##R語言資料分析期中考：
##輸入學號： 209 和名字：柏荃
##壹、自建資料與圖表(請見社團範例)
#(1-1)建立一個data frame，包括brand品牌與market_share市站率
brand <-c("Samsung","Apple","oppo")#第一列
market_share <- c(31.7,22.8,9.3)#第二列
data<-data.frame(brand,market_share)#依序建立圖表
#(1-2)畫長條圖
barplot(sort(market_share,decreasing = TRUE),#排序大到小
names.arg =c("Samsung","Apple","oppo"),#項目名稱
main = "Global Smartphone Market Share",#標題
sub="by YPC",#小標題
xlab = "brand",#x標題
ylab = "market_share",#y標題
col =c(57:59))#顏色
#貳、比較gender 性別與lunch 營養午餐類型
#讀入外部資料
sp <- read.csv(file = "StudentsPerformance.csv", stringsAsFactors = TRUE)
summary(sp)
## gender race.ethnicity parental.level.of.education lunch
## female:518 group A: 89 associate's degree:222 free/reduced:355
## male :482 group B:190 bachelor's degree :118 standard :645
## group C:319 high school :196
## group D:262 master's degree : 59
## group E:140 some college :226
## some high school :179
## test.preparation.course math.score reading.score writing.score
## completed:358 Min. : 0.00 Min. : 17.00 Min. : 10.00
## none :642 1st Qu.: 57.00 1st Qu.: 59.00 1st Qu.: 57.75
## Median : 66.00 Median : 70.00 Median : 69.00
## Mean : 66.09 Mean : 69.17 Mean : 68.05
## 3rd Qu.: 77.00 3rd Qu.: 79.00 3rd Qu.: 79.00
## Max. :100.00 Max. :100.00 Max. :100.00
#欄位名稱------------------------------------------
# gender 性別
# race.ethnicity 種族分群
# parental.level.of.education 父母教育程度
# lunch 營養午餐類型(free/reduced免費或減免餐費，standard為一般類別)
# test.preparation.course
# math.score 數學成績
# reading.score 閱讀成績
# writing.score 寫作成績
#(2-1)計算不同gender 性別與lunch 營養午餐人數的比例(交叉分析表)
t <- table(sp$gender,sp$lunch)
t
##
## free/reduced standard
## female 189 329
## male 166 316
p.t <- prop.table(t)
p.t
##
## free/reduced standard
## female 0.189 0.329
## male 0.166 0.316
p.t <- p.t*100
p.t
##
## free/reduced standard
## female 18.9 32.9
## male 16.6 31.6
#(2-2)呈現gender 性別與lunch 營養午餐人數的圖表
rownames(p.t)
## [1] "female" "male"
label <- rownames(p.t)
label
## [1] "female" "male"
barplot(p.t,
beside =TRUE ,
legend.text =label,
col =c(3,9) )
#參、math.score 數學成績的直方圖與盒狀圖
#直方圖
label <- rownames("math.score")
hist(sp$math.score,
col=c(98:113),
main = "math.score",
sub = "Harry")#直方圖
#盒狀圖
boxplot(sp$math.score,
col=c(98),
main = "math.score",
sub = "Harry")#盒鬚圖
#肆、math.score 數學成績的最大值、最小值、平均數、中位數、標準差
max(sp$math.score)#算最大值
## [1] 100
min(sp$math.score)#算最小值
## [1] 0
mean(sp$math.score)#算平均數
## [1] 66.089
median(sp$math.score)#算中位數
## [1] 66
sd(sp$math.score)#算標準差
## [1] 15.16308
#五、呈現以下兩組關係的散佈圖
#(1)math.score 數學成績與與writing.score 寫作成績
#(2)reading.score 閱讀成績與writing.score 寫作成績
par(mfrow = c(1,2))
plot(sp$math.score,
xlab="math.score",
col=c(77),
sp$writing.score,
ylab="writing.score",
main = "test",
sub = "Harry")
#(2)Petal.Length與Petal.Width
plot(sp$reading.score,
xlab="reading.score",
col=c(1),
sp$writing.score,
ylab="writing.score",
main = "test",
sub = "Harry")
#六、計算以下兩組關係的相關係數
#(1)reading.score 閱讀成績與math.score 數學成績
#(2)writing.score 寫作成績與math.score 數學成績
cor(sp$reading.score, sp$math.score)
## [1] 0.8175797
cor(sp$writing.score, sp$math.score)
## [1] 0.802642
#七、計算不同gender 性別的math.score 數學成績並畫長條圖
par(mfrow = c(1,1))
x<-tapply(sp$math.score,sp$gender,mean)
x
## female male
## 63.63320 68.72822
barplot(sort(x,decreasing = TRUE),
x,main = "gender",
xlab="gender",
ylab="grade",
beside =TRUE ,
col =c(8:5),
sub = "Harry")
