讀取資料

data <- read.table("C:/Users/X510/Desktop/2020-04-20-In-class exercises-2/langMathDutch.txt", header = T)
head(data)
##   school pupil  IQV size lang arith
## 1      1 17001 15.0   29   46    24
## 2      1 17002 14.5   29   45    19
## 3      1 17003  9.5   29   33    24
## 4      1 17004 11.0   29   46    26
## 5      1 17005  8.0   29   20     9
## 6      1 17006  9.5   29   30    13

將class, IQ，分為三個等級

quantile(data$size, probs=seq(from=0, to=1, by=.1))
##   0%  10%  20%  30%  40%  50%  60%  70%  80%  90% 100% 
##  5.0 12.6 16.0 19.0 22.0 24.0 26.0 28.0 30.0 32.0 37.0
dta_size <- with(data, cut(size, ordered=T, breaks=c(0, 20, 27, 40), 
                           labels=c("Small", "Medium", "Large"))) ##分類class

quantile(data$IQV, probs=seq(from=0, to=1, by=.1))
##   0%  10%  20%  30%  40%  50%  60%  70%  80%  90% 100% 
##  4.0  9.3 10.5 11.0 11.5 12.0 12.5 13.0 13.5 14.5 18.0
dta_IQ <- with(data, cut(IQV, ordered=T, breaks=c(0, 11.2, 12.7, 20), 
                         labels=c("Low", "Middle", "High"))) ##分類IQ

library(tidyr)
dta <- cbind(dta_IQ ,cbind(data, dta_size)) ##合併class, IQ
dta.1 <- unite(dta, "class_IQ",c(dta_size, dta_IQ), sep = ",",remove = T)
head(dta.1)
##     class_IQ school pupil  IQV size lang arith
## 1 Large,High      1 17001 15.0   29   46    24
## 2 Large,High      1 17002 14.5   29   45    19
## 3  Large,Low      1 17003  9.5   29   33    24
## 4  Large,Low      1 17004 11.0   29   46    26
## 5  Large,Low      1 17005  8.0   29   20     9
## 6  Large,Low      1 17006  9.5   29   30    13

繪圖

library(ggplot2)
p0 <- ggplot(data=dta.1, aes(x=lang, y=arith)) + labs(x='Language score', y='Arithmetic score') + 
geom_point() + stat_smooth(data=dta.1, formula=y ~ x, method='lm', se=T) + 
  facet_wrap(. ~ class_IQ, ncol=3)
p0