Package 'certetoolbox'

Description

Download properties from the AGB Register.

Usage

agb_property(agb_code, property = NULL)

Arguments

Details

The AGB (Algemeen GegevensBeheer) register is a national database in the Netherlands that assigns a unique AGB code to healthcare providers and institutions. This code is used for identification and administration within the healthcare sector, such as for billing insurance companies, contracting, and data exchange between healthcare providers.

The AGB code is managed by VECOZO and plays a crucial role in ensuring transparency and efficiency in Dutch healthcare administration.

Examples

## Not run: 
agb_property(03033048)
agb_property(c(03033048, 01102504))

agb_property(03033048, property = "last_name")
agb_property(c(03033048, 01102504), "specialty")

## End(Not run)

Description

Uploads a local file to the AMRZNN dashboard data repository via the GitHub Contents API. Creates the file if it does not yet exist, or overwrites it if it does. No local git installation or repository clone is required.

Usage

amrznn_upload(
  local_file,
  repo_path,
  pat = gh::gh_token(),
  commit_message = paste("Automated upload:", Sys.Date()),
  repo = "AMRZNN/dashboard_data",
  verbose = TRUE
)

Arguments

Details

Script taken from https://github.com/AMRZNN/dashboard_data/blob/9c7b65857f5467713fc3e3b01a5c7d4f1144b961/upload_script.R.

Value

Invisibly returns the HTTP status code of the PUT response (200 for update, 201 for new file).

Examples

## Not run: 
amrznn_upload(
  local_file = "output/weekly_resistance.csv",
  repo_path  = "certe/weekly_resistance.csv"
)

## End(Not run)

Description

The as_excel() function relies on the openxlsx2 package for creating an Excel Workbook object in R. These objects can be saved using save_excel() or export_xlsx().

Usage

as_excel(
  ...,
  sheet_names = NULL,
  autofilter = TRUE,
  autowidth = TRUE,
  widths = NULL,
  rows_zebra = TRUE,
  cols_zebra = FALSE,
  freeze_top_row = TRUE,
  digits = 2,
  align = "center",
  table_style = "TableStyleMedium2",
  creator = Sys.info()["user"],
  department = read_secret("department.name"),
  project_number = project_get_current_id(ask = FALSE)
)

save_excel(xl, filename = NULL, overwrite = FALSE)

Arguments

Supported Table Styles

For the argument table_style, use one or more of these table styles as character input. The default is TableStyleMedium2.

Examples

# creates a Workbook object
xl <- as_excel("this is a sheet" = mtcars,
               "another sheet" = anscombe)
xl

# then save it with save_excel() or export_xlsx()

Description

Force Time as UTC

Usage

as.UTC(x, ...)

## S3 method for class 'data.frame'
as.UTC(x, ...)

## S3 method for class 'POSIXct'
as.UTC(x, ...)

## Default S3 method:
as.UTC(x, ...)

Arguments

Examples

Sys.time()
as.UTC(Sys.time())

Description

This function transforms a data.frame by guessing the right data classes and applying them, using readr::parse_guess() and cleaner functions such as cleaner::clean_Date().

Usage

auto_transform(
  x,
  datenames = "en",
  dateformat = "yyyy-mm-dd",
  timeformat = "HH:MM",
  decimal.mark = ".",
  big.mark = "",
  timezone = "Europe/Amsterdam",
  na = c("", "NULL", "NA", "<NA>"),
  snake_case = FALSE,
  ...
)

Arguments

Description

Download data from CBS Open data Statline.

Usage

cbs_topics()

cbs_search(topic, max_print = 25)

cbs_download(identifier, clean_cols = TRUE)

cbs_moreinfo(identifier)

Arguments

Details

cbs_topics() retrieves all topics.

cbs_search() searches for a specific subject.

cbs_download() downloads tables. Input has to be a CBS Identifier (printed in red in cbs_search()), or a tracking number of cbs_search(), or the result of cbs_search().

cbs_moreinfo() gives a detailed explanation for the table. Input can also be a dataset downloaded with cbs_download().

Examples

## Not run: 
cbs_search("Inwoners")

x <- cbs_download(2) # 2nd hit of cbs_search()
str(x)

cbs_moreinfo(x)
cbs_moreinfo(2)

## End(Not run)

Description

The concat() function is at default identical to paste(c(...), sep = "", collapse = "").

The collapse() function is at default identical to paste(x, sep = "", collapse = "").

Usage

concat(..., sep = "")

collapse(x, sep = "")

Arguments

Examples

concat("a", "b", "c")

concat(c("a", "b"), "c")
collapse(c("a", "b"), "c")

concat(letters[1:5], "-")
collapse(letters[1:5], "-")

Description

Transform a data set into an n x m table, e.g. to be used in certestats::confusion_matrix().

Usage

crosstab(
  df,
  identifier,
  compare,
  outcome,
  positive = "^pos.*",
  negative = "^neg.*",
  ...,
  na.rm = TRUE,
  ignore_case = TRUE
)

Arguments

Examples

df <- data.frame(
  order_nr = sort(rep(LETTERS[1:20], 2)),
  test_type = rep(c("Culture", "PCR"), 20),
  result = sample(c("pos", "neg"),
                  size = 40,
                  replace = TRUE,
                  prob = c(0.3, 0.9))
)
head(df)

out <- df |> crosstab(order_nr, test_type, result)
out


df$result <- gsub("pos", "#p", df$result)
df$result <- gsub("neg", "#n", df$result)
head(df)
# gives a warning that pattern matching failed:
df |> crosstab(order_nr, test_type, result)

# define the pattern yourself in such case:
df |> crosstab(order_nr, test_type, result,
               positive = "#p",
               negative = "#n")
                             
                             
# defining classes manually, can be more than 2:
df |> crosstab(order_nr, test_type, result,
               ClassA = "#p", Hello = "#n")
                             
if ("certestats" %in% rownames(utils::installed.packages())) {
  certestats::confusion_matrix(out)
}

Description

These are convenience functions to get certain dates relatively to today.

