Pipe operator

Description

See magrittr::%>% for details.

Usage

lhs %>% rhs

Fast %in% and ⁠%notin%⁠ operators

Description

Check whether values in a vector are in or not in another vector.

Built using data.table::'%chin%' and vctrs::vec_in() for performance.

Usage

x %in% y

x %notin% y

Arguments

Details

Falls back to base::'%in%' when x and y don't share a common type. This means that the behaviour of base::'%in%' is preserved (e.g. "1" %in% c(1, 2) is TRUE) but loses the speedup provided by vctrs::vec_in().

Examples

df <- tidytable(x = 1:4, y = 1:4)

df %>%
  filter(x %in% c(2, 4))

df %>%
  filter(x %notin% c(2, 4))

Apply a function across a selection of columns

Description

Apply a function across a selection of columns. For use in arrange(), mutate(), and summarize().

Usage

across(.cols = everything(), .fns = NULL, ..., .names = NULL)

Arguments

Examples

df <- data.table(
  x = rep(1, 3),
  y = rep(2, 3),
  z = c("a", "a", "b")
)

df %>%
  mutate(across(c(x, y), ~ .x * 2))

df %>%
  summarize(across(where(is.numeric), ~ mean(.x)),
            .by = z)

df %>%
  arrange(across(c(y, z)))

Add a count column to the data frame

Description

Add a count column to the data frame.

df %>% add_count(a, b) is equivalent to using df %>% mutate(n = n(), .by = c(a, b))

Usage

add_count(.df, ..., wt = NULL, sort = FALSE, name = NULL)

add_tally(.df, wt = NULL, sort = FALSE, name = NULL)

Arguments

Examples

df <- data.table(
  a = c("a", "a", "b"),
  b = 1:3
)

df %>%
  add_count(a)

Arrange/reorder rows

Description

Order rows in ascending or descending order.

Usage

arrange(.df, ...)

Arguments

Examples

df <- data.table(
  a = 1:3,
  b = 4:6,
  c = c("a", "a", "b")
)

df %>%
  arrange(c, -a)

df %>%
  arrange(c, desc(a))

Coerce an object to a data.table/tidytable

Description

A tidytable object is simply a data.table with nice printing features.

Note that all tidytable functions automatically convert data.frames & data.tables to tidytables in the background. As such this function will rarely need to be used by the user.

Usage

as_tidytable(x, ..., .name_repair = "unique", .keep_rownames = FALSE)

Arguments

Examples

df <- data.frame(x = -2:2, y = c(rep("a", 3), rep("b", 2)))

df %>%
  as_tidytable()

Do the values from x fall between the left and right bounds?

Description

between() utilizes data.table::between() in the background

Usage

between(x, left, right)

Arguments

Examples

df <- data.table(
  x = 1:5,
  y = 1:5
)

# Typically used in a filter()
df %>%
  filter(between(x, 2, 4))

df %>%
  filter(x %>% between(2, 4))

# Can also use the %between% operator
df %>%
  filter(x %between% c(2, 4))

Bind data.tables by row and column

Description

Bind multiple data.tables into one row-wise or col-wise.

Usage

bind_cols(..., .name_repair = "unique")

bind_rows(..., .id = NULL)

Arguments

Examples

# Binding data together by row
df1 <- data.table(x = 1:3, y = 10:12)
df2 <- data.table(x = 4:6, y = 13:15)

df1 %>%
  bind_rows(df2)

# Can pass a list of data.tables
df_list <- list(df1, df2)

bind_rows(df_list)

# Binding data together by column
df1 <- data.table(a = 1:3, b = 4:6)
df2 <- data.table(c = 7:9)

df1 %>%
  bind_cols(df2)

# Can pass a list of data frames
bind_cols(list(df1, df2))

Combine values from multiple columns

Description

c_across() works inside of mutate_rowwise(). It uses tidyselect so you can easily select multiple variables.

Usage

c_across(cols = everything())

Arguments

Examples

df <- data.table(x = runif(6), y = runif(6), z = runif(6))

df %>%
  mutate_rowwise(row_mean = mean(c_across(x:z)))

data.table::fcase() with vectorized default

Description

This function allows you to use multiple if/else statements in one call.

It is called like data.table::fcase(), but allows the user to use a vector as the default argument.

Usage

case(..., default = NA, ptype = NULL, size = NULL)

Arguments

Examples

df <- tidytable(x = 1:10)

df %>%
  mutate(case_x = case(x < 5, 1,
                       x < 7, 2,
                       default = 3))

Vectorized switch()

Description

Allows the user to succinctly create a new vector based off conditions of a single vector.

Usage

case_match(.x, ..., .default = NA, .ptype = NULL)

Arguments

Examples

df <- tidytable(x = c("a", "b", "c", "d"))

df %>%
  mutate(
    case_x = case_match(x,
                        c("a", "b") ~ "new_1",
                        "c" ~ "new_2",
                        .default = x)
  )

Case when

Description

This function allows you to use multiple if/else statements in one call.

It is called like dplyr::case_when(), but utilizes data.table::fifelse() in the background for improved performance.

