基于另一列中的值将函数应用于给定列的特定行

Question

抱歉，我想可能有一个非常简单的答案，我没能锻炼。

我有一张我修改过的桌子。我只想对年份=2010:2020的人口进行插值。该表仅包括1个国家，但该表有16107行。

我知道插值方程是：mutate_at(vars(population, gdp.x), na.approx, method="linear"

我尝试过申请：apply(ssp[5,6], ssp[2]==2010:2020, mutate_at(vars(population, gdp.x), na.approx, method="linear"))

Groups:   Country [177]
Country      Year Model           Scenario       population   gdp.x SSP   Version Date   Series.Name                   Series.Code  Country.Code gdp.y
<chr>       <dbl> <chr>           <chr>               <dbl>   <dbl> <chr> <chr>   <chr>  <chr>                         <chr>        <chr>        <dbl>
1 Afghanistan  2010 OECD Env-Growth SSP2_v9_130325       28.0  0.0159 SSP2  v9      130325 NA                            NA           NA            NA  
2 Afghanistan  2011 OECD Env-Growth SSP2_v9_130325       NA   NA      SSP2  v9      130325 NA                            NA           NA            NA  
3 Afghanistan  2012 OECD Env-Growth SSP2_v9_130325       NA   NA      SSP2  v9      130325 NA                            NA           NA            NA  
4 Afghanistan  2013 OECD Env-Growth SSP2_v9_130325       NA   NA      SSP2  v9      130325 NA                            NA           NA            NA  
5 Afghanistan  2014 OECD Env-Growth SSP2_v9_130325       NA   NA      SSP2  v9      130325 NA                            NA           NA            NA  
6 Afghanistan  2015 OECD Env-Growth SSP2_v9_130325       31.8  0.0206 SSP2  v9      130325 NA                            NA           NA            NA  
7 Afghanistan  2016 OECD Env-Growth SSP2_v9_130325       NA   NA      SSP2  v9      130325 NA                            NA           NA            NA  
8 Afghanistan  2017 OECD Env-Growth SSP2_v9_130325       NA   NA      SSP2  v9      130325 GDP growth, constant 2010 USD NYGDPMKTPKDZ AFG            2.7
9 Afghanistan  2018 OECD Env-Growth SSP2_v9_130325       NA   NA      SSP2  v9      130325 GDP growth, constant 2010 USD NYGDPMKTPKDZ AFG            1.8
10 Afghanistan  2019 OECD Env-Growth SSP2_v9_130325       NA   NA      SSP2  v9      130325 GDP growth, constant 2010 USD NYGDPMKTPKDZ AFG            2.9
# ... with 16,097 more rows