Usage

yesterday(ref = today())

tomorrow(ref = today())

week(ref = today())

year(ref = today())

last_week(ref = today(), only_start_end = FALSE)

this_week(ref = today(), only_start_end = FALSE)

next_week(ref = today(), only_start_end = FALSE)

last_month(ref = today(), only_start_end = FALSE)

this_month(ref = today(), only_start_end = FALSE)

next_month(ref = today(), only_start_end = FALSE)

last_quarter(ref = today(), only_start_end = FALSE)

this_quarter(ref = today(), only_start_end = FALSE)

next_quarter(ref = today(), only_start_end = FALSE)

last_year(ref = today(), only_start_end = FALSE)

this_year(ref = today(), only_start_end = FALSE)

next_year(ref = today(), only_start_end = FALSE)

last_n_years(n, ref = end_of_last_year(), only_start_end = FALSE)

last_5_years(ref = end_of_last_year(), only_start_end = FALSE)

last_10_years(ref = end_of_last_year(), only_start_end = FALSE)

last_n_months(n, ref = end_of_last_month(), only_start_end = FALSE)

last_3_months(ref = end_of_last_month(), only_start_end = FALSE)

last_6_months(ref = end_of_last_month(), only_start_end = FALSE)

last_n_weeks(n, ref = end_of_last_week(), only_start_end = FALSE)

year_to_date(ref = today(), only_start_end = FALSE)

year_since_date(ref = today(), only_start_end = FALSE)

start_of_last_week(ref = today())

end_of_last_week(ref = today())

start_of_this_week(ref = today())

end_of_this_week(ref = today())

start_of_last_month(ref = today())

end_of_last_month(ref = today())

start_of_this_month(ref = today())

end_of_this_month(ref = today())

start_of_next_month(ref = today())

end_of_next_month(ref = today())

start_of_last_quarter(ref = today())

end_of_last_quarter(ref = today())

start_of_this_quarter(ref = today())

end_of_this_quarter(ref = today())

start_of_next_quarter(ref = today())

end_of_next_quarter(ref = today())

start_of_last_year(ref = today())

end_of_last_year(ref = today())

start_of_this_year(ref = today())

end_of_this_year(ref = today())

start_of_next_year(ref = today())

end_of_next_year(ref = today())

nth_monday(ref = today(), n = 1)

nth_tuesday(ref = today(), n = 1)

nth_wednesday(ref = today(), n = 1)

nth_thursday(ref = today(), n = 1)

nth_friday(ref = today(), n = 1)

nth_saturday(ref = today(), n = 1)

nth_sunday(ref = today(), n = 1)

week2date(wk, yr = year(today()), day = 1)

week2resp_season(wk, remove_outside_season = FALSE)

Arguments

Details

All functions return a vector of dates, except for yesterday(), today(), tomorrow(), week2date(), and the ⁠start_of_*()⁠, ⁠end_of_*()⁠ and ⁠nth_*()⁠ functions; these return 1 date.

Week ranges always start on Mondays and end on Sundays.

year() always returns an integer.

The last_n_years(), last_5_years() and last_10_years() functions have their reference date set to end_of_last_year() at default.

The last_n_months(), last_3_months() and last_6_months() functions have their reference date set to end_of_last_month() at default.

The last_n_weeks() function has its reference date set to end_of_last_week() at default.

week2resp_season() transforms week numbers to an ordered factor, in a range 40-53, 1:39 (or, if remove_outside_season = TRUE, 40-53, 1:20). This function is useful for plotting.

Examples

today()
today() %in% this_month()

next_week()
next_week(only_start_end = TRUE)

# 2nd Monday of last month:
last_month() |> nth_monday(2)

# last_*_years() will have 1 Jan to 31 Dec at default:
last_5_years(only_start_end = TRUE)
last_5_years(today(), only_start_end = TRUE)

last_3_months(only_start_end = TRUE)

year_to_date(only_start_end = TRUE)

## Not run: 

  # great for certedb functions:
  certedb::get_diver_data(last_5_years(),
                          Bepaling == "ACBDE")

## End(Not run)

df <- data.frame(date = sample(seq.Date(start_of_last_year(),
                                        end_of_this_year(),
                                        by = "day"),
                               size = 500))
df$time <- as.POSIXct(paste(df$date, "12:00:00"))

library(dplyr, warn.conflicts = FALSE)

# these are equal:
df |>
  filter(date |> between(start_of_last_week(),
                          end_of_last_week()))
df |>
  filter(date %in% last_week())

# but this does not work:
df |>
  filter(time %in% last_week())

# so be sure to transform times to dates in certain filters
df |>
  filter(as.Date(time) %in% last_week())

Description

These functions can be used to export data sets and plots. They invisibly return the object itself again, allowing for usage in pipes (except for the plot-exporting functions export_pdf(), export_png() and export_html()). The functions work closely together with the certeprojects package to support Microsoft Planner project numbers.

