diff --git a/.gitignore b/.gitignore index ca0dc554..8c9136fd 100644 --- a/.gitignore +++ b/.gitignore @@ -17,4 +17,7 @@ *.html # geospatial lesson files -rosm.cache/* \ No newline at end of file +rosm.cache/* + +# Session build files +session_*_files/* \ No newline at end of file diff --git a/materials/_quarto.yml b/materials/_quarto.yml index b0e56318..6c7e2584 100755 --- a/materials/_quarto.yml +++ b/materials/_quarto.yml @@ -3,8 +3,8 @@ project: output-dir: _book book: - title: "NCEAS Learning Hub’s coreR Course" - subtitle: "October 7-11, 2024" + title: "Fundamentals in Data Management for Qualitative and Quantitative Arctic Research" + subtitle: "January 27-31, 2025" reader-mode: false # NoteHD: cover image is not working @@ -23,33 +23,28 @@ book: - icon: twitter href: https://twitter.com/ucsb_nceas - icon: github - href: https://github.com/NCEAS/nceas-training/tree/2024-10-coreR + href: https://github.com/NCEAS/nceas-training/tree/2025-01-arctic chapters: - index.qmd # preface - - session_01.qmd # Introduction - - session_02.qmd # R Setup - - session_03.qmd # Git and GitHub set up - - session_04.qmd # Intro to R & RStudio - - session_05.qmd # Literate Analysis - - session_06.qmd # Lego Activity + Discussion - - session_07.qmd # Intro to Git and GitHub - - session_08.qmd # Tidy Data + - session_01.qmd # ADC intro + - session_02.qmd # R Setup + - session_03.qmd # Intro to R programming + - session_04.qmd # Thinking preferencees + Social aspects of collab + - session_05.qmd # DMP + - session_06.qmd # Literate analysis + - session_07.qmd # ADC-Fundamental practice 1 + - session_08.qmd # Data Modeling and Tidy Data - session_09.qmd # Cleaning and Wrangling - - session_10.qmd # Practice Session I - joins - - session_11.qmd # Collaborating with Git - - session_12.qmd # Publishing to the Web - - session_13.qmd # Intro to Data Viz - - session_14.qmd # Practice Session II -lobter report - - session_15.qmd # Data Management - - session_16.qmd # Spatial Data - - session_17.qmd # Functions and Packages - - session_18.qmd # Practice Functions and Packages - - session_19.qmd # Office Hour Guidelines - - session_20.qmd # GitHub for Project management - - session_21.qmd # Repro and Provenance - - session_22.qmd # Appendix: Set up in personla comp - + - session_10.qmd # Intro Data Viz + - session_11.qmd # Ethical Data Collection + - session_12.qmd # ADC-Fundamentals practice 2 + - session_13.qmd # Text data + - session_14.qmd # Census data + - session_15.qmd # Metadata best practices & publishing + - session_16.qmd # Data portals + - session_17.qmd # Survey Workflows + - session_18.qmd # Repro and Provenance bibliography: book.bib @@ -62,4 +57,4 @@ format: # pdf: # documentclass: scrreprt -editor: visual \ No newline at end of file +editor: visual diff --git a/materials/images/schedule.png b/materials/images/schedule.png index 2943569d..2919369c 100644 Binary files a/materials/images/schedule.png and b/materials/images/schedule.png differ diff --git a/materials/index.qmd b/materials/index.qmd index 937bb3e7..5710aab3 100644 --- a/materials/index.qmd +++ b/materials/index.qmd @@ -1,36 +1,20 @@ - - ::: column-margin +![](images/arctic-data-center.png){width="80%" fig-align="center"} +::: +::: column-margin ![](cover.png){width="80%" fig-align="center"} - - ::: -## Welcome! {.unnumbered} -coreR is a five-day immersion in R programming for environmental data science. Researchers will gain experience with essential data science tools and best practices to increase their capacity as collaborators, reproducible coders, and open scientists. - -### Course Learning Objectives -- Increase your familiarity and confidence with data science tools -- Overview of tools you can use within the R programming language and RStudio interface -- Effectively manage data using `tidy` data practices and understanding the importance of quality metadata -- Establish best practices and utilize tools like Git & GitHub to optimize collaboration -- Better