All geek questions in one place

Dplyr - PivotTable for Multiple Variables

How to create simple summary statistics using dplyrmultiple variables? However, using a function summarise_eachappears to be suitable for applying multiple functions to multiple columns, the result is a wide, hard-to-read data frame.

+9
source share
5 answers

Use dplyrin conjunction with tidyrto modify the end result.

library(dplyr)
library(tidyr)

df <- tbl_df(mtcars)

df.sum <- df %>%
  select(mpg, cyl, vs, am, gear, carb) %>% # select variables to summarise
  summarise_each(funs(min = min, 
                      q25 = quantile(., 0.25), 
                      median = median, 
                      q75 = quantile(., 0.75), 
                      max = max,
                      mean = mean, 
                      sd = sd))

# the result is a wide data frame
> dim(df.sum)
[1]  1 42

# reshape it using tidyr functions

df.stats.tidy <- df.sum %>% gather(stat, val) %>%
  separate(stat, into = c("var", "stat"), sep = "_") %>%
  spread(stat, val) %>%
  select(var, min, q25, median, q75, max, mean, sd) # reorder columns

> print(df.stats.tidy)

   var  min    q25 median  q75  max     mean        sd
1   am  0.0  0.000    0.0  1.0  1.0  0.40625 0.4989909
2 carb  1.0  2.000    2.0  4.0  8.0  2.81250 1.6152000
3  cyl  4.0  4.000    6.0  8.0  8.0  6.18750 1.7859216
4 gear  3.0  3.000    4.0  4.0  5.0  3.68750 0.7378041
5  mpg 10.4 15.425   19.2 22.8 33.9 20.09062 6.0269481
6   vs  0.0  0.000    0.0  1.0  1.0  0.43750 0.5040161
+29
source

Paljenczy dplyr/tidy data.frame/tibble . : , . dplyr , , .

psych :: description() - , . , , . , , , psych::describe() , , .

, , as_tibble() , data.frames:

library(psych)
library(tidyverse)

# Create an extended version with a bunch of stats 
d.summary.extended <- mtcars %>%
    select(mpg, cyl, vs, am, gear, carb) %>%
    psych::describe(quant=c(.25,.75)) %>%
    as_tibble(rownames="rowname")  %>%
    print()

<OUTPUT>
# A tibble: 6 x 16
  rowname  vars     n     mean        sd median    trimmed     mad   min   max range       skew  kurtosis         se  Q0.25 Q0.75
    <chr> <int> <dbl>    <dbl>     <dbl>  <dbl>      <dbl>   <dbl> <dbl> <dbl> <dbl>      <dbl>     <dbl>      <dbl>  <dbl> <dbl>
1     mpg     1    32 20.09062 6.0269481   19.2 19.6961538 5.41149  10.4  33.9  23.5  0.6106550 -0.372766 1.06542396 15.425  22.8
2     cyl     2    32  6.18750 1.7859216    6.0  6.2307692 2.96520   4.0   8.0   4.0 -0.1746119 -1.762120 0.31570933  4.000   8.0
3      vs     3    32  0.43750 0.5040161    0.0  0.4230769 0.00000   0.0   1.0   1.0  0.2402577 -2.001938 0.08909831  0.000   1.0
4      am     4    32  0.40625 0.4989909    0.0  0.3846154 0.00000   0.0   1.0   1.0  0.3640159 -1.924741 0.08820997  0.000   1.0
5    gear     5    32  3.68750 0.7378041    4.0  3.6153846 1.48260   3.0   5.0   2.0  0.5288545 -1.069751 0.13042656  3.000   4.0
6    carb     6    32  2.81250 1.6152000    2.0  2.6538462 1.48260   1.0   8.0   7.0  1.0508738  1.257043 0.28552971  2.000   4.0
</OUTPUT>

# Select stats for comparison with other solutions
d.summary <- d.summary.extended %>%
    select(var=rowname, min, q25=Q0.25, median, q75=Q0.75, max, mean, sd) %>%
    print()

