structuring JSON data in R - r

I'm new to JSON data and am having a bit of trouble trying to get my data into a combined data frame common to data frames in R. Here is an example of the JSON data:
{
"id": "rub_al_khali",
"conversion_px": 0.0395882818685669,
"n_surfaces": 4,
"lithic_contours": [
{
"surface_id": 0,
"classification": "Ventral",
"total_area_px": 530565.5,
"total_area": 831.5,
"max_breadth": 22.4,
"max_length": 54,
"polygon_count": 7,
"scar_count": 0,
"percentage_detected_scars": 0,
"scar_contours": []
},
{
"surface_id": 1,
"classification": "Dorsal",
"total_area_px": 530503.5,
"total_area": 831.4,
"max_breadth": 22.4,
"max_length": 54,
"polygon_count": 7,
"scar_count": 4,
"percentage_detected_scars": 0.62,
"scar_contours": [
{
"scar_id": 0,
"total_area_px": 129337,
"total_area": 202.7,
"max_breadth": 10.3,
"max_length": 41.7,
"percentage_of_surface": 0.24,
"scar_angle": 1.85,
"polygon_count": 5
},
{
"scar_id": 1,
"total_area_px": 100130,
"total_area": 156.9,
"max_breadth": 7.2,
"max_length": 43,
"percentage_of_surface": 0.19,
"scar_angle": 357.36,
"polygon_count": 4
},
{
"scar_id": 2,
"total_area_px": 93162,
"total_area": 146,
"max_breadth": 6.5,
"max_length": 41.4,
"percentage_of_surface": 0.18,
"scar_angle": 5.01,
"polygon_count": 4
},
{
"scar_id": 3,
"total_area_px": 6148.5,
"total_area": 9.6,
"max_breadth": 4,
"max_length": 7.1,
"percentage_of_surface": 0.01,
"scar_angle": "NaN",
"polygon_count": 9
}
]
},
{
"surface_id": 2,
"classification": "Lateral",
"total_area_px": 176204,
"total_area": 276.2,
"max_breadth": 8.6,
"max_length": 54.2,
"polygon_count": 3,
"scar_count": 2,
"percentage_detected_scars": 0.33,
"scar_contours": [
{
"scar_id": 0,
"total_area_px": 44605,
"total_area": 69.9,
"max_breadth": 5,
"max_length": 50,
"percentage_of_surface": 0.25,
"scar_angle": "NaN",
"polygon_count": 3
},
{
"scar_id": 1,
"total_area_px": 12877,
"total_area": 20.2,
"max_breadth": 1.5,
"max_length": 22.3,
"percentage_of_surface": 0.07,
"scar_angle": "NaN",
"polygon_count": 2
}
]
},
{
"surface_id": 3,
"classification": "Platform",
"total_area_px": 55252.5,
"total_area": 86.6,
"max_breadth": 20.3,
"max_length": 6.6,
"polygon_count": 5,
"scar_count": 1,
"percentage_detected_scars": 0.42,
"scar_contours": [
{
"scar_id": 0,
"total_area_px": 23298.5,
"total_area": 36.5,
"max_breadth": 15,
"max_length": 4.1,
"percentage_of_surface": 0.42,
"scar_angle": "NaN",
"polygon_count": 4
}
]
}
]
}
So far I've used jsonlite to import to R using flatten = TRUE
library(jsonlite)
dta <- fromJSON("~/rub_al_khali.json", flatten = TRUE)
and while this gets me half way there it's not really a combined/comprehensive data.frame. I think that it might be the dta$lithic_contours that is creating the issue. Any help is much appreciated