Usage

export(
  object,
  filename = NULL,
  project_number = project_get_current_id(ask = FALSE),
  overwrite = NULL,
  encrypt = !is.null(filename) && filename %like% "[.]rds$",
  key = read_secret("tools.encryption_password"),
  fn = NULL,
  ...
)

export_rds(
  object,
  filename = NULL,
  project_number = project_get_current_id(ask = FALSE),
  overwrite = NULL,
  encrypt = TRUE,
  key = read_secret("tools.encryption_password"),
  ...
)

export_xlsx(
  ...,
  filename = NULL,
  project_number = project_get_current_id(ask = FALSE),
  overwrite = NULL,
  sheet_names = NULL,
  autofilter = TRUE,
  rows_zebra = TRUE,
  cols_zebra = FALSE,
  freeze_top_row = TRUE,
  table_style = "TableStyleMedium2",
  align = "center"
)

export_excel(
  ...,
  filename = NULL,
  project_number = project_get_current_id(ask = FALSE),
  overwrite = NULL,
  sheet_names = NULL,
  autofilter = TRUE,
  rows_zebra = TRUE,
  cols_zebra = FALSE,
  freeze_top_row = TRUE,
  table_style = "TableStyleMedium2",
  align = "center"
)

export_csv(
  object,
  filename = NULL,
  project_number = project_get_current_id(ask = FALSE),
  overwrite = NULL,
  na = "",
  ...
)

export_csv2(
  object,
  filename = NULL,
  project_number = project_get_current_id(ask = FALSE),
  overwrite = NULL,
  na = "",
  ...
)

export_tsv(
  object,
  filename = NULL,
  project_number = project_get_current_id(ask = FALSE),
  overwrite = NULL,
  na = "",
  ...
)

export_txt(
  object,
  filename = NULL,
  project_number = project_get_current_id(ask = FALSE),
  overwrite = NULL,
  sep = "\t",
  na = "",
  ...
)

export_sav(
  object,
  filename = NULL,
  project_number = project_get_current_id(ask = FALSE),
  overwrite = NULL,
  ...
)

export_spss(
  object,
  filename = NULL,
  project_number = project_get_current_id(ask = FALSE),
  overwrite = NULL,
  ...
)

export_feather(
  object,
  filename = NULL,
  project_number = project_get_current_id(ask = FALSE),
  overwrite = NULL,
  ...
)

export_parquet(
  object,
  filename = NULL,
  project_number = project_get_current_id(ask = FALSE),
  overwrite = NULL,
  ...
)

export_pdf(
  plot,
  filename = NULL,
  project_number = project_get_current_id(ask = FALSE),
  overwrite = NULL,
  size = "A5",
  portrait = FALSE,
  ...
)

export_png(
  plot,
  filename = NULL,
  project_number = project_get_current_id(ask = FALSE),
  overwrite = NULL,
  width = 1000,
  height = 800,
  dpi = NULL,
  ...
)

export_html(
  plot,
  filename = NULL,
  project_number = project_get_current_id(ask = FALSE),
  overwrite = NULL,
  ...
)

encrypt_object(
  object,
  key = read_secret("tools.encryption_password"),
  serialise = TRUE,
  compress = TRUE
)

export_clipboard(
  object,
  sep = "\t",
  na = "",
  header = TRUE,
  quote = FALSE,
  decimal.mark = dec_mark(),
  ...
)

export_teams(
  object,
  filename = NULL,
  full_teams_path = NULL,
  account = connect_teams(),
  ...
)

Arguments

Details

The export() function can export to any file format, also with a manually set export function when passed on to the fn argument. This function fn has to have the object as first argument and the future file location as second argument. If fn is left blank, the ⁠export_*⁠ function will be used based on the filename.

RDS files as created using export_rds() are compatible with R3 and R4.

The export_xlsx() and export_excel() functions use save_excel(as_excel(...)) internally. IMPORTANT: these two functions can accept more than one data.frame. When naming the data sets, the names will become sheet names in the resulting Excel file. For a complete visual overview of supported table styles, see as_excel(). If the last value in ... is a character of length 1 and filename is NULL, this value is assumed to be the filename.

For export_csv(), export_csv2() and export_tsv(), files will be saved in UTF-8 encoding and NA values will be exported as "" at default. Like other ⁠*.csv⁠ and ⁠*.csv2⁠ functions, csv is comma (⁠,⁠) separated and csv2 is semicolon (⁠;⁠) separated.

The export_txt() function exports to a tab-separated file.

Exporting to an SPSS file using export_sav() or export_spss() requires the haven package to be installed.

Exporting to a Feather file using export_feather() requires the arrow package to be installed. Apache Feather provides efficient binary columnar serialization for data sets, enabling easy sharing data across data analysis languages (such as between Python and R).

Exporting to a Parquet file using export_parquet() requires the arrow package to be installed. Apache Parquet is an open source, column-oriented data file format designed for efficient data storage and retrieval.

Exporting to a PDF file using export_pdf() requires the ggplot2 package to be installed. If the filename is left blank in export_pdf(), export_png() or export_html(), the title of plot will be used if it's available and the certeplot2 package is installed, and a timestamp otherwise. NOTE: All export functions invisibly return object again, but the plotting functions invisibly return the file path

Exporting to a PNG file using export_png() requires the ggplot2 and showtext packages to be installed.

Exporting to an HTML file using export_html() requires the ggplot2 and htmltools packages to be installed. The arguments put in ... will be passed on to plotly::layout() if plot is not yet a Plotly object (but rather a ggplot2 object), which of course then requires the plotly package to be installed as well.

Exporting to the clipboard using export_clipboard() requires the clipr package to be installed. The function allows any object (also other than data.frames) to be exported to the clipboard and is only limited to the available amount of RAM memory.

Exporting to Microsoft Teams using export_teams() requires the AzureGraph package to be installed. The function allows any object (also other than data.frames) to be exported to any Team channel. The filename set in filename will determine the exported file type and defaults to an RDS file.

