Upgrade to Pro — share decks privately, control downloads, hide ads and more …

坂本勇人さん改め山田哲人さんの成績予測をやってみた / Baseball Play Study 2020 Winter

2c0947c6a28e7f771ebd9859ecf54e5c?s=47 Shinichi Nakagawa
December 17, 2020
Research
0
2.3k

坂本勇人さん改め山田哲人さんの成績予測をやってみた / Baseball Play Study 2020 Winter

Baseball Play Study 2020冬 LT資料

https://bpstudy.connpass.com/event/197652/

2c0947c6a28e7f771ebd9859ecf54e5c?s=128

Shinichi Nakagawa

December 17, 2020
Tweet

More Decks by Shinichi Nakagawa

See All by Shinichi Nakagawa
BigQueryとPythonではじめるプロ野球選手の成績予測（もしくは成績占い） / Baseball Player Performance Prediction using BigQuery and Python
2c0947c6a28e7f771ebd9859ecf54e5c?s=48 shinyorke
0
76
突然ですが「生涯成績」占ってもいいですか? - プロ野球選手成績予測2022
2c0947c6a28e7f771ebd9859ecf54e5c?s=48 shinyorke
0
57
実践Streamlit & Flask - AIプロジェクトをいい感じにする技術 / Service development with Streamlit and Flask
2c0947c6a28e7f771ebd9859ecf54e5c?s=48 shinyorke
3
8.3k
Flask + Google App Engine（GAE）でWeb APIをデプロイするまで
- Github Actionsを添えて / Flask + App Engine + Github Actions
2c0947c6a28e7f771ebd9859ecf54e5c?s=48 shinyorke
0
610
実践Streamlit & Flask - AIプロジェクトをいい感じにする技術（予告編） / Web application development starting with Streamlit
2c0947c6a28e7f771ebd9859ecf54e5c?s=48 shinyorke
0
210
人間じゃなくて野球のためのスクレイピングとしてのrequests-html / HTML Parsing for Baseball Player
2c0947c6a28e7f771ebd9859ecf54e5c?s=48 shinyorke
1
180
StreamlitとFlaskではじめる, 爆速プロトタイピングとTV砲対策 #jx_tech_talk / AI web application development starting with Streamlit and Flask
2c0947c6a28e7f771ebd9859ecf54e5c?s=48 shinyorke
0
3.1k
坂本勇人選手はいつ通算3,000安打を達成するか? AIに聞いてみました / Hayato Sakamoto Performance Prediction Using Feature Engineering with Machine Learning and Python
2c0947c6a28e7f771ebd9859ecf54e5c?s=48 shinyorke
1
600
特徴量エンジニアリングと野球選手の成績予測 - 野球ではじめる機械学習 / Baseball Player Performance Prediction Using Feature Engineering with Machine Learning and Python
2c0947c6a28e7f771ebd9859ecf54e5c?s=48 shinyorke
6
7.8k

