#R語言資料分析期中考：
#輸入學號：1130730105 名字：潘奕至
#壹、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)
#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
#(1-1)計算不同lunch 營養午餐與race.ethnicity 種族分群人數的比例(交叉分析表)
T<-table(sp$lunch,sp$race.ethnicity)
T
##
## group A group B group C group D group E
## free/reduced 36 69 114 95 41
## standard 53 121 205 167 99
#(1-2)呈現lunch 營養午餐與race.ethnicity 種族分群的圖表
label <- rownames(T)
barplot(T,beside = TRUE,sub = "by allen pan",main = "lunch/group",col = c(10:11))
#貳、reading.score 閱讀成績的直方圖與盒狀圖
boxplot(sp$reading.score,col=6,main = "reading.score boxplot",sub = "by allen pan")
hist(sp$reading.score,col=5,main = "reading.score histgram",sub = "by allen pan")
#參、reading.score 閱讀成績的最大值、最小值、平均數、中位數、標準差
sp$reading.score
## [1] 72 90 95 57 78 83 95 43 64 60 54 52 81 72 53 75 89 32
## [19] 42 58 69 75 54 73 71 74 54 69 70 70 74 65 72 42 87 81
## [37] 81 64 90 56 61 73 58 65 56 54 65 71 74 84 55 69 44 78
## [55] 84 41 85 55 59 17 74 39 61 80 58 64 37 72 58 64 63 55
## [73] 51 57 49 41 26 78 74 68 49 45 47 64 39 80 83 71 70 86
## [91] 72 34 79 45 86 81 66 72 67 67 67 74 91 44 86 67 100 63
## [109] 76 64 89 55 53 58 100 77 85 82 63 69 92 89 93 57 80 95
## [127] 68 77 82 49 84 37 74 81 79 55 54 55 66 61 72 62 55 43
## [145] 73 39 84 68 75 100 67 67 70 49 67 89 74 60 86 62 78 88
## [163] 53 53 92 100 51 76 83 75 73 88 86 67 51 91 54 77 70 100
## [181] 68 64 50 69 52 67 76 66 52 88 65 83 64 62 84 55 69 56
## [199] 53 79 84 81 77 69 41 71 62 80 81 61 79 28 62 51 91 83
## [217] 86 42 77 56 68 85 65 80 66 56 72 50 72 95 64 43 86 87
## [235] 82 75 66 60 52 80 68 83 52 51 74 76 76 70 64 60 49 83
## [253] 70 80 52 73 73 77 75 81 79 79 50 93 73 42 75 72 92 76
## [271] 63 49 53 70 85 78 92 63 86 56 52 48 79 78 46 82 82 89
## [289] 75 76 70 73 60 73 77 62 41 74 46 87 78 54 84 76 75 67
## [307] 87 52 71 57 76 60 61 67 64 66 82 72 71 65 79 86 81 53
## [325] 46 90 61 23 75 55 60 37 56 78 93 68 70 51 38 55 61 73
## [343] 76 72 73 80 61 94 74 74 65 57 78 58 71 72 61 66 62 90
## [361] 62 84 58 34 60 58 58 66 64 84 77 73 74 97 70 43 90 95
## [379] 83 64 86 100 81 49 43 76 73 78 64 70 67 68 67 54 74 45
## [397] 67 89 63 59 54 43 65 99 59 73 65 80 57 84 71 83 66 67
## [415] 72 73 74 73 59 56 93 58 58 85 39 67 83 71 59 63 66 72
## [433] 56 59 66 48 68 66 56 88 81 81 73 83 82 74 66 81 46 73
## [451] 85 92 77 58 61 56 89 54 100 65 58 54 70 90 58 87 31 67
## [469] 88 74 85 69 86 67 90 76 62 68 64 71 71 59 68 52 52 74
## [487] 47 75 53 82 85 64 83 88 64 64 48 78 69 71 79 87 61 89
## [505] 59 82 70 59 78 92 71 50 49 61 97 87 89 74 78 78 49 86
## [523] 58 59 52 60 61 53 41 74 67 54 61 88 69 83 60 66 66 92
## [541] 69 82 77 95 63 83 100 67 67 72 76 90 48 