R: merge based on multiple conditions (with non-equal criteria)

Question

I would like to merge 2 data frames based on multiple conditions.

DF1 <- data.frame(\"col1\" = rep(c(\"A\",\"B\"), 18),
                  \"col2\" = rep(c         


        

Answer 1

With the recent versions of data.table, non-equi joins and update on join are possible:

library(data.table)
head(setDT(DF1)[setDT(DF2), on = c("col1", "col2", "value>=min", "value<=max"), 
                data := data])

   rn col1 col2 value col4 data
1:  1    A    C    22   NA    1
2:  2    B    D    58   NA   NA
3:  3    A    E    35   NA   NA
4:  4    B    C    86   NA   NA
5:  5    A    D    37   NA    3
6:  6    B    E    16   NA   NA

Data

DF1 <- structure(list(rn = 1:36, col1 = c("A", "B", "A", "B", "A", "B", 
"A", "B", "A", "B", "A", "B", "A", "B", "A", "B", "A", "B", "A", 
"B", "A", "B", "A", "B", "A", "B", "A", "B", "A", "B", "A", "B", 
"A", "B", "A", "B"), col2 = c("C", "D", "E", "C", "D", "E", "C", 
"D", "E", "C", "D", "E", "C", "D", "E", "C", "D", "E", "C", "D", 
"E", "C", "D", "E", "C", "D", "E", "C", "D", "E", "C", "D", "E", 
"C", "D", "E"), value = c(22L, 58L, 35L, 86L, 37L, 16L, 46L, 
23L, 88L, 3L, 33L, 25L, 19L, 24L, 9L, 76L, 62L, 68L, 97L, 43L, 
8L, 84L, 36L, 20L, 57L, 99L, 42L, 64L, 87L, 1L, 78L, 34L, 41L, 
32L, 10L, 72L), col4 = c(NA, NA, NA, NA, NA, NA, NA, NA, NA, 
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, 
NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA)), .Names = c("rn", 
"col1", "col2", "value", "col4"), row.names = c(NA, -36L), class = "data.frame")
DF2 <- structure(list(rn = 1:6, col1 = c("A", "A", "A", "A", "A", "A"
), col2 = c("C", "D", "C", "D", "C", "D"), data = c(1L, 3L, 1L, 
3L, 1L, 3L), min = c(0L, 10L, 20L, 30L, 40L, 50L), max = c(10L, 
20L, 30L, 40L, 50L, 60L)), .Names = c("rn", "col1", "col2", "data", 
"min", "max"), row.names = c(NA, -6L), class = "data.frame")

Answer 2

Your data, changing stringsAsFactors=F

DF1 <- data.frame("col1" = rep(c("A","B"), 18),
              "col2" = rep(c("C","D","E"), 12),
              "value"= (sample(1:100,36)),
              "col4" = rep(NA,36),
              stringsAsFactors=F)

DF2 <- data.frame("col1" = rep("A",6),
              "col2" = rep(c("C","D"),3),
              "data" = rep(c(1,3),3),
              "min" = seq(0,59,by=10),
              "max" = seq(10,69,by=10),
              stringsAsFactors=F)

Using dplyr, 1) merge the two data using left_join, 2) check ifelse value is between min and max rowwise, then 3) unselect min and max columns...

library(dplyr)
left_join(DF1, DF2, by=c("col1","col2")) %>%
  rowwise() %>%
  mutate(data = ifelse(between(value,min,max), data, NA)) %>%
  select(-min, -max)

Not sure if you were expecting to perform some kind of aggregation, but here's the output of the above code

    col1  col2 value  col4  data
 1     A     C    23    NA    NA
 2     A     C    23    NA     1
 3     A     C    23    NA    NA
 4     B     D    59    NA    NA
 5     A     E    57    NA    NA
 6     B     C     8    NA    NA

Answer 3

You can do it in two steps:

final <- merge(DF1,DF2,by=c("col1","col2"),all.x = T)
final$data <- ifelse(final$data>=final$min & final$data<=final$max,final$data,"NULL")

Answer 4

Using my package safejoin which wraps fuzzyjoin functions, you can do :

# devtools::install_github("moodymudskipper/safejoin")
library(safejoin)
debugonce(safe_left_join)

safe_left_join(DF1, DF2,  ~
                  X("col1") == Y("col1") & 
                  X("col2") == Y("col2") & 
                  X("value") >= Y("min") &
                  X("value") <= Y("max"),
               conflict = ~.x) %>% 
  head(15)
#    col1 col2 value col4 data min max
# 1     A    C    90   NA   NA  NA  NA
# 2     B    D    20   NA   NA  NA  NA
# 3     A    E     8   NA   NA  NA  NA
# 4     B    C    99   NA   NA  NA  NA
# 5     A    D    42   NA   NA  NA  NA
# 6     B    E    37   NA   NA  NA  NA
# 7     A    C    47   NA    1  40  50
# 8     B    D    61   NA   NA  NA  NA
# 9     A    E    55   NA   NA  NA  NA
# 10    B    C    11   NA   NA  NA  NA
# 11    A    D    81   NA   NA  NA  NA
# 12    B    E    48   NA   NA  NA  NA
# 13    A    C    77   NA   NA  NA  NA
# 14    B    D    58   NA   NA  NA  NA
# 15    A    E     3   NA   NA  NA  NA

The conflict argument here tells the function to return only the conflicted columns from the lhs (col1 and col2).

Answer 5

By using all.x=TRUE all rows of DF1 are kept then adjust condition in filter as follows:

iMed=merge(DF1,DF2,by.x=c('col1','col2'),by.y=c('col1','col2'),all.x=TRUE)
Res=iMed[is.na(iMed[,'min'])|is.na(iMed[,'max'])|(iMed[,'value']<=iMed[,'max'] & iMed[,'value']>=iMed[,'min'] ),]