Other Decks in Research

See All in Research
行政のオープンネスとフェアネスーデジタル庁でDXに取り組む 『民間採用人材』の視点からー
20dd6ed6aa3cf68c2eabe56360512808?s=48 halsk
0
520
JGS594 Lecture 18
B546a9b97d993392e4b22b74b99b91fe?s=48 javiergs
PRO
0
340
まだ生態学に本格導入されていない統計的因果推論手法の紹介：傾向スコア、回帰分断デザイン、操作変数法を中心に
1e65da5f023dc428b8becced82bad823?s=48 takehikoihayashi
2
860
マイクロサービス型システムの監視におけるダッシュボードUI設計に起因する状況認識への影響 / Impact of Dashboard UI Design on Cognitive Accuracy and Load in Monitoring Microservice-based Systems
17cbb387ced351dafe3b30e39b3ed9f7?s=48 mokomoka
1
380
Recent Findings on Density-Ratio Approaches in Machine Learning
Bb6c3fc8c577710c72d03aeb4fa56bf6?s=48 masakat0
0
230
ABCIで回そう爆速深層学習 (基礎編)
E30ae1fd7ecce7aed0032ea0f87f6520?s=48 yoshipon
11
5.4k
Stack-chanで始めるROS音声対話ロボット
E30ae1fd7ecce7aed0032ea0f87f6520?s=48 yoshipon
1
170
2022 東工大 情報通信系 研究室紹介 (大岡山) / Research@ICT, Tokyo Tech (Ookayama Campus) 2022
Add17db4cd1316ad55e989efad1d067e?s=48 icttitech
0
2.8k
論文紹介：User-friendly introduction to PAC-Bayes
C612ab39597a17ba5948cae54d13f99f?s=48 mkimura
0
180
Winnti is Coming - Evolution after Prosecution@HITCON2021
D876ee2ffb76d7590f8b0005d66b7b21?s=48 aragorntseng
0
910
MioGatto による数式グラウンディング データセットの構築 / nlp2022
874fb6168eaee95c155b850a934de418?s=48 wtsnjp
0
120
研究紹介2022年度版
Beeb4cfb45c3fa586526aa131ea67683?s=48 sh01k
0
330

Featured

See All Featured
Ruby is Unlike a Banana
6804f1775cb4babfcc3851298566fbce?s=48 tanoku
91
9.2k
For a Future-Friendly Web
F68cb25ae3e5c2106997454b13b7737d?s=48 brad_frost
164
7.4k
Why You Should Never Use an ORM
88bc30284c6a424b63a92aad27d0ba36?s=48 jnunemaker
PRO
47
5.6k
JavaScript: Past, Present, and Future - NDC Porto 2020
3ab1249be442027903e1180025340b3f?s=48 reverentgeek
37
3.2k
Build your cross-platform service in a week with App Engine
5f83ef806155b403c3393160ce51f955?s=48 jlugia
219
17k
CoffeeScript is Beautiful & I Never Want to Write Plain JavaScript Again
5b9fe87ec1faa67a4599782930f45ec9?s=48 sstephenson
151
12k
Build The Right Thing And Hit Your Dates
016edace78ffe826f2348d1e0c504afd?s=48 maggiecrowley
19
1.2k
The Most Common Mistakes in Cover Letters
1ce0eb06fd6a9e9566a0cb310cfee635?s=48 jrick
PRO
4
24k
A Modern Web Designer's Workflow
8081b26e05bb4354f7d65ffc34cbbd67?s=48 chriscoyier
689
180k
Fashionably flexible responsive web design (full day workshop)
433acaea1012b25d97ae66da9b998dad?s=48 malarkey
396
62k
Designing with Data
F57e2136eb9895eb95ff5dc8a1c02677?s=48 zakiwarfel
91
3.9k
In The Pink: A Labor of Love
E837d2996f52008ace055a08fbfff992?s=48 frogandcode
130
21k

Transcript

  1. ࡔຊ༐ਓ͸͍ͭ௨ࢉ3,000ຊ҆ଧΛ ୡ੒͢Δ͔AIʹฉ͍ͯΈ·ͨ͠ Baseball Play Study 2020ౙ - γʔζϯৼΓฦΓεϖγϟϧ 2020/12/17 Shinichi

    Nakagawa(@shinyorke)

  2. ϫΠʮઌ೔ಉ͡࿩ΛଞॴͰͨ͠Α͏ͳʯ

  3. ͋ͬʢ࡯͠ʣ ೔༵೔ʹʮSports Analyst Meetup #9ʯͰLTͪ͠Όͬͯ·ͨ͠ https://speakerdeck.com/shinyorke/hayato-sakamoto-performance-prediction-using-feature-engineering-with-machine-learning-and-python

