Package {descriptr}

Type:	Package
Title:	Generate Descriptive Statistics
Version:	0.6.1
Description:	Generate descriptive statistics such as measures of location, dispersion, frequency tables, cross tables, group summaries and multiple one/two way tables.
Depends:	R(≥ 3.3.0)
Imports:	dplyr, ggplot2, magrittr, rlang, scales, stats, tidyr, utils
Suggests:	covr, gridExtra, knitr, rmarkdown, testthat (≥ 3.0.0), vdiffr, xplorerr
License:	MIT + file LICENSE
URL:	https://descriptr.rsquaredacademy.com/, https://github.com/rsquaredacademy/descriptr
BugReports:	https://github.com/rsquaredacademy/descriptr/issues
Encoding:	UTF-8
LazyData:	true
VignetteBuilder:	knitr
Config/testthat/edition:	3
Config/roxygen2/version:	8.1.1
NeedsCompilation:	no
Packaged:	2026-11-13 14:18:18 UTC; DELL
Author:	Aravind Hebbali [aut, cre]
Maintainer:	Aravind Hebbali <aravindhebbali@rsquaredacademy.com>
Repository:	CRAN
Date/Publication:	2026-11-13 17:10:20 UTC

descriptr package

Description

Generate descriptive statistics and explore statistical distributions

Author(s)

Maintainer: Aravind Hebbali aravindhebbali@rsquaredacademy.com (ORCID)

Authors:

• Aravind Hebbali aravindhebbali@rsquaredacademy.com (ORCID)

See Also

Useful links:

• https://descriptr.rsquaredacademy.com/

• https://github.com/rsquaredacademy/descriptr

• Report bugs at https://github.com/rsquaredacademy/descriptr/issues

Multiple One & Two Way Tables

Description

ds_auto_freq_table creates multiple one way tables by creating a frequency table for each categorical variable in a data frame. ds_auto_cross_table creates multiple two way tables by creating a cross table for each unique pair of categorical variables in a data frame.

Usage

ds_auto_freq_table(data, ...)

ds_auto_cross_table(data, ...)

Arguments

Details

ds_auto_freq_table is a extension of the ds_freq_table function. It creates a frequency table for each categorical variable in the dataframe. ds_auto_cross_table is a extension of the ds_cross_table function. It creates a two way table for each unique pair of categorical variables in the dataframe.

Deprecated Functions

ds_oway_tables() and ds_tway_tables() have been deprecated. Instead use ds_auto_freq_table() and ds_auto_cross_table().

See Also

ds_freq_table ds_cross_table

Examples

# frequency table for all columns
ds_auto_freq_table(mtcarz)

# frequency table for multiple columns
ds_auto_freq_table(mtcarz, cyl, gear)

# cross table for all columns
ds_auto_cross_table(mtcarz)

# cross table for multiple columns
ds_auto_cross_table(mtcarz, cyl, gear, am)

Tabulation

Description

Generate summary statistics for all continuous variables in data.

Usage

ds_auto_group_summary(data, ...)

Arguments

Examples

# summary statistics of mpg & disp for each level of cyl & gear
ds_auto_group_summary(mtcarz, cyl, gear, mpg, disp)

Descriptive statistics and frequency tables

Description

Generate summary statistics & frequency table for all continuous variables in data.

Usage

ds_auto_summary_stats(data, ...)

Arguments

Examples

# all columns
ds_auto_summary_stats(mtcarz)

# multiple columns
ds_auto_summary_stats(mtcarz, disp, hp)

Two way table

Description

Creates two way tables of categorical variables. The tables created can be visualized as bar plots and mosaic plots.

Usage

ds_cross_table(data, var_1, var_2)

## S3 method for class 'ds_cross_table'
plot(x, stacked = FALSE, proportional = FALSE, print_plot = TRUE, ...)

ds_twoway_table(data, var_1, var_2)

Arguments

Value

ds_cross_table() returns an object of class "ds_cross_table" containing the contingency table and the utility information used to print it. The cell percentages are stored as proportions (values between 0 and 1) in percent_table, row_percent, column_percent and percent_column. The printed cells show percentages computed from the counts and can differ from the rounded proportions stored in the object in the last decimal place. The number of rows dropped because either variable is missing is stored in utility$missing. ds_twoway_table() returns a tibble whose percent, row_percent and col_percent columns are also proportions.

