Subset dataframe based on Values in second dataframe - r

Question

I have one dataframe, df, that has two columns as such:
> head(df1[,c(10,11)])
ColA ColB
1 12 20
2 7 5
3 32 38
4 37 46
5 15 15
6 4 4
I have a second dataframe, also with 2 columns with matching names. Instead, there are only two numbers, as such:
> head(df2)
ColA ColB
1 50 30
I want to subset values from df1 based on the value in the corresponding column from df2 . Doing this manually would look like this:
colA_vector <- df1[df1$colA < 50,]
colB_vector <- df1[df1$ColB < 30,]
How can I do so in a more general purpose way? I do not want to hardcode anything. The column name "ColA" or "ColB" could be anything (so solutions requiring those column names won't really work).
Thank you.

Answer 1

In base R we could do:
nms <- intersect(names(df1), names(df2))
df1[do.call(`&`, Map(`<`, df1[nms], df2[nms])),]
# ColA ColB
# 1 12 20
# 2 7 5
# 5 15 15
# 6 4 4
Or just df1[do.call('&', Map('<', df1, df2)),] if both data.frames have the same order of columns and same names.
Using the package fuzzyjoin might be more readable however:
library(fuzzy_join)
fuzzy_semi_join(df1, df2, match_fun = `<`)
# ColA ColB
# 1 12 20
# 2 7 5
# 5 15 15
# 6 4 4
data
df1 <- read.table(text="
ColA ColB
1 12 20
2 7 5
3 32 38
4 37 46
5 15 15
6 4 4",h=T,strin=F)
df2 <- read.table(text="ColA ColB
1 50 30",h=T,strin=F)

Answer 2

Create a function if we want to do the same task repeatedly
f1 <- function(dat1, dat2, colName) {
dat1[dat1[[colName]] < dat2[[colName]],]
}
f1(df1, df2, "ColA")
# ColA ColB
#1 12 20
#2 7 5
#3 32 38
#4 37 46
#5 15 15
#6 4 4
f1(df1, df2, "ColB")
# ColA ColB
#1 12 20
#2 7 5
#5 15 15
#6 4 4
data
df1 <- structure(list(ColA = c(12L, 7L, 32L, 37L, 15L, 4L), ColB = c(20L,
5L, 38L, 46L, 15L, 4L)), class = "data.frame", row.names = c(NA,
-6L))
df2 <- structure(list(ColA = 50L, ColB = 30L),
class = "data.frame", row.names = "1")

Answer 3

Using dplyr:
df1 %>%
filter(df1[,1] < df2[,1])
ColA ColB
1 12 20
2 7 5
3 32 38
4 37 46
5 15 15
6 4 4
df1 %>%
filter(df1[,2] < df2[,2])
ColA ColB
1 12 20
2 7 5
3 15 15
4 4 4
Subsetting based on both columns simultaneously:
df1 %>%
filter(df1[,1] < df2[,1] & df1[,2] < df2[,2])
ColA ColB
1 12 20
2 7 5
3 15 15
4 4 4

Answer 4

If you don't want to use the fuzzyjoin join package or make your own function, you can just repeat the second dataframe.
df1 <- data.frame("ColA" = c(12, 7, 32),
"ColB" = c(20, 5, 38))
df2 <- data.frame("ColA" = 50,
"ColB" = 30)
n <- nrow(df1)
df2_new <- do.call("rbind", replicate(n, df2, simplify = FALSE))
df1_which <- as.data.frame(df1 < df2_new)
colA_vector <- df1[df1_which$ColA, "ColA"]
colB_vector <- df1[df1_which$ColB, "ColB"]

Answer 5

You can try a tidyverse funtion. Result is a list of the filtered data.frames.
foo <- function(x, y, ColA, ColB){
require(tidyverse)
var1 <- quo_name(ColA)
var2 <- quo_name(ColB)
x %>%
select(a=!!var1, b=!!var2) %>%
mutate(colA_vector= a < y[[ColA]]) %>%
mutate(colB_vector= b < y[[ColB]]) %>%
gather(k, v, -a, -b) %>%
filter(v) %>%
split(.$k) %>%
map(~select(.,-v,-k))
}
foo(df1, df2, "ColA", "ColB")
$colA_vector
a b
1 12 20
2 7 5
3 32 38
4 37 46
5 15 15
6 4 4
$colB_vector
a b
7 12 20
8 7 5
9 15 15
10 4 4