See Also

import()

Examples

library(dplyr, warn.conflicts = FALSE)

# export to two files: 'whole_file.rds' and 'first_ten_rows.xlsx'
starwars |>
  export_rds("whole_file") |>
  slice(1:10) |>
  export_xlsx("first_ten_rows")
  
# the above is equal to:
# starwars |>
#   export("whole_file.rds") |>
#   slice(1:10) |>
#   export("first_ten_rows.xlsx")

# RDS files are encrypted by default
x <- base::readRDS("whole_file.rds")
head(x)
# use decrypt_object() for manual decryption
x <- decrypt_object(x)
head(x)

# this goes automatically with import_rds():
x <- import_rds("whole_file.rds")
head(x)


# Apache's Feather format is column-based
# and allow for cross-language specific and fast file reading
starwars |> export_feather()
import("starwars.feather",
       col_select = starts_with("h")) |> 
  head()
  

# (cleanup)
file.remove("whole_file.rds")
file.remove("first_ten_rows.xlsx")
file.remove("starwars.feather")

## Not run: 

# ---- Microsoft Teams support -------------------------------------------

# IMPORTING

# import from Teams by picking a folder interactively from any Team
x <- import_teams()

# to NOT pick a Teams folder (e.g. in non-interactive mode), set `full_teams_path`
x <- import_teams(full_teams_path = "MyTeam/MyChannel/MyFolder/MyFile.xlsx")


# EXPORTING

# export to Teams by picking a folder interactively from any Team
mtcars |> export_teams()

# the default is RDS, but you can set `filename` to specify yourself
mtcars |> export_teams("mtcars.xlsx")

# to NOT pick a Teams folder (e.g. in non-interactive mode), set `full_teams_path`
mtcars |> export_teams("mtcars.xlsx", full_teams_path = "MyTeam/MyChannel/MyFolder")
mtcars |> export_teams(full_teams_path = "MyTeam/MyChannel/MyFolder")


## End(Not run)

Description

Generates hashes with or without an extra key/salt. This key defaults to the project identifier.

Usage

generate_hash(x, key = TRUE, bits = 256)

Arguments

Details

This function uses the openssl::sha2() function for the hashing, but always returns a character vector.

Examples

generate_hash("a")
generate_hash(c("a", "b", "c"))

generate_hash("a", "secret")
generate_hash(c("a", "b", "c"), "secret")

Description

This function creates unique identifier (IDs) using sample().

Usage

generate_identifier(id_length = 6, n = 1, chars = c(0:9, letters[1:6]))

Arguments

Examples

generate_identifier(8)
generate_identifier(6, 3)

Description

Hospitalname and/or location, with support for all hospitals in Northern Netherlands, including Meppel, Hardenberg and Zwolle.

Usage

hospital_name(x, format = "{naamkort}, {plaats}")

Arguments

Examples

hospital_name(c("MCL", "MCL", "Martini"))
hospital_name(c("Antonius", "WZA", "Martini"), format = "{naam} te {plaats}")

# special case for GGD
hospital_name(c("Martini", "GGD Groningen", "GGD Drenthe"), format = "{naam}")
hospital_name(c("Martini", "GGD Groningen", "GGD Drenthe"), format = "{naamkort}")
hospital_name("ggd friesland", "{naam}")

Description

These functions can be used to import data, from local or remote paths, or from the internet. They work closely with the certeprojects package to support Microsoft Planner project numbers. To support row names and older R versions, ⁠import_*()⁠ functions return plain data.frames, not e.g. tibbles.

Usage

import(
  filename,
  project_number = project_get_current_id(ask = FALSE),
  auto_transform = TRUE,
  encoding = "UTF-8",
  key = read_secret("tools.encryption_password"),
  ...
)

import_rds(
  filename,
  project_number = project_get_current_id(ask = FALSE),
  key = read_secret("tools.encryption_password"),
  ...
)

readRDS(
  filename,
  project_number = project_get_current_id(ask = FALSE),
  key = read_secret("tools.encryption_password"),
  ...
)

import_xlsx(
  filename,
  project_number = project_get_current_id(ask = FALSE),
  sheet = 1,
  range = NULL,
  auto_transform = TRUE,
  datenames = "nl",
  dateformat = "yyyy-mm-dd",
  timeformat = "HH:MM",
  decimal.mark = dec_mark(),
  big.mark = "",
  timezone = "UTC",
  na = c("", "NULL", "NA", "<NA>"),
  skip = 0,
  ...
)

import_excel(
  filename,
  project_number = project_get_current_id(ask = FALSE),
  sheet = 1,
  range = NULL,
  auto_transform = TRUE,
  datenames = "nl",
  dateformat = "yyyy-mm-dd",
  timeformat = "HH:MM",
  decimal.mark = dec_mark(),
  big.mark = "",
  timezone = "UTC",
  na = c("", "NULL", "NA", "<NA>"),
  skip = 0,
  ...
)

import_csv(
  filename,
  project_number = project_get_current_id(ask = FALSE),
  auto_transform = TRUE,
  datenames = "nl",
  dateformat = "yyyy-mm-dd",
  timeformat = "HH:MM",
  decimal.mark = ".",
  big.mark = "",
  timezone = "UTC",
  na = c("", "NULL", "NA", "<NA>"),
  skip = 0,
  encoding = "UTF-8",
  ...
)

import_csv2(
  filename,
  project_number = project_get_current_id(ask = FALSE),
  auto_transform = TRUE,
  datenames = "nl",
  dateformat = "yyyy-mm-dd",
  timeformat = "HH:MM",
  decimal.mark = ",",
  big.mark = "",
  timezone = "UTC",
  na = c("", "NULL", "NA", "<NA>"),
  skip = 0,
  encoding = "UTF-8",
  ...
)

import_tsv(
  filename,
  project_number = project_get_current_id(ask = FALSE),
  auto_transform = TRUE,
  datenames = "nl",
  dateformat = "yyyy-mm-dd",
  timeformat = "HH:MM",
  decimal.mark = ".",
  big.mark = "",
  timezone = "UTC",
  na = c("", "NULL", "NA", "<NA>"),
  skip = 0,
  encoding = "UTF-8",
  ...
)