Examples

# cross table
k <- ds_cross_table(mtcarz, cyl, gear)
k

# bar plot
plot(k)

# stacked bar plot
plot(k, stacked = TRUE)

# proportional bar plot
plot(k, proportional = TRUE)

# returns tibble
ds_twoway_table(mtcarz, cyl, gear)

Corrected Sum of Squares

Description

Compute the corrected sum of squares

Usage

ds_css(data, x = NULL)

Arguments

Examples

# vector
ds_css(mtcars$mpg)

# data.frame
ds_css(mtcars, mpg)

Coefficient of Variation

Description

Compute the coefficient of variation

Usage

ds_cvar(data, x = NULL)

Arguments

Examples

# vector
ds_cvar(mtcars$mpg)

# data.frame
ds_cvar(mtcars, mpg)

Extreme observations

Description

Returns the most extreme observations and their original row indices.

Usage

ds_extreme_obs(data, col, decimals = 2)

Arguments

Details

Missing values are removed before the k = min(5, n) lowest and highest observations are selected. The row indices refer to the data passed in, and ties are reported on distinct rows. decimals applies to both vector and data.frame input.

Examples

# data.frame
ds_extreme_obs(mtcarz, mpg)

# vector
ds_extreme_obs(mtcarz$mpg)

# decimal places
ds_extreme_obs(mtcarz$mpg, decimals = 3)

Frequency table

Description

Frequency table for categorical and continuous data and returns the frequency, cumulative frequency, frequency percent and cumulative frequency percent. plot.ds_freq_table() creates bar plot for the categorical data and histogram for continuous data.

Usage

ds_freq_table(data, col, bins = 5, closed = c("left", "right", "both"))

## S3 method for class 'ds_freq_table'
plot(x, print_plot = TRUE, ...)

Arguments

Details

Percentages are computed over all observations, including missing values, so the Percent column and the Missing row share the same denominator and add up to 100. Continuous data with no non-missing observations, or with no variation, cannot be binned and raise an error.

See Also

ds_cross_table

Examples

# categorical data
ds_freq_table(mtcarz, cyl)

# barplot
k <- ds_freq_table(mtcarz, cyl)
plot(k)

# continuous data
ds_freq_table(mtcarz, mpg)

# barplot
k <- ds_freq_table(mtcarz, mpg)
plot(k)

Geometric Mean

Description

Computes the geometric mean

Usage

ds_gmean(data, x = NULL)

Arguments

Details

Any NA values are stripped before computation. The mean is computed on the log scale, so large values or long vectors do not overflow. If any value is less than or equal to zero, a warning is issued and NA is returned.

See Also

ds_hmean mean

Examples

# vector
ds_gmean(mtcars$mpg)

# data.frame
ds_gmean(mtcars, mpg)

Groupwise descriptive statistics

Description

Descriptive statistics of a continuous variable for the different levels of a categorical variable. plot.ds_group_summary() creates boxplots of the continuous variable for the different levels of the categorical variable.

Usage

ds_group_summary(data, group_by, cols)

## S3 method for class 'ds_group_summary'
plot(x, print_plot = TRUE, ...)

Arguments

Details

Groups with missing values in the continuous variable are summarised using the non-missing observations (na.rm = TRUE), and the number of missing observations is reported in the Missing row of stats. Observations with a missing grouping label are excluded from the summary and from the boxplot. Unused levels of the grouping factor are dropped.

The grouping key in tidy_stats keeps the class of the grouping variable (including ordered factors) and the order of the observed levels. If the grouping column is named like one of the statistic columns, such as length, its column in tidy_stats is suffixed with _group so that every column name is unique.

Value

ds_group_summary() returns an object of class "ds_group_summary". An object of class "ds_group_summary" is a list containing the following components:

See Also

ds_summary_stats

Examples

# ds_group summary
ds_group_summary(mtcarz, cyl, mpg)

# boxplot
k <- ds_group_summary(mtcarz, cyl, mpg)
plot(k)

# tibble
k$tidy_stats

Category wise descriptive statistics

Description

Descriptive statistics of a continuous variable for the combination of levels of two or more categorical variables.

Usage

ds_group_summary_interact(data, col, ...)

Arguments

Details

Character grouping columns are accepted and treated as factors. Factor levels may contain any character, including . and \r. Groups are formed from the values of the grouping columns themselves, so distinct combinations that would serialize to the same character string are never merged. Rows with a missing value in any of the selected columns are excluded.

The grouping columns keep their names in the returned tibble. If a grouping column is named like one of the statistic columns, such as mean, its column is suffixed with _group so that every column name is unique and the statistic keeps its documented name.

