inclass0423

Ex1

#載入package
library(pacman)
p_load(tidyverse)

#載入並整理資料
dta <- read.table("hs0.txt", h = T) %>%
  mutate(female = factor(female, levels(female), 
                         labels = c("Female", "Male")),
         race = factor(race, levels(race), 
                       labels = c("Black", "Asian", "Hispanic", 
                                  "White")),
         ses = ordered(ses, levels = c("low", "middle", 
                                       "high"),
                       labels = c("Low", "Middle", "High"))) %>%
  mutate(race = reorder(race, math, median))

str(dta)

## 'data.frame':    200 obs. of  11 variables:
##  $ id     : int  70 121 86 141 172 113 50 11 84 48 ...
##  $ female : Factor w/ 2 levels "Female","Male": 2 1 2 2 2 2 2 2 2 2 ...
##  $ race   : Factor w/ 4 levels "Black","Hispanic",..: 3 3 3 3 3 3 1 2 3 1 ...
##   ..- attr(*, "scores")= num [1:4(1d)] 45 61 47 54
##   .. ..- attr(*, "dimnames")=List of 1
##   .. .. ..$ : chr  "Black" "Asian" "Hispanic" "White"
##  $ ses    : Ord.factor w/ 3 levels "Low"<"Middle"<..: 1 2 3 3 2 2 2 2 2 2 ...
##  $ schtyp : Factor w/ 2 levels "private","public": 2 2 2 2 2 2 2 2 2 2 ...
##  $ prog   : Factor w/ 3 levels "academic","general",..: 2 3 2 3 1 1 2 1 2 1 ...
##  $ read   : int  57 68 44 63 47 44 50 34 63 57 ...
##  $ write  : int  52 59 33 44 52 52 59 46 57 55 ...
##  $ math   : int  41 53 54 47 57 51 42 45 54 52 ...
##  $ science: int  47 63 58 53 53 63 53 39 58 NA ...
##  $ socst  : int  57 61 31 56 61 61 61 36 51 51 ...

bw <- with(dta, IQR(math)/(length(math)^(1/3)))
ggplot() +
  #以男女數學成績資料做長條圖，男在左女在右
  stat_bin(data = subset(dta, female=="Male"), binwidth = bw,
           aes(math, color = "Male", fill = "Male", y = - ..density.. )) +
  stat_bin(data = subset(dta, female == "Female"), binwidth = bw,
           aes(math, color = "Female", fill = "Female", y = ..density.. )) +
  #設定長條邊框顏色
  scale_color_manual(values = c("black", "black"),
                     guide = guide_legend(title = NULL, direction = "horizontal",
                                          title.position = "top", reverse = TRUE,
                                          label.position = "bottom", label.hjust = .5, label.vjust = .5,
                                          label.theme = element_text(angle = 90) ) ) +
  #設定長條填滿顏色
  scale_fill_manual(values = c("White", "gray80"),
                    guide = guide_legend(title = NULL, reverse = TRUE,
                                         direction = "horizontal", title.position = "top",
                                         label.position = "bottom", label.hjust = .5, label.vjust = .5,
                                         label.theme = element_text(angle = 90))) +
  #設定分數範圍與級距
  scale_x_continuous(limits = c(30, 80), breaks=seq(30, 80, by = 5)) +
  labs(x = "Mathematic score", y = "Density") +
  coord_flip() +
  theme_bw() +
  theme(legend.position=c(.9, .85))

Ex2

library(ggeffects)

#輸入資料並更改資料labels
dta2 <- read.table("hs0.txt", header = T) %>% 
  mutate(female = factor(female, levels(female), 
                         labels = c("Female", "Male")),
         race = factor(race, levels(race), 
                       labels = c("Black", "Asian", "Hispanic", 
                                  "White")),
         ses = ordered(ses, levels = c("low", "middle", 
                                       "high"),
                       labels = c("Low", "Middle", "High")))

#畫圖
m0 <- lm(math ~ read + write + science + socst + race + ses + female, data = dta2)
dta_m0 <- ggpredict(m0, terms = c("race", "female", "ses"))
p1 <- plot(dta_m0)+labs(y = "Mean math score", x = "Race")
print(p1)

Ex3

dta3 <- read.table("kdt.csv", sep="",header=T)
knitr::kable(dta3)

Test	Format	Accuracy	SE
KDT	Picture	93.7	0.9
KDT	Word	96.4	0.7
PPT	Picture	90.6	1.0
PPT	Word	88.9	1.0

ggplot(dta3,aes(Test, Accuracy,fill=Format))+
   coord_cartesian(ylim=c(85,100))+
  geom_bar(stat="identity",position='dodge', colour="black")+
  geom_errorbar(aes(ymin = Accuracy-SE , ymax= Accuracy+SE), width = .2,position=position_dodge(0.9))+
  scale_fill_manual(values=c("steel blue","yellow"))