library(dplyr)
library(ggplot2)
library(tidyr)2
#read the data
dt2 <- read.table("C:/Users/user/Dropbox/1062-Data_manage/0226/Data/nlsy86long.csv", header=T,sep=",")看種族、性別在數學與閱讀分數上的分布
無論性別跟種族為何，數學成績跟閱讀成績有正相關
dt2 %>% ggplot()+ geom_smooth(mapping=aes(math,read,color=sex)) +theme_light() + facet_grid(.~race)
看年齡與成績在性別上的差異
隨著年齡上升，數學與閱讀成績都跟著上升。在6-8歲的時候有性別差異，隨著年齡上升則漸無性別差異。
dt2 %>% gather(subject,score,8:9) %>%
ggplot(.,aes(year,score,color=sex)) +
stat_summary(fun.data = mean_se , geom = "pointrange",
position = position_dodge(0.3)) +
facet_grid(.~subject)+
theme_light()
3
右邊的圖比較接近資料的解釋，21歲以後喝酒是合法的，死亡率比21歲以前高。 (不知道怎麼畫像網頁上那樣的圖，但盡量畫了接近的回歸線)
#read the data
dt3 <- read.table("C:/Users/user/Dropbox/1062-Data_manage/0507/alcohol_age.csv", header=T,sep=",")
#create variable: whether age is above 21
dt3 %>% mutate(more21=ifelse(Age>=21,"yes","no")) %>%
ggplot(.,aes(Age,Alcohol,color=more21)) +
geom_point(size=3) +
theme_bw() +
geom_smooth(method = "lm") +
labs(x="Age (year)", y="Mortality rate from alcohol abuse (per 100,000)") 
4 Everitt
#read the data
dt4 <- read.table("C:/Users/user/Dropbox/1062-Data_manage/0507/inclass/data4.txt", header=T)
#rename variable
colnames(dt4)<- c("country","25-34","35-44","45-54","55-64","65-74")
knitr::kable(head(dt4))| country | 25-34 | 35-44 | 45-54 | 55-64 | 65-74 |
|---|---|---|---|---|---|
| Canada | 22 | 27 | 31 | 34 | 24 |
| Israel | 9 | 19 | 10 | 14 | 27 |
| Japan | 22 | 19 | 21 | 31 | 49 |
| Austria | 29 | 40 | 52 | 53 | 69 |
| France | 16 | 25 | 36 | 47 | 56 |
| Germany | 28 | 35 | 41 | 49 | 52 |
| 看起來東歐 | 國家的男 | 性自殺率 | 比較高， | 國家越先 | 進男性自殺率越低 |
dt4 %>% janitor::adorn_totals("col") %>%
gather(Age,cases,2:6) %>%
ggplot(.,aes(reorder(country,-cases),cases)) +
geom_boxplot() + theme_bw() +
labs(x="Country",y="Deaths per 100,000 from male suicides")
5
前四個變項是測情緒面向，評分方式是1:not at all到4:very much。 第五到八個變項是策略採取的部分，評分方式是1:almost never到4:almost always
#read the data
dt5 <- read.table("C:/Users/user/Dropbox/1062-Data_manage/0507/exercise.txt", header=T)
knitr::kable(head(dt5))| annoy | sad | afraid | angry | approach | avoid | support | agressive | situation | sbj |
|---|---|---|---|---|---|---|---|---|---|
| 4 | 2 | 2 | 2 | 1.00 | 2.00 | 1.00 | 2.50 | Fail | S2 |
| 4 | 4 | 4 | 2 | 4.00 | 3.00 | 1.25 | 1.50 | NoPart | S2 |
| 2 | 2 | 2 | 2 | 2.67 | 3.00 | 1.00 | 2.33 | TeacNo | S2 |
| 4 | 3 | 4 | 4 | 4.00 | 1.50 | 3.25 | 1.00 | Bully | S2 |
| 4 | 2 | 1 | 1 | 1.00 | 2.75 | 1.25 | 1.50 | Work | S2 |
| 4 | 3 | 1 | 4 | 2.33 | 2.50 | 1.00 | 3.67 | MomNo | S2 |
| ####看情 | 境跟情 | 緒的關係 | |||||||
| 在六種不 | 同的情 | 境上，整體 | 來說不常 | 出現害怕的情 | 況，最常 | 感到annoy， | 不過annoy的分 | 數變化也很大 | 。 |
dt5 %>% gather(emotion,e_score,1:4) %>%
ggplot(.,aes(situation,e_score,color=emotion)) +
stat_summary(fun.data = mean_se,position = position_dodge(0.3))+
theme_bw()+
labs(x="Situation",y="Score")
看情境跟採取策略的關係
整體來說比較少採用aggressive的方式，在“沒有全勤(Fail)”跟“作業太多(Word)”這兩種情境上，學生會比較想辦法採取一些策略來解決問題。但如果是被霸凌、被媽媽或老師禁足、被其他同學排擠，等有關社交的情境，學生會比較常採取逃避的策略。
dt5 %>% gather(coping,score,5:8) %>%
ggplot(.,aes(situation,score,color=coping)) +
stat_summary(fun.data = mean_se,position = position_dodge(0.3))+
theme_bw()+
labs(x="Situation",y="Score")
6
7
#read the data
dt7 <- read.table("C:/Users/user/Dropbox/1062-Data_manage/0507/CourseEval.txt", header=T)
dt7 %>% ggplot(.,aes(beauty,eval)) + geom_point() +
facet_wrap(~courseID,ncol=6) + theme_bw() +
labs(x="Beauty judgment score",y="Average course evaluation score")