See Also

ds_group_summary

Examples

ds_group_summary_interact(mtcarz, mpg, cyl, gear)

Harmonic Mean

Description

Computes the harmonic mean

Usage

ds_hmean(data, x = NULL)

Arguments

Details

Any NA values are stripped before computation. If any value is less than or equal to zero, a warning is issued and NA is returned.

See Also

ds_gmean mean

Examples

# vector
ds_hmean(mtcars$mpg)

# data.frame
ds_hmean(mtcars, mpg)

Kurtosis

Description

Compute the kurtosis of a probability distribution.

Usage

ds_kurtosis(data, x = NULL)

Arguments

Details

Any NA values are stripped from x before computation takes place. With n non-missing observations, sample standard deviation s, m_k = \sum ((x_i - \bar{x}) / s)^k and

G_2 = \frac{n (n + 1)}{(n - 1)(n - 2)(n - 3)} m_4 - \frac{3 (n - 1)^2}{(n - 2)(n - 3)},

this is the excess kurtosis. It matches e1071::kurtosis(x, type = 2) and the SAS/SPSS definition.

References

Sheskin, D.J. (2000) Handbook of Parametric and Nonparametric Statistical Procedures, Second Edition. Boca Raton, Florida: Chapman & Hall/CRC.

See Also

ds_skewness

Examples

# vector
ds_kurtosis(mtcars$mpg)

# data.frame
ds_kurtosis(mtcars, mpg)

Launch Shiny App

Description

Launches shiny app

Usage

ds_launch_shiny_app()

Deprecated Function

launch_descriptr() has been deprecated. Instead use ds_launch_shiny_app().

Examples

## Not run: 
ds_launch_shiny_app()

## End(Not run)

Mean Absolute Deviation

Description

Compute the mean absolute deviation about the mean

Usage

ds_mdev(data, x = NULL)

Arguments

Details

The ds_mdev function computes the mean absolute deviation about the mean. It is different from mad in stats package as the statistic used to compute the deviations is not median but mean. Any NA values are stripped from x before computation takes place

See Also

mad

Examples

# vector
ds_mdev(mtcars$mpg)

# data.frame
ds_mdev(mtcars, mpg)

Measures of location

Description

Returns the measures of location such as mean, median & mode.

Usage

ds_measures_location(data, ..., trim = 0.05, decimals = 2)

Arguments

Details

n reports the total number of observations and missing the number of missing values; the measures themselves are computed from the non-missing values.

Examples

# single column
ds_measures_location(mtcarz, mpg)

# multiple columns
ds_measures_location(mtcarz, mpg, disp)

# all columns
ds_measures_location(mtcarz)

# vector
ds_measures_location(mtcarz$mpg)

# vectors of different length
disp <- mtcarz$disp[1:10]
ds_measures_location(mtcarz$mpg, disp)

# decimal places
ds_measures_location(mtcarz, disp, hp, decimals = 3)

Measures of symmetry

Description

Returns the measures of symmetry such as skewness and kurtosis.

Usage

ds_measures_symmetry(data, ..., decimals = 2)

Arguments

Details

n reports the number of non-missing observations and the measures are computed from the non-missing values, for both vector and data-frame input. A variable with no non-missing observations returns n = 0 and NA for every measure.

Examples

# single column
ds_measures_symmetry(mtcarz, mpg)

# multiple columns
ds_measures_symmetry(mtcarz, mpg, disp)

# all columns
ds_measures_symmetry(mtcarz)

# vector
ds_measures_symmetry(mtcarz$mpg)

# vectors of different length
disp <- mtcarz$disp[1:10]
ds_measures_symmetry(mtcarz$mpg, disp)

# decimal places
ds_measures_symmetry(mtcarz, disp, hp, decimals = 3)

Measures of variation

Description

Returns the measures of variation such as range, variance and standard deviation.

Usage

ds_measures_variation(data, ..., decimals = 2)

Arguments

Details

n reports the number of non-missing observations and every measure is computed from the non-missing values, for both vector and data-frame input. A variable with no non-missing observations returns n = 0 and NA for every measure.

