import: Import Data Sets

In certe-medical-epidemiology/certetoolbox: A Certe R Package for Miscellaneous Functions

Import Data Sets

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",
  ...
)

import_rds(filename, project_number = project_get_current_id(ask = FALSE), ...)

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(),
  ...
)

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

filename	the full path of the file to be imported, will be parsed to a character, can also be a remote location (from http/https/ftp/ssh, GitHub/GitLab)
project_number	a Microsoft Planner project number
auto_transform	transform the imported data with auto_transform()
encoding	Default encoding. This only affects how the file is read.
...	arguments passed on to methods
sheet	Excel sheet to import, defaults to first sheet
range	a cell range to read from, allows typical Excel ranges such as "B3:D87" and "Budget!B2:G14"
datenames	language of the date names, such as weekdays and months
dateformat	expected date format, will be coerced with format_datetime()
timeformat	expected time format, will be coerced with format_datetime()
decimal.mark	separator for decimal numbers
big.mark	separator for thousands
timezone	expected time zone
na	values to interpret as NA
skip	number of first rows to skip
sep	character to separate values in a row
col_select	columns to select, supports the tidyselect language)
header	use first row as header
startrow	first row to start importing
search	an ODATA filter, ignores sort and defaults to search only mails with attachments
search_subject	a character, equal to search = "subject:(search_subject)", case-insensitive
search_from	a character, equal to search = "from:(search_from)", case-insensitive
search_when	a Date vector of size 1 or 2, equal to search = "received:date1..date2", see Examples
search_attachment	a character to use a regular expression for attachment file names
folder	email folder name to search in, defaults to Inbox of the current user by calling get_inbox_name()
n	maximum number of emails to search
sort	initial sorting
account	a Teams account from Azure or an AzureAuth Microsoft 365 token, e.g. retrieved with certeprojects::connect_teams()
url	remote location of any data set, can also be a (non-raw) GitHub/GitLab link
full_teams_path	a full path in Teams, including the Team name and the channel name. Leave blank to use interactive mode, which allows file/folder picking from a list in the console.

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 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)

certe-medical-epidemiology/certetoolbox documentation built on April 17, 2025, 3:24 a.m.