dput前20行

structure(list(Country = c("Afghanistan", "Afghanistan", "Afghanistan", 
"Afghanistan", "Afghanistan", "Afghanistan", "Afghanistan", "Afghanistan", 
"Afghanistan", "Afghanistan", "Afghanistan", "Afghanistan", "Afghanistan", 
"Afghanistan", "Afghanistan", "Afghanistan", "Afghanistan", "Afghanistan", 
"Afghanistan", "Afghanistan"), Year = c(2010, 2011, 2012, 2013, 
2014, 2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024, 
2025, 2026, 2027, 2028, 2029), Model = c("OECD Env-Growth", "OECD Env-Growth", 
"OECD Env-Growth", "OECD Env-Growth", "OECD Env-Growth", "OECD Env-Growth", 
"OECD Env-Growth", "OECD Env-Growth", "OECD Env-Growth", "OECD Env-Growth", 
"OECD Env-Growth", "OECD Env-Growth", "OECD Env-Growth", "OECD Env-Growth", 
"OECD Env-Growth", "OECD Env-Growth", "OECD Env-Growth", "OECD Env-Growth", 
"OECD Env-Growth", "OECD Env-Growth"), Scenario = c("SSP2_v9_130325", 
"SSP2_v9_130325", "SSP2_v9_130325", "SSP2_v9_130325", "SSP2_v9_130325", 
"SSP2_v9_130325", "SSP2_v9_130325", "SSP2_v9_130325", "SSP2_v9_130325", 
"SSP2_v9_130325", "SSP2_v9_130325", "SSP2_v9_130325", "SSP2_v9_130325", 
"SSP2_v9_130325", "SSP2_v9_130325", "SSP2_v9_130325", "SSP2_v9_130325", 
"SSP2_v9_130325", "SSP2_v9_130325", "SSP2_v9_130325"), population = c(27.962207, 
NA, NA, NA, NA, 31.82735098, NA, NA, NA, NA, 36.142924, NA, NA, 
NA, NA, 40.89646358, NA, NA, NA, NA), gdp.x = c(0.01593680064, 
NA, NA, NA, NA, 0.02062235783, NA, NA, NA, NA, 0.02575387325, 
NA, NA, NA, NA, 0.03327524539, NA, NA, NA, NA), SSP = c("SSP2", 
"SSP2", "SSP2", "SSP2", "SSP2", "SSP2", "SSP2", "SSP2", "SSP2", 
"SSP2", "SSP2", "SSP2", "SSP2", "SSP2", "SSP2", "SSP2", "SSP2", 
"SSP2", "SSP2", "SSP2"), Version = c("v9", "v9", "v9", "v9", 
"v9", "v9", "v9", "v9", "v9", "v9", "v9", "v9", "v9", "v9", "v9", 
"v9", "v9", "v9", "v9", "v9"), Date = c("130325", "130325", "130325", 
"130325", "130325", "130325", "130325", "130325", "130325", "130325", 
"130325", "130325", "130325", "130325", "130325", "130325", "130325", 
"130325", "130325", "130325"), Series.Name = c(NA, NA, NA, NA, 
NA, NA, NA, "GDP growth, constant 2010 USD", "GDP growth, constant 2010 USD", 
"GDP growth, constant 2010 USD", "GDP growth, constant 2010 USD", 
"GDP growth, constant 2010 USD", NA, NA, NA, NA, NA, NA, NA, 
NA), Series.Code = c(NA, NA, NA, NA, NA, NA, NA, "NYGDPMKTPKDZ", 
"NYGDPMKTPKDZ", "NYGDPMKTPKDZ", "NYGDPMKTPKDZ", "NYGDPMKTPKDZ", 
NA, NA, NA, NA, NA, NA, NA, NA), Country.Code = c(NA, NA, NA, 
NA, NA, NA, NA, "AFG", "AFG", "AFG", "AFG", "AFG", NA, NA, NA, 
NA, NA, NA, NA, NA), gdp.y = c(NA, NA, NA, NA, NA, NA, NA, 2.7, 
1.8, 2.9, -5.5, 1, NA, NA, NA, NA, NA, NA, NA, NA)), row.names = c(NA, 
-20L), groups = structure(list(Country = "Afghanistan", .rows = structure(list(
1:20), ptype = integer(0), class = c("vctrs_list_of", "vctrs_vctr", 
"list"))), row.names = 1L, class = c("tbl_df", "tbl", "data.frame"
), .drop = TRUE), class = c("grouped_df", "tbl_df", "tbl", "data.frame"
))

Answer 1

• 不要混合使用dplyr和基本R语法。

• mutate_at已被取代，您现在可以使用across。

library(dplyr)
ssp %>% 
group_by(year) %>%
mutate(across(c(population, gdp.x), ~if(first(year) %in% 2010:2020) 
na.approx(., method="linear") else .)) -> result
result

Answer 2

我设法解决了这个问题：

我使用对整个数据帧进行了总体插值

mutate_at(vars(population), na.approx, method="linear")

对于gdp，我只想对特定年份进行插值，我使用了case_when:

ssp<-ssp%>%mutate(gdp = case_when(Year>=2010 & Year<=2020 ~ na.approx(gdp)))