Package 'datawizard'

Description

This function can be used to adjust the data for the effect of other variables present in the dataset. It is based on an underlying fitting of regressions models, allowing for quite some flexibility, such as including factors as random effects in mixed models (multilevel partialization), continuous variables as smooth terms in general additive models (non-linear partialization) and/or fitting these models under a Bayesian framework. The values returned by this function are the residuals of the regression models. Note that a regular correlation between two "adjusted" variables is equivalent to the partial correlation between them.

Usage

adjust(
  data,
  effect = NULL,
  select = is.numeric,
  exclude = NULL,
  multilevel = FALSE,
  additive = FALSE,
  bayesian = FALSE,
  keep_intercept = FALSE,
  ignore_case = FALSE,
  regex = FALSE,
  verbose = FALSE
)

data_adjust(
  data,
  effect = NULL,
  select = is.numeric,
  exclude = NULL,
  multilevel = FALSE,
  additive = FALSE,
  bayesian = FALSE,
  keep_intercept = FALSE,
  ignore_case = FALSE,
  regex = FALSE,
  verbose = FALSE
)

Arguments

Value

A data frame comparable to data, with adjusted variables.

Examples

adjusted_all <- adjust(attitude)
head(adjusted_all)
adjusted_one <- adjust(attitude, effect = "complaints", select = "rating")
head(adjusted_one)

adjust(attitude, effect = "complaints", select = "rating", bayesian = TRUE)
adjust(attitude, effect = "complaints", select = "rating", additive = TRUE)
attitude$complaints_LMH <- cut(attitude$complaints, 3)
adjust(attitude, effect = "complaints_LMH", select = "rating", multilevel = TRUE)


# Generate data
data <- simulate_correlation(n = 100, r = 0.7)
data$V2 <- (5 * data$V2) + 20 # Add intercept

# Adjust
adjusted <- adjust(data, effect = "V1", select = "V2")
adjusted_icpt <- adjust(data, effect = "V1", select = "V2", keep_intercept = TRUE)

# Visualize
plot(
  data$V1, data$V2,
  pch = 19, col = "blue",
  ylim = c(min(adjusted$V2), max(data$V2)),
  main = "Original (blue), adjusted (green), and adjusted - intercept kept (red) data"
)
abline(lm(V2 ~ V1, data = data), col = "blue")
points(adjusted$V1, adjusted$V2, pch = 19, col = "green")
abline(lm(V2 ~ V1, data = adjusted), col = "green")
points(adjusted_icpt$V1, adjusted_icpt$V2, pch = 19, col = "red")
abline(lm(V2 ~ V1, data = adjusted_icpt), col = "red")

Description

Assign variable and values labels to a variable or variables in a data frame. Labels are stored as attributes ("label" for variable labels and "labels") for value labels.

Usage

assign_labels(x, ...)

## S3 method for class 'numeric'
assign_labels(x, variable = NULL, values = NULL, ...)

## S3 method for class 'data.frame'
assign_labels(
  x,
  select = NULL,
  exclude = NULL,
  values = NULL,
  ignore_case = FALSE,
  regex = FALSE,
  verbose = TRUE,
  ...
)

Arguments

Value

A labelled variable, or a data frame of labelled variables.

Selection of variables - the select argument

For most functions that have a select argument (including this function), the complete input data frame is returned, even when select only selects a range of variables. That is, the function is only applied to those variables that have a match in select, while all other variables remain unchanged. In other words: for this function, select will not omit any non-included variables, so that the returned data frame will include all variables from the input data frame.

Examples

x <- 1:3
# labelling by providing required number of labels
assign_labels(
  x,
  variable = "My x",
  values = c("one", "two", "three")
)

# labelling using named vectors
data(iris)
out <- assign_labels(
  iris$Species,
  variable = "Labelled Species",
  values = c(`setosa` = "Spec1", `versicolor` = "Spec2", `virginica` = "Spec3")
)
str(out)

# data frame example
out <- assign_labels(
  iris,
  select = "Species",
  variable = "Labelled Species",
  values = c(`setosa` = "Spec1", `versicolor` = "Spec2", `virginica` = "Spec3")
)
str(out$Species)

# Partial labelling
x <- 1:5
assign_labels(
  x,
  variable = "My x",
  values = c(`1` = "lowest", `5` = "highest")
)

Description

This functions divides the range of variables into intervals and recodes the values inside these intervals according to their related interval. It is basically a wrapper around base R's cut(), providing a simplified and more accessible way to define the interval breaks (cut-off values).

Usage

categorize(x, ...)

## S3 method for class 'numeric'
categorize(
  x,
  split = "median",
  n_groups = NULL,
  range = NULL,
  lowest = 1,
  breaks = "exclusive",
  labels = NULL,
  verbose = TRUE,
  ...
)

## S3 method for class 'data.frame'
categorize(
  x,
  select = NULL,
  exclude = NULL,
  split = "median",
  n_groups = NULL,
  range = NULL,
  lowest = 1,
  breaks = "exclusive",
  labels = NULL,
  append = FALSE,
  ignore_case = FALSE,
  regex = FALSE,
  verbose = TRUE,
  ...
)

Arguments

Value

x, recoded into groups. By default x is numeric, unless labels is specified. In this case, a factor is returned, where the factor levels (i.e. recoded groups are labelled accordingly.

Splits and breaks (cut-off values)

Breaks are by default exclusive, this means that these values indicate the lower bound of the next group or interval to begin. Take a simple example, a numeric variable with values from 1 to 9. The median would be 5, thus the first interval ranges from 1-4 and is recoded into 1, while 5-9 would turn into 2 (compare cbind(1:9, categorize(1:9))). The same variable, using split = "quantile" and n_groups = 3 would define breaks at 3.67 and 6.33 (see quantile(1:9, probs = c(1/3, 2/3))), which means that values from 1 to 3 belong to the first interval and are recoded into 1 (because the next interval starts at 3.67), 4 to 6 into 2 and 7 to 9 into 3.

The opposite behaviour can be achieved using breaks = "inclusive", in which case

Recoding into groups with equal size or range

split = "equal_length" and split = "equal_range" try to divide the range of x into intervals of similar (or same) length. The difference is that split = "equal_length" will divide the range of x into n_groups pieces and thereby defining the intervals used as breaks (hence, it is equivalent to cut(x, breaks = n_groups)), while split = "equal_range" will cut x into intervals that all have the length of range, where the first interval by defaults starts at 1. The lowest (or starting) value of that interval can be defined using the lowest argument.

Selection of variables - the select argument

For most functions that have a select argument (including this function), the complete input data frame is returned, even when select only selects a range of variables. That is, the function is only applied to those variables that have a match in select, while all other variables remain unchanged. In other words: for this function, select will not omit any non-included variables, so that the returned data frame will include all variables from the input data frame.