import_txt(
  filename,
  project_number = project_get_current_id(ask = FALSE),
  auto_transform = TRUE,
  sep = "\t",
  datenames = "nl",
  dateformat = "yyyy-mm-dd",
  timeformat = "HH:MM",
  decimal.mark = ",",
  big.mark = "",
  timezone = "UTC",
  na = c("", "NULL", "NA", "<NA>"),
  skip = 0,
  encoding = "UTF-8",
  ...
)

import_sav(
  filename,
  project_number = project_get_current_id(ask = FALSE),
  auto_transform = TRUE,
  datenames = "en",
  dateformat = "yyyy-mm-dd",
  timeformat = "HH:MM",
  decimal.mark = ".",
  big.mark = "",
  timezone = "UTC",
  na = c("", "NULL", "NA", "<NA>"),
  ...
)

import_spss(
  filename,
  project_number = project_get_current_id(ask = FALSE),
  auto_transform = TRUE,
  datenames = "en",
  dateformat = "yyyy-mm-dd",
  timeformat = "HH:MM",
  decimal.mark = ".",
  big.mark = "",
  timezone = "UTC",
  na = c("", "NULL", "NA", "<NA>"),
  ...
)

import_feather(
  filename,
  project_number = project_get_current_id(ask = FALSE),
  col_select = everything(),
  ...
)

decrypt_object(
  object,
  key = read_secret("tools.encryption_password"),
  serialised = TRUE,
  compressed = TRUE
)

import_parquet(
  filename,
  project_number = project_get_current_id(ask = FALSE),
  col_select = everything(),
  ...
)

import_clipboard(
  sep = "\t",
  header = TRUE,
  startrow = 1,
  auto_transform = TRUE,
  datenames = "nl",
  dateformat = "yyyy-mm-dd",
  timeformat = "HH:MM",
  decimal.mark = dec_mark(),
  big.mark = "",
  timezone = "UTC",
  na = c("", "NULL", "NA", "<NA>"),
  ...
)

import_mail_attachment(
  search = "hasattachment:yes",
  search_subject = NULL,
  search_from = NULL,
  search_when = NULL,
  search_attachment = NULL,
  folder = certemail::get_inbox_name(account = account),
  n = 5,
  sort = "received desc",
  account = certemail::connect_outlook(),
  auto_transform = TRUE,
  sep = ",",
  ...
)

import_url(
  url,
  auto_transform = TRUE,
  sep = ",",
  datenames = "en",
  dateformat = "yyyy-mm-dd",
  timeformat = "HH:MM",
  decimal.mark = ".",
  big.mark = "",
  timezone = "UTC",
  na = c("", "NULL", "NA", "<NA>"),
  skip = 0,
  encoding = "UTF-8",
  ...
)

import_teams(
  full_teams_path = NULL,
  account = connect_teams(),
  auto_transform = TRUE,
  sep = ",",
  datenames = "en",
  dateformat = "yyyy-mm-dd",
  timeformat = "HH:MM",
  decimal.mark = ".",
  big.mark = "",
  timezone = "UTC",
  na = c("", "NULL", "NA", "<NA>"),
  skip = 0,
  encoding = "UTF-8"
)

Arguments

Details

Importing any unlisted filetype using import() requires the rio package to be installed.

Importing an Excel file using import_xlsx() or import_excel() requires the readxl package to be installed.

Importing an SPSS file using import_sav() or import_spss() requires the haven package to be installed.

Importing a Feather file using import_feather() requires the arrow package to be installed. Apache Feather provides efficient binary columnar serialization for data sets, enabling easy sharing data across data analysis languages (such as between Python and R). Use the col_select argument (which supports the tidyselect language) for specific data selection to improve importing speed.

Importing a Parquet file using import_parquet() requires the arrow package to be installed. Apache Parquet is an open source, column-oriented data file format designed for efficient data storage and retrieval. Use the col_select argument (which supports the tidyselect language) for specific data selection to improve importing speed.

Importing the clipboard using import_clipboard() requires the clipr package to be installed.

Importing mail attachments using import_mail_attachment() requires the certemail package to be installed. It calls download_mail_attachment() internally and saves the attachment to a temporary folder. For all folder names, run: sapply(certemail::connect_outlook()$list_folders(), function(x) x$properties$displayName).

The import_url() function tries to download the file first, after which it will be imported using the appropriate ⁠import_*()⁠ function.

The import_teams() function uses certeprojects::teams_download_file() to provide an interactive way to select a file in any Team, to download the file, and to import the file using the appropriate ⁠import_*()⁠ function.

See Also

export()

Examples

export_csv(iris)
import_csv("iris") |> head()

# the above is equal to:
# export(iris, "iris.csv")
# import("iris.csv") |> head()


# row names are also supported
export_csv(mtcars)
import_csv("mtcars") |> head()


# Apache's Feather format is column-based
# and allow for specific and fast file reading
library(dplyr, warn.conflicts = FALSE)
starwars |> export_feather()
import("starwars.feather",
       col_select = starts_with("h")) |> 
  head()
  

# (cleanup)
file.remove("iris.csv")
file.remove("mtcars.csv")
file.remove("starwars.feather")

## Not run: 

# ---- Microsoft Teams support -------------------------------------------

# IMPORTING

# import from Teams by picking a folder interactively from any Team
x <- import_teams()

# to NOT pick a Teams folder (e.g. in non-interactive mode), set `full_teams_path`
x <- import_teams(full_teams_path = "MyTeam/MyChannel/MyFolder/MyFile.xlsx")


# EXPORTING

# export to Teams by picking a folder interactively from any Team
mtcars |> export_teams()

# the default is RDS, but you can set `filename` to specify yourself
mtcars |> export_teams("mtcars.xlsx")

# to NOT pick a Teams folder (e.g. in non-interactive mode), set `full_teams_path`
mtcars |> export_teams("mtcars.xlsx", full_teams_path = "MyTeam/MyChannel/MyFolder")
mtcars |> export_teams(full_teams_path = "MyTeam/MyChannel/MyFolder")


## End(Not run)

Description

Generates a JSON representation of a dataset’s structure. Each column includes class, number of unique values, and optionally a truncated list of values unless excluded by type or pattern. All columns are retained in the output.