Usage

case_when(..., .default = NA, .ptype = NULL, .size = NULL)

Arguments

Examples

df <- tidytable(x = 1:10)

df %>%
  mutate(case_x = case_when(x < 5 ~ 1,
                            x < 7 ~ 2,
                            TRUE ~ 3))

Coalesce missing values

Description

Fill in missing values in a vector by pulling successively from other vectors.

Usage

coalesce(..., .ptype = NULL, .size = NULL)

Arguments

Examples

# Use a single value to replace all missing values
x <- c(1:3, NA, NA)
coalesce(x, 0)

# Or match together a complete vector from missing pieces
y <- c(1, 2, NA, NA, 5)
z <- c(NA, NA, 3, 4, 5)
coalesce(y, z)

# Supply lists with dynamic dots
vecs <- list(
  c(1, 2, NA, NA, 5),
  c(NA, NA, 3, 4, 5)
)
coalesce(!!!vecs)

Complete a data.table with missing combinations of data

Description

Turns implicit missing values into explicit missing values.

Usage

complete(.df, ..., fill = list(), .by = NULL)

Arguments

Examples

df <- data.table(x = 1:2, y = 1:2, z = 3:4)

df %>%
  complete(x, y)

df %>%
  complete(x, y, fill = list(z = 10))

Generate a unique id for consecutive values

Description

Generate a unique id for runs of consecutive values

Usage

consecutive_id(...)

Arguments

Examples

x <- c(1, 1, 2, 2, 1, 1)
consecutive_id(x)

Context functions

Description

These functions give information about the "current" group.

• cur_data() gives the current data for the current group

• cur_column() gives the name of the current column (for use in across() only)

• cur_group_id() gives a group identification number

• cur_group_rows() gives the row indices for each group

Can be used inside summarize(), mutate(), & filter()

Usage

cur_column()

cur_data()

cur_group_id()

cur_group_rows()

Examples

df <- data.table(
  x = 1:5,
  y = c("a", "a", "a", "b", "b")
)

df %>%
  mutate(
    across(c(x, y), ~ paste(cur_column(), .x))
  )

df %>%
  summarize(data = list(cur_data()),
            .by = y)

df %>%
  mutate(group_id = cur_group_id(),
         .by = y)

df %>%
  mutate(group_rows = cur_group_rows(),
         .by = y)

Count observations by group

Description

Returns row counts of the dataset.

tally() returns counts by group on a grouped tidytable.

count() returns counts by group on a grouped tidytable, or column names can be specified to return counts by group.

Usage

count(.df, ..., wt = NULL, sort = FALSE, name = NULL)

tally(.df, wt = NULL, sort = FALSE, name = NULL)

Arguments

Examples

df <- data.table(
  x = c("a", "a", "b"),
  y = c("a", "a", "b"),
  z = 1:3
)

df %>%
  count()

df %>%
  count(x)

df %>%
  count(where(is.character))

df %>%
  count(x, wt = z, name = "x_sum")

df %>%
  count(x, sort = TRUE)

df %>%
  tally()

df %>%
  group_by(x) %>%
  tally()

Cross join

Description

Cross join each row of x to every row in y.

Usage

cross_join(x, y, ..., suffix = c(".x", ".y"))

Arguments

Examples

df1 <- tidytable(x = 1:3)
df2 <- tidytable(y = 4:6)

cross_join(df1, df2)

Create a data.table from all unique combinations of inputs

Description

crossing() is similar to expand_grid() but de-duplicates and sorts its inputs.

Usage

crossing(..., .name_repair = "check_unique")

Arguments

Examples

x <- 1:2
y <- 1:2

crossing(x, y)

crossing(stuff = x, y)

Descending order

Description

Arrange in descending order. Can be used inside of arrange()

Usage

desc(x)

Arguments

Examples

df <- data.table(
  a = 1:3,
  b = 4:6,
  c = c("a", "a", "b")
)

df %>%
  arrange(c, desc(a))

Select distinct/unique rows

Description

Retain only unique/distinct rows from an input df.

Usage

distinct(.df, ..., .keep_all = FALSE)

Arguments

Examples

df <- tidytable(
  x = 1:3,
  y = 4:6,
  z = c("a", "a", "b")
)

df %>%
  distinct()

df %>%
  distinct(z)

Drop rows containing missing values

Description

Drop rows containing missing values

Usage

drop_na(.df, ...)

Arguments

Examples

df <- data.table(
  x = c(1, 2, NA),
  y = c("a", NA, "b")
)

df %>%
  drop_na()

df %>%
  drop_na(x)

df %>%
  drop_na(where(is.numeric))

Pipeable data.table call

Description

Pipeable data.table call.

This function does not use data.table's modify-by-reference.

Has experimental support for tidy evaluation for custom functions.

Usage

dt(.df, i, j, ...)

Arguments

Examples

df <- tidytable(
  x = 1:3,
  y = 4:6,
  z = c("a", "a", "b")
)

df %>%
  dt(, double_x := x * 2) %>%
  dt(order(-double_x))

# Experimental support for tidy evaluation for custom functions
add_one <- function(data, col) {
  data %>%
    dt(, new_col := {{ col }} + 1)
}

df %>%
  add_one(x)

Convert a vector to a data.table/tidytable

Description

Converts named and unnamed vectors to a data.table/tidytable.