See Also

• Functions to rename stuff: data_rename(), data_rename_rows(), data_addprefix(), data_addsuffix()

• Functions to reorder or remove columns: data_reorder(), data_relocate(), data_remove()

• Functions to reshape, pivot or rotate data frames: data_to_long(), data_to_wide(), data_rotate()

• Functions to recode data: rescale(), reverse(), categorize(), recode_values(), slide()

• Functions to standardize, normalize, rank-transform: center(), standardize(), normalize(), ranktransform(), winsorize()

• Split and merge data frames: data_partition(), data_merge()

• Functions to find or select columns: data_select(), extract_column_names()

• Functions to filter rows: data_match(), data_filter()

Examples

set.seed(123)
x <- sample(1:10, size = 50, replace = TRUE)

table(x)

# by default, at median
table(categorize(x))

# into 3 groups, based on distribution (quantiles)
table(categorize(x, split = "quantile", n_groups = 3))

# into 3 groups, user-defined break
table(categorize(x, split = c(3, 5)))

set.seed(123)
x <- sample(1:100, size = 500, replace = TRUE)

# into 5 groups, try to recode into intervals of similar length,
# i.e. the range within groups is the same for all groups
table(categorize(x, split = "equal_length", n_groups = 5))

# into 5 groups, try to return same range within groups
# i.e. 1-20, 21-40, 41-60, etc. Since the range of "x" is
# 1-100, and we have a range of 20, this results into 5
# groups, and thus is for this particular case identical
# to the previous result.
table(categorize(x, split = "equal_range", range = 20))

# return factor with value labels instead of numeric value
set.seed(123)
x <- sample(1:10, size = 30, replace = TRUE)
categorize(x, "equal_length", n_groups = 3)
categorize(x, "equal_length", n_groups = 3, labels = c("low", "mid", "high"))

# cut numeric into groups with the mean or median as a label name
x <- sample(1:10, size = 30, replace = TRUE)
categorize(x, "equal_length", n_groups = 3, labels = "mean")
categorize(x, "equal_length", n_groups = 3, labels = "median")

# cut numeric into groups with the requested range as a label name
# each category has the same range, and labels indicate this range
categorize(mtcars$mpg, "equal_length", n_groups = 5, labels = "range")
# in this example, each category has the same range, but labels only refer
# to the ranges of the actual values (present in the data) inside each group
categorize(mtcars$mpg, "equal_length", n_groups = 5, labels = "observed")

Description

Performs a grand-mean centering of data.

Usage

center(x, ...)

centre(x, ...)

## S3 method for class 'numeric'
center(
  x,
  robust = FALSE,
  weights = NULL,
  reference = NULL,
  center = NULL,
  verbose = TRUE,
  ...
)

## S3 method for class 'data.frame'
center(
  x,
  select = NULL,
  exclude = NULL,
  robust = FALSE,
  weights = NULL,
  reference = NULL,
  center = NULL,
  force = FALSE,
  remove_na = c("none", "selected", "all"),
  append = FALSE,
  ignore_case = FALSE,
  verbose = TRUE,
  regex = FALSE,
  ...
)

Arguments

Value

The centered variables.

Selection of variables - the select argument

For most functions that have a select argument (including this function), the complete input data frame is returned, even when select only selects a range of variables. That is, the function is only applied to those variables that have a match in select, while all other variables remain unchanged. In other words: for this function, select will not omit any non-included variables, so that the returned data frame will include all variables from the input data frame.

Note

Difference between centering and standardizing: Standardized variables are computed by subtracting the mean of the variable and then dividing it by the standard deviation, while centering variables involves only the subtraction.

See Also

If centering within-clusters (instead of grand-mean centering) is required, see demean(). For standardizing, see standardize(), and makepredictcall.dw_transformer() for use in model formulas.

Examples

data(iris)

# entire data frame or a vector
head(iris$Sepal.Width)
head(center(iris$Sepal.Width))
head(center(iris))
head(center(iris, force = TRUE))

# only the selected columns from a data frame
center(anscombe, select = c("x1", "x3"))
center(anscombe, exclude = c("x1", "x3"))

# centering with reference center and scale
d <- data.frame(
  a = c(-2, -1, 0, 1, 2),
  b = c(3, 4, 5, 6, 7)
)

# default centering at mean
center(d)

# centering, using 0 as mean
center(d, center = 0)

# centering, using -5 as mean
center(d, center = -5)

Description

Compute the coefficient of variation (CV, ratio of the standard deviation to the mean, $\sigma/\mu$) for a set of numeric values.

Usage

coef_var(x, ...)

distribution_coef_var(x, ...)

## S3 method for class 'numeric'
coef_var(
  x,
  mu = NULL,
  sigma = NULL,
  method = c("standard", "unbiased", "median_mad", "qcd"),
  trim = 0,
  remove_na = FALSE,
  n = NULL,
  ...
)

Arguments

Details

CV is only applicable of values taken on a ratio scale: values that have a fixed meaningfully defined 0 (which is either the lowest or highest possible value), and that ratios between them are interpretable For example, how many sandwiches have I eaten this week? 0 means "none" and 20 sandwiches is 4 times more than 5 sandwiches. If I were to center the number of sandwiches, it will no longer be on a ratio scale (0 is no "none" it is the mean, and the ratio between 4 and -2 is not meaningful). Scaling a ratio scale still results in a ratio scale. So I can re define "how many half sandwiches did I eat this week ( = sandwiches * 0.5) and 0 would still mean "none", and 20 half-sandwiches is still 4 times more than 5 half-sandwiches.

This means that CV is NOT invariant to shifting, but it is to scaling:

sandwiches <- c(0, 4, 15, 0, 0, 5, 2, 7)
coef_var(sandwiches)
#> [1] 1.239094

coef_var(sandwiches / 2) # same
#> [1] 1.239094

coef_var(sandwiches + 4) # different! 0 is no longer meaningful!
#> [1] 0.6290784

Value

The computed coefficient of variation for x.

Examples

coef_var(1:10)
coef_var(c(1:10, 100), method = "median_mad")
coef_var(c(1:10, 100), method = "qcd")
coef_var(mu = 10, sigma = 20)
coef_var(mu = 10, sigma = 20, method = "unbiased", n = 30)

Description

Tries to convert vector to numeric if possible (if no warnings or errors). Otherwise, leaves it as is.

Usage

coerce_to_numeric(x)

Arguments

Value

Numeric vector (if possible)

Examples

coerce_to_numeric(c("1", "2"))
coerce_to_numeric(c("1", "2", "A"))

Description

Build a deviation contrast matrix, a type of effects contrast matrix.

Usage

contr.deviation(n, base = 1, contrasts = TRUE, sparse = FALSE)

Arguments

Details

In effects coding, unlike treatment/dummy coding (stats::contr.treatment()), each contrast sums to 0. In regressions models, this results in an intercept that represents the (unweighted) average of the group means. In ANOVA settings, this also guarantees that lower order effects represent main effects (and not simple or conditional effects, as is the case when using R's default stats::contr.treatment()).

Deviation coding (contr.deviation) is a type of effects coding. With deviation coding, the coefficients for factor variables are interpreted as the difference of each factor level from the base level (this is the same interpretation as with treatment/dummy coding). For example, for a factor group with levels "A", "B", and "C", with contr.devation, the intercept represents the overall mean (average of the group means for the 3 groups), and the coefficients groupB and groupC represent the differences between the A group mean and the B and C group means, respectively.

Sum coding (stats::contr.sum()) is another type of effects coding. With sum coding, the coefficients for factor variables are interpreted as the difference of each factor level from the grand (across-groups) mean. For example, for a factor group with levels "A", "B", and "C", with contr.sum, the intercept represents the overall mean (average of the group means for the 3 groups), and the coefficients group1 and group2 represent the differences the A and B group means from the overall mean, respectively.