Usage

json_data_structure(
  dataset,
  dataset_name = NULL,
  n_first = 100,
  cols_exclude = "(bsn|id$|num[mb]er)",
  output_file = NULL
)

Arguments

Value

Invisibly returns the structured list written to JSON.

Description

Convenient wrapper around grepl() to match a pattern: x %like% pattern. It always returns a logical vector and is always case-insensitive (use x %like_case% pattern for case-sensitive matching). Also, pattern can be as long as x to compare items of each index in both vectors, or they both can have the same length to iterate over all cases.

Usage

like(x, pattern, ignore.case = TRUE)

x %like% pattern

x %unlike% pattern

x %like_case% pattern

x %unlike_case% pattern

Arguments

Details

These like() and ⁠%like%⁠/⁠%unlike%⁠ functions:

• Are case-insensitive (use ⁠%like_case%⁠/⁠%unlike_case%⁠ for case-sensitive matching)

• Support multiple patterns

• Check if pattern is a valid regular expression and sets fixed = TRUE if not, to greatly improve speed (vectorised over pattern)

• Always use compatibility with Perl unless fixed = TRUE, to greatly improve speed

Using RStudio? The ⁠%like%⁠/⁠%unlike%⁠ functions can also be directly inserted in your code from the Addins menu and can have its own keyboard shortcut like Shift+Ctrl+L or Shift+Cmd+L (see menu Tools > ⁠Modify Keyboard Shortcuts...⁠). If you keep pressing your shortcut, the inserted text will be iterated over ⁠%like%⁠ -> ⁠%unlike%⁠ -> ⁠%like_case%⁠ -> ⁠%unlike_case%⁠.

Value

A logical vector

Source

Idea from the like function from the data.table package, although altered as explained in Details.

See Also

grepl()

Examples

a <- "This is a test"
b <- "TEST"
a %like% b
b %like% a

# also supports multiple patterns
a <- c("Test case", "Something different", "Yet another thing")
b <- c(     "case",           "diff",      "yet")
a %like% b
a %unlike% b

a[1] %like% b
a %like% b[1]

Description

This function is analogous to all ⁠mo_*⁠ functions of the AMR package, see AMR::mo_property().

Usage

mo_glims(
  x,
  language = AMR::get_AMR_locale(),
  keep_synonyms = getOption("AMR_keep_synonyms", FALSE),
  ...
)

Arguments

Examples

mo_glims("E. coli")

library(dplyr, warn.conflicts = FALSE)
data.frame(mo = c("ESCCOL", "Staph aureus")) |>
  mutate(glims = mo_glims())
  
# even works for non-existing entries in AMR package
mo_glims("Streptococcus mitis/oralis")

if (require(AMR, warn.conflicts = FALSE)) {
  as.mo("Streptococcus mitis/oralis")
}
if (require("AMR")) {
  mo_genus("Streptococcus mitis/oralis")
}
if (require("AMR")) {
  mo_gramstain("Streptococcus mitis/oralis")
}

Description

Default in R >= 4.6.0.

Usage

x %notin% table

Arguments

Description

P-symbol format as asterisk

Usage

p_symbol(p, emptychar = " ")

Arguments

Description

Securely transfer any R object with full attribute preservation and cross-platform JSON compatibility. This uses the same approach as the mmbi.epi package of the UMCG.

Usage

post_data(
  object,
  url,
  authorization_header = NULL,
  compress = TRUE,
  encrypt = TRUE,
  key = read_secret("tools.encryption_password")
)

create_json_body(
  object,
  compress = TRUE,
  encrypt = TRUE,
  key = read_secret("tools.encryption_password")
)

Arguments

Examples

## Not run: 

post_data(iris,
          url = "https://some-server:8000/post",
          compress = TRUE,
          encrypt = TRUE)

## End(Not run)

# MANUAL WAY -----------------------------------------------------------

# use create_json_body() to make a(n encrypted) JSON of an object

iris_json <- iris |> create_json_body(compress = TRUE, encrypt = TRUE)

# curl -X POST https://some-server:8000/post
#      -H "Content-Type: application/json"
#      -d '...'

# replace the "..." with the outcome of create_json_body():
iris_json

Description

Checks if files contain privacy sensitive data and moves them to a 'vault folder' if this is the case.

Usage

privacy_check(
  path = getwd(),
  vault = paste0(path, "/vault"),
  log_file = paste0(vault, "/_privacy_log.txt"),
  suspicious_cols = "(zip.*code|postcode|bsn|geboortedatum)"
)

Arguments

Description

This function reads from a local or remote YAML file, as set in the environmental variable "secrets_file".

Usage

read_secret(property, file = Sys.getenv("secrets_file"))

Arguments

Details

In the secrets file, the property name and value have to be separated with a colon (:), as is intended in YAML files.

The default value for file is the environmental variable "secrets_file".

The file will be read using read_yaml(), which allows almost any local path or remote connection (such as websites).

Examples

# for this example, create a temporary 'secrets' file
my_secrets_file <- tempfile(fileext = ".yaml")
Sys.setenv(secrets_file = my_secrets_file)
writeLines(c("tenant_id: 8fb3c03060e02e89",
             "default_users: user_1"),
           my_secrets_file)

read_secret("tenant_id")
read_secret("default_users")

Description

Returns the relative reference directory for non-projects.

Usage

ref_dir(sub = "")

Arguments

Details

This function returns the absolute path using tools::file_path_as_absolute().

