Initial commit

.Rprofile

@@ -0,0 +1 @@
+source("renv/activate.R")

.github/workflows/test-targets-workflow.yml

@@ -0,0 +1,47 @@
+name: test targets workflow
+
+on:
+  push:
+    branches: [main, master]
+  pull_request:
+    branches: [main, master]
+  workflow_dispatch:
+    # branches:
+    #   - '*'
+
+jobs:
+  test-targets-workflow:
+    runs-on: ubuntu-latest
+    container: rocker/tidyverse:4.3.3
+    env:
+      GIT_CRYPT_KEY64: ${{ secrets.GIT_CRYPT_KEY64 }}
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install system dependencies
+        run: |
+          apt-get update && apt-get install -y --no-install-recommends \
+          libxt6 libglpk-dev
+          
+      - name: Trust git repo
+        run: |
+          git config --global --add safe.directory /__w/ihtm-targets-template/ihtm-targets-template
+          
+      - name: Install packages from renv.lock (with cache)
+        if: ${{ !env.ACT }}  
+        uses: r-lib/actions/setup-renv@v2
+        with:
+          cache-version: 2
+
+      - name: Install packages from renv.lock (local, no cache)
+        if: ${{ env.ACT }}  
+        run: |
+          renv::restore()
+        shell: Rscript {0}
+
+      - name: Run workflow
+        run: |
+          targets::tar_make()
+        shell: Rscript {0}
+
+

.gitignore

@@ -0,0 +1,6 @@
+.Rproj.user
+.Rhistory
+.RData
+.Ruserdata
+_targets
+docs

R/utils.R

@@ -0,0 +1,34 @@
+#' 
+#' Collect all targets and lists of targets in the environment
+#' 
+#' 
+all_targets <- function(env = parent.env(environment()), 
+                        type = "tar_target", 
+                        add_list_names = TRUE) {
+
+  ## Function to determine if an object is a type (a target), 
+  ## or a list on only that type
+  rfn <- function(obj) 
+    inherits(obj, type) || (is.list(obj) && all(vapply(obj, rfn, logical(1))))
+
+  ## Get the names of everything in the environment 
+  ## (e.g. sourced in the _targets.R file)
+  objs <- ls(env)
+
+  out <- list()
+  for (o in objs) {
+    obj <- get(o, envir = env)      ## Get each top-level object in turn
+    if (rfn(obj)) {                 ## For targets and lists of targets
+      out[[length(out) + 1]] <- obj ## Add them to the output
+
+      ## If the object is a list of targets, add a vector of the target names 
+      ## to the environment So that one can call `tar_make(list_name)` to make 
+      ## all the targets in that list
+      if (add_list_names && is.list(obj)) {
+        target_names <- vapply(obj, \(x) x$settings$name, character(1))
+        assign(o, target_names, envir = env)
+      }
+    }
+  }
+  return(out)
+}

README.Rmd

@@ -0,0 +1,71 @@
+---
+output: github_document
+---
+
+<!-- README.md is generated from README.Rmd. Please edit that file -->
+
+```{r, include = FALSE}
+knitr::opts_chunk$set(
+  collapse = TRUE,
+  comment = "#>"
+)
+```
+
+# A template R workflow for general data analysis
+
+<!-- badges: start -->
+<!-- badges: end -->
+
+This repository is a template for a [`docker`](https://www.docker.com/get-started)-containerised, [`{targets}`](https://docs.ropensci.org/targets/)-based, [`{renv}`](https://rstudio.github.io/renv/articles/renv.html)-enabled [`R`](https://cran.r-project.org/) workflow for general data analysis.
+
+## About the Project
+
+
+
+## Repository Structure
+
+The project repository is structured as follows:
+
+```
+sc-policy-review
+    |-- .github/
+    |-- data/
+    |-- data-raw/
+    |-- outputs/
+    |-- R/
+    |-- reports
+    |-- renv
+    |-- renv.lock
+    |-- .Rprofile
+    |-- packages.R
+    |-- _targets.R
+```
+
+* `.github` contains project testing and automated deployment of outputs workflows via continuous integration and continuous deployment (CI/CD) using Github Actions.
+
+* `data/` contains intermediate and final data outputs produced by the workflow.
+
+* `data-raw/` contains raw datasets, usually either downloaded from source or added manually, that are used in the project. This directory is empty given that the raw datasets used in this project are restricted and are only distributed to eligible members of the project. This directory is kept here to maintain reproducibility of project directory structure and ensure that the workflow runs as expected. Those who are collaborating on this project and who have permissions to use the raw datasets should include their copies of the raw dataset into this directory in their local versions of this repository.
+
+* `outputs/` contains compiled reports and figures produced by the workflow.
+
+* `R/` contains functions developed/created specifically for use in this workflow.
+
+* `reports/` contains literate code for R Markdown reports rendered in the workflow.
+
+* `renv/` contains `renv` package specific files and directories used by the package for maintaining R package dependencies within the project. The directory `renv/library`, is a library that contains all packages currently used by the project. This directory, and all files and sub-directories within it, are all generated and managed by the `renv` package. Users should not change/edit these manually.
+
+* `renv.lock` file is the `renv` lockfile which records enough metadata about every package used in this project that it can be re-installed on a new machine. This file is generated by the `renv` package and should not be changed/edited manually.
+
+* `.Rprofile` file is a project R profile generated when initiating `renv` for the first time. This file is run automatically every time R is run within this project, and `renv` uses it to configure the R session to use the `renv` project library.
+
+* `packages.R` file lists out all R package dependencies required by the workflow.
+
+* `_targets.R` file defines the steps in the workflow's data ingest, data processing, data analysis, and reporting pipeline.
+
+## Reproducibility
+
+### R package dependencies
+
+This project was built using `R 4.4.0`. This project uses the `renv` framework to record R package dependencies and versions. Packages and versions used are recorded in `renv.lock` and code used to manage dependencies is in `renv/` and other files in the root project directory. On starting an R session in the working directory, run `renv::restore()` to install R package dependencies.
+