Examples

# single column
ds_measures_variation(mtcarz, mpg)

# multiple columns
ds_measures_variation(mtcarz, mpg, disp)

# all columns
ds_measures_variation(mtcarz)

# vector
ds_measures_variation(mtcarz$mpg)

# vectors of different length
disp <- mtcarz$disp[1:10]
ds_measures_variation(mtcarz$mpg, disp)

# decimal places
ds_measures_variation(mtcarz, disp, hp, decimals = 3)

Mode

Description

Compute the sample mode

Usage

ds_mode(data, x = NULL)

Arguments

Details

Any NA values are stripped from x before computation takes place. If several values are tied for the highest frequency, the smallest of them is returned.

Value

Mode of x

See Also

mean median

Examples

# vector
ds_mode(mtcars$mpg)

# data.frame
ds_mode(mtcars, mpg)

Percentiles

Description

Returns the percentiles

Usage

ds_percentiles(data, ..., decimals = 2)

Arguments

Details

n reports the number of non-missing observations and the percentiles are computed from the non-missing values, for both vector and data-frame input. A variable with no non-missing observations returns n = 0 and NA for every percentile.

Examples

# single column
ds_percentiles(mtcarz, mpg)

# multiple columns
ds_percentiles(mtcarz, mpg, disp)

# all columns
ds_percentiles(mtcarz)

# vector
ds_percentiles(mtcarz$mpg)

# vectors of different length
disp <- mtcarz$disp[1:10]
ds_percentiles(mtcarz$mpg, disp)

# decimal places
ds_percentiles(mtcarz, disp, hp, decimals = 3)

Generate bar plots

Description

Creates bar plots if the data has categorical variables.

Usage

ds_plot_bar(data, ..., fill = "blue", print_plot = TRUE)

Arguments

Examples

# plot single variable
ds_plot_bar(mtcarz, cyl)

# plot multiple variables
ds_plot_bar(mtcarz, cyl, gear)

# plot all variables
ds_plot_bar(mtcarz)

Generate grouped bar plots

Description

Creates grouped bar plots if the data has categorical variables.

Usage

ds_plot_bar_grouped(data, ..., print_plot = TRUE)

Arguments

Examples

# subset data
mt <- dplyr::select(mtcarz, cyl, gear, am)

# grouped bar plot
ds_plot_bar_grouped(mtcarz, cyl, gear)

# plot all variables
ds_plot_bar_grouped(mt)

Generate stacked bar plots

Description

Creates stacked bar plots if the data has categorical variables.

Usage

ds_plot_bar_stacked(data, ..., print_plot = TRUE)

Arguments

Examples

# subset data
mt <- dplyr::select(mtcarz, cyl, gear, am)

# stacked bar plot
ds_plot_bar_stacked(mtcarz, cyl, gear)

# plot all variables
ds_plot_bar_stacked(mt)

Compare distributions

Description

Creates box plots if the data has both categorical & continuous variables.

Usage

ds_plot_box_group(data, ..., print_plot = TRUE)

Arguments

Examples

# subset data
mt <- dplyr::select(mtcarz, cyl, disp, mpg)

# plot select variables
ds_plot_box_group(mtcarz, cyl, gear, mpg)

# plot all variables
ds_plot_box_group(mt)

Generate box plots

Description

Creates box plots if the data has continuous variables.

Usage

ds_plot_box_single(data, ..., print_plot = TRUE)

Arguments

Examples

# plot single variable
ds_plot_box_single(mtcarz, mpg)

# plot multiple variables
ds_plot_box_single(mtcarz, mpg, disp, hp)

# plot all variables
ds_plot_box_single(mtcarz)

Generate density plots

Description

Creates density plots if the data has continuous variables.

Usage

ds_plot_density(data, ..., color = "blue", print_plot = TRUE)

Arguments

Examples

# plot single variable
ds_plot_density(mtcarz, mpg)

# plot multiple variables
ds_plot_density(mtcarz, mpg, disp, hp)

# plot all variables
ds_plot_density(mtcarz)

Generate histograms

Description

Creates histograms if the data has continuous variables.

Usage

ds_plot_histogram(data, ..., bins = 5, fill = "blue", print_plot = TRUE)

Arguments

Examples

# plot single variable
ds_plot_histogram(mtcarz, mpg)

# plot multiple variables
ds_plot_histogram(mtcarz, mpg, disp, hp)

# plot all variables
ds_plot_histogram(mtcarz)

Generate scatter plots

Description

Creates scatter plots if the data has continuous variables.

