Update/Replace Values in Dataframe with Tidyverse Join
Picking up Alistaire's and Nettle's suggestions and transforming into a working solution
df1 %>%
left_join(lookup_df, by = "state_abbrev") %>%
mutate(state_name = coalesce(state_name.x, state_name.y)) %>%
select(-state_name.x, -state_name.y)
# A tibble: 10 x 3 state_abbrev value state_name <chr> <int> <chr> 1 AL 671 Alabama 2 AK 501 Alaska 3 AZ 1030 Arizona 4 AR 694 Arkansas 5 CA 881 California 6 CO 821 Colorado 7 CT 742 Connecticut 8 DE 665 Delaware 9 FL 948 Florida 10 GA 790 Georgia
The OP has stated to prefer a "tidyverse" solution. However, update joins are already available with the data.table
package:
library(data.table)
setDT(df1)[setDT(lookup_df), on = "state_abbrev", state_name := i.state_name]
df1
state_abbrev state_name value 1: AL Alabama 1103 2: AK Alaska 1036 3: AZ Arizona 811 4: AR Arkansas 604 5: CA California 868 6: CO Colorado 1129 7: CT Connecticut 819 8: DE Delaware 1194 9: FL Florida 888 10: GA Georgia 501
Benchmark
library(bench)
bm <- press(
na_share = c(0.1, 0.5, 0.9),
n_row = length(state.abb) * 2 * c(1, 100, 10000),
{
n_na <- na_share * length(state.abb)
set.seed(1)
na_idx <- sample(length(state.abb), n_na)
tmp <- data.table(state_abbrev = state.abb, state_name = state.name)
lookup_df <-tmp[na_idx]
tmp[na_idx, state_name := NA]
df0 <- as_tibble(tmp[sample(length(state.abb), n_row, TRUE)])
mark(
dplyr = {
df1 <- copy(df0)
df1 <- df1 %>%
left_join(lookup_df, by = "state_abbrev") %>%
mutate(state_name = coalesce(state_name.x, state_name.y)) %>%
select(-state_name.x, -state_name.y)
df1
},
upd_join = {
df1 <- copy(df0)
setDT(df1)[setDT(lookup_df), on = "state_abbrev", state_name := i.state_name]
df1
}
)
}
)
ggplot2::autoplot(bm)
data.table
's upate join is always faster (note the log time scale).
As the update join modifies the data object, a fresh copy is used for each benchmark run.
There's currently no one-shot for trying to coalesce more than one column (which can be done by using a lookup table approach within ifelse(is.na(value), ..., value)
), though there has been discussion of how such behavior may be implemented. For now, you can build it manually. If you've got a lot of columns, you can coalesce
programmatically, or even put it in a function.
library(tidyverse)
df1 <- tibble(
state_abbrev = state.abb[1:10],
state_name = c(state.name[1:5], rep(NA, 3), state.name[9:10]),
value = sample(500:1200, 10, replace=TRUE)
)
lookup_df <- tibble(
state_abbrev = state.abb[6:8],
state_name = state.name[6:8]
)
df1 %>%
full_join(lookup_df, by = 'state_abbrev') %>%
bind_cols(map_dfc(grep('.x', names(.), value = TRUE), function(x){
set_names(
list(coalesce(.[[x]], .[[gsub('.x', '.y', x)]])),
gsub('.x', '', x)
)
})) %>%
select(union(names(df1), names(lookup_df)))
#> # A tibble: 10 x 3
#> state_abbrev state_name value
#> <chr> <chr> <int>
#> 1 AL Alabama 877
#> 2 AK Alaska 1048
#> 3 AZ Arizona 973
#> 4 AR Arkansas 860
#> 5 CA California 938
#> 6 CO Colorado 639
#> 7 CT Connecticut 547
#> 8 DE Delaware 672
#> 9 FL Florida 667
#> 10 GA Georgia 1142
Here is a single line solution with rows_update()
:
df1 %>%
rows_update(lookup_df, by = "state_abbrev")
Demo:
library(dplyr)
### Main Dataframe ###
df1 <- tibble(
state_abbrev = state.abb[1:10],
state_name = c(state.name[1:5], rep(NA, 3), state.name[9:10]),
value = sample(500:1200, 10, replace=TRUE)
)
### Lookup Dataframe ###
lookup_df <- tibble(
state_abbrev = state.abb[6:8],
state_name = state.name[6:8]
)
df1 %>%
rows_update(lookup_df, by = "state_abbrev")
#> # A tibble: 10 x 3
#> state_abbrev state_name value
#> <chr> <chr> <int>
#> 1 AL Alabama 532
#> 2 AK Alaska 640
#> 3 AZ Arizona 521
#> 4 AR Arkansas 523
#> 5 CA California 970
#> 6 CO Colorado 695
#> 7 CT Connecticut 504
#> 8 DE Delaware 1088
#> 9 FL Florida 979
#> 10 GA Georgia 1059
in order to preserve the column order:
df1 %>%
left_join(lookup_df, by = "state_abbrev") %>%
mutate(state_name.x = coalesce(state_name.x, state_name.y)) %>%
rename(state_name = state_name.x) %>%
select(-state_name.y)