Initial commit

.Rbuildignore

@@ -0,0 +1,16 @@
+^qtkit\.Rproj$
+^\.Rproj\.user$
+^LICENSE\.md$
+^README\.Rmd$
+^cran-comments\.md$
+^.*\.code-workspace$
+^_pkgdown\.yml$
+^docs$
+^pkgdown$
+^README\.Rmd$
+^\.github$
+^vignettes/articles$
+^\.httr-oauth$
+^\.lintr
+^data-raw$
+

.gitignore

@@ -0,0 +1,28 @@
+# RStudio
+.Rproj.user
+.Rhistory
+.Rdata
+.Ruserdata
+.Renviron
+*.Rproj
+
+# VSCode
+*.code-workspace
+.lintr
+
+# R
+.httr-oauth
+data-raw
+inst/doc
+vignettes/articles/_site/
+vignettes/articles/data/
+
+# GitHub Actions
+.github/workflows/pkgdown.yaml
+
+# macOS
+.DS_Store
+
+# Misc
+*_cache
+packages.bib

DESCRIPTION

@@ -0,0 +1,16 @@
+Title: Quantitative Text Kit
+Version: 0.9.4
+Authors@R:
+    person("Jerid", "Francom", , "[email protected]", role = c("aut", "cre"),
+           comment = c(ORCID = "0000-0001-5972-6330"))
+Description: Support package for the textbook "An Introduction to
+    Quantitative Text Analysis for Linguists: Reproducible Research using
+    R".
+Date: 2024-03-10
+License: GPL (>= 3)
+Suggests:
+    testthat (>= 3.0.0)
+Config/testthat/edition: 3
+Encoding: UTF-8
+Roxygen: list(markdown = TRUE)
+RoxygenNote: 7.3.1

NAMESPACE

@@ -0,0 +1,4 @@
+# Generated by roxygen2: do not edit by hand
+
+export(create_data_origin)
+importFrom(utils,write.csv)

R/create_data_origin.R

@@ -0,0 +1,43 @@
+#' Create data origin file
+#'
+#' This function creates a data frame with attributes about the origin of the data,
+#' writes it to a CSV file at the specified file path, and returns the data frame, if requested.
+#'
+#' @param file_path A character string specifying the file path where the data origin file should be saved.
+#' @param return A logical value indicating whether the data origin should be returned.
+#' @param force A logical value indicating whether to overwrite the file if it already exists.
+#' @return A data frame containing the data origin information.
+#' @export
+#'
+#' @examples
+#' \dontrun{
+#' create_data_origin("data_origin.csv")
+#' }
+#' @importFrom utils write.csv
+#'
+create_data_origin <- function(file_path, return = FALSE, force = FALSE) {
+  # Check to see if `file_path` is a character string
+  if (!is.character(file_path)) stop("`file_path` must be a character string.")
+
+  # Check to see if file exists at `file_path`
+  if (file.exists(file_path) && !force) {
+    stop("File already exists at `file_path`. Set `force = TRUE` to overwrite.")
+  }
+
+  # Create a data frame with the data origin information
+  data_origin <- data.frame(
+    attribute = c("Resource name", "Data source", "Data sampling frame", "Data collection date(s)", "Data format", "Data schema", "License", "Attribution"),
+    description = c("The name of the resource.", "URL, DOI, etc.", "Language, language variety, modality, genre, etc.", "The dates the data was collected.", ".txt, .csv, .xml, .html, etc.", "Relationships between data elements: files, folders, etc.", "CC BY, CC BY-SA, etc.", "Citation information.")
+  )
+
+  # Write the data origin to a file
+  write.csv(data_origin, file = file_path, row.names = FALSE)
+
+  # Return message
+  message("Data origin file created at `file_path`.")
+
+  # Return the data origin, if requested
+  if (return) {
+    return(data_origin)
+  }
+}

README.Rmd

@@ -0,0 +1,56 @@
+---
+output: github_document
+---
+
+<!-- README.md is generated from README.Rmd. Please edit that file -->
+
+```{r, include = FALSE}
+knitr::opts_chunk$set(
+  collapse = TRUE,
+  comment = "#>",
+  fig.path = "man/figures/README-",
+  out.width = "100%"
+)
+```
+
+# qtkit
+
+<!-- badges: start -->
+[![Lifecycle: experimental](https://img.shields.io/badge/lifecycle-experimental-orange.svg)](https://lifecycle.r-lib.org/articles/stages.html#experimental)
+[![CRAN status](https://www.r-pkg.org/badges/version/qtkit)](https://CRAN.R-project.org/package=qtkit)
+<!-- badges: end -->
+
+The goal of qtkit is to ...
+
+## Installation
+
+You can install the development version of qtkit like so:
+
+``` r
+# FILL THIS IN! HOW CAN PEOPLE INSTALL YOUR DEV PACKAGE?
+```
+
+## Example
+
+This is a basic example which shows you how to solve a common problem:
+
+```{r example}
+library(qtkit)
+## basic example code
+```
+
+What is special about using `README.Rmd` instead of just `README.md`? You can include R chunks like so:
+
+```{r cars}
+summary(cars)
+```
+
+You'll still need to render `README.Rmd` regularly, to keep `README.md` up-to-date. `devtools::build_readme()` is handy for this.
+
+You can also embed plots, for example:
+
+```{r pressure, echo = FALSE}
+plot(pressure)
+```
+
+In that case, don't forget to commit and push the resulting figure files, so they display on GitHub and CRAN.

cran-comments.md

@@ -0,0 +1,5 @@
+## R CMD check results
+
+0 errors | 0 warnings | 1 note
+
+* This is a new release.

tests/testthat.R

@@ -0,0 +1,12 @@
+# This file is part of the standard setup for testthat.
+# It is recommended that you do not modify it.
+#
+# Where should you do additional test configuration?
+# Learn more about the roles of various files in:
+# * https://r-pkgs.org/testing-design.html#sec-tests-files-overview
+# * https://testthat.r-lib.org/articles/special-files.html
+
+library(testthat)
+library(qtkit)
+
+test_check("qtkit")

tests/testthat/test-create_data_origin.R

@@ -0,0 +1,30 @@
+library(testthat)
+
+create_data_origin <- function(n = 100, p = 2) {
+  x <- matrix(rnorm(n * p), ncol = p)
+  colnames(x) <- paste0("X", seq_len(ncol(x)))
+  y <- rnorm(n)
+  data.frame(y, x)
+}
+
+test_that("test create_data_origin function", {
+  # check if create_data_origin returns a data frame
+  expect_is(create_data_origin(), "data.frame")
+
+  # check if number of rows equals to n
+  expect_equal(nrow(create_data_origin()), 100)
+  expect_equal(nrow(create_data_origin(50)), 50)
+
+  # check if number of columns equals to p + 1
+  expect_equal(ncol(create_data_origin()), 3)
+  expect_equal(ncol(create_data_origin(100, 5)), 6)
+
+  # check if the first column is named y
+  expect_equal(colnames(create_data_origin())[1], "y")
+
+  # check if the remaining column names are correct
+  expect_equal(colnames(create_data_origin(100, 5))[-1], paste0("X", 1:5))
+
+  # check if data is generated using normal distribution
+  expect_equal(mean(create_data_origin(1000000, 1)$y) < 0.05, TRUE)
+})