$30 off During Our Annual Pro Sale. View Details »
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
RBC202003_Day2_Period5
Search
sakaue
March 20, 2020
Education
0
42
RBC202003_Day2_Period5
sakaue
March 20, 2020
Tweet
Share
More Decks by sakaue
See All by sakaue
SappoRo.R #11「R によるThe Multilingual Eye-tracking COrpus (MECO) の探索的データ分析」
sakaue
0
100
RBC202003_Day2_Period6
sakaue
0
99
RBC202003_Day2_Period7
sakaue
0
96
Rbootcamp202003_Day2_p8.pdf
sakaue
0
87
RBC202003_Day1_Period1
sakaue
1
78
RBC202003_Day1_Period2
sakaue
0
75
RBC202003_Day1_Period3
sakaue
0
100
RBC202003_Day1_Period4
sakaue
0
60
Other Decks in Education
See All in Education
Evaluation Methods - Lecture 6 - Human-Computer Interaction (1023841ANR)
signer
PRO
0
1.2k
2025年度伊藤正彦ゼミ紹介
imash
0
140
生成AIとの付き合い方 / Generative AI and us
kaityo256
PRO
11
6.6k
KBS新事業創造体験2025_科目説明会
yasuchikawakayama
0
150
The knowledge panel is your new homepage
bradwetherall
0
220
HyRead2526
cbtlibrary
0
160
相互コミュニケーションの難しさ
masakiokuda
0
320
the difficulty into words
ukky86
0
320
1125
cbtlibrary
0
140
いわゆる「ふつう」のキャリアを歩んだ人の割合(若者向け)
hysmrk
0
260
アジャイルの知見から新卒研修作り、そして組織作り
pokotyamu
0
120
✅ レポート採点基準 / How Your Reports Are Assessed
yasslab
PRO
0
150
Featured
See All Featured
Intergalactic Javascript Robots from Outer Space
tanoku
273
27k
I Don’t Have Time: Getting Over the Fear to Launch Your Podcast
jcasabona
34
2.6k
The Language of Interfaces
destraynor
162
25k
The Straight Up "How To Draw Better" Workshop
denniskardys
239
140k
JavaScript: Past, Present, and Future - NDC Porto 2020
reverentgeek
52
5.8k
Designing for humans not robots
tammielis
254
26k
GraphQLとの向き合い方2022年版
quramy
50
14k
