问如何使用dplyr使用条件语句对分组数据进行筛选？

EN

library(dplyr)

df %>%
  group_by(country, year) %>%
  filter(if(n_distinct(version) == 2) version == 'versionA' else TRUE)


#  country   year version 
#  <fct>    <dbl> <fct>   
#1 country1  2011 versionA
#2 country2  2011 versionA
#3 country3  2011 versionB

library(dplyr)
df %>%
  group_by(country, year)  %>% 
  filter((n_distinct(version)  > 1 & version == 'versionA')|row_number() == 1)
# A tibble: 3 x 3
# Groups:   country, year [3]
#  country   year version 
#  <fct>    <dbl> <fct>   
#1 country1  2011 versionA
#2 country2  2011 versionA
#3 country3  2011 versionB

df %>%
    group_by(country, year) %>%
    filter(if(n_distinct(version) > 1) version == 'versionA'
       else row_number() ==1)
# A tibble: 3 x 3
# Groups:   country, year [3]
#  country   year version 
#  <fct>    <dbl> <fct>   
#1 country1  2011 versionA
#2 country2  2011 versionA
#3 country3  2011 versionB

df %>% 
    arrange(country, year, version != 'versionA') %>% 
    group_by(country, year) %>% 
    slice(1)

df %>%
    group_by(country, year) %>%
    summarise(version = if(n_distinct(version) > 1) 'versionA' else first(version))

library(data.table)
setDT(df)[, .SD[if(n_distinct(version) > 1) version == 'versionA' 
          else 1], .(country, year)]

df[!(duplicated(df[1:2])),]

df[!(duplicated(df$country, df$year)),]

library(tidyverse)
df %>%
  filter(!(duplicated(country, year)))

# Create a counter of versions for each year and country: 

df$tmp <- with(lapply(df, function(x){if(is.factor(x)){as.character(x)}else{x}}),
               ave(version, paste0(country, year), FUN = seq.int))

# Subset the dataframe to hold only the first record for each year/country: 

df[which(df$tmp == 1), ]

df %>%
  arrange(version) %>% 
  filter(!(duplicated(country, year)))