See Also

stats::contr.sum()

Examples

data("mtcars")

mtcars <- data_modify(mtcars, cyl = factor(cyl))

c.treatment <- cbind(Intercept = 1, contrasts(mtcars$cyl))
solve(c.treatment)
#>            4 6 8
#> Intercept  1 0 0  # mean of the 1st level
#> 6         -1 1 0  # 2nd level - 1st level
#> 8         -1 0 1  # 3rd level - 1st level

contrasts(mtcars$cyl) <- contr.sum
c.sum <- cbind(Intercept = 1, contrasts(mtcars$cyl))
solve(c.sum)
#>                4      6      8
#> Intercept  0.333  0.333  0.333   # overall mean
#>            0.667 -0.333 -0.333   # deviation of 1st from overall mean
#>           -0.333  0.667 -0.333   # deviation of 2nd from overall mean


contrasts(mtcars$cyl) <- contr.deviation
c.deviation <- cbind(Intercept = 1, contrasts(mtcars$cyl))
solve(c.deviation)
#>                4     6     8
#> Intercept  0.333 0.333 0.333   # overall mean
#> 6         -1.000 1.000 0.000   # 2nd level - 1st level
#> 8         -1.000 0.000 1.000   # 3rd level - 1st level

## With Interactions -----------------------------------------
mtcars <- data_modify(mtcars, am = C(am, contr = contr.deviation))
mtcars <- data_arrange(mtcars, select = c("cyl", "am"))

mm <- unique(model.matrix(~ cyl * am, data = mtcars))
rownames(mm) <- c(
  "cyl4.am0", "cyl4.am1", "cyl6.am0",
  "cyl6.am1", "cyl8.am0", "cyl8.am1"
)

solve(mm)
#>             cyl4.am0 cyl4.am1 cyl6.am0 cyl6.am1 cyl8.am0 cyl8.am1
#> (Intercept)    0.167    0.167    0.167    0.167    0.167    0.167  # overall mean
#> cyl6          -0.500   -0.500    0.500    0.500    0.000    0.000  # cyl MAIN eff: 2nd - 1st
#> cyl8          -0.500   -0.500    0.000    0.000    0.500    0.500  # cyl MAIN eff: 2nd - 1st
#> am1           -0.333    0.333   -0.333    0.333   -0.333    0.333  # am MAIN eff
#> cyl6:am1       1.000   -1.000   -1.000    1.000    0.000    0.000
#> cyl8:am1       1.000   -1.000    0.000    0.000   -1.000    1.000

Description

Replace missing values in a variable or a data frame.

Usage

convert_na_to(x, ...)

## S3 method for class 'numeric'
convert_na_to(x, replacement = NULL, verbose = TRUE, ...)

## S3 method for class 'character'
convert_na_to(x, replacement = NULL, verbose = TRUE, ...)

## S3 method for class 'data.frame'
convert_na_to(
  x,
  select = NULL,
  exclude = NULL,
  replacement = NULL,
  replace_num = replacement,
  replace_char = replacement,
  replace_fac = replacement,
  ignore_case = FALSE,
  regex = FALSE,
  verbose = TRUE,
  ...
)

Arguments

Value

x, where NA values are replaced by replacement.

Selection of variables - the select argument

For most functions that have a select argument (including this function), the complete input data frame is returned, even when select only selects a range of variables. That is, the function is only applied to those variables that have a match in select, while all other variables remain unchanged. In other words: for this function, select will not omit any non-included variables, so that the returned data frame will include all variables from the input data frame.

Examples

# Convert NA to 0 in a numeric vector
convert_na_to(
  c(9, 3, NA, 2, 3, 1, NA, 8),
  replacement = 0
)

# Convert NA to "missing" in a character vector
convert_na_to(
  c("a", NA, "d", "z", NA, "t"),
  replacement = "missing"
)

### For data frames

test_df <- data.frame(
  x = c(1, 2, NA),
  x2 = c(4, 5, NA),
  y = c("a", "b", NA)
)

# Convert all NA to 0 in numeric variables, and all NA to "missing" in
# character variables
convert_na_to(
  test_df,
  replace_num = 0,
  replace_char = "missing"
)

# Convert a specific variable in the data frame
convert_na_to(
  test_df,
  replace_num = 0,
  replace_char = "missing",
  select = "x"
)

# Convert all variables starting with "x"
convert_na_to(
  test_df,
  replace_num = 0,
  replace_char = "missing",
  select = starts_with("x")
)

# Convert NA to 1 in variable 'x2' and to 0 in all other numeric
# variables
convert_na_to(
  test_df,
  replace_num = 0,
  select = list(x2 = 1)
)

Description

Convert non-missing values in a variable into missing values.

Usage

convert_to_na(x, ...)

## S3 method for class 'numeric'
convert_to_na(x, na = NULL, verbose = TRUE, ...)

## S3 method for class 'factor'
convert_to_na(x, na = NULL, drop_levels = FALSE, verbose = TRUE, ...)

## S3 method for class 'data.frame'
convert_to_na(
  x,
  select = NULL,
  exclude = NULL,
  na = NULL,
  drop_levels = FALSE,
  ignore_case = FALSE,
  regex = FALSE,
  verbose = TRUE,
  ...
)

Arguments

Value

x, where all values in na are converted to NA.

Examples

x <- sample(1:6, size = 30, replace = TRUE)
x
# values 4 and 5 to NA
convert_to_na(x, na = 4:5)

# data frames
set.seed(123)
x <- data.frame(
  a = sample(1:6, size = 20, replace = TRUE),
  b = sample(letters[1:6], size = 20, replace = TRUE),
  c = sample(c(30:33, 99), size = 20, replace = TRUE)
)
# for all numerics, convert 5 to NA. Character/factor will be ignored.
convert_to_na(x, na = 5)

# for numerics, 5 to NA, for character/factor, "f" to NA
convert_to_na(x, na = list(6, "f"))

# select specific variables
convert_to_na(x, select = c("a", "b"), na = list(6, "f"))

Description

Safe and intuitive functions to rename variables or rows in data frames. data_rename() will rename column names, i.e. it facilitates renaming variables data_addprefix() or data_addsuffix() add prefixes or suffixes to column names. data_rename_rows() is a convenient shortcut to add or rename row names of a data frame, but unlike row.names(), its input and output is a data frame, thus, integrating smoothly into a possible pipe-workflow.

Usage

data_addprefix(
  data,
  pattern,
  select = NULL,
  exclude = NULL,
  ignore_case = FALSE,
  regex = FALSE,
  verbose = TRUE,
  ...
)

data_addsuffix(
  data,
  pattern,
  select = NULL,
  exclude = NULL,
  ignore_case = FALSE,
  regex = FALSE,
  verbose = TRUE,
  ...
)

data_rename(
  data,
  pattern = NULL,
  replacement = NULL,
  safe = TRUE,
  verbose = TRUE,
  ...
)

data_rename_rows(data, rows = NULL)

Arguments

Value

A modified data frame.