  4. ʲ݁࿦ʳࡔຊ༐ਓબखͷ༧ଌ੒੷ 39ࡀͷγʔζϯ, ͖ͬͱΈΜͳʹॕ෱͞ΕΔͰ͠ΐ͏

  5. ʲ݁࿦ʳࡔຊ͞Μ3,000҆ଧ͸39ࡀ 
 ※2028೥γʔζϯ, ͋͘·ͰݟࠐΈͰ͢

  6. ΊͰͨ͠ΊͰͨ͠ ͝ਗ਼ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠

  7. ͍΍͍΍, ͜ΕͰऴΘΕΜͩΖʢ਒͑ʣ

  8. ͪΌΜͱωλ, ༻ҙͯ͠·͢

  9. ॕɾࢁా఩ਓ༷ϠΫϧτ࢒ཹ ௕ظܖ໿ظؒͷ੒੷Λ 
 AIʹ፻଄ͤ͞ฉ͍ͯΈ·ͨ͠ Baseball Play Study 2020ౙ - γʔζϯৼΓฦΓεϖγϟϧ

    2020/12/17 Shinichi Nakagawa(@shinyorke)

  10. ຊ೔ͷςʔϚ • ϠΫϧτ͍΍೔ຊϓϩ໺ٿͷਓؒࠃๅͱݴͬͯ΋աݴͰ͸ͳ͍ 
 ࢁా఩ਓબख͕ҰମͲΕ΄Ͳͷ੒੷Λࠓޙ࢒͢ͷ͔઎͏ • ͿͬͪΌ͚ܖ໿ֹۚ෼ͷ׆༂͢Δͷ͔?͖ʹͳΔ • ΍͖͏AI͍ͥͬͯ͢͝Θ͔ͬͯ͘ΕͨΒخ͍͠ʢ͜ͳΈʣ

  11. Who am I ?ʢ͓લ୭Αʣ • Shinichi Nakagawaʢத઒ ৳Ұʣ • େ఍ͷSNSͰʮshinyorkeʢ͠ΜΑʔ͘ʣʯͱ໊৐͍ͬͯ·͢

    • JX Press Corporation Senior Engineer 
 ʢJX௨৴ࣾ γχΞɾΤϯδχΞʣ • Baseball Engineer, Data Scientist 
 ʢ໺ੜͷ໺ٿΤϯδχΞɾσʔλαΠΤϯςΟετʣ • ࣗশʮBaseball Play StudyͷϨδΣϯυʯ, ݩɾϓϩͷ໺ٿΤϯδχΞ • ࠷ۙ, 12ٿஂതѪओٛऀʹͳΓ·ͨ͠ʢ͕஍ݩ๺ւಓͳͷͰ೔ϋϜ͖ʹͳΔʣ.

  12. ඵͰৼΓฦΔ2020೥ͷϓϩ໺ٿ • όϯςϦϯυʔϜφΰϠ, ര஀ • ౦ژυʔϜબख, Ҡ੶ʢ༧ఆʣ • 26 -

    4ʢ࡯͠ʣ • ࢁా఩ਓબख, 7೥૯ֹ40ԯԁʢਪఆʣͰϠΫϧτ࢒ཹ

  13. ࢁా఩ਓ͞Μͷ7೥40ԯԁͱ͔͍͏ܖ໿ • ೥เ5ԯԁʢʴΠϯηϯςΟϒʣ×7೥, Β͍͠. • ϑΝϯ͸ΈΜͳخ͍͠Ͱ͠ΐ͏, ϫΠ΋خ͍͠Ͱ͢. • ΋͏ҰਓͷϫΠʮ40ԯԁͬͯݩ͕औΕΔΜ΍Ζ͔ʯ

  14. …ͱ͍͏༁Ͱ, ໺ٿAI͞Μʹฉ͍ͯΈ·ͨ͠.

  15. ࠓճ࢖͏΍͖͏ͷਓ޻஌ೳ PyCon JP 2020Ͱ΍ͬͨ΍ʔͭΛͦͷ··࢖͍·ͨ͠ʢ#spoana ͱಉ͡Ͱ͢ʣ. https://shinyorke.hatenablog.com/entry/baseball-and-ml-with-python

  16. ͻͱ·ͣ݁ՌΛ͓ݟͤ͠·͢.

