Exercise 1
#檢視資料
pacman::p_load(Ecdat, dplyr, tidyr)
data(Caschool, package="Ecdat")
Caschool |> head()
distcod county district grspan enrltot teachers
1 75119 Alameda Sunol Glen Unified KK-08 195 10.90
2 61499 Butte Manzanita Elementary KK-08 240 11.15
3 61549 Butte Thermalito Union Elementary KK-08 1550 82.90
4 61457 Butte Golden Feather Union Elementary KK-08 243 14.00
5 61523 Butte Palermo Union Elementary KK-08 1335 71.50
6 62042 Fresno Burrel Union Elementary KK-08 137 6.40
calwpct mealpct computer testscr compstu expnstu str avginc
1 0.5102 2.0408 67 690.80 0.3435898 6384.911 17.88991 22.690001
2 15.4167 47.9167 101 661.20 0.4208333 5099.381 21.52466 9.824000
3 55.0323 76.3226 169 643.60 0.1090323 5501.955 18.69723 8.978000
4 36.4754 77.0492 85 647.70 0.3497942 7101.831 17.35714 8.978000
5 33.1086 78.4270 171 640.85 0.1280899 5235.988 18.67133 9.080333
6 12.3188 86.9565 25 605.55 0.1824818 5580.147 21.40625 10.415000
elpct readscr mathscr
1 0.000000 691.6 690.0
2 4.583333 660.5 661.9
3 30.000002 636.3 650.9
4 0.000000 651.9 643.5
5 13.857677 641.8 639.9
6 12.408759 605.7 605.4
#參考同學作業隨機抽取學校
set.seed(1234)
t1<-Caschool
random <- group_by(t1, county) %>%
sample_n(1)
pacman::p_load("basicPlotteR")
with(random,
plot(mathscr, readscr,
xlab = "Average math score",
ylab = "Average reading score",
pch = 20, bty="n", col="lightblue",
axes = FALSE))
axis(1, at = seq(600,750, by=10))
axis(2, at = seq(600,750, by=10))
grid()
Exercis 2
#檢查數據
pacman::p_load(MASS)
data(nlschools, package="MASS")
t2 <- nlschools
head(t2)
lang IQ class GS SES COMB
1 46 15.0 180 29 23 0
2 45 14.5 180 29 10 0
3 33 9.5 180 29 15 0
4 46 11.0 180 29 23 0
5 20 8.0 180 29 10 0
6 30 9.5 180 29 10 0
#求置信區間
t2 %>%
group_by(class) %>%
summarize(language_mean <- mean(lang),
language_lb <- language_mean - 1.96*sd(lang),
language_ub <- language_mean + 1.96*sd(lang)) %>% arrange(class)
# A tibble: 133 x 4
class `language_mean <- mean(lang)` `language_lb <- lan~ `language_ub <- lan~
<fct> <dbl> <dbl> <dbl>
1 180 36.4 11.3 45.6
2 280 23.7 16.0 40.8
3 1082 30.4 8.51 48.3
4 1280 30.9 14.8 42.1
5 1580 30.9 2.35 54.5
6 1680 41.5 16.1 40.8
7 1880 32.9 7.91 48.9
8 2180 38.8 9.36 47.5
9 2480 45.0 13.1 43.8
10 2680 40.7 13.5 43.3
# ... with 123 more rows
Exercise 3
#檢視資料
pacman::p_load(carData)
data(OBrienKaiser, package = "carData")
t3<-OBrienKaiser
head(t3)
treatment gender pre.1 pre.2 pre.3 pre.4 pre.5 post.1 post.2 post.3 post.4
1 control M 1 2 4 2 1 3 2 5 3
2 control M 4 4 5 3 4 2 2 3 5
3 control M 5 6 5 7 7 4 5 7 5
4 control F 5 4 7 5 4 2 2 3 5
5 control F 3 4 6 4 3 6 7 8 6
6 A M 7 8 7 9 9 9 9 10 8
post.5 fup.1 fup.2 fup.3 fup.4 fup.5
1 2 2 3 2 4 4
2 3 4 5 6 4 1
3 4 7 6 9 7 6
4 3 4 4 5 3 4
5 3 4 3 6 4 3
6 9 9 10 11 9 6
#寬轉長試圖用spread函數但失敗
#t3 %>%spread(key = row.names,value =？)
#嘗試矩陣轉置但失敗
t4 <- matrix(t3[,3:17])
t5 <- t(t4)
Exercise 4
#讀取數據
majors <- read.table("C:\\Users\\shabby\\Desktop\\DataManagement\\week6\\student_major.txt", header = TRUE)
sports <-read.table("C:\\Users\\shabby\\Desktop\\DataManagement\\week6\\student_sport.txt", header = TRUE)
cafeteria <-read.table("C:\\Users\\shabby\\Desktop\\DataManagement\\week6\\student_cafe.txt", header = TRUE)
#合併表格，根據ID
t6 <- merge(majors, sports, by="id", all = TRUE)
t7 <- merge(cafeteria,t6,by="id", all = TRUE)