Usage

enframe(x, name = "name", value = "value")

Arguments

Examples

vec <- 1:3
names(vec) <- letters[1:3]

enframe(vec)

Expand a data.table to use all combinations of values

Description

Generates all combinations of variables found in a dataset.

expand() is useful in conjunction with joins:

• use with right_join() to convert implicit missing values to explicit missing values

• use with anti_join() to find out which combinations are missing

nesting() is a helper that only finds combinations already present in the dataset.

Usage

expand(.df, ..., .name_repair = "check_unique", .by = NULL)

nesting(..., .name_repair = "check_unique")

Arguments

Examples

df <- tidytable(x = c(1, 1, 2), y = c(1, 1, 2))

df %>%
  expand(x, y)

df %>%
  expand(nesting(x, y))

Create a data.table from all combinations of inputs

Description

Create a data.table from all combinations of inputs

Usage

expand_grid(..., .name_repair = "check_unique")

Arguments

Examples

x <- 1:2
y <- 1:2

expand_grid(x, y)

expand_grid(stuff = x, y)

Extract a character column into multiple columns using regex

Description

Superseded

extract() has been superseded by separate_wider_regex().

Given a regular expression with capturing groups, extract() turns each group into a new column. If the groups don't match, or the input is NA, the output will be NA. When you pass same name in the into argument it will merge the groups together. Whilst passing NA in the into arg will drop the group from the resulting tidytable

Usage

extract(
  .df,
  col,
  into,
  regex = "([[:alnum:]]+)",
  remove = TRUE,
  convert = FALSE,
  ...
)

Arguments

Examples

df <- data.table(x = c(NA, "a-b-1", "a-d-3", "b-c-2", "d-e-7"))
df %>% extract(x, "A")
df %>% extract(x, c("A", "B"), "([[:alnum:]]+)-([[:alnum:]]+)")

# If no match, NA:
df %>% extract(x, c("A", "B"), "([a-d]+)-([a-d]+)")
# drop columns by passing NA
df %>% extract(x, c("A", NA, "B"), "([a-d]+)-([a-d]+)-(\\d+)")
# merge groups by passing same name
df %>% extract(x, c("A", "B", "A"), "([a-d]+)-([a-d]+)-(\\d+)")

Fill in missing values with previous or next value

Description

Fills missing values in the selected columns using the next or previous entry. Can be done by group.

Supports tidyselect

Usage

fill(.df, ..., .direction = c("down", "up", "downup", "updown"), .by = NULL)

Arguments

Examples

df <- data.table(
  a = c(1, NA, 3, 4, 5),
  b = c(NA, 2, NA, NA, 5),
  groups = c("a", "a", "a", "b", "b")
)

df %>%
  fill(a, b)

df %>%
  fill(a, b, .by = groups)

df %>%
  fill(a, b, .direction = "downup", .by = groups)

Filter rows on one or more conditions

Description

Filters a dataset to choose rows where conditions are true.

Usage

filter(.df, ..., .by = NULL)

Arguments

Examples

df <- tidytable(
  a = 1:3,
  b = 4:6,
  c = c("a", "a", "b")
)

df %>%
  filter(a >= 2, b >= 4)

df %>%
  filter(b <= mean(b), .by = c)

Extract the first, last, or nth value from a vector

Description

Extract the first, last, or nth value from a vector.

Note: These are simple wrappers around vctrs::vec_slice().

Usage

first(x, default = NULL, na_rm = FALSE)

last(x, default = NULL, na_rm = FALSE)

nth(x, n, default = NULL, na_rm = FALSE)

Arguments

Examples

vec <- letters

first(vec)
last(vec)
nth(vec, 4)

Read/write files

Description

fread() is a simple wrapper around data.table::fread() that returns a tidytable instead of a data.table.

Usage

fread(...)

Arguments

Examples

fake_csv <- "A,B
             1,2
             3,4"

fread(fake_csv)

Convert character and factor columns to dummy variables

Description

Convert character and factor columns to dummy variables

Usage

get_dummies(
  .df,
  cols = where(~is.character(.x) | is.factor(.x)),
  prefix = TRUE,
  prefix_sep = "_",
  drop_first = FALSE,
  dummify_na = TRUE
)

Arguments

Examples

df <- tidytable(
  chr = c("a", "b", NA),
  fct = as.factor(c("a", NA, "c")),
  num = 1:3
)

# Automatically does all character/factor columns
df %>%
  get_dummies()

df %>%
  get_dummies(cols = chr)

df %>%
  get_dummies(cols = c(chr, fct), drop_first = TRUE)

df %>%
  get_dummies(prefix_sep = ".", dummify_na = FALSE)

Grouping

Description

• group_by() adds a grouping structure to a tidytable. Can use tidyselect syntax.

• ungroup() removes grouping.

Usage

group_by(.df, ..., .add = FALSE)

ungroup(.df, ...)