See Also

• Functions to rename stuff: data_rename(), data_rename_rows(), data_addprefix(), data_addsuffix()

• Functions to reorder or remove columns: data_reorder(), data_relocate(), data_remove()

• Functions to reshape, pivot or rotate data frames: data_to_long(), data_to_wide(), data_rotate()

• Functions to recode data: rescale(), reverse(), categorize(), recode_values(), slide()

• Functions to standardize, normalize, rank-transform: center(), standardize(), normalize(), ranktransform(), winsorize()

• Split and merge data frames: data_partition(), data_merge()

• Functions to find or select columns: data_select(), extract_column_names()

• Functions to filter rows: data_match(), data_filter()

Examples

# Add prefix / suffix to all columns
head(data_addprefix(iris, "NEW_"))
head(data_addsuffix(iris, "_OLD"))

# Rename columns
head(data_rename(iris, "Sepal.Length", "length"))
# data_rename(iris, "FakeCol", "length", safe=FALSE)  # This fails
head(data_rename(iris, "FakeCol", "length")) # This doesn't
head(data_rename(iris, c("Sepal.Length", "Sepal.Width"), c("length", "width")))

# use named vector to rename
head(data_rename(iris, c(length = "Sepal.Length", width = "Sepal.Width")))

# Reset names
head(data_rename(iris, NULL))

# Change all
head(data_rename(iris, replacement = paste0("Var", 1:5)))

Description

data_arrange() orders the rows of a data frame by the values of selected columns.

Usage

data_arrange(data, select = NULL, safe = TRUE)

Arguments

Value

A data frame.

Examples

# Arrange using several variables
data_arrange(head(mtcars), c("gear", "carb"))

# Arrange in decreasing order
data_arrange(head(mtcars), "-carb")

# Throw an error if one of the variables specified doesn't exist
try(data_arrange(head(mtcars), c("gear", "foo"), safe = FALSE))

Description

data_codebook() generates codebooks from data frames, i.e. overviews of all variables and some more information about each variable (like labels, values or value range, frequencies, amount of missing values).

Usage

data_codebook(
  data,
  select = NULL,
  exclude = NULL,
  variable_label_width = NULL,
  value_label_width = NULL,
  max_values = 10,
  range_at = 6,
  ignore_case = FALSE,
  regex = FALSE,
  verbose = TRUE,
  ...
)

## S3 method for class 'data_codebook'
print_html(
  x,
  font_size = "100%",
  line_padding = 3,
  row_color = "#eeeeee",
  ...
)

Arguments

Value

A formatted data frame, summarizing the content of the data frame. Returned columns include the column index of the variables in the original data frame (ID), column name, variable label (if data is labelled), type of variable, number of missing values, unique values (or value range), value labels (for labelled data), and a frequency table (N for each value). Most columns are formatted as character vectors.

Note

There are methods to print() the data frame in a nicer output, as well methods for printing in markdown or HTML format (print_md() and print_html()). The print() method for text outputs passes arguments in ... to insight::export_table().

Examples

data(iris)
data_codebook(iris, select = starts_with("Sepal"))

data(efc)
data_codebook(efc)

# shorten labels
data_codebook(efc, variable_label_width = 20, value_label_width = 15)

# automatic range for numerics at more than 5 unique values
data(mtcars)
data_codebook(mtcars, select = starts_with("c"))

# force all values to be displayed
data_codebook(mtcars, select = starts_with("c"), range_at = 100)

Description

Extract all duplicates, for visual inspection. Note that it also contains the first occurrence of future duplicates, unlike duplicated() or dplyr::distinct()). Also contains an additional column reporting the number of missing values for that row, to help in the decision-making when selecting which duplicates to keep.

Usage

data_duplicated(
  data,
  select = NULL,
  exclude = NULL,
  ignore_case = FALSE,
  regex = FALSE,
  verbose = TRUE
)

Arguments

Value

A dataframe, containing all duplicates.

See Also

data_unique()

Examples

df1 <- data.frame(
  id = c(1, 2, 3, 1, 3),
  year = c(2022, 2022, 2022, 2022, 2000),
  item1 = c(NA, 1, 1, 2, 3),
  item2 = c(NA, 1, 1, 2, 3),
  item3 = c(NA, 1, 1, 2, 3)
)

data_duplicated(df1, select = "id")

data_duplicated(df1, select = c("id", "year"))

# Filter to exclude duplicates
df2 <- df1[-c(1, 5), ]
df2

Description

data_extract() (or its alias extract()) is similar to $. It extracts either a single column or element from an object (e.g., a data frame, list), or multiple columns resp. elements.

Usage

data_extract(data, select, ...)

## S3 method for class 'data.frame'
data_extract(
  data,
  select,
  name = NULL,
  extract = "all",
  as_data_frame = FALSE,
  ignore_case = FALSE,
  regex = FALSE,
  verbose = TRUE,
  ...
)

Arguments

Details

data_extract() can be used to select multiple variables or pull a single variable from a data frame. Thus, the return value is by default not type safe - data_extract() either returns a vector or a data frame.

Extracting single variables (vectors)

When select is the name of a single column, or when select only matches one column, a vector is returned. A single variable is also returned when extract is either ⁠"first⁠ or "last". Setting as_data_frame to TRUE overrides this behaviour and always returns a data frame.

Extracting a data frame of variables

When select is a character vector containing more than one column name (or a numeric vector with more than one valid column indices), or when select uses one of the supported select-helpers that match multiple columns, a data frame is returned. Setting as_data_frame to TRUE always returns a data frame.

Value

A vector (or a data frame) containing the extracted element, or NULL if no matching variable was found.

Examples

# single variable
data_extract(mtcars, cyl, name = gear)
data_extract(mtcars, "cyl", name = gear)
data_extract(mtcars, -1, name = gear)
data_extract(mtcars, cyl, name = 0)
data_extract(mtcars, cyl, name = "row.names")

# selecting multiple variables
head(data_extract(iris, starts_with("Sepal")))
head(data_extract(iris, ends_with("Width")))
head(data_extract(iris, 2:4))

# select first of multiple variables
data_extract(iris, starts_with("Sepal"), extract = "first")

# select first of multiple variables, return as data frame
head(data_extract(iris, starts_with("Sepal"), extract = "first", as_data_frame = TRUE))

Description

This function is comparable to dplyr::group_by(), but just following the datawizard function design. data_ungroup() removes the grouping information from a grouped data frame.

Usage

data_group(
  data,
  select = NULL,
  exclude = NULL,
  ignore_case = FALSE,
  regex = FALSE,
  verbose = TRUE,
  ...
)

data_ungroup(data, verbose = TRUE, ...)

Arguments

Value

A grouped data frame, i.e. a data frame with additional information about the grouping structure saved as attributes.

Examples

data(efc)
suppressPackageStartupMessages(library(poorman, quietly = TRUE))

# total mean
efc %>%
  summarize(mean_hours = mean(c12hour, na.rm = TRUE))

# mean by educational level
efc %>%
  data_group(c172code) %>%
  summarize(mean_hours = mean(c12hour, na.rm = TRUE))

Description

Return a filtered (or sliced) data frame or row indices of a data frame that match a specific condition. data_filter() works like data_match(), but works with logical expressions or row indices of a data frame to specify matching conditions.

Usage

data_match(
  x,
  to,
  match = "and",
  return_indices = FALSE,
  remove_na = TRUE,
  drop_na,
  ...
)

data_filter(x, ...)

Arguments

Details

For data_match(), if match is either "or" or "not", the original row order from x might be changed. If preserving row order is required, use data_filter() instead.

# mimics subset() behaviour, preserving original row order
head(data_filter(mtcars[c("mpg", "vs", "am")], vs == 0 | am == 1))
#>                    mpg vs am
#> Mazda RX4         21.0  0  1
#> Mazda RX4 Wag     21.0  0  1
#> Datsun 710        22.8  1  1
#> Hornet Sportabout 18.7  0  0
#> Duster 360        14.3  0  0
#> Merc 450SE        16.4  0  0

# re-sorting rows
head(data_match(mtcars[c("mpg", "vs", "am")],
                data.frame(vs = 0, am = 1),
                match = "or"))
#>                    mpg vs am
#> Mazda RX4         21.0  0  1
#> Mazda RX4 Wag     21.0  0  1
#> Hornet Sportabout 18.7  0  0
#> Duster 360        14.3  0  0
#> Merc 450SE        16.4  0  0
#> Merc 450SL        17.3  0  0

While data_match() works with data frames to match conditions against, data_filter() is basically a wrapper around ⁠subset(subset = <filter>)⁠. However, unlike subset(), it preserves label attributes and is useful when working with labelled data.

