#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")
library(readr)
#讀取資料
x <- read.csv("Transformed Data Set - Sheet1.csv", stringsAsFactors = TRUE)
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
##
##
##
#查看資料結構
#重新命名欄位名稱
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$gender, x$color)
t
##
## Cool Neutral Warm
## F 17 3 13
## M 20 4 9
#百分比次數分配表
p.t <- prop.table(t)
p.t
##
## Cool Neutral Warm
## F 0.25757576 0.04545455 0.19696970
## M 0.30303030 0.06060606 0.13636364
p.t*100
##
## Cool Neutral Warm
## F 25.757576 4.545455 19.696970
## M 30.303030 6.060606 13.636364
p.t <- round(p.t*100, 2) #先乘一百再四捨五入至小數第二位
#畫分組長條圖
barplot(p.t)
barplot(p.t, beside = TRUE)
#加上圖例與上色
label <- rownames(p.t)
label
## [1] "F" "M"
barplot(p.t,
beside = TRUE,
legend.text = label,
col = c(25:26))
t<- table(x$gender, x$drink)
t
##
## 7UP/Sprite Coca Cola/Pepsi Fanta Other
## F 8 17 6 2
## M 5 15 8 5
#百分比次數分配表
p.t <- prop.table(t)
p.t
##
## 7UP/Sprite Coca Cola/Pepsi Fanta Other
## F 0.12121212 0.25757576 0.09090909 0.03030303
## M 0.07575758 0.22727273 0.12121212 0.07575758
p.t*100
##
## 7UP/Sprite Coca Cola/Pepsi Fanta Other
## F 12.121212 25.757576 9.090909 3.030303
## M 7.575758 22.727273 12.121212 7.575758
p.t <- round(p.t*100, 2) #先乘一百再四捨五入至小數第二位
#畫分組長條圖
barplot(p.t)
barplot(p.t, beside = TRUE)
#加上圖例與上色
label <- rownames(p.t)
label
## [1] "F" "M"
barplot(p.t,
beside = TRUE,
legend.text = label,
col = c(25:26))
#畫圓餅圖
#畫圓餅圖並加上資料標籤
colnames(x)<-c("color", "music", "beverage", "drink", "gender")
x
## color music beverage drink gender
## 1 Cool Rock Vodka 7UP/Sprite F
## 2 Neutral Hip hop Vodka Coca Cola/Pepsi F
## 3 Warm Rock Wine Coca Cola/Pepsi F
## 4 Warm Folk/Traditional Whiskey Fanta F
## 5 Cool Rock Vodka Coca Cola/Pepsi F
## 6 Warm Jazz/Blues Doesn't drink Fanta F
## 7 Cool Pop Beer Coca Cola/Pepsi F
## 8 Warm Pop Whiskey Fanta F
## 9 Warm Rock Other 7UP/Sprite F
## 10 Neutral Pop Wine Coca Cola/Pepsi F
## 11 Cool Pop Other 7UP/Sprite F
## 12 Warm Pop Other 7UP/Sprite F
## 13 Warm Pop Wine 7UP/Sprite F
## 14 Warm Electronic Wine Coca Cola/Pepsi F
## 15 Cool Rock Beer Coca Cola/Pepsi F
## 16 Warm Jazz/Blues Wine Coca Cola/Pepsi F
## 17 Cool Pop Wine 7UP/Sprite F
## 18 Cool Rock Other Coca Cola/Pepsi F
## 19 Cool Rock Other Coca Cola/Pepsi F
## 20 Cool Pop Doesn't drink 7UP/Sprite F
## 21 Cool Pop Beer Fanta F
## 22 Warm Jazz/Blues Whiskey Fanta F
## 23 Cool Rock Vodka Coca Cola/Pepsi F
## 24 Warm Pop Other Coca Cola/Pepsi F
## 25 Cool Folk/Traditional Whiskey 