README.md

@@ -0,0 +1,94 @@
+
+<!-- README.md is generated from README.Rmd. Please edit that file -->
+
+# A template R workflow for general data analysis
+
+<!-- badges: start -->
+
+<!-- badges: end -->
+
+This repository is a template for a
+[`docker`](https://www.docker.com/get-started)-containerised,
+[`{targets}`](https://docs.ropensci.org/targets/)-based,
+[`{renv}`](https://rstudio.github.io/renv/articles/renv.html)-enabled
+[`R`](https://cran.r-project.org/) workflow for general data analysis.
+
+## About the Project
+
+## Repository Structure
+
+The project repository is structured as follows:
+
+    sc-policy-review
+        |-- .github/
+        |-- data/
+        |-- data-raw/
+        |-- outputs/
+        |-- R/
+        |-- reports
+        |-- renv
+        |-- renv.lock
+        |-- .Rprofile
+        |-- packages.R
+        |-- _targets.R
+
+  - `.github` contains project testing and automated deployment of
+    outputs workflows via continuous integration and continuous
+    deployment (CI/CD) using Github Actions.
+
+  - `data/` contains intermediate and final data outputs produced by the
+    workflow.
+
+  - `data-raw/` contains raw datasets, usually either downloaded from
+    source or added manually, that are used in the project. This
+    directory is empty given that the raw datasets used in this project
+    are restricted and are only distributed to eligible members of the
+    project. This directory is kept here to maintain reproducibility of
+    project directory structure and ensure that the workflow runs as
+    expected. Those who are collaborating on this project and who have
+    permissions to use the raw datasets should include their copies of
+    the raw dataset into this directory in their local versions of this
+    repository.
+
+  - `outputs/` contains compiled reports and figures produced by the
+    workflow.
+
+  - `R/` contains functions developed/created specifically for use in
+    this workflow.
+
+  - `reports/` contains literate code for R Markdown reports rendered in
+    the workflow.
+
+  - `renv/` contains `renv` package specific files and directories used
+    by the package for maintaining R package dependencies within the
+    project. The directory `renv/library`, is a library that contains
+    all packages currently used by the project. This directory, and all
+    files and sub-directories within it, are all generated and managed
+    by the `renv` package. Users should not change/edit these manually.
+
+  - `renv.lock` file is the `renv` lockfile which records enough
+    metadata about every package used in this project that it can be
+    re-installed on a new machine. This file is generated by the `renv`
+    package and should not be changed/edited manually.
+
+  - `.Rprofile` file is a project R profile generated when initiating
+    `renv` for the first time. This file is run automatically every time
+    R is run within this project, and `renv` uses it to configure the R
+    session to use the `renv` project library.
+
+  - `packages.R` file lists out all R package dependencies required by
+    the workflow.
+
+  - `_targets.R` file defines the steps in the workflow’s data ingest,
+    data processing, data analysis, and reporting pipeline.
+
+## Reproducibility
+
+### R package dependencies
+
+This project was built using `R 4.4.0`. This project uses the `renv`
+framework to record R package dependencies and versions. Packages and
+versions used are recorded in `renv.lock` and code used to manage
+dependencies is in `renv/` and other files in the root project
+directory. On starting an R session in the working directory, run
+`renv::restore()` to install R package dependencies.

_targets.R

@@ -0,0 +1,50 @@
+################################################################################
+#
+# General Targets Workflow
+#
+################################################################################
+
+## Load libraries and custom functions -----------------------------------------
+suppressPackageStartupMessages(source("packages.R"))
+for (f in list.files(here::here("R"), full.names = TRUE)) source (f)
+
+## Create targets and list targets objects -------------------------------------
+
+### Data targets
+data_targets <- tar_plan(
+
+)
+
+
+### Processing targets
+processing_targets <- tar_plan(
+
+)
+
+
+### Analysis targets
+analysis_targets <- tar_plan(
+
+)
+
+
+### Output targets
+output_targets <- tar_plan(
+
+)
+
+
+### Reporting targets
+report_targets <- tar_plan(
+
+)
+
+
+### Deploy targets
+deploy_targets <- tar_plan(
+
+)
+
+
+## List targets
+all_targets()

ihtm-targets-template.Rproj

@@ -0,0 +1,13 @@
+Version: 1.0
+
+RestoreWorkspace: Default
+SaveWorkspace: Default
+AlwaysSaveHistory: Default
+
+EnableCodeIndexing: Yes
+UseSpacesForTab: Yes
+NumSpacesForTab: 2
+Encoding: UTF-8
+
+RnwWeave: Sweave
+LaTeX: pdfLaTeX

packages.R

@@ -0,0 +1,16 @@
+################################################################################
+#
+# Load packages required for standard workflows
+#
+################################################################################
+
+library(targets)
+library(tarchetypes)
+library(here)
+library(rmarkdown)
+library(knitr)
+library(kableExtra)
+library(dplyr)
+library(tidyr)
+library(openxlsx)
+library(ggplot2)