Value

A filtered data frame, or the row indices that match the specified configuration.

See Also

• Functions to rename stuff: data_rename(), data_rename_rows(), data_addprefix(), data_addsuffix()

• Functions to reorder or remove columns: data_reorder(), data_relocate(), data_remove()

• Functions to reshape, pivot or rotate data frames: data_to_long(), data_to_wide(), data_rotate()

• Functions to recode data: rescale(), reverse(), categorize(), recode_values(), slide()

• Functions to standardize, normalize, rank-transform: center(), standardize(), normalize(), ranktransform(), winsorize()

• Split and merge data frames: data_partition(), data_merge()

• Functions to find or select columns: data_select(), extract_column_names()

• Functions to filter rows: data_match(), data_filter()

Examples

data_match(mtcars, data.frame(vs = 0, am = 1))
data_match(mtcars, data.frame(vs = 0, am = c(0, 1)))

# observations where "vs" is NOT 0 AND "am" is NOT 1
data_match(mtcars, data.frame(vs = 0, am = 1), match = "not")
# equivalent to
data_filter(mtcars, vs != 0 & am != 1)

# observations where EITHER "vs" is 0 OR "am" is 1
data_match(mtcars, data.frame(vs = 0, am = 1), match = "or")
# equivalent to
data_filter(mtcars, vs == 0 | am == 1)

# slice data frame by row indices
data_filter(mtcars, 5:10)

# Define a custom function containing data_filter()
my_filter <- function(data, variable) {
  data_filter(data, variable)
}
my_filter(mtcars, "cyl == 6")

# Pass complete filter-condition as string.
my_filter <- function(data, condition) {
  data_filter(data, condition)
}
my_filter(mtcars, "am != 0")

# string can also be used directly as argument
data_filter(mtcars, "am != 0")

# or as variable
fl <- "am != 0"
data_filter(mtcars, fl)

Description

Merge (join) two data frames, or a list of data frames. However, unlike base R's merge(), data_merge() offers a few more methods to join data frames, and it does not drop data frame nor column attributes.

Usage

data_merge(x, ...)

data_join(x, ...)

## S3 method for class 'data.frame'
data_merge(x, y, join = "left", by = NULL, id = NULL, verbose = TRUE, ...)

## S3 method for class 'list'
data_merge(x, join = "left", by = NULL, id = NULL, verbose = TRUE, ...)

Arguments

Value

A merged data frame.

Merging data frames

Merging data frames is performed by adding rows (cases), columns (variables) or both from the source data frame (y) to the target data frame (x). This usually requires one or more variables which are included in both data frames and that are used for merging, typically indicated with the by argument. When by contains a variable present in both data frames, cases are matched and filtered by identical values of by in x and y.

Left- and right-joins

Left- and right joins usually don't add new rows (cases), but only new columns (variables) for existing cases in x. For join = "left" or join = "right" to work, by must indicate one or more columns that are included in both data frames. For join = "left", if by is an identifier variable, which is included in both x and y, all variables from y are copied to x, but only those cases from y that have matching values in their identifier variable in x (i.e. all cases in x that are also found in y get the related values from the new columns in y). If there is no match between identifiers in x and y, the copied variable from y will get a NA value for this particular case. Other variables that occur both in x and y, but are not used as identifiers (with by), will be renamed to avoid multiple identical variable names. Cases in y where values from the identifier have no match in x's identifier are removed. join = "right" works in a similar way as join = "left", just that only cases from x that have matching values in their identifier variable in y are chosen.

In base R, these are equivalent to merge(x, y, all.x = TRUE) and merge(x, y, all.y = TRUE).

Full joins

Full joins copy all cases from y to x. For matching cases in both data frames, values for new variables are copied from y to x. For cases in y not present in x, these will be added as new rows to x. Thus, full joins not only add new columns (variables), but also might add new rows (cases).

In base R, this is equivalent to merge(x, y, all = TRUE).

Inner joins

Inner joins merge two data frames, however, only those rows (cases) are kept that are present in both data frames. Thus, inner joins usually add new columns (variables), but also remove rows (cases) that only occur in one data frame.

In base R, this is equivalent to merge(x, y).

Binds

join = "bind" row-binds the complete second data frame y to x. Unlike simple rbind(), which requires the same columns for both data frames, join = "bind" will bind shared columns from y to x, and add new columns from y to x.

See Also

• Functions to rename stuff: data_rename(), data_rename_rows(), data_addprefix(), data_addsuffix()

• Functions to reorder or remove columns: data_reorder(), data_relocate(), data_remove()

• Functions to reshape, pivot or rotate data frames: data_to_long(), data_to_wide(), data_rotate()

• Functions to recode data: rescale(), reverse(), categorize(), recode_values(), slide()

• Functions to standardize, normalize, rank-transform: center(), standardize(), normalize(), ranktransform(), winsorize()

• Split and merge data frames: data_partition(), data_merge()

• Functions to find or select columns: data_select(), extract_column_names()

• Functions to filter rows: data_match(), data_filter()

Examples

x <- data.frame(a = 1:3, b = c("a", "b", "c"), c = 5:7, id = 1:3)
y <- data.frame(c = 6:8, d = c("f", "g", "h"), e = 100:102, id = 2:4)

x
y

# "by" will default to all shared columns, i.e. "c" and "id". new columns
# "d" and "e" will be copied from "y" to "x", but there are only two cases
# in "x" that have the same values for "c" and "id" in "y". only those cases
# have values in the copied columns, the other case gets "NA".
data_merge(x, y, join = "left")

# we change the id-value here
x <- data.frame(a = 1:3, b = c("a", "b", "c"), c = 5:7, id = 1:3)
y <- data.frame(c = 6:8, d = c("f", "g", "h"), e = 100:102, id = 3:5)

x
y

# no cases in "y" have the same matching "c" and "id" as in "x", thus
# copied variables from "y" to "x" copy no values, all get NA.
data_merge(x, y, join = "left")

# one case in "y" has a match in "id" with "x", thus values for this
# case from the remaining variables in "y" are copied to "x", all other
# values (cases) in those remaining variables get NA
data_merge(x, y, join = "left", by = "id")

data(mtcars)
x <- mtcars[1:5, 1:3]
y <- mtcars[28:32, 4:6]

# add ID common column
x$id <- 1:5
y$id <- 3:7

# left-join, add new variables and copy values from y to x,
# where "id" values match
data_merge(x, y)

# right-join, add new variables and copy values from x to y,
# where "id" values match
data_merge(x, y, join = "right")

# full-join
data_merge(x, y, join = "full")


data(mtcars)
x <- mtcars[1:5, 1:3]
y <- mtcars[28:32, c(1, 4:5)]

# add ID common column
x$id <- 1:5
y$id <- 3:7

# left-join, no matching rows (because columns "id" and "disp" are used)
# new variables get all NA values
data_merge(x, y)

# one common value in "mpg", so one row from y is copied to x
data_merge(x, y, by = "mpg")

# only keep rows with matching values in by-column
data_merge(x, y, join = "semi", by = "mpg")

# only keep rows with non-matching values in by-column
data_merge(x, y, join = "anti", by = "mpg")

# merge list of data frames. can be of different rows
x <- mtcars[1:5, 1:3]
y <- mtcars[28:31, 3:5]
z <- mtcars[11:18, c(1, 3:4, 6:8)]
x$id <- 1:5
y$id <- 4:7
z$id <- 3:10
data_merge(list(x, y, z), join = "bind", by = "id", id = "source")

Description

Create new variables or modify existing variables in a data frame. Unlike base::transform(), data_modify() can be used on grouped data frames, and newly created variables can be directly used.