jsonlite::fromJSON() returns a list, but the element lithic_contours contains a data.frame. Just subset the list to get your data.frame:
# Subset the list on lithic_contours with $ ...
df <- jsonlite::fromJSON(<file>, flatten = TRUE)$lithic_contours
# ... and it's already a data.frame
class(df)
#> [1] "data.frame"
# Turning into a tibble for better printing
tibble::as_tibble(df)
#> # A tibble: 4 × 10
#> surface_id classification total_area_px total_area max_breadth max_length
#> <int> <chr> <dbl> <dbl> <dbl> <dbl>
#> 1 0 Ventral 530566. 832. 22.4 54
#> 2 1 Dorsal 530504. 831. 22.4 54
#> 3 2 Lateral 176204 276. 8.6 54.2
#> 4 3 Platform 55252. 86.6 20.3 6.6
#> # … with 4 more variables: polygon_count <int>, scar_count <int>,
#> # percentage_detected_scars <dbl>, scar_contours <list>
Created on 2022-04-04 by the reprex package (v2.0.1)
Update: unnesting list column
The scar_contours column of your dataframe is a list column. This is actually often a quite convenient format for analysis, but if you want to remove it you can use the function tidyr::unnest():
library(tidyr)
df %>% unnest(scar_contours, names_repair = "minimal")
#> # A tibble: 7 × 17
#> surface_id classification total_area_px total_area max_breadth max_length
#> <int> <chr> <dbl> <dbl> <dbl> <dbl>
#> 1 1 Dorsal 530504. 831. 22.4 54
#> 2 1 Dorsal 530504. 831. 22.4 54
#> 3 1 Dorsal 530504. 831. 22.4 54
#> 4 1 Dorsal 530504. 831. 22.4 54
#> 5 2 Lateral 176204 276. 8.6 54.2
#> 6 2 Lateral 176204 276. 8.6 54.2
#> 7 3 Platform 55252. 86.6 20.3 6.6
#> # … with 11 more variables: polygon_count <int>, scar_count <int>,
#> # percentage_detected_scars <dbl>, scar_id <int>, total_area_px <dbl>,
#> # total_area <dbl>, max_breadth <dbl>, max_length <dbl>,
#> # percentage_of_surface <dbl>, scar_angle <dbl>, polygon_count <int>

Related

Unable to transform variables by user defined transformation function in r

I am trying to transform variables using a user defined function but facing issues in same.
1. sample dataframe:
librar(tidyverse)
df_test <- tribble(
~sales, ~var1, ~var2,
22, 230.1, 37.8,
10, 44.5, 39.3,
9, 17.2, 45.9,
19, 151.5, 41.3,
13, 180.8, 10.8,
7, 8.7, 48.9,
12, 57.5, 32.8,
13, 120.2, 19.6,
5, 8.6, 2.1,
11, 199.8, 2.6)
df_test
2. Tranformation table
# transfm dataframe
df_transfm <- df_test %>%
select(var1,var2)
df_transfm
3. User defined function to transform variable
# function to transform variables
adstock_transfrm <- function(x, df, adstock_rate = .5){
df %>%
mutate(x = if_else(row_number() == 1, x, x * adstock_rate)) %>%
select(x)
}
4. Apply function
df_transfm$var1 <- adstock_transfrm(x = var1,df = df_transfm)
df_transfm
5. Error
Error in `mutate()`:
! Problem while computing `x = if_else(row_number() == 1, x, x * adstock_rate)`.
Caused by error in `if_else()`:
! object 'var1' not found
Backtrace:
1. global adstock_transfrm(x = var1, df = df_transfm)
9. dplyr::if_else(row_number() == 1, x, x * adstock_rate)
Error in mutate(., x = if_else(row_number() == 1, x, x * adstock_rate)) :
Caused by error in `if_else()`:
! object 'var1' not found
6. function2: changed function & applied but getting tibble instead of values:
# function2 to transform variables
adstock_transfrm2 <- function(x, df, adstock_rate = .5){
x = enquo(x)
df %>%
mutate(!!x := if_else(row_number() == 1, !!x, !!x * adstock_rate)) %>%
select(!!x)
}
df_transfm$var1 <- adstock_transfrm2(x = var1,df = df_transfm)
df_transfm
var1
<tibble>
var2
<dbl>
<tibble> 37.8
<tibble> 39.3
<tibble> 45.9
<tibble> 41.3
<tibble> 10.8
<tibble> 48.9
<tibble> 32.8
<tibble> 19.6
<tibble> 2.1
<tibble> 2.6
Any help is much appreciated.