Understanding Cognitive Biases in Performance Measurement
bluesmoon
32
2.7k
Code Reviewing Like a Champion
maltzj
527
40k
Java REST API Framework Comparison - PWX 2021
mraible
34
9k
Building an army of robots
kneath
306
46k
Producing Creativity
orderedlist
PRO
348
40k
Transcript
2020-03-20 ୈ5ݶ σʔλͷཁ bootcamp
Agenda 1. σʔλͷཁͷඞཁੑ (5) 2. ϕΫτϧΛͬͨཁ (20) 3. ߦྻΛͬͨཁ (20)
4. ԋशʹ͙࣍ԋश (45)
Agenda 1. σʔλͷཁͷඞཁੑ (5) 2. ϕΫτϧΛͬͨཁ (20) 3. ߦྻΛͬͨཁ (20)
4. ԋशʹ͙࣍ԋश (45)
1. σʔλͷཁͷඞཁੑ • σʔλΛूΊ͚ͨͩͰԿஅͰ͖ͳ͍ • σʔλΛཁʢཁʣΛ͢Δ͜ͱͰɼશମ͕ Ͳ͏ͳ͍ͬͯͯɼΒ͖͕ͭͲ͏ͳ͍ͬͯ Δ͔͕ѲͰ͖Δ • தؒςετͰऔͬͨ55ྑ͍ʁɼѱ͍ʁ
• ظςετͷฏۉ͕80ͷ߹ɼશମతʹྑ͍Ͱ͖͙͍͋ʁ • ฏۉɾΒ͖ͭʢSDʣʹΑΔʢ͠ɼςετͷ༰ ʹΑΔʢ͠ɼԿΛ͔֬Ί͍͔ͨʹΑΔʣʣ
Agenda 1. σʔλͷཁͷඞཁੑ (5) 2. ϕΫτϧΛͬͨཁ (20) 3. ߦྻΛͬͨཁ (20)
4. ԋशʹ͙࣍ԋश (45)
Agenda 1. σʔλͷཁͷඞཁੑ (5) 2. ϕΫτϧΛͬͨཁ (20) 3. ߦྻΛͬͨཁ (20)
4. ԋशʹ͙࣍ԋश (45)
• sum() ؔ • x <- c(1, 2, 3, 4,
5) • sum(x) • sum(x[2 : 4]) • ϕΫτϧͷ2൪͔Β4൪ͷཁૉͷ૯ • y <- c(1:1000) • sum(y) • sum(y[27:89]) 2. ϕΫτϧΛͬͨཁ
• mean() ؔ: ฏۉΛٻΊΔ • ฏۉ: σʔλͷ૯ΛσʔλͷݸͰׂͬͨ • mean(x); mean(y)
• median() ؔ: தԝΛٻΊΔ • தԝ: খ͍͞ॱʹฒͨ࣌ʹਅΜதͷॱҐʹ͘Δ • median(x); median(y) • ฏۉͷ᠘ • ۃͳ͕ࠞ͟ΔͱӨڹΛड͚ͯ͠·͏ • a <- c(100, 200, 300, 400, 500) • mean(a); median(a) • b <- c(100, 200, 300, 400, 5000) • mean(b); median(b) 2. ϕΫτϧΛͬͨཁ
• max() ؔ: ࠷େΛٻΊΔ • min() ؔ: ࠷খΛٻΊΔ • var()
ؔ: ࢄΛٻΊΔ • sd() ؔ: ඪ४ภࠩΛٻΊΔ • summary() ؔ: ཁ౷ܭྔΛҰʹٻΊΔ • ࠷খ, தԝ, ฏۉ, ࠷େ, Լଆ25%, ্ଆ25% • max(x); max(y) • min(x); min(y) • var(x);var(y) • sd(x); sd(y) • summary(x); summary(y) 2. ϕΫτϧΛͬͨཁ
Agenda 1. σʔλͷཁͷඞཁੑ (5) 2. ϕΫτϧΛͬͨཁ (20) 3. ߦྻΛͬͨཁ (20)
4. ԋशʹ͙࣍ԋश (45)
Agenda 1. σʔλͷཁͷඞཁੑ (5) 2. ϕΫτϧΛͬͨཁ (20) 3. ߦྻΛͬͨཁ (20)
4. ԋशʹ͙࣍ԋश (45)
3. ߦྻΛͬͨཁ • ѻ͍ํϕΫτϧͷཁͱಉ͡ • matrix.4 <- matrix(c(1, 2, 3,
