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
R を用いた分析(補講) (2) — 人工データの生成 / Analysis using R ...
Search
Sponsored
·
SiteGround - Reliable hosting with speed, security, and support you can count on.
→
Kenji Saito
PRO
November 30, 2024
Technology
86
0
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
R を用いた分析(補講) (2) — 人工データの生成 / Analysis using R (supplementary) (2) - Generating artificial data
早稲田大学大学院経営管理研究科「企業データ分析」2024 冬のオンデマンド教材 第12回で使用したスライドです。
Kenji Saito
PRO
November 30, 2024
More Decks by Kenji Saito
See All by Kenji Saito
文化的ループ (推論, エージェント) と思考プロセスの検証可能性 / Cultural Loops (Inference, Agents) and the Verifiability of Thought Processes
ks91
PRO
0
24
アカデミーキャンプ2026 夏 「ヤツらを究めろ!ウチらとヤツらの自由研究∼ シーズン2」DAY 3 / Academy Camp 2026 Summer: Master Them! Our Independent Research Project with Them—Season 2 DAY3
ks91
PRO
0
56
アカデミーキャンプ2026 夏 「ヤツらを究めろ!ウチらとヤツらの自由研究∼ シーズン2」DAY 1 / Academy Camp 2026 Summer: Master Them! Our Independent Research Project with Them—Season 2 DAY1
ks91
PRO
0
59
アカデミーキャンプ2026 夏 「ヤツらを究めろ!ウチらとヤツらの自由研究∼ シーズン2」DAY 2 / Academy Camp 2026 Summer: Master Them! Our Independent Research Project with Them—Season 2 DAY2
ks91
PRO
0
89
責任2.0 ∼ AI が主体となる世界で ∼ / Responsibility 2.0: In a World Where AI Takes Responsibilities
ks91
PRO
0
77
発表と総括 / Presentations and Summary
ks91
PRO
0
230
インシデントレスポンス演習II / Incident Response Exercise II
ks91
PRO
0
110
脱金融のフューチャー・デザイン / Future Design Beyond Finance
ks91
PRO
0
200
戦略と安全保障 / Strategy and Security
ks91
PRO
0
120
Other Decks in Technology
See All in Technology
関東Kaggler会発表資料
takoi
1
260
研究開発部の紹介 / Sansan R&D Profile
sansan33
PRO
4
24k
AIコーディングの次。コードレビューと理解負荷を解消して組織の開発生産性を高める
moongift
PRO
2
2.7k
Sets in Go
ramalho
1
1.1k
20260817_生成AIの動向と中学校・高等学校での活用を考える_v1.00_公開用
doradora09
PRO
0
110
モノリス Rails でも日中に rails db:migrate を走らせたい! / Daytime rails db:migrate on Monolithic Rails!
euglena1215
4
650
AI・HPC開発を支えるGPU環境の新しい選択肢 液冷GPUシステム「AquSys」の取り組み
gpuunite_official
0
130
【AG-UI × A2UI × MCP Apps】Generative UIをやさしく解説する
nrinetcom
PRO
1
150
Adding Right-to-Left support to your web application with CSS logical properties — Lessons from Redmine
vividtone
0
150
AIのためのEthernet技術動向 (SerDes)
markunet
1
240
案件に一番詳しいAIを Amazon Bedrock AgentCore で作る ― 知見が知見を生むチームへ / Compounding Knowledge with AgentCore
yusukeshimizu
1
160
Kiro入門|仕様駆動開発で変わるAI時代の開発スタイル
cmkudo
0
230
Featured
See All Featured
How to Think Like a Performance Engineer
csswizardry
28
2.7k
The Success of Rails: Ensuring Growth for the Next 100 Years
eileencodes
47
8.3k
Unsuck your backbone
ammeep
672
58k
Leading Effective Engineering Teams in the AI Era
addyosmani
9
2.4k
Navigating the Design Leadership Dip - Product Design Week Design Leaders+ Conference 2024
apolaine
2
400