Try pull() instead of select
library(dplyr)
df_test <- tribble(
~sales, ~var1, ~var2,
22, 230.1, 37.8,
10, 44.5, 39.3,
9, 17.2, 45.9,
19, 151.5, 41.3,
13, 180.8, 10.8,
7, 8.7, 48.9,
12, 57.5, 32.8,
13, 120.2, 19.6,
5, 8.6, 2.1,
11, 199.8, 2.6)
# transfm dataframe
df_transfm <- df_test %>%
select(var1,var2)
adstock_transfrm2 <- function(x, df, adstock_rate = .5){
x = enquo(x)
df %>%
mutate(!!x := if_else(row_number() == 1, !!x, !!x * adstock_rate)) %>%
pull(!!x)
}
df_transfm$var1 <- adstock_transfrm2(x = var1,df = df_transfm)
df_transfm
#> # A tibble: 10 × 2
#> var1 var2
#> <dbl> <dbl>
#> 1 230. 37.8
#> 2 22.2 39.3
#> 3 8.6 45.9
#> 4 75.8 41.3
#> 5 90.4 10.8
#> 6 4.35 48.9
#> 7 28.8 32.8
#> 8 60.1 19.6
#> 9 4.3 2.1
#> 10 99.9 2.6

Finding distance between a row and the row two above it in R

I would like to efficiently compute distances between every row in a matrix and the row two rows above it in R...
My attempts at finding a dplyr rowwise solution with lag(., n = 2) have failed, and I'm sure there's a better solution than this for loop.
Thoughts are much appreciated!
library(rdist)
library(tidyverse)
structure(list(sodium = c(140, 152.6, 138, 152.4, 140, 152.6,
141, 152.7, 141, 152.7), chloride = c(103, 148.9, 104, 149, 102,
148.8, 103, 148.9, 104, 149), potassium_plas = c(3.4, 0.34, 4.1,
0.41, 3.7, 0.37, 4, 0.4, 3.7, 0.37), co2_totl = c(31, 3.1, 22,
2.2, 23, 2.3, 27, 2.7, 20, 2), bun = c(11, 1.1, 5, 0.5, 8, 0.8,
21, 2.1, 10, 1), creatinine = c(0.84, 0.084, 0.53, 0.053, 0.69,
0.069, 1.04, 0.104, 1.86, 0.186), calcium = c(9.3, 0.93, 9.8,
0.98, 9.4, 0.94, 9.4, 0.94, 9.1, 0.91), glucose = c(102, 10.2,
99, 9.9, 115, 11.5, 94, 9.4, 122, 12.2), anion_gap = c(6, 0.599999999999989,
12, 1.20000000000001, 15, 1.50000000000001, 11, 1.09999999999998,
17, 1.69999999999999)), row.names = c(NA, -10L), class = c("tbl_df",
"tbl", "data.frame"))
dist_prior <- rep(NA, n = nrow(input_labs))
for(i in 3:nrow(input_labs)){
dist_prior[i] <- cdist(input_labs[i,], input_labs[i-2,])
}

