions
sabderemane
0
110
Save Time (by Creating Custom Rails Generators)
garrettdimon
PRO
32
2.1k
DBのスキルで生き残る技術 - AI時代におけるテーブル設計の勘所
soudai
PRO
62
49k
Rebuilding a faster, lazier Slack
samanthasiow
85
9.4k
Agile Actions for Facilitating Distributed Teams - ADO2019
mkilby
0
110
Transcript
Python Floripa Teste A/B com Jupyter + Python + pandas
JANEIRO.2017 - Daniel Severo
1. What is A/B testing? 2. Why do we need
statistics? 3. The stack: Jupyter + Python + pandas 4. Examples Agenda
WHAT IS A/B TESTING?
Time What is A/B testing?→ The basic concept. Visitor Webpage
Time What is A/B testing?→ The basic concept. • Examples:
◦ Green Button vs. Red Button; ◦ Landing page A vs. Landing Page B; ◦ Algorithm A vs. Algorithm B; ◦ Product A vs. Product B;
Time What is A/B testing?→ The basic concept. Visitor Webpage
A Webpage B 50% 50%
Time What is A/B testing?→ The basic concept. A B
METRICS
What is A/B testing?→ The basic concept.
What is A/B testing?→ The basic concept.
WHY DO WE NEED STATISTICS?
WHY DO WE NEED STATISTICS? • Is the difference between
metrics significant or due to random fluctuations? • When should we stop the test?
WHY DO WE NEED STATISTICS?
WHY DO WE NEED STATISTICS?
WHY DO WE NEED STATISTICS?
WHY DO WE NEED STATISTICS?
THE STACK: JUPYTER+PYTHON+PANDAS
users buy orders products oid, pid, uid, timestamp, ... pid,
name, specs, ... uid, email, gender, ... THE STACK: JUPYTER+PYTHON+PANDAS
users buy orders products oid, pid, uid, timestamp, ... pid,
name, specs, ... uid, email, gender, ... THE STACK: JUPYTER+PYTHON+PANDAS
users buy orders products joint table oid, pid, uid, timestamp,
... pid, name, specs, ... uid, email, gender, ... oid, uid, pid, email, gender, timestamp, name, specs, ... THE STACK: JUPYTER+PYTHON+PANDAS
users buy orders products joint table oid, pid, uid, timestamp,
... pid, name, specs, ... uid, email, gender, ... reports THE STACK: JUPYTER+PYTHON+PANDAS
TURBO ANALYTICS → CÁLCULO DA ELASTICIDADE DE PRODUTOS price quantity
'2016-01-01 15:48:50' '2016-01-02 21:26:12' '2016-01-02 21:41:17' '2016-01-02 23:56:05' '2016-01-03 03:48:57' '2016-01-03 10:42:11' '2016-01-03 12:25:38' '2016-01-03 12:30:55' '2016-01-03 13:23:13' '2016-01-04 16:09:16' . . . 1 2 1 3 2 6 7 10 8 7 R$ 79.99 R$ 79.99 R$ 79.99 R$ 79.99 R$ 69.99 R$ 69.99 R$ 69.99 R$ 69.99 R$ 69.99 R$ 69.99
TURBO ANALYTICS → CÁLCULO DA ELASTICIDADE DE PRODUTOS price quantity
'2016-01-01 15:48:50' '2016-01-02 21:26:12' '2016-01-02 21:41:17' '2016-01-02 23:56:05' '2016-01-03 03:48:57' '2016-01-03 10:42:11' '2016-01-03 12:25:38' '2016-01-03 12:30:55' '2016-01-03 13:23:13' '2016-01-04 16:09:16' . . . 1 2 1 3 2 6 7 10 8 7 R$ 79.99 R$ 79.99 R$ 79.99 R$ 79.99 R$ 69.99 R$ 69.99 R$ 69.99 R$ 69.99 R$ 69.99 R$ 69.99 price quantity '2016-01-01' '2016-01-02' '2016-01-03’ . . . 1 6 40 . . . R$ 79.99 R$ 79.99 R$ 69.99 . . .
TURBO ANALYTICS → CÁLCULO DA ELASTICIDADE DE PRODUTOS price quantity
'2016-01-01 15:48:50' '2016-01-02 21:26:12' '2016-01-02 21:41:17' '2016-01-02 23:56:05' '2016-01-03 03:48:57' '2016-01-03 10:42:11' '2016-01-03 12:25:38' '2016-01-03 12:30:55' '2016-01-03 13:23:13' '2016-01-04 16:09:16' . . . 1 2 1 3 2 6 7 10 8 7 R$ 79.99 R$ 79.99 R$ 79.99 R$ 79.99 R$ 69.99 R$ 69.99 R$ 69.99 R$ 69.99 R$ 69.99 R$ 69.99 price quantity '2016-01-01' '2016-01-02' '2016-01-03’ . . . 1 6 40 . . . R$ 79.99 R$ 79.99 R$ 69.99 . . .
TURBO ANALYTICS → CÁLCULO DA ELASTICIDADE DE PRODUTOS price quantity
'2016-01-01 15:48:50' '2016-01-02 21:26:12' '2016-01-02 21:41:17' '2016-01-02 23:56:05' '2016-01-03 03:48:57' '2016-01-03 10:42:11' '2016-01-03 12:25:38' '2016-01-03 12:30:55' '2016-01-03 13:23:13' '2016-01-04 16:09:16' . . . 1 2 1 3 2 6 7 10 8 7 R$ 79.99 R$ 79.99 R$ 79.99 R$ 69.99 R$ 69.99 R$ 69.99 R$ 69.99 R$ 69.99 R$ 69.99 R$ 69.99 price quantity '2016-01-01' '2016-01-02' '2016-01-03’ . . . 1 6 40 . . . R$ 79.99 R$ 76.66 R$ 69.99 . . .
None
None
+ + ++ + + OBRIGADO!