Pipe operator

Description

See magrittr::%>% for details.

Usage

lhs %>% rhs

as_integer16_or_64

Description

coerce to integer. if too large, coerces to 64-bit integer

Usage

as_integer16_or_64(x)

Arguments

Value

int or int64

auto setwd

Description

Call from a saved R script. Automatically sets your working directory to the directory that you saved the current R script in. Takes no arguments.

Usage

auto_setwd()

Value

No return value.

Clean Data Frame

Description

Uses the functions of framecleaner and other operations to apply cleaning operations to a data frame

Usage

clean_frame(.data)

Arguments

Details

Functions applied in clean_frame

• remove_empty

• rename_with .fn = enc2utf8

• clean_names case = "all_caps", ascii = FALSE)

• set_int

• set_date

• make_na

• as_tibble

Value

data frame

Examples

iris %>%
clean_frame()

create dummies

Description

adapted from the dummy_cols function Added the option to truncate the dummy column names, and to specify dummy cols using tidyselect.

Usage

create_dummies(
  .data,
  ...,
  append_col_name = TRUE,
  max_levels = 10L,
  remove_first_dummy = FALSE,
  remove_most_frequent_dummy = FALSE,
  clean_names = TRUE,
  ignore_na = FALSE,
  split = NULL,
  remove_selected_columns = TRUE
)

Arguments

Details

reference the fastDummies package for documentation on the original function.

Value

data frame

Examples

iris %>%
create_dummies(Species, append_col_name = FALSE) %>%
  tibble::as_tibble()

create flag

Description

create flag

Usage

create_flag(.data, col, flag, full_name = FALSE, drop = FALSE)

Arguments

Value

data frame

Examples

iris %>%
  create_flag(
  col = Species,
  flag = "versicolor",
  drop = TRUE) %>%
  head()

date_yh

Description

creates a semesterly date vector from a date vector

Usage

date_yh(x)

Arguments

Value

date vector

Examples

seq.Date(lubridate::ymd(20200101), lubridate::ymd(20220101), length.out = 10) -> d1
d1 %>%
  tibble::enframe() %>%
  dplyr::mutate(YH = date_yh(value))

date_ym

Description

creates a monthly date vector from a date vector

Usage

date_ym(x)

Arguments

Value

date vector

Examples

seq.Date(lubridate::ymd(20200101), lubridate::ymd(20220101), length.out = 10) -> d1
d1 %>%
  tibble::enframe() %>%
  dplyr::mutate(YM = date_ym(value))

date_yq

Description

creates a quarterly date vector from a date vector

Usage

date_yq(x)

Arguments

Value

date vector

Examples

seq.Date(lubridate::ymd(20200101), lubridate::ymd(20220101), length.out = 10) -> d1
d1 %>%
  tibble::enframe() %>%
  dplyr::mutate(YQ = date_yq(value))

Fill NAs

Description

use tidyselect to fill NA values Default behavior is to fill all integer or double columns cols with 0, preserving their types.

Usage

fill_na(.data, ..., fill = 0L, missing_type = c("all", "NA", "NaN", "Inf"))

Arguments

Value

data frame

Examples

tibble::tibble(x = c(NA, 1L, 2L, NA, NaN, 5L, Inf)) -> tbl

tbl %>%
  fill_na()

tbl %>%
 fill_na(fill = 1L, missing_type = "Inf")

tbl %>%
 fill_na(missing_type = "NaN")

filter for

Description

Filter for all instances of a column that meet a specific condition at least once.

Usage

filter_for(.data, what, where)

Arguments

Value

data frame

Examples

# An example using some time series data
tibble::tibble( CLIENT_ID = c("A1001", "B1001", "C1001",
"A1001", "B1001", "C1001", "A1001", "B1001", "C1001"),
                YEAR = c(2019L, 2019L, 2019L, 2020L, 2020L, 2020L, 2021L, 2021L, 2021L),
                SALES = c(3124, 56424, 3214132, 65534, 2342, 6566, 87654, 2332, 6565)
) %>%
dplyr::arrange(CLIENT_ID, YEAR) -> sales_data

sales_data

# filter for Clients that had sales greater than 4000 in the year 2019.
# this way we can see how the same clients sales looked in subsequent years

sales_data %>%
  filter_for(what = CLIENT_ID, where = YEAR == 2019 & SALES > 4000L)


# filter for clients whose sales were less than 4000 in the year 2021
 sales_data %>%
  filter_for(what = CLIENT_ID, where = YEAR == 2021 & SALES < 4000L)

filter out missings

Description

More complex wrapper around dplyr::filter(!is.na()) to remove NA rows using tidyselect. If any specified column contains an NA the whole row is removed. Reports the amount of rows removed containing NaN, NA, Inf, in that order. For example if one row contains Inf in one column and in another, the removed row will be counted in the NA tally.

