#上課程式碼：
#資料介紹：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")
###類別資料分析###
#問題：男女生各有多少人？
table(x$gender)#算次數
##
## F M
## 33 33
prop.table(table(x$gender))#算百分比
##
## F M
## 0.5 0.5
#問題：最喜歡的color、music、beverage、 drink、gender？
table(x$color)
##
## Cool Neutral Warm
## 37 7 22
prop.table(table(x$color))
##
## Cool Neutral Warm
## 0.5606061 0.1060606 0.3333333
table(x$music)
##
## Electronic Folk/Traditional Hip hop Jazz/Blues
## 8 4 8 4
## Pop R&B and soul Rock
## 17 6 19
prop.table(table(x$music))
##
## Electronic Folk/Traditional Hip hop Jazz/Blues
## 0.12121212 0.06060606 0.12121212 0.06060606
## Pop R&B and soul Rock
## 0.25757576 0.09090909 0.28787879
table(x$beverage)
##
## Beer Doesn't drink Other Vodka Whiskey
## 13 14 11 9 9
## Wine
## 10
prop.table(table(x$beverage))
##
## Beer Doesn't drink Other Vodka Whiskey
## 0.1969697 0.2121212 0.1666667 0.1363636 0.1363636
## Wine
## 0.1515152
table(x$drink)
##
## 7UP/Sprite Coca Cola/Pepsi Fanta Other
## 13 32 14 7
prop.table(table(x$drink))
##
## 7UP/Sprite Coca Cola/Pepsi Fanta Other
## 0.1969697 0.4848485 0.2121212 0.1060606
#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,2)
p.t
##
## Cool Neutral Warm
## F 0.4594595 0.4285714 0.5909091
## M 0.5405405 0.5714286 0.4090909
#將次數變成百分比(乘以100)
p.t <- p.t*100
p.t
##
## Cool Neutral Warm
## F 45.94595 42.85714 59.09091
## M 54.05405 57.14286 40.90909
#四捨五入至小數2位
p.t <- round(p.t,2)
p.t
##
## Cool Neutral Warm
## F 45.95 42.86 59.09
## M 54.05 57.14 40.91
#畫分組長條圖
barplot(p.t)
barplot(p.t, beside = T )
#加上圖例與上色
rownames(p.t)
## [1] "F" "M"
label <- rownames(p.t)
label#文字向量
## [1] "F" "M"
barplot(p.t,
beside =T ,
legend.text = label ,
col = c(30,225),)
#畫圓餅圖
p.t
##
## Cool Neutral Warm
## F 45.95 42.86 59.09
## M 54.05 57.14 40.91
f <- p.t[1,] # 女性資料
m <- p.t[2,] # 男性資料
f
## Cool Neutral Warm
## 45.95 42.86 59.09
m
## Cool Neutral Warm
## 54.05 57.14 40.91
# par()是圖形控制函數，mfrow = c(1,2)表示建立一個1x2的空間，用來呈現後續的圖
par(mfrow =c(1,2))
pie(f, main = "女生")
pie(m, main = "男生")
#dev.off() #離開par()
#畫圓餅圖並加上資料標籤
pie_category <- colnames(p.t)
f_label <- paste(pie_category, f,"%", sep = "")
f_label
## [1] "Cool45.95%" "Neutral42.86%" "Warm59.09%"
m_label <- paste(pie_category, m,"%", sep = "")
m_label
## [1] "Cool54.05%" "Neutral57.14%" "Warm40.91%"
par(mfrow = c(1,2))# c(1,2)，表示建立一個1x2的空間，用來呈現後續的圖
pie(f, labels = f_label , main = "Female")
pie(m, labels = m_label, main = "Male" )
dev.off() #離開par()
## null device
## 1
#問題：男女對飲料的喜好的差異？
#次數分配表
d <- table(x$gender,x$drink)
d
##
## 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.d <- prop.table(d,2)
p.d
##
## 7UP/Sprite Coca Cola/Pepsi Fanta Other
## F 0.6153846 0.5312500 0.4285714 0.2857143
## M 0.3846154 0.4687500 0.5714286 0.7142857
#將次數變成百分比(乘以100)
p.d <- p.d*100