4, 5, 6, 7, 8, 9), nrow = 3, ncol = 3, byrow = TRUE) • matrix.4 ͰதΛ֬ೝ • sum(matrix.4) #ߦྻʹ͋Δͷ૯ • mean(matrix.4) #ߦྻશମͷฏۉ • sum(matrix.4[1,]) #ߦྻ1ߦͷ૯ • mean(matrix.4[,2:3]) #ߦྻ2-3ྻͷฏۉ
3. ߦྻΛͬͨཁ • ͪΐͬͱɾཁૉΛେ͖ͯ͘͠Έ·͠ΐ͏ • matrix.5 <- matrix(c(1:5000), nrow =
100, ncol = 50, byrow = TRUE) • matrix.5 ͰதΛ֬ೝ • sum(matrix.5) #ߦྻʹ͋Δͷ૯ • mean(matrix.5) #ߦྻશମͷฏۉ
3. ߦྻΛͬͨཁ • rowSums() ؔ; colSums() ؔ; • ߦ͝ͱྻ͝ͱʹ૯ΛٻΊΔؔ •
rowSums(matrix.4); rowSums(matrix.5) • colSums(matrix.4); colSums(matrix.5) • rowMeans () ؔ; colMeans() ؔ • ߦ͝ͱྻ͝ͱʹฏۉΛٻΊΔؔ • rowMeans(matrix.4); rowMeans(matrix.5) • colMeans(matrix.4); colMeans(matrix.5)
3. ߦྻΛͬͨཁ • apply() ؔ • ߦ͝ͱྻ͝ͱʹ༷ʑͳؔΛద༻ • apply(ߦྻ໊, Ϛʔδϯ,
ద༻͢Δؔʣ • Ϛʔδϯ͕1ͳΒߦ͝ͱɼ2ͳΒྻ͝ͱ • apply(matrix.4, 1, sum) #ߦ͝ͱͷ૯ • rowSums(matrix.4) ͱಉ͡ॲཧ • apply(matrix.4, 2, mean) #ྻ͝ͱͷฏۉ • colMeans(matrix.4) ͱಉ͡ॲཧ
3. ߦྻΛͬͨཁ • apply() ؔͷଓ͖ • apply(matrix.4, 1, max) •
#ߦ͝ͱͷ࠷େ • apply(matrix.4, 2, summary) • #ྻ͝ͱͷཁ౷ܭྔ
Agenda 1. σʔλͷཁͷඞཁੑ (5) 2. ϕΫτϧΛͬͨཁ (20) 3. ߦྻΛͬͨཁ (20)
4. ԋशʹ͙࣍ԋश (45)
Agenda 1. σʔλͷཁͷඞཁੑ (5) 2. ϕΫτϧΛͬͨཁ (20) 3. ߦྻΛͬͨཁ (20)
4. ԋशʹ͙࣍ԋश (45)
4. ԋशʹ͙࣍ԋश 1. 1͔Β50͔Β·Ͱͷ͕ೖͬͨϕΫτ ϧΛ࡞ͯ͠… 1. ૯, ฏۉ, தԝ, ࠷େ,
࠷খ , ࢄ, ඪ४ภࠩΛٻΊΔ 2. ཁ౷ܭྔΛٻΊΔ
4. ԋशʹ͙࣍ԋशʢώϯτʣ 1. Λൃੜͤ͞ΔʹίϩϯΛ͍·͠ΐ͏ 1. ֤ؔΛηϛίϩϯͰͭͳ͍ͰҰؾʹ࣮ߦ 2. summary() ؔΛ͍·͢
2. 1͔Β10000·Ͱͷ͕ೖͬͨߦྻʢ100ߦɾ100ྻʣΛ࡞ͯ͠… 1. 20ߦʮͱʯ70ߦͷ2ߦͷΈͷ֤૯ΛٻΊΔ 2. 31ྻʮ͔Βʯ80ྻ·Ͱͷ50ྻͷ֤ฏۉΛٻΊΔ 3. ߦ͝ͱɾྻ͝ͱͷ૯ΛٻΊΔʢapply ؔΛ༻ʣ 4.
ߦ͝ͱɾྻ͝ͱͷฏۉΛٻΊΔʢapply ؔΛ༻ʣ 5. ߦ͝ͱɾྻ͝ͱͷཁ౷ܭྔΛٻΊΔʢapply ؔΛ༻ʣ 6. psych ύοέʔδΛͬͯཁ౷ܭྔΛٻΊΔ • ҙͷߦɾྻʹରͯ͠ٻΊͯΈΔ 4. ԋशʹ͙࣍ԋश
2. matrix() ؔΛ͍ɼྻͷࢦఆͱ byrow ͷઃఆʹ༻৺ 1. ߦͷෳࢦఆ c() ؔΛ͍·͠ΐ͏ 2.
ྻͷൣғࢦఆίϩϯΛ͍·͠ΐ͏ 3. apply() ؔͱ sum() ؔΛΈ߹Θͤ·͠ΐ͏ 4. apply() ؔͱ mean() ؔΛΈ߹Θͤ·͠ΐ͏ 5. apply() ؔͷߦͱྻͷࢦఆɼ1 ͔ 2 Ͱ͚·͢ 6. ·ͣ install.packages() ͯ͠ library() Ͱ༗ޮԽ 4. ԋशʹ͙࣍ԋशʢώϯτʣ
Enjoy ! twitter: @sakaue e-mail: tsakaue<AT>hiroshima-u.ac.jp