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
SQLベースのMLパイプライン / ML pipeline based on SQL
Search
hatunina
November 05, 2019
Programming
2.4k
3
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
SQLベースのMLパイプライン / ML pipeline based on SQL
LT
https://connehito.connpass.com/event/149552/
hatunina
November 05, 2019
Other Decks in Programming
See All in Programming
セキュリティの専門家じゃなくてもできる。「セキュリティ意識」をアップデートして サプライチェーン攻撃への耐性を高めよう。
tk3fftk
5
650
PHPで使える日時の表現と、その知り方 #frontend_phpcon_do
o0h
PRO
0
190
軽量Java基盤の設計 DIコンテナに頼らない、長期保守と1秒起動の実現 JJUG CCC 2026 Spring
macha64
0
460
AI 時代のソフトウェア設計の学び方
masuda220
PRO
29
12k
net-httpのHTTP/2対応について
naruse
0
450
AI駆動開発で崩れていくコードベースを立て直す
kyoko_nr_nr
1
440
Copilot CLI の継戦能力を高める コンテキスト管理
nozomutu
1
1.2k
LLM Plugin for Node-REDの利用方法と開発について
404background
0
160
決定論的オーケストレーションの設計と実装 / Design and Implementation of Deterministic Orchestration
nrslib
3
1.1k
CSC307 Lecture 17
javiergs
PRO
0
320
Lemonade + Foundry Toolkit でお手軽アプリ開発
seosoft
1
310
生成AI時代にこそ効くGo | Why Go Works in the Age of Generative AI
mom0tomo
8
3.1k
Featured
See All Featured
Facilitating Awesome Meetings
lara
57
6.9k
Raft: Consensus for Rubyists
vanstee
141
7.5k
Avoiding the “Bad Training, Faster” Trap in the Age of AI
tmiket
0
170
Code Review Best Practice
trishagee
74
20k
Put a Button on it: Removing Barriers to Going Fast.
kastner
60
4.3k
Mobile First: as difficult as doing things right
swwweet
225
10k
The Straight Up "How To Draw Better" Workshop
denniskardys
239
140k
Documentation Writing (for coders)
carmenintech
77
5.4k
YesSQL, Process and Tooling at Scale
rocio
174
15k
WCS-LA-2024
lcolladotor
0
620
Design and Strategy: How to Deal with People Who Don’t "Get" Design
morganepeng
133
19k
Crafting Experiences
bethany
1
170
Transcript
SQLϕʔεͷ MLύΠϓϥΠϯ @hatunina 2019/11/05 Connehito Marche vol.6
ࣗݾհ • hatunina • ࣄۀձࣾͰσʔλΤϯδχΞ • σʔλج൫, ML, WEB։ൃ •
Kaggle Expert • vtuber͕͖
ΞυϗοΫͳMLҊ݅ʹ ͲͷΑ͏ͳύΠϓϥΠϯͰ ରԠ͍ͯ͠·͔͢ʂ
ΞυϗοΫʁ • ͱΓ͋͑ͣͲΕ͘Β͍ਫ਼͕ग़Δͷ͔ݟ͍ͨ • Өڹྗͷڧ͍ಛ͕Γ͍ͨ • Ϧετग़͠ ͳͲͳͲ
ඞཁͳॲཧ • σʔληοτ࡞ • ಛྔΤϯδχΞϦϯά • ϋΠύʔύϥϝʔλௐ • ֶश/ਪ ͜͜Λ42-Ͱʂ
ύΠϓϥΠϯ֓ཁ USBJODTW UFTUDTW TDPSFDTW SVOQZ 42-ϨϙδτϦ DSFBUF@EBUBTFU NPEFM TDPSFDTW NPEFM
είΞϦϯάαʔό ࣮ߦ༻αʔό ग़ྗ ࣮ߦ ςʔϒϧ࡞ είΞϦϯά தؒςʔϒϧ είΞϦϯάςʔϒϧ Ҋ݅͝ͱʹ42-Λม͑Δ͚ͩ
create_dataset !"" common !"" annkenn01 !"" annkenn02 #"" annkenn03 common
!"" create_feats $ !"" feats_01.sql $ !"" feats_02.sql $ !"" feats_03.sql $ !"" feats_04.sql $ #"" feats_05.sql #"" create_score !"" create_table.sql #"" insert_score.sql annkenn01 !"" create_train_list $ !"" create_train_table.sql $ !"" insert_pos.sql $ #"" insert_neg.sql !"" create_feats -> ../common/create_feats !"" create_score_list $ !"" create_score_table.sql $ #"" insert_score.sql !"" create_score -> ../common/create_score #"" select_dataset #"" select.sql σΟϨΫτϦߏ • commonʹ֤Ҋ݅ͷڞ௨SQLʢಛྔΤϯδχΞϦϯάɺείΞϦϯά݁ՌςʔϒϧͳͲʣ • Ҋ݅͝ͱʹσΟϨΫτϦ/SQLΛ࡞ • ڞ௨SQLcommonΛࢀর • ਖ਼ྫ/ෛྫͷநग़ • ༻͢Δಛͷநग़ͳͲ
SQLΛϕʔεʹ͢ΔϝϦσϝ • ͍ճ͍͢͠͠ • ڞ༗/Ҿܧ͕͍͢͠ • ςʔϒϧఆٛॻ͕ͦͷ··༻ಛͷઆ໌ॻʹͳΔ • DB͕ࠞΜͰ͍Δͱσʔλ࡞͕ϘτϧωοΫʹͳΓ͕ͪ
Ҏ্Ͱ͢ʂ ࣭͋Ε࠙ձͰ ͓͕͚͍ͩ͘͞ʂʂ