Arguments

Examples

df <- data.table(
  a = 1:3,
  b = 4:6,
  c = c("a", "a", "b"),
  d = c("a", "a", "b")
)

df %>%
  group_by(c, d) %>%
  summarize(mean_a = mean(a)) %>%
  ungroup()

# Can also use tidyselect
df %>%
  group_by(where(is.character)) %>%
  summarize(mean_a = mean(a)) %>%
  ungroup()

Selection helper for grouping columns

Description

Selection helper for grouping columns

Usage

group_cols()

Examples

df <- tidytable(
  x = c("a", "b", "c"),
  y = 1:3,
  z = 1:3
)

df %>%
  group_by(x) %>%
  select(group_cols(), y)

Split data frame by groups

Description

Split data frame by groups. Returns a list.

Usage

group_split(.df, ..., .keep = TRUE, .named = FALSE)

Arguments

Examples

df <- tidytable(
  a = 1:3,
  b = 1:3,
  c = c("a", "a", "b"),
  d = c("a", "a", "b")
)

df %>%
  group_split(c, d)

df %>%
  group_split(c, d, .keep = FALSE)

df %>%
  group_split(c, d, .named = TRUE)

Get the grouping variables

Description

Get the grouping variables

Usage

group_vars(x)

Arguments

Examples

df <- data.table(
  a = 1:3,
  b = 4:6,
  c = c("a", "a", "b"),
  d = c("a", "a", "b")
)

df %>%
  group_by(c, d) %>%
  group_vars()

Create conditions on a selection of columns

Description

Helpers to apply a filter across a selection of columns.

Usage

if_all(.cols = everything(), .fns = NULL, ...)

if_any(.cols = everything(), .fns = NULL, ...)

Arguments

Examples

iris %>%
  filter(if_any(ends_with("Width"), ~ .x > 4))

iris %>%
  filter(if_all(ends_with("Width"), ~ .x > 2))

Fast if_else

Description

Fast version of base::ifelse().

Usage

if_else(condition, true, false, missing = NA, ..., ptype = NULL, size = NULL)

Arguments

Examples

x <- 1:5
if_else(x < 3, 1, 0)

# Can also be used inside of mutate()
df <- data.table(x = x)

df %>%
  mutate(new_col = if_else(x < 3, 1, 0))

Run invisible garbage collection

Description

Run garbage collection without the gc() output. Can also be run in the middle of a long pipe chain. Useful for large datasets or when using parallel processing.

Usage

inv_gc(x)

Arguments

Examples

# Can be run with no input
inv_gc()

df <- tidytable(col1 = 1, col2 = 2)

# Or can be used in the middle of a pipe chain (object is unaltered)
df %>%
  filter(col1 < 2, col2 < 4) %>%
  inv_gc() %>%
  select(col1)

Check if the tidytable is grouped

Description

Check if the tidytable is grouped

Usage

is_grouped_df(x)

Arguments

Examples

df <- data.table(
  a = 1:3,
  b = c("a", "a", "b")
)

df %>%
  group_by(b) %>%
  is_grouped_df()

Test if the object is a tidytable

Description

This function returns TRUE for tidytables or subclasses of tidytables, and FALSE for all other objects.

Usage

is_tidytable(x)

Arguments

Examples

df <- data.frame(x = 1:3, y = 1:3)

is_tidytable(df)

df <- tidytable(x = 1:3, y = 1:3)

is_tidytable(df)

Get lagging or leading values

Description

Find the "previous" or "next" values in a vector. Useful for comparing values behind or ahead of the current values.

Usage

lag(x, n = 1L, default = NA)

lead(x, n = 1L, default = NA)

Arguments

Examples

x <- 1:5

lag(x, 1)
lead(x, 1)

# Also works inside of `mutate()`
df <- tidytable(x = 1:5)

df %>%
  mutate(lag_x = lag(x))

Join two data.tables together

Description

Join two data.tables together

Usage

left_join(x, y, by = NULL, suffix = c(".x", ".y"), ..., keep = FALSE)

right_join(x, y, by = NULL, suffix = c(".x", ".y"), ..., keep = FALSE)

inner_join(x, y, by = NULL, suffix = c(".x", ".y"), ..., keep = FALSE)

full_join(x, y, by = NULL, suffix = c(".x", ".y"), ..., keep = FALSE)

anti_join(x, y, by = NULL)

semi_join(x, y, by = NULL)

Arguments

Examples

df1 <- data.table(x = c("a", "a", "b", "c"), y = 1:4)
df2 <- data.table(x = c("a", "b"), z = 5:6)

df1 %>% left_join(df2)
df1 %>% inner_join(df2)
df1 %>% right_join(df2)
df1 %>% full_join(df2)
df1 %>% anti_join(df2)

Apply a function to each element of a vector or list

Description

The map functions transform their input by applying a function to each element and returning a list/vector/data.table.

