期中考_R_113年班.R

##R語言資料分析期中考：
#輸入學號： 001    和名字：Shaq
##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
#(1-2)畫長條圖
brand <- c("Sansung", "Apple", "oppo")
market_share <- c(31.7, 22.8, 9.3)
df <- data.frame(brand, market_share)
df

##     brand market_share
## 1 Sansung         31.7
## 2   Apple         22.8
## 3    oppo          9.3

barplot(df$market_share, 
        main = "Global Smartphone Market Share", 
        sub = "by Peter Liu", 
        names.arg = c("Sansung", "Apple", "oppo"), 
        xlab = "brand", 
        ylab = "market_share",
        col = c(11:14))

#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)
#(2-2)呈現gender 性別與lunch 營養午餐人數的圖表
t1 <- table(sp$gender, sp$lunch)
t1

##         
##          free/reduced standard
##   female          189      329
##   male            166      316

p.t1 <- prop.table(t1)
p.t1 <- round(p.t1*100,2)
p.t1

##         
##          free/reduced standard
##   female         18.9     32.9
##   male           16.6     31.6

label <- rownames(p.t1)
barplot(p.t1, 
        beside = TRUE, 
        legend.text = label, 
        col = c("pink", "lightblue"),
        main = "Gender/Lunch",
        sub = "By Peter Liu")

#參、math.score 數學成績的直方圖與盒狀圖
boxplot(sp$math.score, col = "cyan",
        main = "Math Score boxplot",
        sub = "By Peter Liu")

hist(sp$math.score, col = "yellow",
     xlab = "Math Score",
     main = "Math Score histgram",
     sub = "By Peter Liu")

#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$math.score, sp$writing, col = "blue")
plot(sp$reading.score, sp$writing, col = "red")

#六、計算以下兩組關係的相關係數
#(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
cor(sp$math.score, sp$writing)

## [1] 0.802642

cor(sp$reading.score, sp$writing)

## [1] 0.9545981

#七、計算不同gender 性別的math.score 數學成績並畫長條圖
math <- tapply(sp$math.score, sp$gender, mean)
math

##   female     male 
## 63.63320 68.72822

barplot(sort(math, decreasing = T),
        col = c("lightblue", "pink"),
        xlab = "Gender", 
        ylab = "Math Score",
        main = "Gender/Math Score",
        sub = "By Peter Liu")