#set-up
options(digits = 4, show.signif.stars = FALSE)
pacman::p_load(mlmRev, HSAUR3, knitr, kableExtra,
readr, dplyr, ggplot2, tidyr, car,
magrittr, tibble, purrr, stringr)
EX1
dta1 <- read.csv("nlsy86long.csv")
head(dta1)
## id sex race time grade year month math read
## 1 2390 Female Majority 1 0 6 67 14.286 19.048
## 2 2560 Female Majority 1 0 6 66 20.238 21.429
## 3 3740 Female Majority 1 0 6 67 17.857 21.429
## 4 4020 Male Majority 1 0 5 60 7.143 7.143
## 5 6350 Male Majority 1 1 7 78 29.762 30.952
## 6 7030 Male Majority 1 0 5 62 14.286 17.857
dta1 %>%
gather(key = test_var, value = test_score, 8:9) %>%
head
## id sex race time grade year month test_var test_score
## 1 2390 Female Majority 1 0 6 67 math 14.286
## 2 2560 Female Majority 1 0 6 66 math 20.238
## 3 3740 Female Majority 1 0 6 67 math 17.857
## 4 4020 Male Majority 1 0 5 60 math 7.143
## 5 6350 Male Majority 1 1 7 78 math 29.762
## 6 7030 Male Majority 1 0 5 62 math 14.286
EX2
dta2 <- car::Vocab
head(dta2)
## year sex education vocabulary
## 20040001 2004 Female 9 3
## 20040002 2004 Female 14 6
## 20040003 2004 Male 14 9
## 20040005 2004 Female 17 8
## 20040008 2004 Male 14 1
## 20040010 2004 Male 14 7
str(dta2)
## 'data.frame': 21638 obs. of 4 variables:
## $ year : int 2004 2004 2004 2004 2004 2004 2004 2004 2004 2004 ...
## $ sex : Factor w/ 2 levels "Female","Male": 1 1 2 1 2 2 1 2 2 1 ...
## $ education : int 9 14 14 17 14 14 12 10 11 9 ...
## $ vocabulary: int 3 6 9 8 1 7 6 6 5 1 ...
ggplot(dta2, aes(x = education, y = vocabulary, color = sex))+
geom_point()+
stat_smooth(method = "lm")+
facet_wrap(~ year)
EX3
#載入資料
source("passwd.txt")
link3 <- paste0("http://", IDPW, "140.116.183.121/~sheu/dataM/Data/probeL.txt")
dta3 <- read.table(link3, header = T)
head(dta3)
## ID Response_Time Position
## 1 S01 51 1
## 2 S01 36 2
## 3 S01 50 3
## 4 S01 35 4
## 5 S01 42 5
## 6 S02 27 1
dta3W <- dta3 %>%
mutate(pre = rep("Pos", dim(dta3)[1])) %>%
unite( Position_new, pre, Position) %>%
spread(Position_new, Response_Time) %>%
arrange(ID)
## Warning: package 'bindrcpp' was built under R version 3.4.3
head(dta3W)
## ID Pos_1 Pos_2 Pos_3 Pos_4 Pos_5
## 1 S01 51 36 50 35 42
## 2 S02 27 20 26 17 27
## 3 S03 37 22 41 37 30
## 4 S04 42 36 32 34 27
## 5 S05 27 18 33 14 29
## 6 S06 43 32 43 35 40
EX4
source("passwd.txt")
link4.1 <- paste0("http://", IDPW, "140.116.183.121/~sheu/dataM/Rdw/data/nobel_countries.txt")
country <- read.table(link4.1, header = T)
link4.2 <- paste0("http://", IDPW, "140.116.183.121/~sheu/dataM/Rdw/data/nobel_winners.txt")
winner <- read.table(link4.2, header = T)
semi_join(country, winner)
## Joining, by = "Year"
## Country Year
## 1 France 2014
## 2 UK 1950
## 3 UK 2017
## 4 US 2016
## 5 Canada 2013
## 6 China 2012
left_join(country, winner)
## Joining, by = "Year"
## Country Year Name Gender
## 1 France 2014 Patrick Modiano Male
## 2 UK 1950 Bertrand Russell Male
## 3 UK 2017 Kazuo Ishiguro Male
## 4 US 2016 Bob Dylan Male
## 5 Canada 2013 Alice Munro Female
## 6 China 2012 Mo Yan Male
## 7 Russia 2015 <NA> <NA>
## 8 Sweden 2011 <NA> <NA>
anti_join(country, winner)
## Joining, by = "Year"
## Country Year
## 1 Russia 2015
## 2 Sweden 2011
full_join(country, winner)
## Joining, by = "Year"
## Country Year Name Gender
## 1 France 2014 Patrick Modiano Male
## 2 UK 1950 Bertrand Russell Male
## 3 UK 2017 Kazuo Ishiguro Male
## 4 US 2016 Bob Dylan Male
## 5 Canada 2013 Alice Munro Female
## 6 China 2012 Mo Yan Male
## 7 Russia 2015 <NA> <NA>
## 8 Sweden 2011 <NA> <NA>
## 9 <NA> 1938 Pearl Buck Female