Usage

data_modify(data, ...)

## S3 method for class 'data.frame'
data_modify(data, ..., .if = NULL, .at = NULL, .modify = NULL)

Arguments

Note

data_modify() can also be used inside functions. However, it is recommended to pass the recode-expression as character vector or list of characters.

Examples

data(efc)
new_efc <- data_modify(
  efc,
  c12hour_c = center(c12hour),
  c12hour_z = c12hour_c / sd(c12hour, na.rm = TRUE),
  c12hour_z2 = standardize(c12hour)
)
head(new_efc)

# using strings instead of literal expressions
new_efc <- data_modify(
  efc,
  "c12hour_c = center(c12hour)",
  "c12hour_z = c12hour_c / sd(c12hour, na.rm = TRUE)",
  "c12hour_z2 = standardize(c12hour)"
)
head(new_efc)

# using character strings, provided as variable
stand <- "c12hour_c / sd(c12hour, na.rm = TRUE)"
new_efc <- data_modify(
  efc,
  c12hour_c = center(c12hour),
  c12hour_z = stand
)
head(new_efc)

# providing expressions as character vector
new_exp <- c(
  "c12hour_c = center(c12hour)",
  "c12hour_z = c12hour_c / sd(c12hour, na.rm = TRUE)"
)
new_efc <- data_modify(efc, new_exp)
head(new_efc)

# attributes - in this case, value and variable labels - are preserved
str(new_efc)

# overwrite existing variable, remove old variable
out <- data_modify(iris, Petal.Length = 1 / Sepal.Length, Sepal.Length = NULL)
head(out)

# works on grouped data
grouped_efc <- data_group(efc, "c172code")
new_efc <- data_modify(
  grouped_efc,
  c12hour_c = center(c12hour),
  c12hour_z = c12hour_c / sd(c12hour, na.rm = TRUE),
  c12hour_z2 = standardize(c12hour),
  id = 1:n()
)
head(new_efc)

# works from inside functions
foo <- function(data, z) {
  head(data_modify(data, z))
}
foo(iris, "var_a = Sepal.Width / 10")

new_exp <- c("SW_double = 2 * Sepal.Width", "SW_fraction = SW_double / 10")
foo(iris, new_exp)

# modify at specific positions or if condition is met
d <- iris[1:5, ]
data_modify(d, .at = "Species", .modify = as.numeric)
data_modify(d, .if = is.factor, .modify = as.numeric)

# can be combined with dots
data_modify(d, new_length = Petal.Length * 2, .at = "Species", .modify = as.numeric)

# new variables used in `.at` or `.if`
data_modify(
  d,
  new_length = Petal.Length * 2,
  .at = c("Petal.Length", "new_length"),
  .modify = round
)

# combine "extract_column_names()" and ".at" argument
out <- data_modify(
  d,
  .at = extract_column_names(d, select = starts_with("Sepal")),
  .modify = as.factor
)
# "Sepal.Length" and "Sepal.Width" are now factors
str(out)

Description

Creates data partitions (for instance, a training and a test set) based on a data frame that can also be stratified (i.e., evenly spread a given factor) using the by argument.

Usage

data_partition(
  data,
  proportion = 0.7,
  by = NULL,
  seed = NULL,
  row_id = ".row_id",
  verbose = TRUE,
  ...
)

Arguments

Value

A list of data frames. The list includes one training set per given proportion and the remaining data as test set. List elements of training sets are named after the given proportions (e.g., ⁠$p_0.7⁠), the test set is named ⁠$test⁠.

See Also

• Functions to rename stuff: data_rename(), data_rename_rows(), data_addprefix(), data_addsuffix()

• Functions to reorder or remove columns: data_reorder(), data_relocate(), data_remove()

• Functions to reshape, pivot or rotate data frames: data_to_long(), data_to_wide(), data_rotate()

• Functions to recode data: rescale(), reverse(), categorize(), recode_values(), slide()

• Functions to standardize, normalize, rank-transform: center(), standardize(), normalize(), ranktransform(), winsorize()

• Split and merge data frames: data_partition(), data_merge()

• Functions to find or select columns: data_select(), extract_column_names()

• Functions to filter rows: data_match(), data_filter()

Examples

data(iris)
out <- data_partition(iris, proportion = 0.9)
out$test
nrow(out$p_0.9)

# Stratify by group (equal proportions of each species)
out <- data_partition(iris, proportion = 0.9, by = "Species")
out$test

# Create multiple partitions
out <- data_partition(iris, proportion = c(0.3, 0.3))
lapply(out, head)

# Create multiple partitions, stratified by group - 30% equally sampled
# from species in first training set, 50% in second training set and
# remaining 20% equally sampled from each species in test set.
out <- data_partition(iris, proportion = c(0.3, 0.5), by = "Species")
lapply(out, function(i) table(i$Species))

Description

This function creates a table a data frame, showing all column names, variable types and the first values (as many as fit into the screen).

Usage

data_peek(x, ...)

## S3 method for class 'data.frame'
data_peek(
  x,
  select = NULL,
  exclude = NULL,
  ignore_case = FALSE,
  regex = FALSE,
  width = NULL,
  verbose = TRUE,
  ...
)

Arguments

Value

A data frame with three columns, containing information about the name, type and first values of the input data frame.

Note

To show only specific or a limited number of variables, use the select argument, e.g. select = 1:5 to show only the first five variables.

Examples

data(efc)
data_peek(efc)
# show variables two to four
data_peek(efc, select = 2:4)

Description

This functions imports data from various file types. It is a small wrapper around haven::read_spss(), haven::read_stata(), haven::read_sas(), readxl::read_excel() and data.table::fread() resp. readr::read_delim() (the latter if package data.table is not installed). Thus, supported file types for importing data are data files from SPSS, SAS or Stata, Excel files or text files (like '.csv' files). All other file types are passed to rio::import(). data_write() works in a similar way.

Usage

data_read(
  path,
  path_catalog = NULL,
  encoding = NULL,
  convert_factors = TRUE,
  verbose = TRUE,
  ...
)

data_write(
  data,
  path,
  delimiter = ",",
  convert_factors = FALSE,
  save_labels = FALSE,
  verbose = TRUE,
  ...
)

Arguments

Value

A data frame.

Supported file types

• data_read() is a wrapper around the haven, data.table, readr readxl and rio packages. Currently supported file types are .txt, .csv, .xls, .xlsx, .sav, .por, .dta and .sas (and related files). All other file types are passed to rio::import().

• data_write() is a wrapper around haven, readr and rio packages, and supports writing files into all formats supported by these packages.

Compressed files (zip) and URLs

data_read() can also read the above mentioned files from URLs or from inside zip-compressed files. Thus, path can also be a URL to a file like "http://www.url.com/file.csv". When path points to a zip-compressed file, and there are multiple files inside the zip-archive, then the first supported file is extracted and loaded.