We could loop over the sequence of rows in map and apply the function, append NAs at the beginning to make the length correct
library(dplyr)
library(rdist)
library(purrr)
input_labs %>%
mutate(dist_prior = c(NA_real_, NA_real_,
map_dbl(3:n(), ~ cdist(cur_data()[.x,], cur_data()[.x-2, ]))))
-output
# A tibble: 10 × 10
sodium chloride potassium_plas co2_totl bun creatinine calcium glucose anion_gap dist_prior
<dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
1 140 103 3.4 31 11 0.84 9.3 102 6 NA
2 153. 149. 0.34 3.1 1.1 0.084 0.93 10.2 0.600 NA
3 138 104 4.1 22 5 0.53 9.8 99 12 13.0
4 152. 149 0.41 2.2 0.5 0.053 0.98 9.9 1.20 1.30
5 140 102 3.7 23 8 0.69 9.4 115 15 16.8
6 153. 149. 0.37 2.3 0.8 0.069 0.94 11.5 1.50 1.68
7 141 103 4 27 21 1.04 9.4 94 11 25.4
8 153. 149. 0.4 2.7 2.1 0.104 0.94 9.4 1.10 2.54
9 141 104 3.7 20 10 1.86 9.1 122 17 31.5
10 153. 149 0.37 2 1 0.186 0.91 12.2 1.70 3.15
Or may split by row on the original data and the laged one and use map2 to loop over the list and apply
input_labs$dist_prior <- map2_dbl(
asplit(lag(input_labs, n = 2), 1),
asplit(input_labs, 1),
~ cdist(as.data.frame.list(.x), as.data.frame.list(.y))[,1])

in Base R you can use diff and rowSums as shown below:
c(NA, NA, sqrt(rowSums(diff(as.matrix(input_labs), 2)^2)))
[1] NA NA 12.955157 1.295516 16.832873 1.683287 25.381342 2.538134 31.493688 3.149369
You can cbind the results to the original dataframe.

Removing blank rows in the two data frames and combine them

I have a dataset which contains two groups. First 3 columns are 1st group and next 3 columns are 2nd group. They contains missing values at random manner.
I have to delete the rows containing complete missing values in any one group. And both group contains at least one value in the row.
At last I have to combine both the groups.
I have tried many R codes. Please suggest some useful R function for this issue.
example data structure

If your data is properly named, this can be done using starts_with and if_any (otherwise you might rename your columns first as you see fit)
library(tidyverse)
df <- tribble(
~x1, ~x2, ~x3, ~y1, ~y2, ~y3,
26.4, 26.5, 26.6, 26.7, 26.4, 26.5,
NA, NA, NA, 23.7, NA, NA,
27.2, 28.0, 27.9, 27.6, 27.8, 27.7,
NA, 24.2, 24.9, 23.9, 24.9, 24.0,
24.3, NA, 24.3, 24.0, 24.1, 24.5,
26.9, 26.7, 27.0, 26.9, 26.8, 26.8,
24.4, 24.4, 24.5, 24.8, 24.3, 24.3,
NA, NA, NA, 23.9, NA, NA,
NA, NA, NA, 23.9, NA, NA,
24.9, NA, NA, 24.9, NA, NA,
NA, NA, NA, 24.5, NA, NA,
28.3, 28.2, 28.3, 28.2, 28.4, 28.3,
28.3, 28.4, 28.1, 28.3, 28.3, 28.2
)
df %>% filter(!if_all(starts_with("x"), is.na) & !if_all(starts_with("y"), is.na))
#> # A tibble: 9 × 6
#> x1 x2 x3 y1 y2 y3
#> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 26.4 26.5 26.6 26.7 26.4 26.5
#> 2 27.2 28 27.9 27.6 27.8 27.7
#> 3 NA 24.2 24.9 23.9 24.9 24
#> 4 24.3 NA 24.3 24 24.1 24.5
#> 5 26.9 26.7 27 26.9 26.8 26.8
#> 6 24.4 24.4 24.5 24.8 24.3 24.3
#> 7 24.9 NA NA 24.9 NA NA
#> 8 28.3 28.2 28.3 28.2 28.4 28.3
#> 9 28.3 28.4 28.1 28.3 28.3 28.2
Created on 2022-06-18 by the reprex package (v2.0.1)

