问题
I have a bunch of data frames with different variables. I want to read them into R and add columns to those that are short of a few variables so that they all have a common set of standard variables, even if some are unobserved.
In other words... Is there a way to add columns of NA in the tidyverse when a column does not exist? My current attempt works for adding new variables where the column doesn't exist (top_speed) but fails when the column already exists (mpg) (it sets all observations to the first value, Mazda RX4).
library(tidyverse)
mtcars %>%
tbl_df() %>%
rownames_to_column("car") %>%
mutate(top_speed = ifelse("top_speed" %in% names(.), top_speed, NA),
mpg = ifelse("mpg" %in% names(.), mpg, NA)) %>%
select(car, top_speed, mpg, everything())
# # A tibble: 32 x 13
# car top_speed mpg cyl disp hp drat wt qsec vs am gear carb
# <chr> <lgl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
# 1 Mazda RX4 NA 21 6 160.0 110 3.90 2.620 16.46 0 1 4 4
# 2 Mazda RX4 Wag NA 21 6 160.0 110 3.90 2.875 17.02 0 1 4 4
# 3 Datsun 710 NA 21 4 108.0 93 3.85 2.320 18.61 1 1 4 1
# 4 Hornet 4 Drive NA 21 6 258.0 110 3.08 3.215 19.44 1 0 3 1
# 5 Hornet Sportabout NA 21 8 360.0 175 3.15 3.440 17.02 0 0 3 2
# 6 Valiant NA 21 6 225.0 105 2.76 3.460 20.22 1 0 3 1
# 7 Duster 360 NA 21 8 360.0 245 3.21 3.570 15.84 0 0 3 4
# 8 Merc 240D NA 21 4 146.7 62 3.69 3.190 20.00 1 0 4 2
# 9 Merc 230 NA 21 4 140.8 95 3.92 3.150 22.90 1 0 4 2
# 10 Merc 280 NA 21 6 167.6 123 3.92 3.440 18.30 1 0 4 4
回答1:
Another option that does not require creating a helper function (or an already complete data.frame) using tibble's add_column:
library(tibble)
cols <- c(top_speed = NA_real_, nhj = NA_real_, mpg = NA_real_)
add_column(mtcars, !!!cols[setdiff(names(cols), names(mtcars))])
回答2:
We could create a helper function to create the column
fncols <- function(data, cname) {
add <-cname[!cname%in%names(data)]
if(length(add)!=0) data[add] <- NA
data
}
fncols(mtcars, "mpg")
fncols(mtcars, c("topspeed","nhj","mpg"))
回答3:
Try the following,
library(tidyverse)
mtcars %>%
tbl_df() %>%
rownames_to_column("car") %>%
mutate(top_speed = if ("top_speed" %in% names(.)){return(top_speed)}else{return(NA)},
mpg = if ("mpg" %in% names(.)){return(mpg)}else{return(NA)}) %>%
select(car, top_speed, mpg, everything())
# A tibble: 32 x 13
car top_speed mpg cyl disp hp drat wt qsec vs am gear carb
<chr> <lgl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 Mazda RX4 NA 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4
2 Mazda RX4 Wag NA 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4
3 Datsun 710 NA 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1
4 Hornet 4 Drive NA 21.4 6 258.0 110 3.08 3.215 19.44 1 0 3 1
5 Hornet Sportabout NA 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2
6 Valiant NA 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1
7 Duster 360 NA 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4
8 Merc 240D NA 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2
9 Merc 230 NA 22.8 4 140.8 95 3.92 3.150 22.90 1 0 4 2
10 Merc 280 NA 19.2 6 167.6 123 3.92 3.440 18.30 1 0 4 4
# ... with 22 more rows
I think the ifelse() doesn't inherit the class from the object.
回答4:
If you had an empty dataframe that contains all the names to check for, you can use bind_rows to add columns.
I used purrr:map_dfr to make the empty tibble with the appropriate column names.
columns = c("top_speed", "mpg") %>%
map_dfr( ~tibble(!!.x := logical() ) )
# A tibble: 0 x 2
# ... with 2 variables: top_speed <lgl>, mpg <lgl>
bind_rows(columns, mtcars)
# A tibble: 32 x 12
top_speed mpg cyl disp hp drat wt qsec vs am gear carb
<lgl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 NA 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4
2 NA 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4
3 NA 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1
回答5:
You can use the rowwise function like this :
library(tidyverse)
mtcars %>%
tbl_df() %>%
rownames_to_column("car") %>%
rowwise() %>%
mutate(top_speed = ifelse("top_speed" %in% names(.), top_speed, NA),
mpg = ifelse("mpg" %in% names(.), mpg, NA)) %>%
select(car, top_speed, mpg, everything())
回答6:
You can bind columns of the new data.frame with a fake complete data.frame filled with NA, rename the duplicated columns, and then filter only the original names.
# your default complete vector of col names
standard.variables = names(mtcars)
# prep
default=mtcars %>% mutate_all(.funs=function(x) NA)
# treat with a data.frame missing 3 columns
test=mtcars %>% select(-mpg, -disp, -am)
bind_cols(test, default) %>% setNames(make.names(names(.), unique=TRUE)) %>%
select_(.dots=standard.variables) %>% head(2)
#### mpg cyl disp hp drat wt qsec vs am gear carb
#### 1 NA 6 NA 110 3.9 2.620 16.46 0 NA 4 4
#### 2 NA 6 NA 110 3.9 2.875 17.02 0 NA 4 4
回答7:
If you already have a dataframe with all the required columns, say
library(tidyverse)
df_with_required_columns =
mtcars %>%
mutate(top_speed = NA_real_) %>%
select(top_speed, mpg)
then you can simply bind_rows filtering out all the rows:
mtcars %>%
rownames_to_column("car") %>%
bind_rows( df_with_required_columns %>% filter(F) ) %>%
select(car, top_speed, mpg, everything())
Note that missing columns will take the type from df_with_required_columns.
来源：https://stackoverflow.com/questions/45857787/adding-column-if-it-does-not-exist