p.d
##
## 7UP/Sprite Coca Cola/Pepsi Fanta Other
## F 61.53846 53.12500 42.85714 28.57143
## M 38.46154 46.87500 57.14286 71.42857
#四捨五入至小數2位
p.d <- round(p.d,2)
p.d
##
## 7UP/Sprite Coca Cola/Pepsi Fanta Other
## F 61.54 53.12 42.86 28.57
## M 38.46 46.88 57.14 71.43
#畫分組長條圖
barplot(p.d)
barplot(p.d, beside = T )
#加上圖例與上色
rownames(p.d)
## [1] "F" "M"
label.1 <- rownames(p.d)
label.1
## [1] "F" "M"
barplot(p.d,
beside =T ,
legend.text = label.1 ,
col = c(20,23))
#畫圓餅圖
p.d
##
## 7UP/Sprite Coca Cola/Pepsi Fanta Other
## F 61.54 53.12 42.86 28.57
## M 38.46 46.88 57.14 71.43
f.d <- p.d[1,] # 女性資料
m.d <- p.d[2,] # 男性資料
f.d
## 7UP/Sprite Coca Cola/Pepsi Fanta Other
## 61.54 53.12 42.86 28.57
m.d
## 7UP/Sprite Coca Cola/Pepsi Fanta Other
## 38.46 46.88 57.14 71.43
# par()是圖形控制函數，mfrow = c(1,2)表示建立一個1x2的空間，用來呈現後續的圖
par(mfrow =c(1,2))
pie(f.d, main = "女生")
## Warning in title(main = main, ...): conversion failure on '女生' in
## 'mbcsToSbcs': dot substituted for <e5>
## Warning in title(main = main, ...): conversion failure on '女生' in
## 'mbcsToSbcs': dot substituted for <a5>
## Warning in title(main = main, ...): conversion failure on '女生' in
## 'mbcsToSbcs': dot substituted for <b3>
## Warning in title(main = main, ...): conversion failure on '女生' in
## 'mbcsToSbcs': dot substituted for <e7>
## Warning in title(main = main, ...): conversion failure on '女生' in
## 'mbcsToSbcs': dot substituted for <94>
## Warning in title(main = main, ...): conversion failure on '女生' in
## 'mbcsToSbcs': dot substituted for <9f>
pie(m.d, main = "男生")
## Warning in title(main = main, ...): conversion failure on '男生' in
## 'mbcsToSbcs': dot substituted for <e7>
## Warning in title(main = main, ...): conversion failure on '男生' in
## 'mbcsToSbcs': dot substituted for <94>
## Warning in title(main = main, ...): conversion failure on '男生' in
## 'mbcsToSbcs': dot substituted for <b7>
## Warning in title(main = main, ...): conversion failure on '男生' in
## 'mbcsToSbcs': dot substituted for <e7>
## Warning in title(main = main, ...): conversion failure on '男生' in
## 'mbcsToSbcs': dot substituted for <94>
## Warning in title(main = main, ...): conversion failure on '男生' in
## 'mbcsToSbcs': dot substituted for <9f>
#dev.off() #離開par()
#畫圓餅圖並加上資料標籤
pie_category <- colnames(p.d)
f_label.d <- paste(pie_category, f,"%", sep = "")
f_label.d
## [1] "7UP/Sprite45.95%" "Coca Cola/Pepsi42.86%" "Fanta59.09%"
## [4] "Other45.95%"
m_label.d <- paste(pie_category, m,"%", sep = "")
m_label.d
## [1] "7UP/Sprite54.05%" "Coca Cola/Pepsi57.14%" "Fanta40.91%"
## [4] "Other54.05%"
par(mfrow = c(1,2))# c(1,2)，表示建立一個1x2的空間，用來呈現後續的圖
pie(f.d, labels = f_label.d, main = "Female")
pie(m.d, labels = m_label.d, main = "Male" )
dev.off() #離開par()
## null device
## 1