  17. ࢁా఩ਓ༷ͷࠓޙ - ҆ଧɾຊྥଧɾଧ఺ 150҆ଧͪΐ͍, 17ʙ19ຊྥଧΛՔ͗ͭͭ, 70ଧ఺Ҏ্Ք͙੒੷

  18. ࢁా఩ਓ༷ͷࠓޙ - ଧ཰ 32, 33ࡀ͋ͨΓͰಥવ޼ଧʹ໨֮Ίͯͯ໘ന͍݁Ռʹ

  19. ࢁా఩ਓ༷ͷࠓޙΛ·ͱΊΔͱ ͜ΕͰͣͬͱηΧϯυ΍ͬͯ͘ΕΔͳΒ͗͢͢͝Ͱ͸ ͑?τϦϓϧεϦʔ??͏ʔʔΜ ೥౓ ೥ྸ ଧ਺ ҆ଧ ຊྥଧ ଧ఺ ଧ཰

                                                    

  20. ࢁా఩ਓ༷ͷ௨ࢉ੒੷ʢ༧ଌʣ ͜ΕͰηΧϯυͬͯڧ͗͢͸͠·ͤΜ͔ʢ਒͑ʣ ظؒ ଧ਺ ҆ଧ ຊྥଧ ଧ఺ ଧ཰ ೥·Ͱ ˞ݱ࣮

          ˞༧ଌ੒੷      ௨ࢉʢ༧ଌʣ     

  21. ࢁా఩ਓ༷ͷ௨ࢉ੒੷ʢ༧ଌʣ ͜ΕͰηΧϯυͬͯڧ͗͢͸͠·ͤΜ͔ʢ਒͑ʣ ظؒ ଧ਺ ҆ଧ ຊྥଧ ଧ఺ ଧ཰ ೥·Ͱ ˞ݱ࣮

          ˞༧ଌ੒੷      ௨ࢉʢ༧ଌʣ      334ͪΌ͏Μ͔ʔ͍

  22. ࢁా఩ਓ༷2027ʢ34ʣ͕࢒͢ه࿥ • ௨ࢉຊྥଧɾଧ఺ɾଧ཰Ͱߴ໦कಓࢯΛ௒͑Δ • ௨ࢉ2,236҆ଧͰ໊ٿձೖΓ·ͬͨͳ͠ • ໊࣮ͱ΋ʹϓϩ໺ٿ্࢙࠷ڧͷηΧϯυʹͳΔՄೳੑ

  23. ͱ͸͍͑Ͱ͢Α • 7೥ܖ໿தͷτϦϓϧεϦʔʢ3ׂ30ຊྥଧ30౪ྥʣ͸ଟ෼ແཧ • ਓ޻஌ೳ͸500ଧ੮Ҏ্Ք͙༧ଌΛ͍ͯ͠Δ͚Ͳ, 
 ఩ਓ༷Ҋ֎ނোͱ͔཭୤͋Δͷ͕ͪΐͬͱ৺഑ • ηΧϯυ͸कඋෛ୲͕͔ͳΓ͋ΔϙδγϣϯͳͷͰ 


    ଧྗΛ׆͔ͨ͢Ίͷίϯόʔτ΋͋Δ͔΋͠Εͳ͍

  24. ݁࿦ • ೔ຊҰͷηΧϯυʹͳΓͦ͏ͳͷͰ7೥40ԯͷܖ໿͸ଟ෼ଥ౰ • ͱ͸͍͑େࣄʹ࢖ͬͯཉ͍͠, ͋ΔҙຯਓؒࠃๅͰ͢͠ • ͘Ε͙Ε΋਎ମʹؾΛ͚ͭͯؤுͬͯ΄͍͠ʂ

  25. ήʔϜηοτ⚾ ͝ਗ਼ௌ͋Γ͕ͱ͏͍͟͝·ͨ͠. Shinichi Nakagawa(Twitter/Facebook/etc… @shinyorke)