#下載資料：https://www.kaggle.com/hb20007/gender-classification?select=Transformed+Data+Set+-+Sheet1.csv
#檔名為"Transformed Data Set - Sheet1.csv"
#從電腦端上傳(upload)到rstudio cloud
#install.packages("readr")第一次使用需安裝
library(readr)#用library呼叫套件
#讀取資料，命名為"x"
x <- read.csv("Transformed Data Set - Sheet1.csv", stringsAsFactors = TRUE)
x
## Favorite.Color Favorite.Music.Genre Favorite.Beverage Favorite.Soft.Drink
## 1 Cool Rock Vodka 7UP/Sprite
## 2 Neutral Hip hop Vodka Coca Cola/Pepsi
## 3 Warm Rock Wine Coca Cola/Pepsi
## 4 Warm Folk/Traditional Whiskey Fanta
## 5 Cool Rock Vodka Coca Cola/Pepsi
## 6 Warm Jazz/Blues Doesn't drink Fanta
## 7 Cool Pop Beer Coca Cola/Pepsi
## 8 Warm Pop Whiskey Fanta
## 9 Warm Rock Other 7UP/Sprite
## 10 Neutral Pop Wine Coca Cola/Pepsi
## 11 Cool Pop Other 7UP/Sprite
## 12 Warm Pop Other 7UP/Sprite
## 13 Warm Pop Wine 7UP/Sprite
## 14 Warm Electronic Wine Coca Cola/Pepsi
## 15 Cool Rock Beer Coca Cola/Pepsi
## 16 Warm Jazz/Blues Wine Coca Cola/Pepsi
## 17 Cool Pop Wine 7UP/Sprite
## 18 Cool Rock Other Coca Cola/Pepsi
## 19 Cool Rock Other Coca Cola/Pepsi
## 20 Cool Pop Doesn't drink 7UP/Sprite
## 21 Cool Pop Beer Fanta
## 22 Warm Jazz/Blues Whiskey Fanta
## 23 Cool Rock Vodka Coca Cola/Pepsi
## 24 Warm Pop Other Coca Cola/Pepsi
## 25 Cool Folk/Traditional Whiskey 7UP/Sprite
## 26 Warm R&B and soul Whiskey Coca Cola/Pepsi
## 27 Cool Pop Beer Other
## 28 Cool Pop Doesn't drink Other
## 29 Cool Pop Doesn't drink Coca Cola/Pepsi
## 30 Cool Electronic Doesn't drink Fanta
## 31 Warm Rock Other Coca Cola/Pepsi
## 32 Neutral Rock Beer Coca Cola/Pepsi
## 33 Cool R&B and soul Beer Coca Cola/Pepsi
## 34 Warm R&B and soul Wine Other
## 35 Neutral Hip hop Beer 7UP/Sprite
## 36 Warm Electronic Other Coca Cola/Pepsi
## 37 Neutral Rock Doesn't drink Coca Cola/Pepsi
## 38 Cool Pop Other Fanta
## 39 Cool Pop Whiskey Fanta
## 40 Warm Rock Vodka 7UP/Sprite
## 41 Cool Rock Vodka Coca Cola/Pepsi
## 42 Neutral Pop Doesn't drink 7UP/Sprite
## 43 Warm R&B and soul Doesn't drink Coca Cola/Pepsi
## 44 Cool Rock Wine 7UP/Sprite
## 45 Cool Folk/Traditional Beer Other
## 46 Cool Hip hop Beer Coca Cola/Pepsi
## 47 Cool Hip hop Wine Coca Cola/Pepsi
## 48 Cool R&B and soul Whiskey 7UP/Sprite
## 49 Cool Rock Doesn't drink Other
## 50 Warm Hip hop Beer Coca Cola/Pepsi
## 51 Cool R&B and soul Doesn't drink Coca Cola/Pepsi
## 52 Cool Rock Doesn't drink Coca Cola/Pepsi
## 53 Cool Hip hop Doesn't drink Other
## 54 Warm Rock Beer Fanta
## 55 Cool Electronic Doesn't drink Fanta
## 56 Cool Electronic Other Fanta
## 57 Warm Folk/Traditional Other Fanta
## 58 Warm Electronic Vodka Fanta