Usage

filter_missing(.data, ..., remove_inf = TRUE)

## S3 method for class 'data.frame'
filter_missing(.data, ..., remove_inf = TRUE, condition = c("any", "all"))

Arguments

Details

S3 method, can also be used on vectors

Value

data frame

Examples

tibble::tibble(x = c(NA, 1L, 2L, NA, NaN, 5L, Inf),
y = c(1L, NA, 2L, NA, Inf, 5L, Inf)) -> tbl1

tbl1

# remove any row with a missing or Inf
tbl1 %>%
filter_missing()

# remove any row with Na or NaN in the x column
tbl1 %>%
filter_missing(x, remove_inf = FALSE)

# only remove rows where every entry is Na, NaN, or Inf
tbl1 %>%
filter_missing(condition = "all")

import directory

Description

import directory

Usage

import_dir(
  dir,
  ...,
  method = c("rio", "vroom", "vroom_jp", "read_csv"),
  return_type = c("df", "list")
)

Arguments

Value

data frame

import tibble

Description

wrapper around multiple file readers. The default being import set to return a tibble Also available vroom and vroom_jp for japanese characters.

Usage

import_tibble(
  path,
  ...,
  method = c("rio", "vroom", "vroom_jp", "read_csv", "read_excel")
)

Arguments

Details

Supports multiple types of importing through method

Value

a tibble

is integerish character

Description

companion to rlang::is_integerish that returns true only for integerish character vectors.

Usage

is_integerish_character(x)

Arguments

Value

a logical

is integery

Description

practical extension of rlang::is_integerish that supports integer64, integers in character strings, and doesn't coerce factors

Usage

is_integery(x)

Arguments

Value

logical

is missing or inf

Description

is missing or inf

Usage

is_missing_or_inf(x)

Arguments

Value

logical

is_probability

Description

is_probability

Usage

is_probability(x)

Arguments

Value

logical

Make NAs

Description

Set elements to NA values using tidyselect specification. Don't use this function on columns of different modes at once. Defaults to choosing all character columns.

Usage

## S3 method for class 'data.frame'
make_na(.data, ..., vec = c("-", "", " ", "null", "NA", "NA_"))

make_na(.data, ..., vec = c("-", "", " ", "null", "NA", "NA_"))

Arguments

Value

data frame

Examples

# easily set NA values. blank space and empty space are default options

tibble::tibble(x = c("a", "b", "", "d", " ", "", "e")) %>%
   make_na()

pad auto

Description

Automatically pads elements of a column to the largest sized element. Useful when an integer code with leading zeros is read in as an integer and needs to be fixed.

Usage

pad_auto(mdb, ..., side = "left", pad = "0")

Arguments

Value

data frame

Examples

# good for putting leading 0's

tibble::tibble(x = 1:10) %>%
  pad_auto(x)

pad column

Description

wrapper around mutate and str_pad

Usage

pad_col(mdb, ..., width, pad = "0", side = "left")

Arguments

Value

data frame

Examples

 # manually pad with 0's (or other value)
 # use case over [pad_auto()]: the desired width is greater than the widest element

 tibble::tibble(
 ID = c(2, 13, 86, 302)
 ) %>%
 pad_col(ID, width = 4)

recode_chr

Description

recode_chr

Usage

recode_chr(df, col, old_names, new_name, regex = FALSE, negate = FALSE)

Arguments

Value

df

Examples

# Use a negative regex to rename all species other than "virginica" to "none"

iris %>%
   recode_chr(
 col = Species,
 old_names = "vir",
 new_name = "none",
 regex = TRUE,
 negate = TRUE) %>%
 dplyr::count(Species)

# Specify old names using a regex

iris %>%
   recode_chr(
   col = Species,
   old_names = "set|vir",
   new_name = "other",
   regex = TRUE) %>%
   dplyr::count(Species)

Relocate All

Description

Arranges columns alphabetically and then by type The user can supply a tidyselect argument to specify columns that should come first

Usage

relocate_all(.data, ..., regex = NULL)

Arguments

Value

data frame

Examples

iris %>%
head %>%
relocate_all(matches("Petal"))

remove infs

Description

remove infs

Usage

remove_infs(x)

Arguments

Value

vec

remove nans

Description

remove nans

Usage

remove_nans(x)

Arguments

Value

vec

remove nas

Description

remove nas

Usage

remove_nas(x)

Arguments

Value

vec

Remove Whitespace

Description

Remove whitespace from columns using a tidyselect specification.

Usage

remove_whitespace(.data, ...)

Arguments

Value

data frame

Examples

tibble::tibble(a = c(" a ", "b ", " c")) -> t1

t1

t1 %>%
remove_whitespace()

select_otherwise

Description

flexible select operator that powers the tidy consultant universe. Used to set sensible defaults and flexibly return the chosen columns. A developer focused function, but may be useful in interactive programming due to the ability to return different types.