Description

Can be used in dplyr-syntax to remember values and objects for later use. Objects are (temporarily) stored in the certetoolbox package environment.

Usage

remember(.data, ...)

recall(x = NULL, delete = TRUE)

Arguments

Details

values can be saved with remember() and recalled (and deleted) with recall().

Examples

library(dplyr, warn.conflicts = FALSE)

x <- mtcars %>% remember(nrow(.)) 
recall()
recall() # value removed
x <- mtcars %>% remember(n = nrow(.)) 
recall(n)
recall(n) # value removed

## Not run: 
 tbl %>%
   filter(...) %>%
   remember(rows = nrow(.)) %>%
   group_by(...) %>%
   summarise(...) %>%
   plot2(title = "Test",
         subtitle = paste("n =", recall(rows)))

## End(Not run)

Description

Formats bytes into human-readable units, from "kB" (10^3) to "YB" (10^23).

Usage

size_humanreadable(bytes, decimals = 1, decimal.mark = dec_mark())

Arguments

Details

If using object.size() on an object, this function is equal to using format2() to format the object size.

Examples

size_humanreadable(c(12, 1234, 123456, 12345678))

size_humanreadable(1024 ^ c(0:4))

Description

Format a data.frame as flextable::flextable() with Certe style, bold headers and Dutch number formats. This function can also transform existing flextable and gtsummary objects to allow the formatting provided in this tbl_flextable() function.

Usage

tbl_flextable(
  x,
  row.names = rownames(x),
  row.names.bold = TRUE,
  rows.italic = NULL,
  rows.bold = NULL,
  rows.height = NULL,
  rows.fill = NULL,
  rows.zebra = TRUE,
  row.total = FALSE,
  row.total.name = "Totaal",
  row.total.function = sum,
  row.total.widths = NULL,
  row.total.bold = TRUE,
  row.extra.header = list(values = NULL, widths = 1),
  row.extra.footer = list(values = NULL, widths = 1),
  column.names = colnames(x),
  column.names.bold = TRUE,
  columns.width = NULL,
  columns.percent = NULL,
  columns.italic = NULL,
  columns.bold = NULL,
  columns.fill = NULL,
  columns.zebra = FALSE,
  column.total = FALSE,
  column.total.name = "Totaal",
  column.total.function = sum,
  column.total.bold = TRUE,
  align = "c",
  align.part = "all",
  caption = "",
  na = "",
  logicals = c("X", ""),
  round.numbers = 2,
  round.percent = 1,
  format.dates = "d mmm yyyy",
  decimal.mark = dec_mark(),
  big.mark = big_mark(),
  font.family = "Source Sans Pro",
  font.size = 9,
  font.size.header = font.size + 1,
  values.colour = NULL,
  values.fill = NULL,
  values.bold = NULL,
  values.italic = NULL,
  autofit = is.null(columns.width) & is.null(rows.height),
  autofit.fullpage = TRUE,
  autofit.fullpage.width = 16,
  vline = NULL,
  vline.part = c("body", "footer"),
  theme = current_markdown_colour(),
  colours = list(rows.fill.even = paste0(theme, "6"), rows.fill.odd = paste0(theme, "5"),
    columns.fill = paste0(theme, "5"), values.fill = paste0(theme, "3"), values.colour =
    theme, vline.colour = theme, hline.colour = theme, header.fill = theme, header.colour
    = "white", vline.header.colour = "white"),
  split.across.pages = NROW(x) > 37,
  print = !interactive(),
  ...
)

## S3 method for class 'certetoolbox_flextable'
print(x, use_knitr = !is_latex_output(), ...)

Arguments

Details

Run tbl_markdown() on a flextable object to transform it into markdown for use in Quarto or R Markdown reports. If print = TRUE in non-interactive sessions (Quarto or R Markdown), the flextable object will also be printed in markdown.

The value for theme is dependent on whether a colour is set in the markdown YAML header. Otherwise, use theme to set a Certe colour theme, defaults to "certeblauw":

# from the example below
tbl_flextable(df)

tbl_flextable(df, theme = "certeroze")

tbl_flextable(df, theme = "certegeel")

tbl_flextable(df, theme = "certegroen", vline = c(2:3))

tbl_flextable(
  df,
  theme = "certelila",
  row.total = TRUE,
  row.total.function = median,
  round.numbers = 4,
  row.extra.header = list(values = LETTERS[1:5])
)

Value

flextable::flextable object

See Also

flextable::flextable()

Examples

## Not run: 

# generate a data.frame
df <- data.frame(text = LETTERS[1:10],
                 `decimal numbers` = runif(10, 0, 10),
                 `whole numbers` = as.integer(runif(10, 0, 10)),
                 `logical values` = as.logical(round(runif(10, 0, 1))),
                 dates = today() - runif(10, 200, 2000),
                 stringsAsFactors = FALSE)

# default
tbl_flextable(df)      # dataset has no row names
tbl_flextable(mtcars)  # dataset has row names

# print in markdown
df |> 
  tbl_flextable() |> 
  tbl_markdown()
  
# transform a gtsummary to a flextable
iris |>
  tbl_gtsummary(Species, add_p = TRUE) |>
  tbl_flextable()
  
# extra formatting
tbl_flextable(df,
              logicals = c("X", "-"),     # replaces TRUE en FALSE
              values.colour = "X",
              values.fill = "X",
              row.names = "S. aureus",
              columns.italic = 1,
              format.dates = "ddd dd-mm-yy",
              round.numbers = 3)

# row totals
tbl_flextable(df,
              row.total = TRUE,           # add row total
              row.total.function = max,   # instead of sum()
              row.total.name = "Maximum", # also works with dates
              columns.percent = 2,        # 2nd column as percentages
              round.percent = 0)          # rounding percentages