## 59 Warm Jazz/Blues Vodka Coca Cola/Pepsi
## 60 Cool Pop Whiskey Other
## 61 Cool Electronic Whiskey Coca Cola/Pepsi
## 62 Cool Rock Vodka Coca Cola/Pepsi
## 63 Cool Hip hop Beer Coca Cola/Pepsi
## 64 Neutral Hip hop Doesn't drink Fanta
## 65 Cool Rock Wine Coca Cola/Pepsi
## 66 Cool Electronic Beer Coca Cola/Pepsi
## Gender
## 1 F
## 2 F
## 3 F
## 4 F
## 5 F
## 6 F
## 7 F
## 8 F
## 9 F
## 10 F
## 11 F
## 12 F
## 13 F
## 14 F
## 15 F
## 16 F
## 17 F
## 18 F
## 19 F
## 20 F
## 21 F
## 22 F
## 23 F
## 24 F
## 25 F
## 26 F
## 27 F
## 28 F
## 29 F
## 30 F
## 31 F
## 32 F
## 33 F
## 34 M
## 35 M
## 36 M
## 37 M
## 38 M
## 39 M
## 40 M
## 41 M
## 42 M
## 43 M
## 44 M
## 45 M
## 46 M
## 47 M
## 48 M
## 49 M
## 50 M
## 51 M
## 52 M
## 53 M
## 54 M
## 55 M
## 56 M
## 57 M
## 58 M
## 59 M
## 60 M
## 61 M
## 62 M
## 63 M
## 64 M
## 65 M
## 66 M
#查看資料結構
summary(x)
## Favorite.Color Favorite.Music.Genre Favorite.Beverage
## Cool :37 Electronic : 8 Beer :13
## Neutral: 7 Folk/Traditional: 4 Doesn't drink:14
## Warm :22 Hip hop : 8 Other :11
## Jazz/Blues : 4 Vodka : 9
## Pop :17 Whiskey : 9
## R&B and soul : 6 Wine :10
## Rock :19
## Favorite.Soft.Drink Gender
## 7UP/Sprite :13 F:33
## Coca Cola/Pepsi:32 M:33
## Fanta :14
## Other : 7
##
##
##
#重新命名欄位名稱
colnames(x) #檢視欄位名稱
## [1] "Favorite.Color" "Favorite.Music.Genre" "Favorite.Beverage"
## [4] "Favorite.Soft.Drink" "Gender"
colnames(x) <- c("color", "music", "beverage", "drink", "gender")
#問題：男女對顏色的喜好的差異？
#次數分配表
t <- table(x$gender,x$music)
t
##
## Electronic Folk/Traditional Hip hop Jazz/Blues Pop R&B and soul Rock
## F 2 2 1 3 13 2 10
## M 6 2 7 1 4 4 9
#百分比次數分配表
p.t <- prop.table(t)
p.t
##
## Electronic Folk/Traditional Hip hop Jazz/Blues Pop R&B and soul
## F 0.03030303 0.03030303 0.01515152 0.04545455 0.19696970 0.03030303
## M 0.09090909 0.03030303 0.10606061 0.01515152 0.06060606 0.06060606
##
## Rock
## F 0.15151515
## M 0.13636364
#將次數變成百分比(乘以100)
p.t <- p.t*100
p.t
##
## Electronic Folk/Traditional Hip hop Jazz/Blues Pop R&B and soul
## F 3.030303 3.030303 1.515152 4.545455 19.696970 3.030303
## M 9.090909 3.030303 10.606061 1.515152 6.060606 6.060606
##
## Rock
## F 15.151515
## M 13.636364
#四捨五入至小數2位
p.t <- round(p.t,2)
p.t
##
## Electronic Folk/Traditional Hip hop Jazz/Blues Pop R&B and soul Rock
## F 3.03 3.03 1.52 4.55 19.70 3.03 15.15
## M 9.09 3.03 10.61 1.52 6.06 6.06 13.64
#畫分組長條圖
barplot(p.t)
barplot(p.t, beside =TRUE)
#加上圖例與上色
rownames(p.t)
## [1] "F" "M"
label <- rownames(p.t)
label
## [1] "F" "M"
barplot(p.t,main = "Love music", sub = "by PEICHANG"
,beside =TRUE,
legend.text =label,
col =c(69,87))
