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
阪神タイガース優勝のひみつ - Pythonでシュッと調べた件 / SABRmetrics ...
Search
Shinichi Nakagawa
October 01, 2023
Research
1
1.3k
阪神タイガース優勝のひみつ - Pythonでシュッと調べた件 / SABRmetrics for Python
PyLadies Tokyo 9周年LT
Shinichi Nakagawa
October 01, 2023
Tweet
Share
More Decks by Shinichi Nakagawa
See All by Shinichi Nakagawa
実践Dash - 手を抜きながら本気で作るデータApplicationの基本と応用 / Dash for Python and Baseball
shinyorke
2
1.1k
Terraform, GitHub Actions, Cloud Buildでデータ基盤をProvisioningする / Data Platform provisioning for Google Cloud and Terraform
shinyorke
2
2.8k
Cloud RunとCloud PubSubでサーバレスなデータ基盤2024 with Terraform / Cloud Run and PubSub with Terraform
shinyorke
10
2.8k
自らを強いエンジニアにするための3つの習慣 / I need to be myself, I can't be no one else
shinyorke
77
58k
Pythonとクラウドと野球の推し活. / Baseball Data Platform for Python and Google Cloud
shinyorke
2
2.7k
月額コーヒー3.34杯分のコストでオオタニサンの活躍を見守るデータ基盤のはなし / Pyhack Con
shinyorke
2
460
俺のDXを実現するためのサーバレスなデータ基盤開発と運用 / Serverless Data Platform and Baseball
shinyorke
5
11k
機械学習エンジニアが目指すキャリアパスとその実話 / My Journey to Become a ML Engineer
shinyorke
9
16k
一人でも小さく始められるGoogle Cloudで実現するほぼサーバレスなデータ基盤 / Serverless Dataplatform for Google Cloud
shinyorke
0
530
Other Decks in Research
See All in Research
Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve
eumesy
PRO
7
1.2k
Human-Informed Machine Learning Models and Interactions
hiromu1996
2
470
ニュースメディアにおける事前学習済みモデルの可能性と課題 / IBIS2024
upura
3
510
クロスセクター効果研究会 熊本都市交通リノベーション~「車1割削減、渋滞半減、公共交通2倍」の実現へ~
trafficbrain
0
250
ECCV2024読み会: Minimalist Vision with Freeform Pixels
hsmtta
1
140
論文読み会 SNLP2024 Instruction-tuned Language Models are Better Knowledge Learners. In: ACL 2024
s_mizuki_nlp
1
350
テキストマイニングことはじめー基本的な考え方からメディアディスコース研究への応用まで
langstat
1
120
Geospecific View Generation - Geometry-Context Aware High-resolution Ground View Inference from Satellite Views
satai
1
100
機械学習による言語パフォーマンスの評価
langstat
6
720
Weekly AI Agents News! 7月号 論文のアーカイブ
masatoto
1
220