• map() returns a list

• ⁠_lgl()⁠, ⁠_int⁠, ⁠_dbl⁠,⁠_chr⁠, ⁠_df⁠ variants return their specified type

• ⁠_dfr⁠ & ⁠_dfc⁠ Return all data frame results combined utilizing row or column binding

Usage

map(.x, .f, ...)

map_lgl(.x, .f, ...)

map_int(.x, .f, ...)

map_dbl(.x, .f, ...)

map_chr(.x, .f, ...)

map_dfc(.x, .f, ...)

map_dfr(.x, .f, ..., .id = NULL)

map_df(.x, .f, ..., .id = NULL)

walk(.x, .f, ...)

map_vec(.x, .f, ..., .ptype = NULL)

map2(.x, .y, .f, ...)

map2_lgl(.x, .y, .f, ...)

map2_int(.x, .y, .f, ...)

map2_dbl(.x, .y, .f, ...)

map2_chr(.x, .y, .f, ...)

map2_dfc(.x, .y, .f, ...)

map2_dfr(.x, .y, .f, ..., .id = NULL)

map2_df(.x, .y, .f, ..., .id = NULL)

map2_vec(.x, .y, .f, ..., .ptype = NULL)

pmap(.l, .f, ...)

pmap_lgl(.l, .f, ...)

pmap_int(.l, .f, ...)

pmap_dbl(.l, .f, ...)

pmap_chr(.l, .f, ...)

pmap_dfc(.l, .f, ...)

pmap_dfr(.l, .f, ..., .id = NULL)

pmap_df(.l, .f, ..., .id = NULL)

pmap_vec(.l, .f, ..., .ptype = NULL)

Arguments

Examples

map(c(1,2,3), ~ .x + 1)

map_dbl(c(1,2,3), ~ .x + 1)

map_chr(c(1,2,3), as.character)

Add/modify/delete columns

Description

With mutate() you can do 3 things:

• Add new columns

• Modify existing columns

• Delete columns

Usage

mutate(
  .df,
  ...,
  .by = NULL,
  .keep = c("all", "used", "unused", "none"),
  .before = NULL,
  .after = NULL
)

Arguments

Examples

df <- data.table(
  a = 1:3,
  b = 4:6,
  c = c("a", "a", "b")
)

df %>%
  mutate(double_a = a * 2,
         a_plus_b = a + b)

df %>%
  mutate(double_a = a * 2,
         avg_a = mean(a),
         .by = c)

df %>%
  mutate(double_a = a * 2, .keep = "used")

df %>%
  mutate(double_a = a * 2, .after = a)

Add/modify columns by row

Description

Allows you to mutate "by row". this is most useful when a vectorized function doesn't exist.

Usage

mutate_rowwise(
  .df,
  ...,
  .keep = c("all", "used", "unused", "none"),
  .before = NULL,
  .after = NULL
)

Arguments

Examples

df <- data.table(x = 1:3, y = 1:3 * 2, z = 1:3 * 3)

# Compute the mean of x, y, z in each row
df %>%
  mutate_rowwise(row_mean = mean(c(x, y, z)))

# Use c_across() to more easily select many variables
df %>%
  mutate_rowwise(row_mean = mean(c_across(x:z)))

Number of observations in each group

Description

Helper function that can be used to find counts by group.

Can be used inside summarize(), mutate(), & filter()

Usage

n()

Examples

df <- data.table(
  x = 1:3,
  y = 4:6,
  z = c("a","a","b")
 )

df %>%
  summarize(count = n(), .by = z)

Count the number of unique values in a vector

Description

This is a faster version of length(unique(x)) that calls data.table::uniqueN().

Usage

n_distinct(..., na.rm = FALSE)

Arguments

Examples

x <- sample(1:10, 1e5, rep = TRUE)
n_distinct(x)

Convert values to NA

Description

Convert values to NA.

Usage

na_if(x, y)

Arguments

Examples

vec <- 1:3
na_if(vec, 3)

Nest columns into a list-column

Description

Nest columns into a list-column

Usage

nest(.df, ..., .by = NULL, .key = NULL, .names_sep = NULL)

Arguments

Examples

df <- data.table(
  a = 1:3,
  b = 1:3,
  c = c("a", "a", "b"),
  d = c("a", "a", "b")
)

df %>%
  nest(data = c(a, b))

df %>%
  nest(data = where(is.numeric))

df %>%
  nest(.by = c(c, d))

Nest data.tables

Description

Nest data.tables by group.

Note: nest_by() does not return a rowwise tidytable.

Usage

nest_by(.df, ..., .key = "data", .keep = FALSE)

Arguments

Examples

df <- data.table(
  a = 1:5,
  b = 6:10,
  c = c(rep("a", 3), rep("b", 2)),
  d = c(rep("a", 3), rep("b", 2))
)

df %>%
  nest_by()

df %>%
  nest_by(c, d)

df %>%
  nest_by(where(is.character))

df %>%
  nest_by(c, d, .keep = TRUE)

Nest join

Description

Join the data from y as a list column onto x.

Usage

nest_join(x, y, by = NULL, keep = FALSE, name = NULL, ...)

Arguments

Examples

df1 <- tidytable(x = 1:3)
df2 <- tidytable(x = c(2, 3, 3), y = c("a", "b", "c"))

out <- nest_join(df1, df2)
out
out$df2

Create a tidytable from a list

Description

Create a tidytable from a list

Usage

new_tidytable(x = list())

Arguments

Examples

l <- list(x = 1:3, y = c("a", "a", "b"))

new_tidytable(l)

Selection version of across()

Description

Select a subset of columns from within functions like mutate(), summarize(), or filter().