I am not sure I understand your question, but here is a demonstration using dplyr::if_all() , dplyr::if_any()
library(tidyverse)
# Example data
# have to delete the rows containing complete missing values in any one group.
# And both group contains at least one value in the row. (Not sure what that means)
# At last I have to combine both the groups.
d <- tibble::tribble(
~gr1_col1, ~gr1_col2, ~gr1_col3, ~gr2_col1, ~gr2_col2, ~gr2_col3,
1, 2, NA, 1, 1, 1,
NA, NA, NA, NA, 1, 1,
NA, 1, 1, NA, NA, 1,
1, NA, 2, NA, NA, NA,
)
d
#> # A tibble: 4 x 6
#> gr1_col1 gr1_col2 gr1_col3 gr2_col1 gr2_col2 gr2_col3
#> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 1 2 NA 1 1 1
#> 2 NA NA NA NA 1 1
#> 3 NA 1 1 NA NA 1
#> 4 1 NA 2 NA NA NA
d %>%
dplyr::filter(
# First group
!dplyr::if_all(.cols = c(1, 2, 3), .fns = is.na), # removing rows if all columns 1, 2 and 3 are NA
# second group
!if_all(.cols = c(4, 5, 6), .fns = is.na) # removing rows if all columns 1, 2 and 3 are NA
)
#> # A tibble: 2 x 6
#> gr1_col1 gr1_col2 gr1_col3 gr2_col1 gr2_col2 gr2_col3
#> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl>
#> 1 1 2 NA 1 1 1
#> 2 NA 1 1 NA NA 1
# Not sure what you mean with how you want to combine groups
Created on 2022-06-17 by the reprex package (v2.0.1)

Mutate across multiple columns based on condition (length of unique values)

I'm trying to create a function inside mutate() + across() that changes into factor any variable which has five or less unique values (or any arbitrary number) wit the idea of using later that factors to do some grouping. I think the logic of the function is correct but I'm getting some incorrect dimensions error (error in Spanish). For the sake of simplicity, I'm using the mtcars database.
mtcars %>%
mutate(across(1:ncol(.),
function(x) {
if_else(length(unique(x[,i]))<=5,
as.factor(x),
x)}
))
Error: Problem with `mutate()` input `..1`.
i `..1 = across(...)`.
x número incorreto de dimensiones
Run `rlang::last_error()` to see where the error occurred.
Any help or advice will be much appreciated.

Here we need if/else as ifelse/if_else requires all arguments to be of equal length. The length(unique expression returns a logical value of length 1 and this may break the condition. Also, with dplyr, we can use select-helpers i.e. everything() to select all the columns
library(dplyr)
out <- mtcars %>%
mutate(across(everything(),
function(x) {
if(length(unique(x))<=5)
as.factor(x) else
x}
))
-output
> str(out)
'data.frame': 32 obs. of 11 variables:
$ mpg : num 21 21 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 ...
$ cyl : Factor w/ 3 levels "4","6","8": 2 2 1 2 3 2 3 1 1 2 ...
$ disp: num 160 160 108 258 360 ...
$ hp : num 110 110 93 110 175 105 245 62 95 123 ...
$ drat: num 3.9 3.9 3.85 3.08 3.15 2.76 3.21 3.69 3.92 3.92 ...
$ wt : num 2.62 2.88 2.32 3.21 3.44 ...
$ qsec: num 16.5 17 18.6 19.4 17 ...
$ vs : Factor w/ 2 levels "0","1": 1 1 2 2 1 2 1 2 2 2 ...
$ am : Factor w/ 2 levels "0","1": 2 2 2 1 1 1 1 1 1 1 ...
$ gear: Factor w/ 3 levels "3","4","5": 2 2 2 1 1 1 1 2 2 2 ...
$ carb: num 4 4 1 1 2 1 4 2 2 4 ...
In addition, the lambda function can be concise with ~ and make use of n_distinct
mtcars %>%
mutate(across(everything(),
~ if(n_distinct(.x) <=5) as.factor(.x) else .x))