Physics of Language Models: Part 3.1, Knowledge Storage and Extraction
sosk
1
950
Leveraging LLMs for Unsupervised Dense Retriever Ranking (SIGIR 2024)
kampersanda
2
190
Featured
See All Featured
The Success of Rails: Ensuring Growth for the Next 100 Years
eileencodes
44
6.8k
Mobile First: as difficult as doing things right
swwweet
222
8.9k
Optimizing for Happiness
mojombo
376
70k
I Don’t Have Time: Getting Over the Fear to Launch Your Podcast
jcasabona
28
2k
jQuery: Nuts, Bolts and Bling
dougneiner
61
7.5k
Six Lessons from altMBA
skipperchong
27
3.5k
The Pragmatic Product Professional
lauravandoore
31
6.3k
Understanding Cognitive Biases in Performance Measurement
bluesmoon
26
1.4k
StorybookのUI Testing Handbookを読んだ
zakiyama
27
5.3k
Building Applications with DynamoDB
mza
90
6.1k
Measuring & Analyzing Core Web Vitals
bluesmoon
4
120
Typedesign – Prime Four
hannesfritz
40
2.4k
Transcript
ʮ͓ࢄาʯΛͨ݁͠Ռ ࡕਆλΠΨʔε͕༏উͨ݅͠. ࡕਆλΠΨʔε༏উΛه೦ͯ͠PythonͰσʔλੳͨ͠Β ࢥΘͣʮͦΒɺͦ͏Αʯͱೲಘͯ͠͠·ͬͨ. Shinichi Nakagawa(@shinyorke) 2023/10/01 PyLadies Tokyo
9पه೦ύʔςΟʔ
Who am I ? ʢ͓લ୭Α?ʣ • Shinichi Nakagawa@shinyorke • େख֎ࢿܥITίϯαϧاۀϚωʔδϟʔ
• ຊۀͰSREతͳࣄΛ͍ͯ͠·͢. • ΤϯδχΞతʹԿͰͰ͖Δਓ. • దͳ⽁ωλ͔ΒLTΛ͢ΔΤϯδχΞͷਓ. • ஶ໊ͳٕज़ϒϩάʮLean Baseballʯͷਓ. • ຖ10,000าఔͷʮ͓ࢄาʯ͕՝. ※͓ࢄาͷূڌ݅
PyLadies Tokyo 9प͓ΊͰͱ͏͍͟͝·͢🎉 ʢ9ܦͬͯ͠·ͬͨͷ͔…ͳ͍ͭʣ
͏Ұ͓ͭΊͰ͍ͨࣄ͕ ͋Γ·͢ΑͶʁ🐯
ࡕਆλΠΨʔε, ηɾϦʔά༏উ͓ΊͰͱ͏͍͟͝·͢🎉 2005Ҏདྷ18ͿΓͷ༏উ🐯
334 ʲ౾ࣝʳ͓ೃછΈͷͪ͜Βͷࣈ18લͷ༏উ͕ΩοΧέͰര.
18ͿΓʹʮ༏উʯΛ Ϳ͔ͪ·ͨ͠ࡕਆλΠΨʔε ݁ہԿ͕ྑ͔ͬͨͷ͔🤔
ࡕਆλΠΨʔε༏উͷཧ༝ʢͲΕਖ਼ղʣ 1. ໊কʮԬాজʯ௨শʮͲΜͰΜʯͷಜ෮ؼ. →18લͷ༏উԬాಜ&ʮͦΒɺͦ͏Αʯͱೲಘߦ໊͘ࡃ. 2. ࣆJAPAN͕༏উͨ͠WBCʹελϝϯڃͷબखΛग़͍ͯ͠ͳ͔ͬͨ. ࡕਆ͔Βதͱ౬ઙͷΈ͔ͭ͞΄Ͳग़ճଟ͘ͳ͍. 3.
ʮ͓ࢄาେࣄʯʮ໎ͬͨΒา͚ʯͱ͍͏ҙࣝͷժੜ͑. ۩ମతʹʮ࢛ٿʢϑΥΞϘʔϧʣʯΛࢁબΜͩ.
ʮʰ͓ࢄาେࣄʱʰ໎ͬͨΒา͚ʱͱ͍͏ҙࣝͷժੜ͑ʯ ͜Ε͕ࡕਆλΠΨʔε༏উͷͬͱΒ͍͠ཧ༝ͩͱσʔλݴͬͯ·ͨ͠.
ࡕਆͷεʔύʔυϥΠͳʮ͓ࢄาʯͷྲّྀ • όολʔࡾৼ͍͍͔ͯ͠Βʮۃʹ͓ࢄาʯ͠ͳ͍͞. • ϐονϟʔࡾৼΛऔΒͳ͍͍͔ͯ͘ΒʮࢄาΛࢭΊΖʯ. ͳ͓ٿʹ͓͚Δʮ͓ࢄาʯʮ࢛ٿʢϑΥΞϘʔϧʣʯͷࣄ. ※εϥϯάతʹʮࢄาʯͱಡΜͰ͍·͢ʢʮา͔ͤΔʯͱ͔ݴ͏ʣ.
ࡕਆλΠΨʔε͓ࢄาͷྲّྀᶃ όολʔࡾৼͯ͠ ͍͍͔Β ʮۃʹ͓ࢄาʯ ͠ͳ͍͞. ࡾৼ͍͍͔ͯ͠Βา͚. 11
ʮދଧઢʯվΊʮ”า”ଧઢʯ • 2023ͷࡕਆλΠΨʔε, νʔϜͱ࢛ͯ͠ٿͷ͕ΊͪΌͪ͘Όଟ͍. • ηɾϦʔάͲ͜Ζ͔ϓϩٿશମͰΠέͯΔग़ྥͷߴ͞. • Ұํ, ࢛ٿΛऔΓʹߦ͘ͷʹͭͨΊࡾৼ૿͍͑ͯΔ.