Usage

ds_plot_scatter(data, ..., print_plot = TRUE)

Arguments

Examples

# plot select variables
ds_plot_scatter(mtcarz, mpg, disp)

# plot all variables
ds_plot_scatter(mtcarz)

Range

Description

Compute the range of a numeric vector

Usage

ds_range(data, x = NULL)

Arguments

Value

Range of x

See Also

range

Examples

# vector
ds_range(mtcars$mpg)

# data.frame
ds_range(mtcars, mpg)

Index Values

Description

Returns the original positions of values in a vector.

Usage

ds_rindex(data, values)

Arguments

Details

Positions refer to the vector passed in; missing values are not removed before the indices are computed.

Value

Original positions of the values in data. Missing values are ignored, and all matching positions are returned. In case data does not contain a value, NULL is returned.

Examples

# returns index of 21
ds_rindex(mtcars$mpg, 21)

# returns NULL
ds_rindex(mtcars$mpg, 22)

Screen data

Description

Screen data and return details such as variable names, class, levels and missing values. plot.ds_screener() creates bar plots to visualize of missing observations for each variable in a data set.

Usage

ds_screener(data)

## S3 method for class 'ds_screener'
plot(x, ...)

Arguments

Value

ds_screener() returns an object of class "ds_screener". An object of class "ds_screener" is a list containing the following components:

Examples

# screen data
ds_screener(mtcarz)
ds_screener(airquality)

# plot
x <- ds_screener(airquality)
plot(x)

Skewness

Description

Compute the skewness of a probability distribution.

Usage

ds_skewness(data, x = NULL)

Arguments

Details

Any NA values are stripped from x before computation takes place. For n non-missing observations, sample standard deviation s and m_k = \sum ((x_i - \bar{x}) / s)^k, the skewness is

G_1 = \frac{n}{(n - 1)(n - 2)} m_3.

This is the adjusted Fisher-Pearson standardized moment coefficient; it matches e1071::skewness(x, type = 2) and the SAS/SPSS definition.

References

Sheskin, D.J. (2000) Handbook of Parametric and Nonparametric Statistical Procedures, Second Edition. Boca Raton, Florida: Chapman & Hall/CRC.

See Also

kurtosis

Examples

# vector
ds_skewness(mtcars$mpg)

# data.frame
ds_skewness(mtcars, mpg)

Standard error of mean

Description

Returns the standard error of mean.

Usage

ds_std_error(x)

Arguments

Details

Missing values are removed before computation and the number of non-missing observations is used. A vector with no non-missing observations returns NA.

Examples

ds_std_error(mtcars$mpg)

Descriptive statistics

Description

Range of descriptive statistics for continuous data.

Usage

ds_summary_stats(data, ...)

Arguments

See Also

summary ds_freq_table ds_cross_table

Examples

# numeric data
ds_summary_stats(mtcarz$mpg)

# single variable
ds_summary_stats(mtcarz, mpg)

# multiple variables
ds_summary_stats(mtcarz, mpg, disp, hp)

# all variables
ds_summary_stats(mtcarz)

Tail Observations

Description

Returns the n highest/lowest observations from a numeric vector.

Usage

ds_tailobs(data, n, type = c("low", "high"), decimals = 2)

Arguments

Details

Any NA values are stripped from data before computation takes place.

Value

n highest/lowest observations from data

See Also

top_n

Examples

# 5 lowest observations
ds_tailobs(mtcarz$mpg, 5)

# 5 highest observations
ds_tailobs(mtcarz$mpg, 5, type = "high")

# specify decimal places to display
ds_tailobs(mtcarz$mpg, 5, decimals = 3)

Tidy descriptive statistics

Description

Descriptive statistics for multiple variables.

Usage

ds_tidy_stats(data, ...)

Arguments

Value

A tibble.

Deprecated Functions

ds_multi_stats() have been deprecated. Instead use ds_tidy_stats().

Examples

# all columns
ds_tidy_stats(mtcarz)

# multiple columns
ds_tidy_stats(mtcarz, mpg, disp, hp)

High School and Beyond Data Set

Description

A dataset containing demographic information and standardized test scores of high school students.

Usage

hsb

Format

A data frame with 200 rows and 10 variables:

id

id of the student

female

gender of the student

race

ethnic background of the student

ses

socio-economic status of the student

schtyp

school type

prog

program type

read

scores from test of reading

write

scores from test of writing

math

scores from test of math

science

scores from test of science

socst

scores from test of social studies

Source

https://nces.ed.gov/surveys/hsb/

mtcarz

Description

Copy of mtcars data set with modified variable types

Usage

mtcarz

Format

An object of class data.frame with 32 rows and 11 columns.