我有以下数据框列表:
a<-data.frame(
Data0=c("Y","Y","Y","Y","Y","Y","N","N","N","N","N","N"),
Data1=c(16,18,19,20,21,50,16,18,19,20,21,50),
Data2=c(2.2291,2.0743,1.9369,1.8148,1.7064,1.6102,2.2291,2.0743,1.9369,1.8148,1.7064,1.6102)
)
b<-data.frame(
Data0=c(-2 , 0 , 1 , 2 , 3 , 4 , 5 , 6 , 7 , 8 , 9 ,10 ,11) ,
Data1=c(0.8891 ,0.8891,0.9051,1,0.8891,0.8891,0.7907,0.8891,0.9929,0.8891,0.8891,0.8891,0.8891)
)
dfl<-list(a,b)
我想为列表中的每个数据帧创建一个函数,该函数返回最后一列中的数字,用于前面列中的匹配变量。
对于 a ,如果我发送&#34; Y&#34; 16,我想要2.2291和 b ,如果我发送5我想要0.7907。 a 的问题在于,如果我发送一个小于16的数字,对于&#34; Y&#34;或&#34; N&#34;,我希望它返回值,就像它是16,而不操纵输入变量。我设法为 b 执行此操作,但对于 a ,我有一个&#34; split&#34;介于&#34; Y&#34;和&#34; N&#34;,我不知道如何解决这个问题。
到目前为止:
get_value<-function(vector){
if (length(vector)==1) {
from<-append(head(unlist(dfl[[2]][1],use.names=FALSE),-1),-9999,0)
to <-unlist(dfl[[2]][1],use.names=FALSE)
match_from<-vector > from
match_to<-vector <=to
pos<-which(match_from==match_to)
return(unlist(dfl[[2]][pos,2]))
}
else{
print("not sure what to do for a")
}
}
get_value(4)
get_value(-44)
解决方案需要考虑到有时候对于 a ,Data0和Data1列已经切换了位置。
修改: 输入/输出表:
INPUT OUTPUT
c("Y",13) --> 2.2291
c("Y",50) --> 1.6102
c("N",20) --> 1.8148
c("N",50) --> 1.6102
c(-44)) --> 0.8891
答案 0 :(得分:1)
好的,我终于找到了办法,但它并不那么优雅,所以请帮助。
get_value<-function(vector){
if (length(vector)==1) {
from<-append(head(unlist(dfl[[2]][1],use.names=FALSE),-1),-9999,0)
to <-unlist(dfl[[2]][1],use.names=FALSE)
match_from<-vector > from
match_to<-vector <= to
pos<-which(match_from==match_to)
return(unlist(dfl[[2]][pos,2]))
}
else{
pos_1<-which(unlist(dfl[[1]][1],use.names=FALSE)==vector[1])
from<-append(head(as.numeric(unlist(dfl[[1]][2],use.names=FALSE))[pos_1],-1),-9999,0)
to <-as.numeric(unlist(dfl[[1]][2],use.names=FALSE))[pos_1]
match_from<-as.numeric(vector[2]) > from
match_to <-as.numeric(vector[2]) <=to
pos<-pos_1[match_from == match_to]
return(unlist(dfl[[1]][pos,3]))
}
}
答案 1 :(得分:1)
使用tidyverse
函数的替代方法如下:
library(tidyverse)
library(magrittr)
get_value<-function(vector){
if (length(vector)==1)
{ df <- dfl[[2]]
k <- df %>%
arrange(Data0)%>%
filter(Data0 >= vector) %>%
select(Data1) %>%
head(1)
}
else
{df <- dfl[[1]]
k <- df %>%
arrange(Data0)%>%
filter(Data0 == vector[1]) %>%
filter(Data1 >= vector[2]) %>%
select(Data2) %>%
head(1)
}
return(k)
}
并测试一些输出:
> get_value(c(-44))
Data1
1 0.8891
> get_value(c('N',16))
Data2
1 2.2291
> get_value(c('Y',16))
Data2
1 2.2291
> get_value(c('N',12))
Data2
1 2.2291
> get_value(c('Y',11))
Data2
1 2.2291
> get_value(c('Y',18))
Data2
1 2.0743