62 45 39 72 67
## [559] 70 66 75 74 90 80 51 43 100 71 48 68 75 96 62 66 81 55
## [577] 51 91 56 61 97 79 73 75 77 76 73 63 64 66 57 62 68 76
## [595] 100 79 24 54 77 82 60 29 78 57 89 72 84 58 64 63 60 59
## [613] 90 77 93 68 45 78 81 73 61 63 51 96 58 97 70 48 57 51
## [631] 64 60 74 88 84 74 80 92 76 74 52 88 81 79 65 81 70 62
## [649] 53 79 56 80 86 70 79 67 67 66 60 87 77 66 71 69 63 60
## [667] 73 85 74 72 76 57 78 84 77 64 78 82 75 61 72 68 55 40
## [685] 66 99 75 78 58 90 53 76 74 77 63 89 82 72 78 66 81 67
## [703] 84 64 63 72 34 59 87 61 84 85 100 81 70 94 78 96 76 73
## [721] 72 59 90 48 43 74 75 51 92 39 77 46 89 47 58 57 79 66
## [739] 71 60 73 57 84 73 55 79 75 64 60 84 69 72 77 90 55 95
## [757] 58 68 59 77 72 58 81 62 63 72 75 62 71 60 48 73 67 78
## [775] 65 58 72 44 79 85 56 90 85 59 81 51 79 38 65 65 62 66
## [793] 74 84 52 68 70 84 60 55 73 80 94 85 76 81 74 45 75 54
## [811] 31 47 64 84 80 86 59 70 72 91 90 90 52 87 58 67 68 69
## [829] 86 54 60 86 60 82 50 64 64 82 57 77 52 58 44 77 65 85
## [847] 85 54 72 75 67 68 85 67 64 97 68 79 49 73 62 86 42 71
## [865] 93 82 53 42 74 51 58 72 84 90 62 64 82 61 72 76 64 70
## [883] 73 46 51 76 100 72 65 51 85 92 67 74 62 34 29 78 54 78
## [901] 84 78 48 100 84 77 48 84 75 64 42 84 61 62 61 70 100 61
## [919] 77 96 70 53 66 65 70 64 56 61 43 56 74 57 71 75 87 63
## [937] 57 58 81 68 66 91 66 62 68 61 82 58 50 75 73 77 74 52
## [955] 69 57 87 100 63 81 58 54 100 76 57 70 68 63 76 84 100 72
## [973] 50 65 63 82 62 65 41 95 24 78 85 87 75 51 59 75 45 86
## [991] 81 82 76 72 63 99 55 71 78 86
max(sp$reading.score)
## [1] 100
min(sp$reading.score)
## [1] 17
mean(sp$reading.score)
## [1] 69.169
median(sp$reading.score)
## [1] 70
sd(sp$reading.score)
## [1] 14.60019
#肆、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.score,col="green")
plot(sp$reading.score,sp$writing.score,col="red")
#伍、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
cor(sp$math.score,sp$writing.score)
## [1] 0.802642
#(2)reading.score 閱讀成績與writing.score 寫作成績
cor(sp$reading.score,sp$writing.score)
## [1] 0.9545981
#陸、計算不同gender 性別的math.score 數學成績並畫長條圖
x<-tapply(sp$math.score,sp$gender,mean)
x
## female male
## 63.63320 68.72822
barplot(x,main = "gender", sub = "by allen pan",xlab="gender",ylab="grade",
beside =TRUE ,
col =c(1:2))
##柒、以下為一連鎖商店的業績 ####
# 分店：A, B, C, D, E, F, G, H
# 業績：20, 35, 55, 58, 63, 47, 70, 88
#7-1、請將這4家分店的業績合併為一個data frame
branch<- c( "B","D","C","A")
sales <- c(35,58,55,20)
data<-data.frame(branch,sales)
#7-2、請畫出這4家分店的業績的長條圖。
barplot(sort(data$sales, decreasing = TRUE),
names.arg = data$sales,
main="Perfoemance Assessment",
sub = "by allen pan",
xlab="branch",
ylab="sales",
col =c(11:14))