Usage

pick(...)

Arguments

Examples

df <- tidytable(
  x = 1:3,
  y = 4:6,
  z = c("a", "a", "b")
)

df %>%
  mutate(row_sum = rowSums(pick(x, y)))

Pivot data from wide to long

Description

pivot_longer() "lengthens" the data, increasing the number of rows and decreasing the number of columns.

Usage

pivot_longer(
  .df,
  cols = everything(),
  names_to = "name",
  values_to = "value",
  names_prefix = NULL,
  names_sep = NULL,
  names_pattern = NULL,
  names_ptypes = NULL,
  names_transform = NULL,
  names_repair = "check_unique",
  values_drop_na = FALSE,
  values_ptypes = NULL,
  values_transform = NULL,
  fast_pivot = FALSE,
  ...
)

Arguments

Examples

df <- data.table(
  x = 1:3,
  y = 4:6,
  z = c("a", "b", "c")
)

df %>%
  pivot_longer(cols = c(x, y))

df %>%
  pivot_longer(cols = -z, names_to = "stuff", values_to = "things")

Pivot data from long to wide

Description

"Widens" data, increasing the number of columns and decreasing the number of rows.

Usage

pivot_wider(
  .df,
  names_from = name,
  values_from = value,
  id_cols = NULL,
  names_sep = "_",
  names_prefix = "",
  names_glue = NULL,
  names_sort = FALSE,
  names_repair = "unique",
  values_fill = NULL,
  values_fn = NULL,
  unused_fn = NULL
)

Arguments

Examples

df <- tidytable(
  id = 1,
  names = c("a", "b", "c"),
  vals = 1:3
)

df %>%
  pivot_wider(names_from = names, values_from = vals)

df %>%
  pivot_wider(
    names_from = names, values_from = vals, names_prefix = "new_"
  )

Pull out a single variable

Description

Pull a single variable from a data.table as a vector.

Usage

pull(.df, var = -1, name = NULL)

Arguments

Examples

df <- data.table(
  x = 1:3,
  y = 1:3
)

# Grab column by name
df %>%
  pull(y)

# Grab column by position
df %>%
  pull(1)

# Defaults to last column
df %>%
  pull()

Recode values

Description

superseded

recode() has been superseded by case_match().

Replace old values of a vector with new values.

Usage

recode(.x, ..., .default = NULL, .missing = NULL)

Arguments

Examples

char_vec <- c("a", "b", "c")
recode(char_vec, a = "Apple", b = "Banana")

num_vec <- 1:3
recode(num_vec, `1` = 10, `2` = 25, .default = 100)

Objects exported from other packages

Description

These objects are imported from other packages. Follow the links below to see their documentation.

data.table

%between%, %chin%, %like%, data.table, fwrite, getDTthreads, setDTthreads

pillar

glimpse

rlang

enexpr, enexprs, enquo, enquos, expr, exprs, quo, quos, sym, syms

tidyselect

all_of, any_of, contains, ends_with, everything, last_col, matches, num_range, starts_with, where

Reframe a data frame

Description

Reframe a data frame. Note this is a simple alias for summarize() that always returns an ungrouped tidytable.

Usage

reframe(.df, ..., .by = NULL)

Arguments

Examples

mtcars %>%
  reframe(qs = quantile(disp, c(0.25, 0.75)),
          prob = c(0.25, 0.75),
          .by = cyl)

Relocate a column to a new position

Description

Move a column or columns to a new position

Usage

relocate(.df, ..., .before = NULL, .after = NULL)

Arguments

Examples

df <- data.table(
  a = 1:3,
  b = 1:3,
  c = c("a", "a", "b"),
  d = c("a", "a", "b")
)

df %>%
  relocate(c, .before = b)

df %>%
  relocate(a, b, .after = c)

df %>%
  relocate(where(is.numeric), .after = c)

Rename variables by name

Description

Rename variables from a data.table.

Usage

rename(.df, ...)

Arguments

Examples

df <- data.table(x = 1:3, y = 4:6)

df %>%
  rename(new_x = x,
         new_y = y)

Rename multiple columns

Description

Rename multiple columns with the same transformation

Usage

rename_with(.df, .fn = NULL, .cols = everything(), ...)

Arguments

Examples

df <- data.table(
  x = 1,
  y = 2,
  double_x = 2,
  double_y = 4
)

df %>%
  rename_with(toupper)

df %>%
  rename_with(~ toupper(.x))

df %>%
  rename_with(~ toupper(.x), .cols = c(x, double_x))

Replace missing values

Description

Replace NAs with specified values

Usage

replace_na(.x, replace)

Arguments

Examples

df <- data.table(
  x = c(1, 2, NA),
  y = c(NA, 1, 2)
)

# Using replace_na() inside mutate()
df %>%
  mutate(x = replace_na(x, 5))

# Using replace_na() on a data frame
df %>%
  replace_na(list(x = 5, y = 0))

Ranking functions

Description

Ranking functions:

• row_number(): Gives other row number if empty. Equivalent to frank(ties.method = "first") if provided a vector.