Another way would be to use a predicate function in where inside across.
We can either define a custom function:
library(dplyr)
few_unique_vals <- function(x) {
length(unique(x))<=5
}
mtcars %>%
mutate(across(where(few_unique_vals), as.factor)) %>%
glimpse # for better printing
#> Rows: 32
#> Columns: 11
#> $ mpg <dbl> 21.0, 21.0, 22.8, 21.4, 18.7, 18.1, 14.3, 24.4, 22.8, 19.2, 17.8,~
#> $ cyl <fct> 6, 6, 4, 6, 8, 6, 8, 4, 4, 6, 6, 8, 8, 8, 8, 8, 8, 4, 4, 4, 4, 8,~
#> $ disp <dbl> 160.0, 160.0, 108.0, 258.0, 360.0, 225.0, 360.0, 146.7, 140.8, 16~
#> $ hp <dbl> 110, 110, 93, 110, 175, 105, 245, 62, 95, 123, 123, 180, 180, 180~
#> $ drat <dbl> 3.90, 3.90, 3.85, 3.08, 3.15, 2.76, 3.21, 3.69, 3.92, 3.92, 3.92,~
#> $ wt <dbl> 2.620, 2.875, 2.320, 3.215, 3.440, 3.460, 3.570, 3.190, 3.150, 3.~
#> $ qsec <dbl> 16.46, 17.02, 18.61, 19.44, 17.02, 20.22, 15.84, 20.00, 22.90, 18~
#> $ vs <fct> 0, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0,~
#> $ am <fct> 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0,~
#> $ gear <fct> 4, 4, 4, 3, 3, 3, 3, 4, 4, 4, 4, 3, 3, 3, 3, 3, 3, 4, 4, 4, 3, 3,~
#> $ carb <dbl> 4, 4, 1, 1, 2, 1, 4, 2, 2, 4, 4, 3, 3, 3, 4, 4, 4, 1, 2, 1, 1, 2,~
Or we can use an anonymous purrr-style function:
mtcars %>%
mutate(across(where(~ length(unique(.x))<=5),
as.factor)) %>%
glimpse # for better printing
#> Rows: 32
#> Columns: 11
#> $ mpg <dbl> 21.0, 21.0, 22.8, 21.4, 18.7, 18.1, 14.3, 24.4, 22.8, 19.2, 17.8,~
#> $ cyl <fct> 6, 6, 4, 6, 8, 6, 8, 4, 4, 6, 6, 8, 8, 8, 8, 8, 8, 4, 4, 4, 4, 8,~
#> $ disp <dbl> 160.0, 160.0, 108.0, 258.0, 360.0, 225.0, 360.0, 146.7, 140.8, 16~
#> $ hp <dbl> 110, 110, 93, 110, 175, 105, 245, 62, 95, 123, 123, 180, 180, 180~
#> $ drat <dbl> 3.90, 3.90, 3.85, 3.08, 3.15, 2.76, 3.21, 3.69, 3.92, 3.92, 3.92,~
#> $ wt <dbl> 2.620, 2.875, 2.320, 3.215, 3.440, 3.460, 3.570, 3.190, 3.150, 3.~
#> $ qsec <dbl> 16.46, 17.02, 18.61, 19.44, 17.02, 20.22, 15.84, 20.00, 22.90, 18~
#> $ vs <fct> 0, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0,~
#> $ am <fct> 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0,~
#> $ gear <fct> 4, 4, 4, 3, 3, 3, 3, 4, 4, 4, 4, 3, 3, 3, 3, 3, 3, 4, 4, 4, 3, 3,~
#> $ carb <dbl> 4, 4, 1, 1, 2, 1, 4, 2, 2, 4, 4, 3, 3, 3, 4, 4, 4, 1, 2, 1, 1, 2,~
Created on 2022-03-15 by the reprex package (v2.0.1)

Is it possible to have glimpse() output with column numbers?