<OUTPUT>
# A tibble: 6 x 8
    var   min    q25 median   q75   max     mean        sd
  <chr> <dbl>  <dbl>  <dbl> <dbl> <dbl>    <dbl>     <dbl>
1   mpg  10.4 15.425   19.2  22.8  33.9 20.09062 6.0269481
2   cyl   4.0  4.000    6.0   8.0   8.0  6.18750 1.7859216
3    vs   0.0  0.000    0.0   1.0   1.0  0.43750 0.5040161
4    am   0.0  0.000    0.0   1.0   1.0  0.40625 0.4989909
5  gear   3.0  3.000    4.0   4.0   5.0  3.68750 0.7378041
6  carb   1.0  2.000    2.0   4.0   8.0  2.81250 1.6152000    
</OUTPUT>
+9

( ), stargazer.

df <- data.frame(mtcars)
cols <- c('mpg', 'cyl', 'vs', 'am', 'gear', 'carb')
stargazer(
    df[, cols], type = "text", 
    summary.stat = c("min", "p25", "median", "p75", "max", "median", "sd")
)

================================================================
Statistic  Min   Pctl(25) Median Pctl(75)  Max   Median St. Dev.
----------------------------------------------------------------
mpg       10.400  15.430  19.200  22.800  33.900 19.200  6.027
cyl         4       4       6       8       8      6     1.786
vs          0       0       0       1       1      0     0.504
am          0       0       0       1       1      0     0.499
gear        3       3       4       4       5      4     0.738
carb        1       2       2       4       8      2     1.615
----------------------------------------------------------------

'latex' 'html' 'out'.

+7

broom::tidy purrr::map_df. broom::tidy . purrr::map_df , , .

library(tidyverse)
mtcars %>% 
    select(mpg, cyl, vs, am, gear, carb) %>% 
    map_df(.f = ~ broom::tidy(summary(.x)), .id = "variable")


# A tibble: 6 x 7
# variable minimum    q1 median   mean    q3 maximum
# <chr>      <dbl> <dbl>  <dbl>  <dbl> <dbl>   <dbl>
# 1 mpg         10.4  15.4   19.2 20.1    22.8    33.9
# 2 cyl          4     4      6    6.19    8       8  
# 3 vs           0     0      0    0.438   1       1  
# 4 am           0     0      0    0.406   1       1  
# 5 gear         3     3      4    3.69    4       5  
# 6 carb         1     2      2    2.81    4       8
+2

, data.table. , .

dt <- data.table(mtcars)

cols <- c('mpg', 'cyl', 'vs', 'am', 'gear', 'carb')
functions <- c('min', 'q25', 'median', 'q75', 'max', 'mean', 'sd')

dt.sum <- dt[
    , 
    lapply(
        .SD, 
        function(x) list(
                min(x), quantile(x, 0.25), median(x), 
                quantile(x, 0.75), max(x), mean(x), sd(x)
        )
    ),
    .SDcols = cols
]

dt.sum
     mpg   cyl     vs     am   gear  carb
1:  10.4     4      0      0      3     1
2: 15.43     4      0      0      3     2
3:  19.2     6      0      0      4     2
4:  22.8     8      1      1      4     4
5:  33.9     8      1      1      5     8
6: 20.09 6.188 0.4375 0.4062  3.688 2.812
7: 6.027 1.786  0.504  0.499 0.7378 1.615

# transpose and provide meaningful names
dt.sum.t <- as.data.table(t(sum))[]
setnames(dt.sum.t, names(dt.sum.t), functions)
dt.sum.t[, var := cols]
setcolorder(dt.sum.t, c("var", functions))

dt.sum.t
    var  min   q25 median  q75  max   mean     sd
1:  mpg 10.4 15.43   19.2 22.8 33.9  20.09  6.027
2:  cyl    4     4      6    8    8  6.188  1.786
3:   vs    0     0      0    1    1 0.4375  0.504
4:   am    0     0      0    1    1 0.4062  0.499
5: gear    3     3      4    4    5  3.688 0.7378
6: carb    1     2      2    4    8  2.812  1.615
+1

Source: https://habr.com/ru/post/1622762/

More articles:


All Articles