7UP/Sprite F
## 26 Warm R&B and soul Whiskey Coca Cola/Pepsi F
## 27 Cool Pop Beer Other F
## 28 Cool Pop Doesn't drink Other F
## 29 Cool Pop Doesn't drink Coca Cola/Pepsi F
## 30 Cool Electronic Doesn't drink Fanta F
## 31 Warm Rock Other Coca Cola/Pepsi F
## 32 Neutral Rock Beer Coca Cola/Pepsi F
## 33 Cool R&B and soul Beer Coca Cola/Pepsi F
## 34 Warm R&B and soul Wine Other M
## 35 Neutral Hip hop Beer 7UP/Sprite M
## 36 Warm Electronic Other Coca Cola/Pepsi M
## 37 Neutral Rock Doesn't drink Coca Cola/Pepsi M
## 38 Cool Pop Other Fanta M
## 39 Cool Pop Whiskey Fanta M
## 40 Warm Rock Vodka 7UP/Sprite M
## 41 Cool Rock Vodka Coca Cola/Pepsi M
## 42 Neutral Pop Doesn't drink 7UP/Sprite M
## 43 Warm R&B and soul Doesn't drink Coca Cola/Pepsi M
## 44 Cool Rock Wine 7UP/Sprite M
## 45 Cool Folk/Traditional Beer Other M
## 46 Cool Hip hop Beer Coca Cola/Pepsi M
## 47 Cool Hip hop Wine Coca Cola/Pepsi M
## 48 Cool R&B and soul Whiskey 7UP/Sprite M
## 49 Cool Rock Doesn't drink Other M
## 50 Warm Hip hop Beer Coca Cola/Pepsi M
## 51 Cool R&B and soul Doesn't drink Coca Cola/Pepsi M
## 52 Cool Rock Doesn't drink Coca Cola/Pepsi M
## 53 Cool Hip hop Doesn't drink Other M
## 54 Warm Rock Beer Fanta M
## 55 Cool Electronic Doesn't drink Fanta M
## 56 Cool Electronic Other Fanta M
## 57 Warm Folk/Traditional Other Fanta M
## 58 Warm Electronic Vodka Fanta M
## 59 Warm Jazz/Blues Vodka Coca Cola/Pepsi M
## 60 Cool Pop Whiskey Other M
## 61 Cool Electronic Whiskey Coca Cola/Pepsi M
## 62 Cool Rock Vodka Coca Cola/Pepsi M
## 63 Cool Hip hop Beer Coca Cola/Pepsi M
## 64 Neutral Hip hop Doesn't drink Fanta M
## 65 Cool Rock Wine Coca Cola/Pepsi M
## 66 Cool Electronic Beer Coca Cola/Pepsi M
#問題，男女對顏色的喜好的差異？
#次數分配表
#table=算次數的函數 table(列,欄)
t <- table(x$gender, x$drink)
t
##
## 7UP/Sprite Coca Cola/Pepsi Fanta Other
## F 8 17 6 2
## M 5 15 8 5
#百分比次數分配表
p.t <- prop.table(t)
p.t
##
## 7UP/Sprite Coca Cola/Pepsi Fanta Other
## F 0.12121212 0.25757576 0.09090909 0.03030303
## M 0.07575758 0.22727273 0.12121212 0.07575758
p.t*100
##
## 7UP/Sprite Coca Cola/Pepsi Fanta Other
## F 12.121212 25.757576 9.090909 3.030303
## M 7.575758 22.727273 12.121212 7.575758
#round=取小數(,2)四捨五入取道第二位
p.t <-round(p.t*100,2)
p.t
##
## 7UP/Sprite Coca Cola/Pepsi Fanta Other
## F 12.12 25.76 9.09 3.03
## M 7.58 22.73 12.12 7.58
#畫分組長條圖
barplot(p.t)
barplot(p.t,beside = TRUE)
#加上圖例與上色
label <- rownames(p.t)
label
## [1] "F" "M"
barplot(p.t,
beside = TRUE,
legend.text = label,
col = c(15:14))