I am working with a data frame with 200+ variables and sometimes I have to choose variables based on their indexes as I also have to check their values.
I was expecting something like this:
Rows: 32
Columns: 11
[1] $ mpg <dbl> 21.0, 21.0, 22.8, 21.4, 18.7, 18.1, 14.3, 24.4, 22.8, 19.2, 17.8, 16.4, 17.3, 15.2, 10.4, 10.4…
[2] $ cyl <dbl> 6, 6, 4, 6, 8, 6, 8, 4, 4, 6, 6, 8, 8, 8, 8, 8, 8, 4, 4, 4, 4, 8, 8, 8, 8, 4, 4, 4, 8, 6, 8, 4
[3] $ disp <dbl> 160.0, 160.0, 108.0, 258.0, 360.0, 225.0, 360.0, 146.7, 140.8, 167.6, 167.6, 275.8, 275.8, 275…
[4] $ hp <dbl> 110, 110, 93, 110, 175, 105, 245, 62, 95, 123, 123, 180, 180, 180, 205, 215, 230, 66, 52, 65, …
[5] $ drat <dbl> 3.90, 3.90, 3.85, 3.08, 3.15, 2.76, 3.21, 3.69, 3.92, 3.92, 3.92, 3.07, 3.07, 3.07, 2.93, 3.00…
[6] $ wt <dbl> 2.620, 2.875, 2.320, 3.215, 3.440, 3.460, 3.570, 3.190, 3.150, 3.440, 3.440, 4.070, 3.730, 3.7…
[7] $ qsec <dbl> 16.46, 17.02, 18.61, 19.44, 17.02, 20.22, 15.84, 20.00, 22.90, 18.30, 18.90, 17.40, 17.60, 18.…
[8] $ vs <dbl> 0, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 1
[9] $ am <dbl> 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1
[10] $ gear <dbl> 4, 4, 4, 3, 3, 3, 3, 4, 4, 4, 4, 3, 3, 3, 3, 3, 3, 4, 4, 4, 3, 3, 3, 3, 3, 4, 5, 5, 5, 5, 5, 4
[11] $ carb <dbl> 4, 4, 1, 1, 2, 1, 4, 2, 2, 4, 4, 3, 3, 3, 4, 4, 4, 1, 2, 1, 1, 2, 2, 4, 2, 1, 2, 2, 4, 6, 8, 2
Any suggestions?

This doesn't put the output in quite the form you have it, but seems pretty close:
library(dplyr, warn.conflicts = FALSE)
glimpse_plus <- function(x, width = NULL, ...) {
x_orig <- x
names(x) <- paste0("[", 1:length(x), "]: ", names(x))
glimpse(x, width = width, ...)
invisible(x_orig)
}
glimpse_plus(mtcars)
#> Rows: 32
#> Columns: 11
#> $ `[1]: mpg` <dbl> 21.0, 21.0, 22.8, 21.4, 18.7, 18.1, 14.3, 24.4, 22.8, 19.…
#> $ `[2]: cyl` <dbl> 6, 6, 4, 6, 8, 6, 8, 4, 4, 6, 6, 8, 8, 8, 8, 8, 8, 4, 4, …
#> $ `[3]: disp` <dbl> 160.0, 160.0, 108.0, 258.0, 360.0, 225.0, 360.0, 146.7, 1…
#> $ `[4]: hp` <dbl> 110, 110, 93, 110, 175, 105, 245, 62, 95, 123, 123, 180, …
#> $ `[5]: drat` <dbl> 3.90, 3.90, 3.85, 3.08, 3.15, 2.76, 3.21, 3.69, 3.92, 3.9…
#> $ `[6]: wt` <dbl> 2.620, 2.875, 2.320, 3.215, 3.440, 3.460, 3.570, 3.190, 3…
#> $ `[7]: qsec` <dbl> 16.46, 17.02, 18.61, 19.44, 17.02, 20.22, 15.84, 20.00, 2…
#> $ `[8]: vs` <dbl> 0, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, …
#> $ `[9]: am` <dbl> 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, …
#> $ `[10]: gear` <dbl> 4, 4, 4, 3, 3, 3, 3, 4, 4, 4, 4, 3, 3, 3, 3, 3, 3, 4, 4, …
#> $ `[11]: carb` <dbl> 4, 4, 1, 1, 2, 1, 4, 2, 2, 4, 4, 3, 3, 3, 4, 4, 4, 1, 2, …
Created on 2021-06-19 by the reprex package (v2.0.0)