How STYLIGHT went responsive
nonsquared
100
6.2k
Darren the Foodie - Storyboard
khoart
PRO
3
3.7k
Highjacked: Video Game Concept Design
rkendrick25
PRO
1
440
How To Speak Unicorn (iThemes Webinar)
marktimemedia
1
540
Self-Hosted WebAssembly Runtime for Runtime-Neutral Checkpoint/Restore in Edge–Cloud Continuum
chikuwait
0
720
Breaking role norms: Why Content Design is so much more than writing copy - Taylor Woolridge
uxyall
0
370
Tell your own story through comics
letsgokoyo
1
1k
Transcript
Boxes and whiskers — generated by Stable Diffusion XL v1.0
2024 12 R ( ) (2) — (WBS) 2024 12 R ( ) (2) — — 2024-11 – p.1/14
https://speakerdeck.com/ks91/collections/corporate-data-analysis-2024-winter 2024 12 R ( ) (2) — — 2024-11
– p.2/14
( 20 ) 1 • 2 R • 3 •
4 • 5 • 6 ( ) • 7 (1) • 8 (2) • 9 R ( ) (1) — Welch • 10 R ( ) (2) — χ2 • 11 R ( ) (1) — • 12 R ( ) (2) — • 13 GPT-4 14 GPT-4 15 ( ) LaTeX Overleaf 8 (12/16 ) / (2 ) OK / 2024 12 R ( ) (2) — — 2024-11 – p.3/14
N(µ, σ2) ρ 2 ( : ˆ y = a
+ b1 x1 + b2 x2 + e ) 2024 12 R ( ) (2) — — 2024-11 – p.4/14
N(µ, σ2) “rnorm()” set.seed(173205) # # N(50, 10^2) 100 x
<- rnorm(n=100, mean=50, sd=10) # x # hist(x) mean(x) sd(x) 2024 12 R ( ) (2) — — 2024-11 – p.5/14
Histogram of x x Frequency 10 20 30 40 50
60 70 80 0 5 10 15 20 25 30 35 mean(x) : 50.06994 sd(x) : 10.30096 2024 12 R ( ) (2) — — 2024-11 – p.6/14
ρ 2 (1/2) MASS “mvrnorm()” “ .R” # r =
0.9 # t = 3.7 # r = 15.2 # t = 7.5 # = -0.5 # <- matrix(c( r^2, * t * r, * r * t, t^2 ), nrow=2) 2024 12 R ( ) (2) — — 2024-11 – p.7/14
“mvrnorm()” = S xx S xy S xy S yy
= S xx rS x S y rS x S y S yy ( r = S xy S x S y ) 2 x, y x, y, z, . . . 2024 12 R ( ) (2) — — 2024-11 – p.8/14
ρ 2 (2/2) MASS “mvrnorm()” “ .R” # set.seed(28284) <-
mvrnorm(n=100, mu=c( r, t), Sigma= ) <- pmin(pmax( [,1], 13.0), 19.9) <- pmin(pmax( [,2], 0.0), 20.0) “ [,1]” “ [,2]” plot 2024 12 R ( ) (2) — — 2024-11 – p.9/14
0 5 10 15 20 13 14 15 16 17
18 ㈇ࡢ┦㛵ࡢ 㐌ᙜࡓࡾࡢㄢእ㐠ື㛫 100m㉮ࡢࢱ࣒ (⛊) r : -0.5932345 ( ) -0.5884094 ( ) 2024 12 R ( ) (2) — — 2024-11 – p.10/14
(1/2) “ .R” n <- 50 # a <- 49.4
# ( (158cm ) ) # r_father <- 0.306 mean_father <- 168.78 sd_father <- 3.2 # r_mother <- 0.37 mean_mother <- 155.32 sd_mother <- 2.45 2024 12 R ( ) (2) — — 2024-11 – p.11/14
(2/2) “ .R” <- round(rnorm(n=n, mean=mean_father, sd=sd_father), digits=1) <- round(rnorm(n=n,
mean=mean_mother, sd=sd_mother), digits=1) e <- rnorm(n=n, mean=0, sd=2.8) # <- round(a + r_father * + r_mother * + e, digits=1) 1 “round()” plot 2024 12 R ( ) (2) — — 2024-11 – p.12/14
ፉ㌟㛗 160 165 170 175 152 156 160 164 160
165 170 175 ∗㌟㛗 152 156 160 164 150 154 158 150 154 158 ẕ㌟㛗 : 34.2484 : 0.3545 : 0.4137 : 0.2831 2024 12 R ( ) (2) — — 2024-11 – p.13/14
2024 12 R ( ) (2) — — 2024-11 –
p.14/14