General behaviour

data_read() detects the appropriate ⁠read_*()⁠ function based on the file-extension of the data file. Thus, in most cases it should be enough to only specify the path argument. However, if more control is needed, all arguments in ... are passed down to the related ⁠read_*()⁠ function. The same applies to data_write(), i.e. based on the file extension provided in path, the appropriate ⁠write_*()⁠ function is used automatically.

SPSS specific behaviour

data_read() does not import user-defined ("tagged") NA values from SPSS, i.e. argument user_na is always set to FALSE when importing SPSS data with the haven package. Use convert_to_na() to define missing values in the imported data, if necessary. Furthermore, data_write() compresses SPSS files by default. If this causes problems with (older) SPSS versions, use compress = "none", for example data_write(data, "myfile.sav", compress = "none").

Differences to other packages that read foreign data formats

data_read() is most comparable to rio::import(). For data files from SPSS, SAS or Stata, which support labelled data, variables are converted into their most appropriate type. The major difference to rio::import() is for data files from SPSS, SAS, or Stata, i.e. file types that support labelled data. data_read() automatically converts fully labelled numeric variables into factors, where imported value labels will be set as factor levels. If a numeric variable has no value labels or less value labels than values, it is not converted to factor. In this case, value labels are preserved as "labels" attribute. Character vectors are preserved. Use convert_factors = FALSE to remove the automatic conversion of numeric variables to factors.

Description

data_relocate() will reorder columns to specific positions, indicated by before or after. data_reorder() will instead move selected columns to the beginning of a data frame. Finally, data_remove() removes columns from a data frame. All functions support select-helpers that allow flexible specification of a search pattern to find matching columns, which should be reordered or removed.

Usage

data_relocate(
  data,
  select,
  before = NULL,
  after = NULL,
  ignore_case = FALSE,
  regex = FALSE,
  verbose = TRUE,
  ...
)

data_reorder(
  data,
  select,
  exclude = NULL,
  ignore_case = FALSE,
  regex = FALSE,
  verbose = TRUE,
  ...
)

data_remove(
  data,
  select = NULL,
  exclude = NULL,
  ignore_case = FALSE,
  regex = FALSE,
  verbose = FALSE,
  ...
)

Arguments

Value

A data frame with reordered columns.

See Also

• Functions to rename stuff: data_rename(), data_rename_rows(), data_addprefix(), data_addsuffix()

• Functions to reorder or remove columns: data_reorder(), data_relocate(), data_remove()

• Functions to reshape, pivot or rotate data frames: data_to_long(), data_to_wide(), data_rotate()

• Functions to recode data: rescale(), reverse(), categorize(), recode_values(), slide()

• Functions to standardize, normalize, rank-transform: center(), standardize(), normalize(), ranktransform(), winsorize()

• Split and merge data frames: data_partition(), data_merge()

• Functions to find or select columns: data_select(), extract_column_names()

• Functions to filter rows: data_match(), data_filter()

Examples

# Reorder columns
head(data_relocate(iris, select = "Species", before = "Sepal.Length"))
head(data_relocate(iris, select = "Species", before = "Sepal.Width"))
head(data_relocate(iris, select = "Sepal.Width", after = "Species"))
# which is same as
head(data_relocate(iris, select = "Sepal.Width", after = -1))

# Reorder multiple columns
head(data_relocate(iris, select = c("Species", "Petal.Length"), after = "Sepal.Width"))
# which is same as
head(data_relocate(iris, select = c("Species", "Petal.Length"), after = 2))

# Reorder columns
head(data_reorder(iris, c("Species", "Sepal.Length")))

# Remove columns
head(data_remove(iris, "Sepal.Length"))
head(data_remove(iris, starts_with("Sepal")))

Description

Expand a data frame by replicating rows based on another variable that contains the counts of replications per row.

Usage

data_replicate(
  data,
  expand = NULL,
  select = NULL,
  exclude = NULL,
  remove_na = FALSE,
  ignore_case = FALSE,
  verbose = TRUE,
  regex = FALSE,
  ...
)

Arguments

Value

A dataframe with each row replicated as many times as defined in expand.

Examples

data(mtcars)
data_replicate(head(mtcars), "carb")

Description

Restore the type of columns according to a reference data frame

Usage

data_restoretype(data, reference = NULL, ...)

Arguments

Value

A data frame with columns whose types have been restored based on the reference data frame.

Examples

data <- data.frame(
  Sepal.Length = c("1", "3", "2"),
  Species = c("setosa", "versicolor", "setosa"),
  New = c("1", "3", "4")
)

fixed <- data_restoretype(data, reference = iris)
summary(fixed)

Description

This function rotates a data frame, i.e. columns become rows and vice versa. It's the equivalent of using t() but restores the data.frame class, preserves attributes and prints a warning if the data type is modified (see example).

Usage

data_rotate(data, rownames = NULL, colnames = FALSE, verbose = TRUE)

data_transpose(data, rownames = NULL, colnames = FALSE, verbose = TRUE)

Arguments

Value

A (rotated) data frame.

See Also

• Functions to rename stuff: data_rename(), data_rename_rows(), data_addprefix(), data_addsuffix()

• Functions to reorder or remove columns: data_reorder(), data_relocate(), data_remove()

• Functions to reshape, pivot or rotate data frames: data_to_long(), data_to_wide(), data_rotate()

• Functions to recode data: rescale(), reverse(), categorize(), recode_values(), slide()

• Functions to standardize, normalize, rank-transform: center(), standardize(), normalize(), ranktransform(), winsorize()

• Split and merge data frames: data_partition(), data_merge()

• Functions to find or select columns: data_select(), extract_column_names()

• Functions to filter rows: data_match(), data_filter()

Examples

x <- mtcars[1:3, 1:4]

x

data_rotate(x)
data_rotate(x, rownames = "property")

# use values in 1. column as column name
data_rotate(x, colnames = TRUE)
data_rotate(x, rownames = "property", colnames = TRUE)

# use either first column or specific column for column names
x <- data.frame(a = 1:5, b = 11:15, c = 21:25)
data_rotate(x, colnames = TRUE)
data_rotate(x, colnames = "c")

Description

This functions seeks variables in a data frame, based on patterns that either match the variable name (column name), variable labels, value labels or factor levels. Matching variable and value labels only works for "labelled" data, i.e. when the variables either have a label attribute or labels attribute.

data_seek() is particular useful for larger data frames with labelled data - finding the correct variable name can be a challenge. This function helps to find the required variables, when only certain patterns of variable names or labels are known.

Usage

data_seek(data, pattern, seek = c("names", "labels"), fuzzy = FALSE)

Arguments

Value

A data frame with three columns: the column index, the column name and - if available - the variable label of all matched variables in data.

Examples

# seek variables with "Length" in variable name or labels
data_seek(iris, "Length")

# seek variables with "dependency" in names or labels
# column "e42dep" has a label-attribute "elder's dependency"
data(efc)
data_seek(efc, "dependency")

# "female" only appears as value label attribute - default search is in
# variable names and labels only, so no match
data_seek(efc, "female")
# when we seek in all sources, we find the variable "e16sex"
data_seek(efc, "female", seek = "all")

# typo, no match
data_seek(iris, "Lenght")
# typo, fuzzy match
data_seek(iris, "Lenght", fuzzy = TRUE)

Description

extract_column_names() returns column names from a data set that match a certain search pattern, while data_select() returns the found data.