• min_rank(): Equivalent to frank(ties.method = "min")

• dense_rank(): Equivalent to frank(ties.method = "dense")

• percent_rank(): Ranks by percentage from 0 to 1

• cume_dist(): Cumulative distribution

Usage

row_number(x)

min_rank(x)

dense_rank(x)

percent_rank(x)

cume_dist(x)

Arguments

Examples

df <- data.table(x = rep(1, 3), y = c("a", "a", "b"))

df %>%
  mutate(row = row_number())

Convert to a rowwise tidytable

Description

Convert to a rowwise tidytable.

Usage

rowwise(.df)

Arguments

Examples

df <- tidytable(x = 1:3, y = 1:3 * 2, z = 1:3 * 3)

# Compute the mean of x, y, z in each row
df %>%
  rowwise() %>%
  mutate(row_mean = mean(c(x, y, z)))

# Use c_across() to more easily select many variables
df %>%
  rowwise() %>%
  mutate(row_mean = mean(c_across(x:z))) %>%
  ungroup()

Select or drop columns

Description

Select or drop columns from a data.table

Usage

select(.df, ...)

Arguments

Examples

df <- data.table(
  x1 = 1:3,
  x2 = 1:3,
  y = c("a", "b", "c"),
  z = c("a", "b", "c")
)

df %>%
  select(x1, y)

df %>%
  select(x1:y)

df %>%
  select(-y, -z)

df %>%
  select(starts_with("x"), z)

df %>%
  select(where(is.character), x1)

df %>%
  select(new = x1, y)

Separate a character column into multiple columns

Description

Superseded

separate() has been superseded by separate_wider_delim().

Separates a single column into multiple columns using a user supplied separator or regex.

If a separator is not supplied one will be automatically detected.

Note: Using automatic detection or regex will be slower than simple separators such as "," or ".".

Usage

separate(
  .df,
  col,
  into,
  sep = "[^[:alnum:]]+",
  remove = TRUE,
  convert = FALSE,
  ...
)

Arguments

Examples

df <- data.table(x = c("a", "a.b", "a.b", NA))

# "sep" can be automatically detected (slower)
df %>%
  separate(x, into = c("c1", "c2"))

# Faster if "sep" is provided
df %>%
  separate(x, into = c("c1", "c2"), sep = ".")

Split a string into rows

Description

If a column contains observations with multiple delimited values, separate them each into their own row.

Usage

separate_longer_delim(.df, cols, delim, ...)

Arguments

Examples

df <- data.table(
  x = 1:3,
  y = c("a", "d,e,f", "g,h"),
  z = c("1", "2,3,4", "5,6")
)

df %>%
  separate_longer_delim(c(y, z), ",")

Separate a collapsed column into multiple rows

Description

Superseded

separate_rows() has been superseded by separate_longer_delim().

If a column contains observations with multiple delimited values, separate them each into their own row.

Usage

separate_rows(.df, ..., sep = "[^[:alnum:].]+", convert = FALSE)

Arguments

Examples

df <- data.table(
  x = 1:3,
  y = c("a", "d,e,f", "g,h"),
  z = c("1", "2,3,4", "5,6")
)

separate_rows(df, y, z)

separate_rows(df, y, z, convert = TRUE)

Separate a character column into multiple columns

Description

Separates a single column into multiple columns

Usage

separate_wider_delim(
  .df,
  cols,
  delim,
  ...,
  names = NULL,
  names_sep = NULL,
  names_repair = "check_unique",
  too_few = c("align_start", "error"),
  too_many = c("drop", "error"),
  cols_remove = TRUE
)

Arguments

Examples

df <- tidytable(x = c("a", "a_b", "a_b", NA))

df %>%
  separate_wider_delim(x, delim = "_", names = c("left", "right"))

df %>%
  separate_wider_delim(x, delim = "_", names_sep = "")

Separate a character column into multiple columns using regex patterns

Description

Separate a character column into multiple columns using regex patterns

Usage

separate_wider_regex(
  .df,
  cols,
  patterns,
  ...,
  names_sep = NULL,
  names_repair = "check_unique",
  too_few = "error",
  cols_remove = TRUE
)

Arguments

Examples

df <- tidytable(id = 1:3, x = c("m-123", "f-455", "f-123"))

df %>%
  separate_wider_regex(x, c(gender = ".", ".", unit = "\\d+"))

Choose rows in a data.table

Description

Choose rows in a data.table. Grouped data.tables grab rows within each group.

Usage

slice_head(.df, n = 5, ..., .by = NULL, by = NULL)

slice_tail(.df, n = 5, ..., .by = NULL, by = NULL)

slice_max(.df, order_by, n = 1, ..., with_ties = TRUE, .by = NULL, by = NULL)

slice_min(.df, order_by, n = 1, ..., with_ties = TRUE, .by = NULL, by = NULL)

slice(.df, ..., .by = NULL)

slice_sample(
  .df,
  n,
  prop,
  weight_by = NULL,
  replace = FALSE,
  .by = NULL,
  by = NULL
)

Arguments

Examples

df <- data.table(
  x = 1:4,
  y = 5:8,
  z = c("a", "a", "a", "b")
)

df %>%
  slice(1:3)

df %>%
  slice(1, 3)

df %>%
  slice(1:2, .by = z)

df %>%
  slice_head(1, .by = z)

df %>%
  slice_tail(1, .by = z)

df %>%
  slice_max(order_by = x, .by = z)

df %>%
  slice_min(order_by = y, .by = z)

Aggregate data using summary statistics

Description

Aggregate data using summary statistics such as mean or median. Can be calculated by group.