You can take a look at skimr package.
library(skimr)
skim(mtcars)
-- Data Summary ------------------------
Values
Name mtcars
Number of rows 32
Number of columns 11
_______________________
Column type frequency:
numeric 11
________________________
Group variables None
-- Variable type: numeric ------------------------------------------------------------------------------------
# A tibble: 11 x 11
skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
* <chr> <int> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <chr>
1 mpg 0 1 20.1 6.03 10.4 15.4 19.2 22.8 33.9 ▃▇▅▁▂
2 cyl 0 1 6.19 1.79 4 4 6 8 8 ▆▁▃▁▇
3 disp 0 1 231. 124. 71.1 121. 196. 326 472 ▇▃▃▃▂
4 hp 0 1 147. 68.6 52 96.5 123 180 335 ▇▇▆▃▁
5 drat 0 1 3.60 0.535 2.76 3.08 3.70 3.92 4.93 ▇▃▇▅▁
6 wt 0 1 3.22 0.978 1.51 2.58 3.32 3.61 5.42 ▃▃▇▁▂
7 qsec 0 1 17.8 1.79 14.5 16.9 17.7 18.9 22.9 ▃▇▇▂▁
8 vs 0 1 0.438 0.504 0 0 0 1 1 ▇▁▁▁▆
9 am 0 1 0.406 0.499 0 0 0 1 1 ▇▁▁▁▆
10 gear 0 1 3.69 0.738 3 3 4 4 5 ▇▁▆▁▂
11 carb 0 1 2.81 1.62 1 2 2 4 8 ▇▂▅▁▁

A possible approach: change the variable names (updated to reflect OP's formatting).
library(dplyr)
names(mtcars) <- paste0("[", 1:ncol(mtcars), "] ", names(mtcars))
glimpse(mtcars)
#> Rows: 32
#> Columns: 11
#> $ `[1] mpg` <dbl> 21.0, 21.0, 22.8, 21.4, 18.7, 18.1, 14.3, 24.4, 22.8, 19.2~
#> $ `[2] cyl` <dbl> 6, 6, 4, 6, 8, 6, 8, 4, 4, 6, 6, 8, 8, 8, 8, 8, 8, 4, 4, 4~
#> $ `[3] disp` <dbl> 160.0, 160.0, 108.0, 258.0, 360.0, 225.0, 360.0, 146.7, 14~
#> $ `[4] hp` <dbl> 110, 110, 93, 110, 175, 105, 245, 62, 95, 123, 123, 180, 1~
#> $ `[5] drat` <dbl> 3.90, 3.90, 3.85, 3.08, 3.15, 2.76, 3.21, 3.69, 3.92, 3.92~
#> $ `[6] wt` <dbl> 2.620, 2.875, 2.320, 3.215, 3.440, 3.460, 3.570, 3.190, 3.~
#> $ `[7] qsec` <dbl> 16.46, 17.02, 18.61, 19.44, 17.02, 20.22, 15.84, 20.00, 22~
#> $ `[8] vs` <dbl> 0, 0, 1, 1, 0, 1, 0, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1, 1~
#> $ `[9] am` <dbl> 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1~
#> $ `[10] gear` <dbl> 4, 4, 4, 3, 3, 3, 3, 4, 4, 4, 4, 3, 3, 3, 3, 3, 3, 4, 4, 4~
#> $ `[11] carb` <dbl> 4, 4, 1, 1, 2, 1, 4, 2, 2, 4, 4, 3, 3, 3, 4, 4, 4, 1, 2, 1~
Created on 2021-06-20 by the reprex package (v2.0.0)

Resources