In r4ds/bookclub-dsieur: Data Science in Education Using R Book Club

Walkthrough 2: Approaching Gradebook Data From a Data Science Perspective

Learning objectives:

Learn about importing excel spreadsheets using a file path or here(), tidying data with clean_names() and remove_empty() from the {janitor} package, transforming data with pivot_longer() using contains() from the {stringr} package, visualizing data, correlation analysis with cor(), and modeling data with lm().

Slides

r knitr::include_url("./R/2021-03-17/chapter_8_presentation.html")

Walkthrough 2 Rmd Script

r knitr::include_url("./R/2021-03-17/chapter_8_notes.html")

Meeting Videos

Cohort 1

r knitr::include_url("https://www.youtube.com/embed/CNRWp-ao_Pc")

Meeting chat log

00:24:07    Rob Lucas:  Do you all use {janitor}? The book mentioned that it was developed by an education person, and I wondered if it was used more in education contexts.
00:24:23    Ronak Patel:    clean_names() has changed my life
00:24:26    Alyssa Ibarra:  I have never used it before this.
00:24:39    edgarzamora:    ^^^ Ronak +1
00:24:45    Isabella Velásquez: +1 to clean_names()!
00:25:55    Isabella Velásquez: {janitor} is by Sam Firke from The New Teacher Project, but I think can be used in any data cleaning context : https://github.com/sfirke/janitor
00:26:34    Mike Haugen:    And then when you create objects, do you make them snake_case?
00:26:38    Mike Haugen:    https://r4ds.had.co.nz/workflow-basics.html?q=snake_case#whats-in-a-name
00:27:32    Isabella Velásquez: usually I do. I only use camelCase in Shiny
00:27:50    edgarzamora:    By default it is snake_case
00:29:56    edgarzamora:    select(-c(absent, late))
00:30:30    Ryan Woodbury:  I do it that way too
00:30:54    Ronak Patel:    same, especially when exploring data. never know what you want to drop and it saves some time.
00:31:18    Isabella Velásquez: are these xaringan slides? so cool
00:37:38    Rob Lucas:  Why color code those if the boxplots aren't even ordered correctly?
00:38:06    Ronak Patel:    does anyone have a quick way to order them?
00:38:34    edgarzamora:    fct_reorder() maybe?
00:38:58    Ryan Woodbury:  Check out, reorder_within() from tidytext
00:40:03    Ryan Woodbury:  https://juliasilge.com/blog/reorder-within/
00:50:54    Isabella Velásquez: Awesome job!!!
00:53:38    Ronak Patel:    in a regression, isn't independence of variables an assumption?
00:54:03    Ryan Woodbury:  The errors are independent
00:54:06    Ryan Woodbury:  Should be
00:55:10    Ryan Woodbury:  That is a good question. I want to help find an answer!
00:55:46    Mike Haugen:    Thanks!