Usage

data_select(
  data,
  select = NULL,
  exclude = NULL,
  ignore_case = FALSE,
  regex = FALSE,
  verbose = TRUE,
  ...
)

extract_column_names(
  data,
  select = NULL,
  exclude = NULL,
  ignore_case = FALSE,
  regex = FALSE,
  verbose = TRUE,
  ...
)

find_columns(
  data,
  select = NULL,
  exclude = NULL,
  ignore_case = FALSE,
  regex = FALSE,
  verbose = TRUE,
  ...
)

Arguments

Details

Specifically for data_select(), select can also be a named character vector. In this case, the names are used to rename the columns in the output data frame. See 'Examples'.

Note that it is possible to either pass an entire select helper or only the pattern inside a select helper as a function argument:

foo <- function(data, pattern) {
  extract_column_names(data, select = starts_with(pattern))
}
foo(iris, pattern = "Sep")

foo2 <- function(data, pattern) {
  extract_column_names(data, select = pattern)
}
foo2(iris, pattern = starts_with("Sep"))

This means that it is also possible to use loop values as arguments or patterns:

for (i in c("Sepal", "Sp")) {
  head(iris) |>
    extract_column_names(select = starts_with(i)) |>
    print()
}

However, this behavior is limited to a "single-level function". It will not work in nested functions, like below:

inner <- function(data, arg) {
  extract_column_names(data, select = arg)
}
outer <- function(data, arg) {
  inner(data, starts_with(arg))
}
outer(iris, "Sep")

In this case, it is better to pass the whole select helper as the argument of outer():

outer <- function(data, arg) {
  inner(data, arg)
}
outer(iris, starts_with("Sep"))

Value

extract_column_names() returns a character vector with column names that matched the pattern in select and exclude, or NULL if no matching column name was found. data_select() returns a data frame with matching columns.

See Also

• Functions to rename stuff: data_rename(), data_rename_rows(), data_addprefix(), data_addsuffix()

• Functions to reorder or remove columns: data_reorder(), data_relocate(), data_remove()

• Functions to reshape, pivot or rotate data frames: data_to_long(), data_to_wide(), data_rotate()

• Functions to recode data: rescale(), reverse(), categorize(), recode_values(), slide()

• Functions to standardize, normalize, rank-transform: center(), standardize(), normalize(), ranktransform(), winsorize()

• Split and merge data frames: data_partition(), data_merge()

• Functions to find or select columns: data_select(), extract_column_names()

• Functions to filter rows: data_match(), data_filter()

Examples

# Find column names by pattern
extract_column_names(iris, starts_with("Sepal"))
extract_column_names(iris, ends_with("Width"))
extract_column_names(iris, regex("\\."))
extract_column_names(iris, c("Petal.Width", "Sepal.Length"))

# starts with "Sepal", but not allowed to end with "width"
extract_column_names(iris, starts_with("Sepal"), exclude = contains("Width"))

# find numeric with mean > 3.5
numeric_mean_35 <- function(x) is.numeric(x) && mean(x, na.rm = TRUE) > 3.5
extract_column_names(iris, numeric_mean_35)

# find range of colum names by range, using character vector
extract_column_names(mtcars, c("cyl:hp", "wt"))

# rename returned columns for "data_select()"
head(data_select(mtcars, c(`Miles per Gallon` = "mpg", Cylinders = "cyl")))

Description

Separates a single variable into multiple new variables.

Usage

data_separate(
  data,
  select = NULL,
  new_columns = NULL,
  separator = "[^[:alnum:]]+",
  guess_columns = NULL,
  merge_multiple = FALSE,
  merge_separator = "",
  fill = "right",
  extra = "drop_right",
  convert_na = TRUE,
  exclude = NULL,
  append = FALSE,
  ignore_case = FALSE,
  verbose = TRUE,
  regex = FALSE,
  ...
)

Arguments

Value

A data frame with the newly created variable(s), or - when append = TRUE - data including new variables.

See Also

data_unite()

Examples

# simple case
d <- data.frame(
  x = c("1.a.6", "2.b.7", "3.c.8"),
  stringsAsFactors = FALSE
)
d
data_separate(d, new_columns = c("a", "b", "c"))

# guess number of columns
d <- data.frame(
  x = c("1.a.6", NA, "2.b.6.7", "3.c", "x.y.z"),
  stringsAsFactors = FALSE
)
d
data_separate(d, guess_columns = "mode")

data_separate(d, guess_columns = "max")

# drop left-most column
data_separate(d, guess_columns = "mode", extra = "drop_left")

# merge right-most column
data_separate(d, guess_columns = "mode", extra = "merge_right")

# fill columns with fewer values with left-most values
data_separate(d, guess_columns = "mode", fill = "value_left")

# fill and merge
data_separate(
  d,
  guess_columns = "mode",
  fill = "value_left",
  extra = "merge_right"
)

# multiple columns to split
d <- data.frame(
  x = c("1.a.6", "2.b.7", "3.c.8"),
  y = c("x.y.z", "10.11.12", "m.n.o"),
  stringsAsFactors = FALSE
)
d
# split two columns, default column names
data_separate(d, guess_columns = "mode")

# split into new named columns, repeating column names
data_separate(d, new_columns = c("a", "b", "c"))

# split selected variable new columns
data_separate(d, select = "y", new_columns = c("a", "b", "c"))

# merge multiple split columns
data_separate(
  d,
  new_columns = c("a", "b", "c"),
  merge_multiple = TRUE
)

# merge multiple split columns
data_separate(
  d,
  new_columns = c("a", "b", "c"),
  merge_multiple = TRUE,
  merge_separator = "-"
)

# separate multiple columns, give proper column names
d_sep <- data.frame(
  x = c("1.a.6", "2.b.7.d", "3.c.8", "5.j"),
  y = c("m.n.99.22", "77.f.g.34", "44.9", NA),
  stringsAsFactors = FALSE
)

data_separate(
  d_sep,
  select = c("x", "y"),
  new_columns = list(
    x = c("A", "B", "C"), # separate "x" into three columns
    y = c("EE", "FF", "GG", "HH") # separate "y" into four columns
  ),
  verbose = FALSE
)

Description

This function can be used to compute summary statistics for a data frame or a matrix.

Usage

data_summary(x, ...)

## S3 method for class 'data.frame'
data_summary(x, ..., by = NULL, remove_na = FALSE)

Arguments

Value

A data frame with the requested summary statistics.

Examples

data(iris)
data_summary(iris, MW = mean(Sepal.Width), SD = sd(Sepal.Width))
data_summary(
  iris,
  MW = mean(Sepal.Width),
  SD = sd(Sepal.Width),
  by = "Species"
)

# same as
d <- data_group(iris, "Species")
data_summary(d, MW = mean(Sepal.Width), SD = sd(Sepal.Width))

# multiple groups
data(mtcars)
data_summary(mtcars, MW = mean(mpg), SD = sd(mpg), by = c("am", "gear"))

# expressions can also be supplied as character strings
data_summary(mtcars, "MW = mean(mpg)", "SD = sd(mpg)", by = c("am", "gear"))

# count observations within groups
data_summary(mtcars, observations = n(), by = c("am", "gear"))

# first and last observations of "mpg" within groups
data_summary(
  mtcars,
  first = mpg[1],
  last = mpg[length(mpg)],
  by = c("am", "gear")
)