# column names
tbl_flextable(df,
              column.names = c("1" = "Column 1",
                               "2" = "Column 2",
                               dates = "DATES!"))
tbl_flextable(df,
              column.names = LETTERS)

# vertical lines, alignment and row names
tbl_flextable(df,
              align = "lrrcc", # also works: c("l", "r", "r", "c", "c")
              font.size = 12,
              vline = c(2, 4),
              vline.part = "all",
              row.names = paste("Experiment", 1:10))

# width of cells and table
tbl_flextable(data.frame(test1 = "A", test2 = "B"),
              vline = 1,
              autofit.fullpage.width = 16, # default values in cm
              columns.width = c(1, 3))     # ratio; cells become 4 and 12 cm

tbl_flextable(data.frame(test1 = "A", test2 = "B"),
              vline = 1,
              autofit.fullpage = FALSE,    # no fullpage autofit
              columns.width = c(1, 3))     # cells become 1 and 3 cm
              
# adding extra header or footer
tbl_flextable(data.frame(test1 = "A", test2 = "B"),
              row.extra.header = list(values = c("Header", "Header"),
                                      widths = c(1, 1)),
              row.extra.footer = list(values = c("Footer", "Footer"),
                                      widths = c(1, 1)))

## End(Not run)

Description

Summarise a data.frame as gtsummary with Dutch defaults. These objects are based on the gt package by RStudio. To provide Certe style and compatibility with MS Word, use tbl_flextable() to transform the gtsummary object.

Usage

tbl_gtsummary(
  x,
  by = NULL,
  label = NULL,
  digits = 1,
  ...,
  language = "nl",
  column1_name = "Eigenschap",
  add_n = FALSE,
  add_p = FALSE,
  add_ci = FALSE,
  add_overall = FALSE,
  decimal.mark = dec_mark(),
  big.mark = big_mark()
)

Arguments

Details

tbl_gtsummary() creates a summary table with gtsummary::tbl_summary(), to which different extra columns can be added e.g. with add_p = TRUE and add_overall = TRUE.

Examples

# These examples default to the Dutch language

iris |>
  tbl_gtsummary()

iris |> 
  tbl_gtsummary(Species, add_p = TRUE)
  
iris |> 
  tbl_gtsummary(Species, add_n = TRUE)
  
# support strata by providing 
iris2 <- iris
iris2$Category <- sample(LETTERS[1:2], size = 150, replace = TRUE)
head(iris2)

iris2 |> 
  tbl_gtsummary(c(Category, Species))

# transform to flextable 
# (formats to Certe style and allows rendering to Word)
iris |> 
  tbl_gtsummary(Species) |> 
  tbl_flextable()

Description

Prints a data.frame as Markdown, LaTeX or HTML using knitr::kable(), with bold headers and Dutch number formats.

Usage

tbl_markdown(
  x,
  row.names = rownames(x),
  column.names = colnames(x),
  align = NULL,
  padding = 2,
  caption = "",
  na = "",
  type = "markdown",
  format.dates = "dd-mm-yyyy",
  decimal.mark = dec_mark(),
  big.mark = big_mark(),
  logicals = c("X", ""),
  columns.percent = NA,
  column.names.bold = TRUE,
  round.numbers = 2,
  round.percent = 1,
  newlines.leading = 0,
  newlines.trailing = 2,
  print = TRUE
)

Arguments

Details

When in an R Markdown rapport a table is printed using this function, column headers only print well if newlines.leading >= 2, or by manually using cat("\\n\\n") before printing the table.

Value

character

See Also

knitr::kable()

Examples

tbl_markdown(mtcars[1:6, 1:6], padding = 1)

Description

Update a data.frame using specific integers for row numbers or a vectorised filter. Also supports dplyr groups. see Examples.

Usage

## S3 method for class 'data.frame'
update(object, rows, ...)

Arguments

Examples

iris |> 
  update(3:4, Species = c("A", "B")) |> 
  head()
  
iris |> 
  update(Species == "setosa" & Sepal.Length > 5,
         Species = "something else") |> 
  head()
  
if (require("dplyr")) {

  # also supports dplyr groups:
  iris |> 
    group_by(Species) |>
    # update every 2nd to 4th row in group
    update(2:4, Species = "test") |> 
    # groups will be updated automatically
    count()

}

Description

Download Wikipedia daily page views for any language, using the Wikimedia REST API.

Usage

wikipedia_pageviews(
  articles,
  date_range = last_6_months(),
  language = "nl",
  platform = c("all-access", "mobile-web", "mobile-app", "desktop"),
  agent = c("all-agents", "user", "spider", "automated")
)

Arguments

Details

See example: https://pageviews.wmcloud.org/?project=nl.wikipedia.org&platform=all-access&agent=all-agents&redirects=0&start=2024-06-01&end=2025-02-01&pages=Griep|Influenzavirus_A

Examples

wikipedia_pageviews("Griep")

articles <- c("Griep", "Koorts", "Hoest", "Verkoudheid", "Influenzavirus A",
              "Respiratoir syncytieel virus", "Keelpijn", "SARS-CoV-2")

if (require("certeplot2") && require("certestats") && require("dplyr")) {
  articles |>
    wikipedia_pageviews(c("2024-07-01", "2025-02-01")) |>
    group_by(article) |>
    mutate(z = z_score(views),
           z_ma = moving_average(z, w = 7, side = "left")) |>
    plot2(
      x = date,
      y = z_ma,
      category = article,
      type = "line",
      category.sort = "freq-asc",
      legend.position = "right",
      y.title = "7-daagse Z-score",
      x.title = "",
      title = "Wikipedia bezochte pagina's",
      subtitle = "Z-scores respiratoire seizoen")
}

if (require("certeplot2")) {
  wikipedia_pageviews("Dog",
                      language = "en",
                      date_range = last_5_years()) |>
    plot2(x = date, y = views)
}