communicate scientific analyses and results using Markdown, GitHub webpages, and R packages like `ggplot` and `leaflet` - - -### Week's Schedule - - -![](images/schedule.png) - +## About the course {.unnumbered} -## NCEAS Expertise - -The [National Center for Ecological Analysis and Synthesis (NCEAS)](https://www.nceas.ucsb.edu/), a research affiliate of UCSB, is a leading expert on interdisciplinary data science and works collaboratively to answer the world's largest and most complex questions. The NCEAS approach leverages existing data and employs a team science philosophy to squeeze out all potential insights and solutions efficiently - this is called [synthesis science](https://www.nceas.ucsb.edu/our-approach). - -NCEAS has over 25 years of success with this model among working groups and environmental professionals. Together with the Delta Science Program and the Delta Stewardship Council we are excited to pass along skills, workflows, mindsets learn throughout the years. +This 5-day in-person workshop will provide researchers with an overview of reproducible and ethical research practices, steps and methods for more easily documenting and preserving their data at the Arctic Data Center, and an introduction to programming in R. Special attention will be paid to qualitative data management, including practices working with sensitive data. Example datasets will draw from natural and social sciences, and methods for conducting reproducible research will be discussed in the context of both qualitative and quantitative data. Responsible and reproducible data management practices will be discussed as they apply to all aspects of the data life cycle. This includes ethical data collection and data sharing, data sovereignty, and the [CARE](https://www.gida-global.org/care) principles. The CARE principles are guidelines that help ensure open data practices (like the FAIR principles) appropriately engage with Indigenous Peoples’ rights and interests. +## Week's Schedule +::: column-body-outset +![](images/schedule.png){.lightbox width=100%} +::: ## Code of Conduct @@ -42,15 +26,8 @@ These written materials are the result of a continuous and collaborative effort This work is licensed under a [Creative Commons Attribution 4.0 International License](http://creativecommons.org/licenses/by/4.0/). +**Citation:** Matthew B. Jones, Angie Garcia, Nicole Greco, Justin Kadi, Jim Regetz (2025), Fundamentals in Data Management for Qualitative and Quantitative Arctic Research. Arctic Data Center & NCEAS Learning Hub. URL . -**Citation:** Camila Vargas Poulsen, Casey Ohara, Shayna Sura (2024), NCEAS coreR for Delta Science Program, October 2024, NCEAS Learning Hub. URL . - -**Additional contributors:** Ben Bolker, Amber E. Budden, Julien Brun, Samantha Csik, Halina Do-Linh, Natasha Haycock-Chavez, S. Jeanette Clark, Julie Lowndes, Stephanie Hampton, Matt Jone, Samanta Katz, Erin McLean, Bryce Mecum, Deanna Pennington, Karthik Ram, Jim Regetz, Tracy Teal, Daphne Virlar-Knight, Leah Wasser. - - +**Additional contributors:** Ben Bolker, Amber E. Budden, Julien Brun, Samantha Csik, Halina Do-Linh, Natasha Haycock-Chavez, S. Jeanette Clark, Julie Lowndes, Stephanie Hampton, Samanta Katz, Erin McLean, Bryce Mecum, Casey O'Hara, Deanna Pennington, Karthik Ram, Jim Regetz, Tracy Teal, Camila Vargas-Poulsen, Daphne Virlar-Knight, Leah Wasser. This is a Quarto book. To learn more about Quarto books visit . - - - - diff --git a/materials/session_01.qmd b/materials/session_01.qmd index 9a8bfa4a..453958b8 100644 --- a/materials/session_01.qmd +++ b/materials/session_01.qmd @@ -1,10 +1,9 @@ --- -title: "Course Introduction" +title: "Introduction to the Arctic Data Center" title-block-banner: true format: html: code-overflow: wrap --- - -{{< include /sections/reproducibility-intro.qmd >}} +{{< include /sections/adc-intro-to-policies.qmd >}} diff --git a/materials/session_02.qmd b/materials/session_02.qmd index 938afa3a..4e87f5aa 100644 --- a/materials/session_02.qmd +++ b/materials/session_02.qmd @@ -5,11 +5,5 @@ title-block-banner: true --- - - - {{< include /sections/rstudio-server-setup.qmd >}} - - - diff --git a/materials/session_03.qmd b/materials/session_03.qmd index 0c0d129e..bebf3865 100644 --- a/materials/session_03.qmd +++ b/materials/session_03.qmd @@ -1,11 +1,9 @@ --- -title: "Git and GitHub Setup" +title: "Introduction to R Programming" title-block-banner: true -code-annotations: hover +execute: + eval: false --- - - - -{{< include /sections/git-setup.qmd >}} +{{< include /sections/intro-r-programming.qmd >}} diff --git a/materials/session_04.qmd b/materials/session_04.qmd index e371b82a..c7865326 100644 --- a/materials/session_04.qmd +++ b/materials/session_04.qmd @@ -1,17 +1,20 @@ --- -title: "Working in R & RStudio" +title: "Thinking Preferences & Social Aspects of Collaboration" title-block-banner: true -# execute: -# eval: false -# format: -# html: -# code-link: true -# code-fold: true -# code-summary: "Answer" -# code-overflow: wrap +execute: + eval: false +format: + html: + code-link: true + code-fold: true + code-summary: "Answer" + code-overflow: wrap --- -{{< include /sections/intro-r-programming.qmd >}} +{{< include /sections/collaboration-thinking-preferences.qmd >}} + + +{{< include /sections/collaboration-social-data-policies.qmd >}} diff --git a/materials/session_05.qmd b/materials/session_05.qmd index 6a3452f8..86b8bdb4 100644 --- a/materials/session_05.qmd +++ b/materials/session_05.qmd @@ -1,8 +1,6 @@ --- -title: "Literate Analysis with Quarto" +title: "Writing Data Management Plans" title-block-banner: true --- - - -{{< include /sections/r-intro-quarto.qmd >}} +{{< include /sections/data-management-plans-reduced.qmd >}} diff --git a/materials/session_06.qmd b/materials/session_06.qmd index ec3d710b..940f0d70 100644 --- a/materials/session_06.qmd +++ b/materials/session_06.qmd @@ -1,12 +1,6 @@ --- -title: "Reproducibility: a Lego activity" +title: "Literate Analysis with Quarto" title-block-banner: true -format: - html: - code-overflow: wrap - code-link: true --- - - - +{{< include /sections/r-intro-quarto.qmd >}} \ No newline at end of file diff --git a/materials/session_07.qmd b/materials/session_07.qmd index 73181427..df9834d7 100644 --- a/materials/session_07.qmd +++ b/materials/session_07.qmd @@ -1,8 +1,14 @@ --- -title: "Git and GitHub" +title: "R Practice: Literate Analysis " title-block-banner: true +execute: + eval: false +# format: +# html: +# code-link: true +# code-fold: true +# code-summary: "Example Code" +# code-overflow: wrap --- - -{{< include /sections/git-github-intro.qmd >}} - +{{< include /sections/exercise-intro-programming-socialsci.qmd >}} \ No newline at end of file diff --git a/materials/session_08.qmd b/materials/session_08.qmd index 612a0a24..90eddab7 100644 --- a/materials/session_08.qmd +++ b/materials/session_08.qmd @@ -1,15 +1,10 @@ --- -title: "Tidy Data" +title: "Data Modeling Essentials" title-block-banner: true +format: + html: + code-overflow: wrap + code-link: true --- - - - -{{< include /sections/intro-tidy-data.qmd >}} - - - - - - +{{< include /sections/data-modeling-socialsci.qmd >}} diff --git a/materials/session_09.qmd b/materials/session_09.qmd index 65c9e02b..a4f60fdb 100644 --- a/materials/session_09.qmd +++ b/materials/session_09.qmd @@ -1,11 +1,14 @@ --- title: "Cleaning and Wrangling Data" title-block-banner: true +execute: + eval: false +format: + html: + code-link: true + code-fold: true + code-summary: "Answer" + code-overflow: wrap --- - - {{< include /sections/clean-wrangle-data.qmd >}} - - - diff --git a/materials/session_10.qmd b/materials/session_10.qmd index f270ff80..eac85f15 100644 --- a/materials/session_10.qmd +++ b/materials/session_10.qmd @@ -1,14 +1,9 @@ --- -title: "Practice Session: Joins" +title: "Intro to Data Visualization" title-block-banner: true -execute: - eval: false format: html: - code-link: true - code-fold: true - code-summary: "Answer" code-overflow: wrap --- -{{< include /sections/r-practice-tidy-data-joins.qmd >}} +{{< include /sections/visualization-ggplot-leaflet.qmd >}} diff --git a/materials/session_11.qmd b/materials/session_11.qmd index 6d12d75d..9995fa5a 100644 --- a/materials/session_11.qmd +++ b/materials/session_11.qmd @@ -1,10 +1,6 @@ --- -title: "Collaborating with Git and GitHub" +title: "Ethical Data Collection" title-block-banner: true --- - -{{< include /sections/git-collab-merge-conflicts.qmd >}} - - - +{{< include /sections/data-ethics-eloka-2023.qmd >}} diff --git a/materials/session_12.qmd b/materials/session_12.qmd index 3499f545..8d9cfd2f 100644 --- a/materials/session_12.qmd +++ b/materials/session_12.qmd @@ -1,9 +1,8 @@ --- -title: "Publishing to the Web" +title: "R Practice: Cleaning and Wrangling" title-block-banner: true - +execute: + eval: false --- - - -{{< include /sections/git-github-publishing-analysis.qmd >}} +{{< include /sections/exercise-tidyverse-socialsci.qmd >}} diff --git a/materials/session_13.qmd b/materials/session_13.qmd index 8e57c7da..f37b4b95 100644 --- a/materials/session_13.qmd +++ b/materials/session_13.qmd @@ -1,10 +1,14 @@ --- -title: "Data Visualization" +title: "Working with Text Data in R" title-block-banner: true +# execute: +# eval: false +# format: +# html: +# code-link: true +# code-fold: true +# code-summary: "Answer" +# code-overflow: wrap --- - - - -{{< include /sections/visualization-delta.qmd >}} - +{{< include /sections/intro-tidy-text-data.qmd >}} diff --git a/materials/session_14.qmd b/materials/session_14.qmd index 02932911..95cae438 100644 --- a/materials/session_14.qmd +++ b/materials/session_14.qmd @@ -1,16 +1,6 @@ --- -title: "Practice Session: Collaborative Report" +title: "U.S Census Data in R" title-block-banner: true -execute: - eval: false -format: - html: - code-link: true - code-fold: true - code-summary: "Answer" - code-overflow: wrap --- - - -{{< include /sections/r-practice-clean-wrangle-visualize.qmd >}} +{{< include /sections/census-data.qmd >}} \ No newline at end of file diff --git a/materials/session_15.qmd b/materials/session_15.qmd index a5ee49dc..cf7a65ca 100644 --- a/materials/session_15.qmd +++ b/materials/session_15.qmd @@ -1,18 +1,6 @@ --- -title: "Data Management Essentials" +title: "Metadata Best Practices and Data Publishing" title-block-banner: true -execute: - eval: false --- - - - -{{< include /sections/data-management-essentials.qmd >}} - - - - - - - +{{< include /sections/metadata-adc-data-documentation-socialsci.qmd >}} diff --git a/materials/session_16.qmd b/materials/session_16.qmd index 14f0e758..6b88b229 100644 --- a/materials/session_16.qmd +++ b/materials/session_16.qmd @@ -1,11 +1,10 @@ --- -title: "Working with Spatial Data" +title: "Creating Data Portals" title-block-banner: true format: - html: + html: code-link: true code-overflow: wrap --- -{{< include /sections/geospatial-vector-analysis.qmd >}} - +{{< include /sections/adc-creating-data-portals.qmd >}} diff --git a/materials/session_17.qmd b/materials/session_17.qmd index 60bcf3da..2854ebbb 100644 --- a/materials/session_17.qmd +++ b/materials/session_17.qmd @@ -1,11 +1,14 @@ --- -title: "Writing Functions" +title: "Reproducible Survey Workflow" title-block-banner: true +execute: + eval: false +format: + html: + code-link: true + code-fold: true + code-summary: "Answer" + code-overflow: wrap --- - - - -{{< include /sections/r-creating-functions.qmd >}} - - \ No newline at end of file +{{< include /sections/survey-workflow.qmd >}} diff --git a/materials/session_18.qmd b/materials/session_18.qmd index 632b4d2a..109dc817 100644 --- a/materials/session_18.qmd +++ b/materials/session_18.qmd @@ -1,8 +1,6 @@ --- -title: "Practice Session: Functions" +title: "Provenance and Reproducibility" title-block-banner: true --- - - -{{< include /sections/r-practice-functions-and-packages.qmd >}} \ No newline at end of file +{{< include /sections/provenance-reproducibility-datapaper.qmd >}}