Usage

select_otherwise(
  .data,
  ...,
  otherwise = NULL,
  col = NULL,
  return_type = c("names", "index", "df")
)

Arguments

Value

integer vector by default. possibly data frame or character vector

Examples

iris %>%
select_otherwise(where(is.double), return_type = "index")

set character

Description

set character

Usage

set_chr(.data, ...)

Arguments

Value

dataframe

Examples

iris %>%
tibble::as_tibble() %>%
set_chr(tidyselect::everything())

set date

Description

set dates manually or automatically

Usage

set_date(.data, ..., date_fn = lubridate::ymd)

Arguments

Details

note: can be called without any ... arguments and instead automatically determines which character columns are actually dates, then proceeds to set them. It checks for the date specified in date_fn and also ymd_hms. On auto detect mode, it sets ymd_hms output to ymd dates instead of datetimes with hms. This is because of the common occurrence of trying to extract a ymd date from an excel workbook, and having it come with extra 00:00:00. If you need a datetime, manually supply the appropriate lubridate function.

Auto mode is experimental. Commonly detected error is a long character string of integers being interpreted as a date.

Value

tibble

Examples

tibble::tibble(date_col1 = c("20190101", "20170205"),
date_col2 = c("20201015", "20180909"),
not_date_col = c("a345", "b040")) -> t1

t1

t1 %>%
set_date()

t1 %>%
set_date(date_col1)

set double

Description

set double

Usage

set_dbl(.data, ...)

## S3 method for class 'character'
set_dbl(.data, ...)

## S3 method for class 'factor'
set_dbl(.data, ...)

## S3 method for class 'Date'
set_dbl(.data, ...)

## S3 method for class 'numeric'
set_dbl(.data, ...)

## S3 method for class 'integer64'
set_dbl(.data, ...)

## S3 method for class 'data.frame'
set_dbl(.data, ...)

Arguments

Value

tibble

Examples

date_col <- c(lubridate::ymd(20180101), lubridate::ymd(20210420))


tibble::tibble(int = c(1L, 2L),
fct = factor(c(10, 11)),
date = date_col,
chr = c("a2.1", "rtg50.5")) -> t1

t1

t1 %>%
set_dbl(tidyselect::everything())

# s3 method works for vectors individually
# custom date coercion to represent date as a number. For lubridate's coercion method, use set_int
date_col %>%
set_dbl

set factor

Description

allows option to manually set the first level of the factor, for consistency with yardstick which automatically considers the first level as the "positive class" when evaluating classification.

Usage

set_fct(
  .data,
  ...,
  first_level = NULL,
  order_fct = FALSE,
  labels = NULL,
  max_levels = Inf
)

## S3 method for class 'data.frame'
set_fct(.data, ..., first_level = NULL, order_fct = FALSE, max_levels = Inf)

## Default S3 method:
set_fct(.data, ..., first_level = NULL, order_fct = FALSE, max_levels = Inf)

Arguments

Value

tibble

Examples

## simply set the first level of a factor

iris$Species %>% levels

iris %>%
  set_fct(Species, first_level = "virginica") %>%
  dplyr::pull(Species) %>%
  levels()

set integer

Description

set integer

Usage

set_int(.data, ...)

## S3 method for class 'data.frame'
set_int(.data, ...)

## S3 method for class 'grouped_df'
set_int(.data, ...)

Arguments

Value

tibble

Examples

int_vec <- c("1", "2", "10")

tibble::tibble(
  chr_int = int_vec,
  dbl_int = c(1.0, 5.0, 20.0),
  chr_int64 = c("1033493932", "4432500065", "30303022192"),
  string_int = c("SALES2020", "SALES2021", "SALES2022")) -> tbl

# automatically coerce integerish cols in a tibble
tbl

# integerish doubles or chars will be detected for coercion automatically
tbl %>%
  set_int()

# string_int requires parsing, so it must be specified directly for coercion
tbl %>%
  set_int(matches("str|chr"))

# s3 method works for vectors as well

int_vec

int_vec %>%
set_int()

set logical

Description

note: for non-binary data, all values other than the true_level will be set to false

Usage

## S3 method for class 'data.frame'
set_lgl(.data, ..., true_level = 1L)

set_lgl(.data, ..., true_level = 1L)

## Default S3 method:
set_lgl(.data, ...)

## S3 method for class 'numeric'
set_lgl(.data, ..., true_level = 1L)

## S3 method for class 'character'
set_lgl(.data, ..., true_level = c("T", "TRUE"))

Arguments

Value

dataframe

Examples

# convert a 1/0 vector back into T/F

tibble::tibble(x = c(1, 0, 0, 1, 0, 1)) %>%
set_lgl(x)

set type groups

Description

set type groups

Usage

set_type_groups(.data, ..., setter)

Arguments

Value

tibble