这里有一个类似的版本,按组大小/连续性过滤(在您发布时已经编写了它,所以我想我还是继续吧)。
library(tidyverse)
set.seed(42)
testdf=data.frame(FY=c("FY13","FY14","FY15","FY14","FY15","FY13","FY14","FY15","FY13","FY15","FY13","FY14","FY15","FY13","FY14","FY15"),
Region=c(rep("AFRICA",5),rep("ASIA",5),rep("AMERICA",6)),
QST=c(rep("Q2",3),rep("Q5",2),rep("Q2",3),rep("Q5",2),rep("Q2",3),rep("Q5",3)),
Very.Satisfied=runif(16,min = 0, max=1),
Total.Very.Satisfied=floor(runif(16,min=10,max=120)))
test_final <- testdf %>%
group_by(Region,QST) %>% # group by region
mutate(numdate = as.numeric(str_remove(FY, "FY"))) %>%
filter(n() >= 2 & max(diff(numdate)) < 2) %>% # filter out singleton groups
mutate(slopes = coef(lm(Very.Satisfied~numdate))[2])
test_final %>% select(Region, QST, slopes)
#> # A tibble: 14 x 3
#> # Groups: Region, QST [5]
#> Region QST slopes
#> <fct> <fct> <dbl>
#> 1 AFRICA Q2 -0.314
#> 2 AFRICA Q2 -0.314
#> 3 AFRICA Q2 -0.314
#> 4 AFRICA Q5 -0.189
#> 5 AFRICA Q5 -0.189
#> 6 ASIA Q2 -0.192
#> 7 ASIA Q2 -0.192
#> 8 ASIA Q2 -0.192
#> 9 AMERICA Q2 0.238
#> 10 AMERICA Q2 0.238
#> 11 AMERICA Q2 0.238
#> 12 AMERICA Q5 0.342
#> 13 AMERICA Q5 0.342
#> 14 AMERICA Q5 0.342
test_final %>% group_by(Region) %>%
summarise(Value = max(slopes),
Top_Question = QST[which.max(slopes)])
#> # A tibble: 3 x 3
#> Region Value Top_Question
#> <fct> <dbl> <fct>
#> 1 AFRICA -0.189 Q5
#> 2 AMERICA 0.342 Q5
#> 3 ASIA -0.192 Q2
创建于2019-01-21
reprex package
(v0.2.1)