11ଧ੮ʹ1ճ͓ࢄา͢ΔࡕਆλΠΨʔε͞Μ༏लʢϦʔά1Ґʣ. ࠷ԼҐதυϥΰϯζΑΓ1.5ഒͷϖʔεͰʮ͓ࢄาʯΛྔ࢈.
Ұํ, ࡾઢͷ۶ࢦͰ4.5ଧ੮ʹҰࡾৼ͍ͯ͠ΔʢϦʔάϫʔετʣ. ܭࢉ্ελϝϯͷશଧऀ͕ࢼ߹தʹ1ճࡾৼ͍ͯ͠Δࣄʹ.
2ͭͷάϥϑΛ͚ͬͭͯ͘ࢄา͢ΔॱʹฒͨϞϊ. ࡕਆૉΒ͍͠, Ұํʮྩͷถ૽ಈʯͷத͞Μ(ry
ࡕਆλΠΨʔε͓ࢄาͷྲّྀᶄ ϐονϟʔࡾৼΛ औΒͳ͍͍͔ͯ͘Β ʮࢄาΛࢭΊΖʯ. ૬खͷଧऀΛྥʹग़͔͢Βͣ. 16
૬खͷʮࢄาʯΛઈରʹࢭΊΔखਞ. • 2023ͷࡕਆλΠΨʔε, νʔϜͱͯ͠खͷ༩࢛ٿ͕গͳ͍. • ༩࢛ٿ͕গͳ͍ = ૬खʹ࢛ٿʢࢄาʣΛ͍ͤͯ͞ͳ͍. • ͦͦ͜͜ࡾৼऔΕ͓ͯΓ,
ࡕਆखਞͷ༏ल͕͞Θ͔Δ.
༏लͳࡕਆखਞ, ૬खʹ࢛ٿʢࢄาʣΛ࠷༩͍͑ͯͳ͍ʢϦʔά1Ґʣ. ૬खଧऀʹແବͳ࢛ٿΛग़͞ͳ͍ͱ͍͏పఈͨ͠ํ.
༏लͳࡕਆखਞ, ૬ख͔Βͦͦ͜͜ࡾৼΛୣ͏༷ʢϦʔά4Ґʣ. ࢛ٿ͕ݮΔͱ͍͏͜ͱࡾৼΛऔΕͳ͍ࣄʹܨ͕Δ͕ҧͬͯͨ…ੌ͍🐯
2ͭͷάϥϑΛ͚ͬͭͯ͘ࢄาͤ͞ͳ͍ॱʹฒͨϞϊ. ࡕਆ͕ૉΒ͍͕͠, DeNAͷʮࡾৼͨ͘͞ΜऔΔʯʮ࢛ٿগͳ͍ʯ͔͍͍ͬ͜.
???ʮPythonͷ͕ແ͍͡Όͳ͍͔ʁ͍͍͔͛Μʹ͠Ζʯ
ࠓͷσʔλ શ෦PythonͰ ͍͍ײ͡ʹ🐍 େͨ͠ίʔυ͡Όͳ͍ͷͰͥͻਅࣅͯͬͯ͠Έͯ. https://gist.github.com/Shinichi-Nakagawa/3ca01932532ba41ceaef94bd722107b9 NPBͷWebαΠτΛ εΫϨΠϐϯά Google ColabͰ γϡοͱՄࢹԽ.
ʲ݁ʳࡕਆλΠΨʔεʮ͓ࢄาʯͷྲّྀ • όολʔࡾৼ͍͍͔ͯ͠Βʮۃʹ͓ࢄาʯ͠ͳ͍͞. • ϐονϟʔࡾৼΛऔΒͳ͍͍͔ͯ͘ΒʮࢄาΛࢭΊΖʯ. • ͳ͓, ࢛ٿ͕૿͑Δͱࡾৼ૿͑ΔʢʣͳͷͰ(ry ͓Θ͔Γ͍͚ͨͩͨͩΖ͏͔?
͝ਗ਼ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠🐯