Title:	Tools for Cleaning Rectangular Data
Version:	1.11.0
Description:	A dependency-free collection of simple functions for cleaning rectangular data. This package allows to detect, count and replace values or discard rows/columns using a predicate function. In addition, it provides tools to check conditions and return informative error messages.
License:	GPL (≥ 3)
URL:	https://codeberg.org/tesselle/arkhe, https://packages.tesselle.org/arkhe/
BugReports:	https://codeberg.org/tesselle/arkhe/issues
Depends:	R (≥ 3.5)
Imports:	methods, stats, utils
Suggests:	tinytest
Encoding:	UTF-8
RoxygenNote:	7.3.2.9000
X-schema.org-isPartOf:	https://www.tesselle.org
X-schema.org-keywords:	data-cleaning, statistics, r-package
Collate:	'AllGenerics.R' 'append.R' 'predicates.R' 'assert.R' 'arkhe-deprecated.R' 'arkhe-internal.R' 'arkhe-package.R' 'assign.R' 'clean.R' 'compact.R' 'conditions.R' 'count.R' 'describe.R' 'detect.R' 'discard.R' 'get.R' 'keep.R' 'mathematics.R' 'remove.R' 'replace.R' 'scale.R' 'seek.R' 'sparsity.R' 'statistics.R' 'utilities.R' 'zzz.R'
NeedsCompilation:	no
Packaged:	2025-05-12 15:14:41 UTC; nfrerebeau
Author:	Nicolas Frerebeau [aut, cre], Brice Lebrun [art] (Logo designer), Université Bordeaux Montaigne [fnd], CNRS [fnd]
Maintainer:	Nicolas Frerebeau <nicolas.frerebeau@u-bordeaux-montaigne.fr>
Repository:	CRAN
Date/Publication:	2025-05-12 17:30:02 UTC

arkhe: Tools for Cleaning Rectangular Data

Description

A dependency-free collection of simple functions for cleaning rectangular data. This package allows to detect, count and replace values or discard rows/columns using a predicate function. In addition, it provides tools to check conditions and return informative error messages.

Details

Archéosciences Bordeaux (UMR 6034)
Maison de l'Archéologie
Université Bordeaux Montaigne
F-33607 Pessac cedex
France

Package options

arkhe uses the following options() to configure behavior:

• arkhe.verbose: a logical scalar. Should R report extra information on progress? Defaults to interactive().

Author(s)

Maintainer: Nicolas Frerebeau nicolas.frerebeau@u-bordeaux-montaigne.fr (ORCID)

Other contributors:

• Brice Lebrun (ORCID) (Logo designer) [artist]

• Université Bordeaux Montaigne (ROR) [funder]

• CNRS (ROR) [funder]

See Also

Useful links:

• https://codeberg.org/tesselle/arkhe

• https://packages.tesselle.org/arkhe/

• Report bugs at https://codeberg.org/tesselle/arkhe/issues

Add a (Named) Vector as a Column

Description

Add a (Named) Vector as a Column

Usage

append_column(x, ...)

## S4 method for signature 'data.frame'
append_column(x, column, after = 0, var = ".col")

Arguments

Details

If column is named, names will be matched to the row names of x. Only the first match is retained, and elements of column without a match are removed. This allows to add as a column a vector whose length is less than the number of rows in x (NAs will be inserted).

Value

A data.frame.

Author(s)

N. Frerebeau

See Also

Other data preparation tools: append_rownames(), assign(), compact(), count(), detect(), discard(), get(), keep(), seek()

Examples

X <- data.frame(
  x = 1:5,
  y = 6:10,
  row.names = LETTERS[1:5]
)

Y <- c(D = 44, B = 55, Z = 22)

append_column(X, Y, after = 3)

Convert Row Names to an Explicit Column

Description

Convert Row Names to an Explicit Column

Usage

append_rownames(x, ...)

## S4 method for signature 'data.frame'
append_rownames(x, after = 0, remove = TRUE, var = "rownames")

Arguments

Value

A data.frame.

Author(s)

N. Frerebeau

See Also

Other data preparation tools: append_column(), assign(), compact(), count(), detect(), discard(), get(), keep(), seek()

Examples

X <- data.frame(
  x = 1:5,
  y = 6:10,
  z = LETTERS[1:5]
)

## Assign column to row names
(Y <- assign_rownames(X, 3))

## Append row names to data.frame
(Z <- append_rownames(Y))

Deprecated Functions in arkhe

Description

These functions still work but will be removed (defunct) in the next version.

Usage

needs(...)

assert_dimensions(...)

compact_cols(...)

discard_cols(...)

keep_cols(...)

Check Numeric Trend

Description

Check Numeric Trend

Usage

assert_constant(x, ...)

assert_decreasing(x, ...)

assert_increasing(x, ...)

Arguments

Value

Throws an error, if any, and returns x invisibly otherwise.

Author(s)

N. Frerebeau

See Also

Other checking methods: assert_dim(), assert_empty(), assert_infinite(), assert_length(), assert_lower(), assert_missing(), assert_names(), assert_numeric, assert_package(), assert_square(), assert_type(), assert_unique()

Check Object Dimensions

Description

Check Object Dimensions

Usage

assert_dim(x, expected)

assert_nrow(x, expected)

assert_ncol(x, expected)

Arguments

Value

Throws an error, if any, and returns x invisibly otherwise.

Author(s)

N. Frerebeau

See Also

Other checking methods: assert_constant(), assert_empty(), assert_infinite(), assert_length(), assert_lower(), assert_missing(), assert_names(), assert_numeric, assert_package(), assert_square(), assert_type(), assert_unique()

Check Object Filling

Description

Checks if an object is (not) empty.

Usage

assert_empty(x)

assert_filled(x)

Arguments

Value

Throws an error, if any, and returns x invisibly otherwise.

Author(s)

N. Frerebeau

See Also

Other checking methods: assert_constant(), assert_dim(), assert_infinite(), assert_length(), assert_lower(), assert_missing(), assert_names(), assert_numeric, assert_package(), assert_square(), assert_type(), assert_unique()

Check Infinite Values

Description

Checks if an object contains any infinite (Inf) values.

Usage

assert_infinite(x)

Arguments

Value

Throws an error, if any, and returns x invisibly otherwise.

Author(s)

N. Frerebeau

See Also

Other checking methods: assert_constant(), assert_dim(), assert_empty(), assert_length(), assert_lower(), assert_missing(), assert_names(), assert_numeric, assert_package(), assert_square(), assert_type(), assert_unique()

Check Object Length(s)

Description

Check Object Length(s)

Usage

assert_length(
  x,
  expected,
  allow_empty = empty,
  allow_null = FALSE,
  empty = FALSE
)

assert_lengths(x, expected)

Arguments

Value

Throws an error, if any, and returns x invisibly otherwise.

Author(s)

N. Frerebeau

See Also

Other checking methods: assert_constant(), assert_dim(), assert_empty(), assert_infinite(), assert_lower(), assert_missing(), assert_names(), assert_numeric, assert_package(), assert_square(), assert_type(), assert_unique()

Check Numeric Relations

Description

Check Numeric Relations

Usage

assert_lower(x, y, ...)

assert_greater(x, y, ...)

Arguments

Value

Throws an error, if any, and returns x invisibly otherwise.

Author(s)

N. Frerebeau

See Also

Other checking methods: assert_constant(), assert_dim(), assert_empty(), assert_infinite(), assert_length(), assert_missing(), assert_names(), assert_numeric, assert_package(), assert_square(), assert_type(), assert_unique()

Check Missing Values

Description

Checks if an object contains any missing (NA, NaN) values.

Usage

assert_missing(x)

Arguments

Value

Throws an error, if any, and returns x invisibly otherwise.

Author(s)

N. Frerebeau

See Also

Other checking methods: assert_constant(), assert_dim(), assert_empty(), assert_infinite(), assert_length(), assert_lower(), assert_names(), assert_numeric, assert_package(), assert_square(), assert_type(), assert_unique()

Check Object Names

Description

Check Object Names

Usage

assert_names(x, expected = NULL)

assert_rownames(x, expected = NULL)

assert_colnames(x, expected = NULL)

Arguments

Value

Throws an error, if any, and returns x invisibly otherwise.

Author(s)

N. Frerebeau

See Also

Other checking methods: assert_constant(), assert_dim(), assert_empty(), assert_infinite(), assert_length(), assert_lower(), assert_missing(), assert_numeric, assert_package(), assert_square(), assert_type(), assert_unique()

Check Numeric Values

Description

Check Numeric Values

Usage

assert_count(x, na.rm = FALSE, ...)

assert_whole(x, na.rm = FALSE, ...)

assert_positive(x, na.rm = FALSE, ...)

assert_negative(x, na.rm = FALSE, ...)

assert_odd(x, na.rm = FALSE, ...)

assert_even(x, na.rm = FALSE, ...)

Arguments

Value

Throws an error, if any, and returns x invisibly otherwise.

Author(s)

N. Frerebeau

See Also

Other checking methods: assert_constant(), assert_dim(), assert_empty(), assert_infinite(), assert_length(), assert_lower(), assert_missing(), assert_names(), assert_package(), assert_square(), assert_type(), assert_unique()

Check the Availability of a Package

Description

Check the Availability of a Package

Usage

assert_package(x, ask = interactive())

Arguments

Details

assert_package() is designed for use inside other functions in your own package to check for the availability of a suggested package.

If the required packages are not available and R is running interactively, the user will be asked to install the packages.

Value

Invisibly returns NULL.

Author(s)

N. Frerebeau

See Also

Other checking methods: assert_constant(), assert_dim(), assert_empty(), assert_infinite(), assert_length(), assert_lower(), assert_missing(), assert_names(), assert_numeric, assert_square(), assert_type(), assert_unique()

Check Matrix

Description

Check Matrix

Usage

assert_square(x)

assert_symmetric(x)

Arguments

Value

Throw an error, if any, and returns x invisibly otherwise.

Author(s)

N. Frerebeau

See Also

Other checking methods: assert_constant(), assert_dim(), assert_empty(), assert_infinite(), assert_length(), assert_lower(), assert_missing(), assert_names(), assert_numeric, assert_package(), assert_type(), assert_unique()

Check Data Types

Description

Check Data Types

Usage

assert_type(x, expected, allow_empty = TRUE, allow_null = FALSE)

assert_scalar(x, expected)

assert_function(x)

Arguments

Value

Throws an error, if any, and returns x invisibly otherwise.

Author(s)

N. Frerebeau

See Also

Other checking methods: assert_constant(), assert_dim(), assert_empty(), assert_infinite(), assert_length(), assert_lower(), assert_missing(), assert_names(), assert_numeric, assert_package(), assert_square(), assert_unique()

Check Duplicates

Description

Checks if an object contains duplicated elements.

Usage

assert_unique(x)

Arguments

Value

Throws an error, if any, and returns x invisibly otherwise.

Author(s)

N. Frerebeau

See Also

Other checking methods: assert_constant(), assert_dim(), assert_empty(), assert_infinite(), assert_length(), assert_lower(), assert_missing(), assert_names(), assert_numeric, assert_package(), assert_square(), assert_type()

Assign a Specific Row/Column to the Column/Row Names

Description

Assign a Specific Row/Column to the Column/Row Names

Usage

assign_colnames(x, ...)

assign_rownames(x, ...)

## S4 method for signature 'data.frame'
assign_rownames(x, column, remove = TRUE)

## S4 method for signature 'data.frame'
assign_colnames(x, row, remove = TRUE)

Arguments

Value

A data.frame.

Author(s)

N. Frerebeau

See Also

Other data preparation tools: append_column(), append_rownames(), compact(), count(), detect(), discard(), get(), keep(), seek()

Examples

X <- data.frame(
  x = 1:5,
  y = 6:10,
  z = LETTERS[1:5]
)

## Assign column to row names
(Y <- assign_rownames(X, 3))

## Append row names to data.frame
(Z <- append_rownames(Y))

Nonparametric Bootstrap Estimation

Description

Samples randomly from the elements of object with replacement.

Usage

bootstrap(object, ...)

## S4 method for signature 'numeric'
bootstrap(
  object,
  do,
  n,
  ...,
  f = NULL,
  level = 0.95,
  interval = c("basic", "normal", "percentiles")
)

Arguments

Value

If f is NULL (the default), bootstrap() returns a named numeric vector with the following elements:

original

The observed value of do applied to object.

mean

The bootstrap estimate of mean of do.

bias

The bootstrap estimate of bias of do.

error

The bootstrap estimate of standard error of do.

lower

The lower limit of the bootstrap confidence interval at level.

upper

The upper limit of the bootstrap confidence interval at level

If f is a function, bootstrap() returns the result of f applied to the n values of do.

Author(s)

N. Frerebeau

References

Davison, A. C. & Hinkley, D. V. (1997). Bootstrap Methods and Their Application. Cambridge Series on Statistical and Probabilistic Mathematics. Cambridge: Cambridge University Press.

See Also

confidence_bootstrap()

Other resampling methods: jackknife(), resample_multinomial(), resample_uniform()

Examples

x <- rnorm(20)

## Bootstrap
bootstrap(x, do = mean, n = 100)

## Estimate the 25th and 95th percentiles
quant <- function(x) { quantile(x, probs = c(0.25, 0.75)) }
bootstrap(x, n = 100, do = mean, f = quant)

## Get the n bootstrap estimates
(z <- bootstrap(x, n = 100, do = mean, f = function(x) { x }))

## Basic bootstrap confidence interval
confidence_bootstrap(z, level = 0.95, type = "basic", t0 = mean(x))

Class Diagnostic

Description

Class Diagnostic

Usage

check_class(object, conditions)

Arguments

Value

Throw an error if conditions is of non-zero length, invisibly returns TRUE if not.

Author(s)

N. Frerebeau

Remove Leading/Trailing Whitespace

Description

Remove Leading/Trailing Whitespace

Usage

clean_whitespace(x, ...)

## S4 method for signature 'data.frame'
clean_whitespace(x, which = c("both", "left", "right"), squish = TRUE)

## S4 method for signature 'matrix'
clean_whitespace(x, which = c("both", "left", "right"), squish = TRUE)

Arguments

Author(s)

N. Frerebeau

See Also

trimws()

Other data cleaning tools: remove_Inf(), remove_NA(), remove_constant(), remove_empty(), remove_zero(), replace_Inf(), replace_NA(), replace_empty(), replace_zero()

Examples

x <- data.frame(
  A = c("  Both ", "  Left", "Right  "),
  B = 1:3
)

clean_whitespace(x, which = "both")
clean_whitespace(x, which = "left")
clean_whitespace(x, which = "right")

Remove Empty Rows/Columns

Description

Removes empty rows/columns in an array-like object.

Usage

compact(x, ...)

compact_columns(x, ...)

compact_rows(x, ...)

## S4 method for signature 'ANY'
compact(x, margin = 1, na.rm = FALSE, verbose = getOption("arkhe.verbose"))

## S4 method for signature 'ANY'
compact_columns(x, na.rm = FALSE, verbose = getOption("arkhe.verbose"))

## S4 method for signature 'ANY'
compact_rows(x, na.rm = FALSE, verbose = getOption("arkhe.verbose"))

Arguments

Details

A row/column is empty if it contains only zeros (if of type numeric) or zero length character strings (if of type character).

Author(s)

N. Frerebeau

See Also

Other data preparation tools: append_column(), append_rownames(), assign(), count(), detect(), discard(), get(), keep(), seek()

Examples

## Create a data.frame
X <- data.frame(A = 0, B = 1:5, C = 6, D = "", F = letters[1:5])
X

## Remove empty columns
compact(X, margin = 2)

Concatenate

Description

Concatenates character vectors.

Usage

x %+% y

Arguments

Value

A character vector.

See Also

Other utilities: null

Conditions

Description

• throw_error() stops execution of the current expression and executes an error action.

• throw_warning() generates a warning message.

• catch_conditions() and catch_message() handles unusual conditions.

Usage

throw_error(.subclass, message, call = NULL, ...)

throw_warning(.subclass, message, call = NULL, ...)

catch_message(expr)

catch_conditions(expr)

Arguments

Author(s)

N. Frerebeau

Confidence Interval for Binomial Proportions

Description

Computes Wald interval for a proportion at a desired level of significance.

Usage

confidence_binomial(object, ...)

## S4 method for signature 'numeric'
confidence_binomial(
  object,
  n,
  level = 0.95,
  method = "wald",
  corrected = FALSE
)

Arguments

Value

A length-two numeric vector giving the lower and upper confidence limits.

Author(s)

N. Frerebeau

See Also

Other summary statistics: confidence_bootstrap(), confidence_mean(), confidence_multinomial(), interval_credible(), interval_hdr()

Examples

## Confidence interval for a mean
x <- seq(from = -4, to = 4, by = 0.01)
y <- dnorm(x)

mean(y)
confidence_mean(y, type = "student")
confidence_mean(y, type = "normal")

## Confidence interval for a propotion
confidence_binomial(118, n = 236)

x <- c(35, 74, 22, 69)
confidence_multinomial(x)

Nonparametric Bootstrap Confidence Interval

Description

Computes equi-tailed two-sided nonparametric confidence interval.

Usage

confidence_bootstrap(object, ...)

## S4 method for signature 'numeric'
confidence_bootstrap(
  object,
  level = 0.95,
  type = c("basic", "normal", "student", "percentiles"),
  t0 = NULL,
  var_t0 = NULL,
  var_t = NULL,
  ...
)

Arguments

Value

A length-two numeric vector giving the lower and upper confidence limits.

Author(s)

N. Frerebeau

References

Davison, A. C. & Hinkley, D. V. (1997). Bootstrap Methods and Their Application. Cambridge Series on Statistical and Probabilistic Mathematics. Cambridge: Cambridge University Press.

See Also

bootstrap()

Other summary statistics: confidence_binomial(), confidence_mean(), confidence_multinomial(), interval_credible(), interval_hdr()

Examples

x <- rnorm(20)

## Bootstrap
bootstrap(x, do = mean, n = 100)

## Estimate the 25th and 95th percentiles
quant <- function(x) { quantile(x, probs = c(0.25, 0.75)) }
bootstrap(x, n = 100, do = mean, f = quant)

## Get the n bootstrap estimates
(z <- bootstrap(x, n = 100, do = mean, f = function(x) { x }))

## Basic bootstrap confidence interval
confidence_bootstrap(z, level = 0.95, type = "basic", t0 = mean(x))

Confidence Interval for a Mean

Description

Computes a confidence interval for a mean at a desired level of significance.

Usage

confidence_mean(object, ...)

## S4 method for signature 'numeric'
confidence_mean(object, level = 0.95, type = c("student", "normal"))

Arguments

Value

A length-two numeric vector giving the lower and upper confidence limits.

Author(s)

N. Frerebeau

See Also

Other summary statistics: confidence_binomial(), confidence_bootstrap(), confidence_multinomial(), interval_credible(), interval_hdr()

Examples

## Confidence interval for a mean
x <- seq(from = -4, to = 4, by = 0.01)
y <- dnorm(x)

mean(y)
confidence_mean(y, type = "student")
confidence_mean(y, type = "normal")

## Confidence interval for a propotion
confidence_binomial(118, n = 236)

x <- c(35, 74, 22, 69)
confidence_multinomial(x)

Confidence Interval for Multinomial Proportions

Description

Computes Wald interval for a proportion at a desired level of significance.

Usage

confidence_multinomial(object, ...)

## S4 method for signature 'numeric'
confidence_multinomial(
  object,
  level = 0.95,
  method = "wald",
  corrected = FALSE
)

Arguments

Value

A two column numeric matrix giving the lower and upper confidence limits.

Author(s)

N. Frerebeau

See Also

Other summary statistics: confidence_binomial(), confidence_bootstrap(), confidence_mean(), interval_credible(), interval_hdr()

Examples

## Confidence interval for a mean
x <- seq(from = -4, to = 4, by = 0.01)
y <- dnorm(x)

mean(y)
confidence_mean(y, type = "student")
confidence_mean(y, type = "normal")

## Confidence interval for a propotion
confidence_binomial(118, n = 236)

x <- c(35, 74, 22, 69)
confidence_multinomial(x)

Count Values Using a Predicate

Description

Counts values by rows/columns using a predicate function.

Usage

count(x, ...)

## S4 method for signature 'data.frame'
count(x, f, margin = 1, negate = FALSE, na.rm = FALSE, ...)

## S4 method for signature 'matrix'
count(x, f, margin = 1, negate = FALSE, na.rm = FALSE, ...)

Arguments

Value

A numeric vector.

Author(s)

N. Frerebeau

See Also

Other data preparation tools: append_column(), append_rownames(), assign(), compact(), detect(), discard(), get(), keep(), seek()

Examples

## Create a data matrix
X <- matrix(sample(1:10, 25, TRUE), nrow = 5, ncol = 5)

## Add NA
k <- sample(1:25, 3, FALSE)
X[k] <- NA
X

## Count missing values in rows
count(X, f = is.na, margin = 1)
## Count non-missing values in columns
count(X, f = is.na, margin = 2, negate = TRUE)

Data Description

Description

Describes an object.

Usage

describe(x, ...)

## S4 method for signature 'ANY'
describe(x)

Arguments

Value

describe() is called for its side-effects. Invisibly returns x.

Author(s)

N. Frerebeau

See Also

Other data summaries: sparsity()

Examples

## Create a data matrix
X <- matrix(sample(0:9, 15, TRUE), nrow = 3, ncol = 5)

## Add NA
k <- sample(1:15, 3, FALSE)
X[k] <- NA

## Sparsity
sparsity(X)

## Quick description
describe(X)

Find Rows/Columns Using a Predicate

Description

Finds rows/columns in an array-like object using a predicate function.

Usage

detect(x, ...)

## S4 method for signature 'ANY'
detect(x, f, margin = 1, negate = FALSE, all = FALSE, na.rm = FALSE, ...)

Arguments

Value

A logical vector.

Author(s)

N. Frerebeau

See Also

Other data preparation tools: append_column(), append_rownames(), assign(), compact(), count(), discard(), get(), keep(), seek()

Examples

## Create a data matrix
X <- matrix(sample(1:10, 25, TRUE), nrow = 5, ncol = 5)

## Add NA
k <- sample(1:25, 3, FALSE)
X[k] <- NA
X

## Find row with NA
detect(X, f = is.na, margin = 1)
## Find column without any NA
detect(X, f = is.na, margin = 2, negate = TRUE, all = TRUE)

Remove Rows/Columns Using a Predicate

Description

Removes rows/columns in an array-like object using a predicate function.

Usage

discard(x, ...)

discard_columns(x, ...)

discard_rows(x, ...)

## S4 method for signature 'ANY'
discard(
  x,
  f,
  margin = 1,
  negate = FALSE,
  all = FALSE,
  na.rm = FALSE,
  verbose = getOption("arkhe.verbose"),
  ...
)

## S4 method for signature 'ANY'
discard_rows(
  x,
  f,
  negate = FALSE,
  all = FALSE,
  na.rm = FALSE,
  verbose = getOption("arkhe.verbose"),
  ...
)

## S4 method for signature 'ANY'
discard_columns(
  x,
  f,
  negate = FALSE,
  all = FALSE,
  na.rm = FALSE,
  verbose = getOption("arkhe.verbose"),
  ...
)

Arguments

Author(s)

N. Frerebeau

See Also

Other data preparation tools: append_column(), append_rownames(), assign(), compact(), count(), detect(), get(), keep(), seek()

Examples

## Create a data matrix
X <- matrix(sample(1:10, 25, TRUE), nrow = 5, ncol = 5)

## Add NA
k <- sample(1:25, 3, FALSE)
X[k] <- NA
X

## Remove row with any NA
discard(X, f = is.na, margin = 1, all = FALSE)
## Remove column with any NA
discard(X, f = is.na, margin = 2, all = FALSE)

Get Rows/Columns by Name

Description

Returns rows/columns selected by name in an array-like object.

Usage

get_columns(x, ...)

get_rows(x, ...)

## S4 method for signature 'ANY'
get_columns(x, select = NULL, names = NULL, ...)

## S4 method for signature 'ANY'
get_rows(x, select = NULL, names = NULL, ...)

Arguments

Value

An object of the same sort as x.

Author(s)

N. Frerebeau

See Also

Other data preparation tools: append_column(), append_rownames(), assign(), compact(), count(), detect(), discard(), keep(), seek()

Examples

## Seek columns
seek_columns(iris, select = startsWith, prefix = "Petal")
seek_columns(iris, names = c("Petal.Length", "Petal.Width"))

## Get columns
x <- get_columns(iris, select = startsWith, prefix = "Petal")
head(x)

x <- get_columns(iris, names = c("Petal.Length", "Petal.Width"))
head(x)

Bayesian Credible Interval

Description

Computes the shortest credible interval within which an unobserved parameter value falls with a particular probability.

Usage

interval_credible(x, ...)

## S4 method for signature 'numeric'
interval_credible(x, level = 0.95)

Arguments

Value

A three-columns numeric matrix giving the lower and upper boundaries of the credible interval and associated probability.

Author(s)

N. Frerebeau

See Also

Other summary statistics: confidence_binomial(), confidence_bootstrap(), confidence_mean(), confidence_multinomial(), interval_hdr()

Examples

## HDR of the Old Faithful eruption times
interval_hdr(faithful$eruptions)

Highest Density Regions

Description

Highest Density Regions

Usage

interval_hdr(x, y, ...)

## S4 method for signature 'numeric,numeric'
interval_hdr(x, y, level = 0.954)

## S4 method for signature 'numeric,missing'
interval_hdr(x, level = 0.954, ...)

Arguments

Value

A three-columns numeric matrix giving the lower and upper boundaries of the HPD interval and associated probabilities.

Author(s)

N. Frerebeau

References

Hyndman, R. J. (1996). Computing and graphing highest density regions. American Statistician, 50: 120-126. doi:10.2307/2684423.

See Also

Other summary statistics: confidence_binomial(), confidence_bootstrap(), confidence_mean(), confidence_multinomial(), interval_credible()

Examples

## HDR of the Old Faithful eruption times
interval_hdr(faithful$eruptions)

Scalar Type Predicates

Description

Scalar Type Predicates

Usage

is_scalar_list(x)

is_scalar_atomic(x)

is_scalar_vector(x)

is_scalar_numeric(x)

is_scalar_integer(x)

is_scalar_double(x)

is_scalar_character(x)

is_scalar_logical(x)

Arguments

Value

A logical scalar.

See Also

Other predicates: predicate-attributes, predicate-data, predicate-matrix, predicate-names, predicate-numeric, predicate-trend, predicate-type

Jackknife Estimation

Description

Jackknife Estimation

Usage

jackknife(object, ...)

## S4 method for signature 'numeric'
jackknife(object, do, ..., f = NULL)

Arguments

Value

If f is NULL (the default), jackknife() returns a named numeric vector with the following elements:

original

The observed value of do applied to object.

mean

The jackknife estimate of mean of do.

bias

The jackknife estimate of bias of do.

error

The jackknife estimate of standard error of do.

If f is a function, jackknife() returns the result of f applied to the leave-one-out values of do.

Author(s)

N. Frerebeau

See Also

Other resampling methods: bootstrap(), resample_multinomial(), resample_uniform()

Examples

x <- rnorm(20)

## Jackknife
jackknife(x, do = mean) # Sample mean

## Get the leave-one-out values instead of summary
jackknife(x, do = mean, f = function(x) { x })

Keep Rows/Columns Using a Predicate

Description

Keeps rows/columns in an array-like object using a predicate function.

Usage

keep(x, ...)

keep_columns(x, ...)

keep_rows(x, ...)

## S4 method for signature 'ANY'
keep(
  x,
  f,
  margin = 1,
  negate = FALSE,
  all = FALSE,
  na.rm = FALSE,
  verbose = getOption("arkhe.verbose"),
  ...
)

## S4 method for signature 'ANY'
keep_rows(
  x,
  f,
  negate = FALSE,
  all = FALSE,
  na.rm = FALSE,
  verbose = getOption("arkhe.verbose"),
  ...
)

## S4 method for signature 'ANY'
keep_columns(
  x,
  f,
  negate = FALSE,
  all = FALSE,
  na.rm = FALSE,
  verbose = getOption("arkhe.verbose"),
  ...
)

Arguments

Author(s)

N. Frerebeau

See Also

Other data preparation tools: append_column(), append_rownames(), assign(), compact(), count(), detect(), discard(), get(), seek()

Examples

## Create a data matrix
X <- matrix(sample(1:10, 25, TRUE), nrow = 5, ncol = 5)

## Add NA
k <- sample(1:25, 3, FALSE)
X[k] <- NA
X

## Keep row without any NA
keep(X, f = is.na, margin = 1, negate = TRUE, all = TRUE)
## Keep row without any NA
keep(X, f = is.na, margin = 2, negate = TRUE, all = TRUE)

Label Percentages

Description

Label Percentages

Usage

label_percent(x, digits = NULL, trim = FALSE)

Arguments

Value

A character vector.

Greatest Common Divisor

Description

Computes the greatest common divisor (GCD) of two integer using the Euclidean algorithm.

Usage

math_gcd(x, y)

## S4 method for signature 'numeric,numeric'
math_gcd(x, y)

Arguments

Value

A numeric vector.

Author(s)

N. Frerebeau

See Also

Other mathematic functions: math_lcm()

Least Common Multiple

Description

Computes the lowest common multiple of the denominators of a set of fractions.

Usage

math_lcm(x, y)

## S4 method for signature 'numeric,numeric'
math_lcm(x, y)

Arguments

Value

A numeric vector.

Author(s)

N. Frerebeau

See Also

Other mathematic functions: math_gcd()

Default value for NULL

Description

Replaces NULL with a default value.

Usage

x %||% y

Arguments

Value

If x is NULL, returns y; otherwise returns x.

See Also

Other utilities: concat

Attributes Predicates

Description

• has_length() checks how long is an object.

• is_empty() checks is an object is empty (any zero-length dimensions).

Usage

has_length(x, n = NULL)

is_empty(x)

Arguments

Value

A logical scalar.

See Also

Other predicates: is_scalar, predicate-data, predicate-matrix, predicate-names, predicate-numeric, predicate-trend, predicate-type

Utility Predicates

Description

• has_missing() and has_infinite() check if an object contains missing or infinite values.

• has_duplicates() checks if an object has duplicated elements.

Usage

has_missing(x)

has_infinite(x)

has_duplicates(x)

is_unique(x, tolerance = sqrt(.Machine$double.eps), na.rm = FALSE)

Arguments

Value

A logical scalar.

See Also

Other predicates: is_scalar, predicate-attributes, predicate-matrix, predicate-names, predicate-numeric, predicate-trend, predicate-type

Matrix Predicates

Description

• is_square() checks if a matrix is square.

• is_symmetric() checks if a matrix is symmetric.

Usage

is_square(x)

is_symmetric(x)

Arguments

Value

A logical scalar.

See Also

Other predicates: is_scalar, predicate-attributes, predicate-data, predicate-names, predicate-numeric, predicate-trend, predicate-type

Names Predicates

Description

Checks if an object is named.

Usage

has_names(x, names = NULL)

has_rownames(x, names = NULL)

has_colnames(x, names = NULL)

Arguments

Value

A logical scalar.

See Also

Other predicates: is_scalar, predicate-attributes, predicate-data, predicate-matrix, predicate-numeric, predicate-trend, predicate-type

Numeric Predicates

Description

Check numeric objects:

• is_zero() checks if an object contains only zeros.

• is_odd() and is_even() check if a number is odd or even, respectively.

• is_positive() and is_negative check if an object contains only (strictly) positive or negative numbers.

• is_whole() checks if an object only contains whole numbers.

Usage

is_zero(x, tolerance = sqrt(.Machine$double.eps), ...)

is_odd(x, ...)

is_even(x, ...)

is_positive(x, strict = FALSE, ...)

is_negative(x, strict = FALSE, ...)

is_whole(x, tolerance = sqrt(.Machine$double.eps), ...)

Arguments

Value

A logical vector.

See Also

Other predicates: is_scalar, predicate-attributes, predicate-data, predicate-matrix, predicate-names, predicate-trend, predicate-type

Numeric Trend Predicates

Description

Check numeric objects:

• is_constant() checks for equality among all elements of a vector.

• is_increasing() and is_decreasing() check if a sequence of numbers is monotonically increasing or decreasing, respectively.

Usage

is_constant(x, tolerance = sqrt(.Machine$double.eps), na.rm = FALSE)

is_increasing(x, na.rm = FALSE)

is_decreasing(x, na.rm = FALSE)

is_greater(x, y, strict = FALSE, na.rm = FALSE)

is_lower(x, y, strict = FALSE, na.rm = FALSE)

Arguments

Value

A logical scalar.

See Also

Other predicates: is_scalar, predicate-attributes, predicate-data, predicate-matrix, predicate-names, predicate-numeric, predicate-type

Type Predicates

Description

Type Predicates

Usage

is_list(x)

is_atomic(x)

is_vector(x)

is_numeric(x)

is_integer(x)

is_double(x)

is_character(x)

is_logical(x)

is_error(x)

is_warning(x)

is_message(x)

Arguments

Value

A logical scalar.

See Also

Other predicates: is_scalar, predicate-attributes, predicate-data, predicate-matrix, predicate-names, predicate-numeric, predicate-trend

Remove Rows/Columns with Infinite Values

Description

Removes rows/columns that contain infinite values.

Usage

remove_Inf(x, ...)

## S4 method for signature 'ANY'
remove_Inf(x, margin = 1, all = FALSE, verbose = getOption("arkhe.verbose"))

Arguments

Author(s)

N. Frerebeau

See Also

Other data cleaning tools: clean_whitespace(), remove_NA(), remove_constant(), remove_empty(), remove_zero(), replace_Inf(), replace_NA(), replace_empty(), replace_zero()

Examples

## Create a data matrix
X <- matrix(sample(1:10, 25, TRUE), nrow = 5, ncol = 5)

## Add Inf
k <- sample(1:25, 3, FALSE)
X[k] <- Inf
X

## Remove rows with Inf
remove_Inf(X, margin = 1)

## Replace Inf with zeros
replace_Inf(X, value = 0)

Remove Rows/Columns with Missing Values

Description

Removes rows/columns that contain missing values.

Usage

remove_NA(x, ...)

## S4 method for signature 'ANY'
remove_NA(x, margin = 1, all = FALSE, verbose = getOption("arkhe.verbose"))

Arguments

Author(s)

N. Frerebeau

See Also

Other data cleaning tools: clean_whitespace(), remove_Inf(), remove_constant(), remove_empty(), remove_zero(), replace_Inf(), replace_NA(), replace_empty(), replace_zero()

Examples

## Create a data matrix
X <- matrix(sample(1:10, 25, TRUE), nrow = 5, ncol = 5)

## Add NA
k <- sample(1:25, 3, FALSE)
X[k] <- NA
X

## Remove rows with NA
remove_NA(X, margin = 1)

## Replace NA with zeros
replace_NA(X, value = 0)

Remove Constant Columns

Description

Remove Constant Columns

Usage

remove_constant(x, ...)

## S4 method for signature 'ANY'
remove_constant(x, na.rm = FALSE, verbose = getOption("arkhe.verbose"))

Arguments

Author(s)

N. Frerebeau

See Also

Other data cleaning tools: clean_whitespace(), remove_Inf(), remove_NA(), remove_empty(), remove_zero(), replace_Inf(), replace_NA(), replace_empty(), replace_zero()

Examples

## Create a data.frame
X <- data.frame(A = 1, B = 1:3)
X

remove_constant(X)

## Add NA
X[1, 1] <- NA
remove_constant(X)
remove_constant(X, na.rm = TRUE)

Remove Rows/Columns with Empty String

Description

Removes rows/columns that contain empty strings.

Usage

remove_empty(x, ...)

## S4 method for signature 'ANY'
remove_empty(x, margin = 1, all = FALSE, verbose = getOption("arkhe.verbose"))

Arguments

Author(s)

N. Frerebeau

See Also

Other data cleaning tools: clean_whitespace(), remove_Inf(), remove_NA(), remove_constant(), remove_zero(), replace_Inf(), replace_NA(), replace_empty(), replace_zero()

Examples

## Create a data matrix
X <- matrix(sample(LETTERS, 25, TRUE), nrow = 5, ncol = 5)

## Add empty string
k <- sample(1:25, 3, FALSE)
X[k] <- ""
X

## Remove rows with empty strings
remove_empty(X, margin = 1)

## Replace empty strings
replace_empty(X, value = "XXX")

Remove Rows/Columns with Zeros

Description

Removes rows/columns that contain zeros.

Usage

remove_zero(x, ...)

## S4 method for signature 'ANY'
remove_zero(x, margin = 1, all = FALSE, verbose = getOption("arkhe.verbose"))

Arguments

Author(s)

N. Frerebeau

See Also

Other data cleaning tools: clean_whitespace(), remove_Inf(), remove_NA(), remove_constant(), remove_empty(), replace_Inf(), replace_NA(), replace_empty(), replace_zero()

Examples

## Create a data matrix
X <- matrix(sample(1:10, 25, TRUE), nrow = 5, ncol = 5)

## Add zero
k <- sample(1:25, 3, FALSE)
X[k] <- 0
X

## Remove rows with zero
remove_zero(X, margin = 1)

## Replace zero
replace_zero(X, value = 1)

Replace Infinite Values

Description

Replaces infinite values values.

Usage

replace_Inf(x, ...)

## S4 method for signature 'matrix'
replace_Inf(x, value = 0)

## S4 method for signature 'data.frame'
replace_Inf(x, value = 0)

Arguments

Author(s)

N. Frerebeau

See Also

Other data cleaning tools: clean_whitespace(), remove_Inf(), remove_NA(), remove_constant(), remove_empty(), remove_zero(), replace_NA(), replace_empty(), replace_zero()

Examples

## Create a data matrix
X <- matrix(sample(1:10, 25, TRUE), nrow = 5, ncol = 5)

## Add Inf
k <- sample(1:25, 3, FALSE)
X[k] <- Inf
X

## Remove rows with Inf
remove_Inf(X, margin = 1)

## Replace Inf with zeros
replace_Inf(X, value = 0)

Replace Missing Values

Description

Replaces missing values values.

Usage

replace_NA(x, ...)

## S4 method for signature 'matrix'
replace_NA(x, value = 0)

## S4 method for signature 'data.frame'
replace_NA(x, value = 0)

Arguments

Author(s)

N. Frerebeau

See Also

Other data cleaning tools: clean_whitespace(), remove_Inf(), remove_NA(), remove_constant(), remove_empty(), remove_zero(), replace_Inf(), replace_empty(), replace_zero()

Examples

## Create a data matrix
X <- matrix(sample(1:10, 25, TRUE), nrow = 5, ncol = 5)

## Add NA
k <- sample(1:25, 3, FALSE)
X[k] <- NA
X

## Remove rows with NA
remove_NA(X, margin = 1)

## Replace NA with zeros
replace_NA(X, value = 0)

Replace Empty String

Description

Replaces empty strings.

Usage

replace_empty(x, ...)

## S4 method for signature 'matrix'
replace_empty(x, value)

## S4 method for signature 'data.frame'
replace_empty(x, value)

Arguments

Author(s)

N. Frerebeau

See Also

Other data cleaning tools: clean_whitespace(), remove_Inf(), remove_NA(), remove_constant(), remove_empty(), remove_zero(), replace_Inf(), replace_NA(), replace_zero()

Examples

## Create a data matrix
X <- matrix(sample(LETTERS, 25, TRUE), nrow = 5, ncol = 5)

## Add empty string
k <- sample(1:25, 3, FALSE)
X[k] <- ""
X

## Remove rows with empty strings
remove_empty(X, margin = 1)

## Replace empty strings
replace_empty(X, value = "XXX")

Replace Zeros

Description

Replaces zeros.

Usage

replace_zero(x, ...)

## S4 method for signature 'matrix'
replace_zero(x, value)

## S4 method for signature 'data.frame'
replace_zero(x, value)

Arguments

Author(s)

N. Frerebeau

See Also

Other data cleaning tools: clean_whitespace(), remove_Inf(), remove_NA(), remove_constant(), remove_empty(), remove_zero(), replace_Inf(), replace_NA(), replace_empty()

Examples

## Create a data matrix
X <- matrix(sample(1:10, 25, TRUE), nrow = 5, ncol = 5)

## Add zero
k <- sample(1:25, 3, FALSE)
X[k] <- 0
X

## Remove rows with zero
remove_zero(X, margin = 1)

## Replace zero
replace_zero(X, value = 1)

Draw Multinomial Random Sample

Description

Draws a random (sub)sample from a multinomial distribution.

Usage

resample_multinomial(object, ...)

## S4 method for signature 'numeric'
resample_multinomial(object, n, size = sum(object), ...)

Arguments

Value

A numeric matrix with n rows and k columns.

Author(s)

N. Frerebeau

See Also

stats::rmultinom()

Other resampling methods: bootstrap(), jackknife(), resample_uniform()

Examples

## Uniform distribution
x <- rnorm(20)
resample_uniform(x, n = 10)

## Multinomial distribution
x <- sample(1:100, 20, TRUE)
resample_multinomial(x, n = 10)

Draw Uniform Random Sample

Description

Draws a random (sub)sample (with or without replacement).

Usage

resample_uniform(object, ...)

## S4 method for signature 'numeric'
resample_uniform(object, n, size = length(object), replace = FALSE, ...)

Arguments

Value

A numeric matrix with n rows and size columns.

Author(s)

N. Frerebeau

See Also

Other resampling methods: bootstrap(), jackknife(), resample_multinomial()

Examples

## Uniform distribution
x <- rnorm(20)
resample_uniform(x, n = 10)

## Multinomial distribution
x <- sample(1:100, 20, TRUE)
resample_multinomial(x, n = 10)

Rescale Continuous Vector (minimum, midpoint, maximum)

Description

Rescales continuous vector to have specified minimum, midpoint and maximum.

Usage

scale_midpoint(x, to = c(0, 1), from = range(x, finite = TRUE), midpoint = 0)

Arguments

Value

A numeric vector.

Note

For internal use only.

See Also

Other scales: scale_range()

Rescale Continuous Vector (minimum, maximum)

Description

Rescales continuous vector to have specified minimum and maximum.

Usage

scale_range(x, to = c(0, 1), from = range(x, finite = TRUE))

Arguments

Value

A numeric vector.

Note

For internal use only.

See Also

Other scales: scale_midpoint()

Search Rows/Columns by Name

Description

Searches rows/columns by name in an array-like object.

Usage

seek_columns(x, ...)

seek_rows(x, ...)

## S4 method for signature 'data.frame'
seek_rows(x, select = NULL, names = NULL, ...)

## S4 method for signature 'matrix'
seek_rows(x, select = NULL, names = NULL, ...)

## S4 method for signature 'data.frame'
seek_columns(x, select = NULL, names = NULL, ...)

## S4 method for signature 'matrix'
seek_columns(x, select = NULL, names = NULL, ...)

Arguments

Value

An integer vector or NULL.

Author(s)

N. Frerebeau

See Also

Other data preparation tools: append_column(), append_rownames(), assign(), compact(), count(), detect(), discard(), get(), keep()

Examples

## Seek columns
seek_columns(iris, select = startsWith, prefix = "Petal")
seek_columns(iris, names = c("Petal.Length", "Petal.Width"))

## Get columns
x <- get_columns(iris, select = startsWith, prefix = "Petal")
head(x)

x <- get_columns(iris, names = c("Petal.Length", "Petal.Width"))
head(x)

Sparsity

Description

Computes data sparsity (proportion of zeros).

Usage

sparsity(x, ...)

## S4 method for signature 'matrix'
sparsity(x, count = FALSE)

## S4 method for signature 'data.frame'
sparsity(x, count = FALSE)

Arguments

Details

If x is a data.frame, sparsity is computed on numeric variables only.

Value

A length-one numeric vector.

Author(s)

N. Frerebeau

See Also

Other data summaries: describe()

Examples

## Create a data matrix
X <- matrix(sample(0:9, 15, TRUE), nrow = 3, ncol = 5)

## Add NA
k <- sample(1:15, 3, FALSE)
X[k] <- NA

## Sparsity
sparsity(X)

## Quick description
describe(X)

Validate a Condition

Description

Validate a Condition

Usage

validate(expr)

Arguments

Value

Returns NULL on success, otherwise returns the error as a string.

Author(s)

N. Frerebeau

Evaluate an Expression with a Temporarily Seed

Description

Evaluate an Expression with a Temporarily Seed

Usage

with_seed(expr, seed, ..., envir = parent.frame(), rounding = TRUE)

Arguments

Value

The results of expr evaluated.

See Also

set.seed()