Usage

summarize(
  .df,
  ...,
  .by = NULL,
  .sort = TRUE,
  .groups = "drop_last",
  .unpack = FALSE
)

summarise(
  .df,
  ...,
  .by = NULL,
  .sort = TRUE,
  .groups = "drop_last",
  .unpack = FALSE
)

Arguments

Examples

df <- data.table(
  a = 1:3,
  b = 4:6,
  c = c("a", "a", "b"),
  d = c("a", "a", "b")
)

df %>%
  summarize(avg_a = mean(a),
            max_b = max(b),
            .by = c)

df %>%
  summarize(avg_a = mean(a),
            .by = c(c, d))

Build a data.table/tidytable

Description

Constructs a data.table, but one with nice printing features.

Usage

tidytable(..., .name_repair = "unique")

Arguments

Examples

tidytable(x = 1:3, y = c("a", "a", "b"))

Internal vctrs methods

Description

These methods are the extensions that allow tidytable objects to work with vctrs.

Select top (or bottom) n rows (by value)

Description

Select the top or bottom entries in each group, ordered by wt.

Usage

top_n(.df, n = 5, wt = NULL, .by = NULL)

Arguments

Examples

df <- data.table(
  x = 1:5,
  y = 6:10,
  z = c(rep("a", 3), rep("b", 2))
)

df %>%
  top_n(2, wt = y)

df %>%
  top_n(2, wt = y, .by = z)

Add new variables and drop all others

Description

Unlike mutate(), transmute() keeps only the variables that you create

Usage

transmute(.df, ..., .by = NULL)

Arguments

Examples

df <- data.table(
  a = 1:3,
  b = 4:6,
  c = c("a", "a", "b")
)

df %>%
  transmute(double_a = a * 2)

Rowwise tidytable creation

Description

Create a tidytable using a rowwise setup.

Usage

tribble(...)

Arguments

Examples

tribble(
  ~ x, ~ y,
  "a", 1,
  "b", 2,
  "c", 3
)

Uncount a data.table

Description

Uncount a data.table

Usage

uncount(.df, weights, .remove = TRUE, .id = NULL)

Arguments

Examples

df <- data.table(x = c("a", "b"), n = c(1, 2))

uncount(df, n)

uncount(df, n, .id = "id")

Unite multiple columns by pasting strings together

Description

Convenience function to paste together multiple columns into one.

Usage

unite(.df, col = ".united", ..., sep = "_", remove = TRUE, na.rm = FALSE)

Arguments

Examples

df <- tidytable(
    a = c("a", "a", "a"),
    b = c("b", "b", "b"),
    c = c("c", "c", NA)
)

df %>%
  unite("new_col", b, c)

df %>%
  unite("new_col", where(is.character))

df %>%
  unite("new_col", b, c, remove = FALSE)

df %>%
  unite("new_col", b, c, na.rm = TRUE)

df %>%
  unite()

Unnest list-columns

Description

Unnest list-columns.

Usage

unnest(
  .df,
  ...,
  keep_empty = FALSE,
  .drop = TRUE,
  names_sep = NULL,
  names_repair = "unique"
)

Arguments

Examples

df1 <- tidytable(x = 1:3, y = 1:3)
df2 <- tidytable(x = 1:2, y = 1:2)
nested_df <-
  data.table(
    a = c("a", "b"),
    frame_list = list(df1, df2),
    vec_list = list(4:6, 7:8)
  )

nested_df %>%
  unnest(frame_list)

nested_df %>%
  unnest(frame_list, names_sep = "_")

nested_df %>%
  unnest(frame_list, vec_list)

Unnest a list-column of vectors into regular columns

Description

Turns each element of a list-column into a row.

Usage

unnest_longer(
  .df,
  col,
  values_to = NULL,
  indices_to = NULL,
  indices_include = NULL,
  keep_empty = FALSE,
  names_repair = "check_unique",
  simplify = NULL,
  ptype = NULL,
  transform = NULL
)

Arguments

Examples

df <- tidytable(
  x = 1:3,
  y = list(0, 1:3, 4:5)
)

df %>% unnest_longer(y)

Unnest a list-column of vectors into a wide data frame

Description

Unnest a list-column of vectors into a wide data frame

Usage

unnest_wider(
  .df,
  col,
  names_sep = NULL,
  simplify = NULL,
  names_repair = "check_unique",
  ptype = NULL,
  transform = NULL
)

Arguments

Examples

df <- tidytable(
  x = 1:3,
  y = list(0, 1:3, 4:5)
)

# Automatically creates names
df %>% unnest_wider(y)

# But you can provide names_sep for increased naming control
df %>% unnest_wider(y, names_sep = "_")