Last updated: 2020-06-12

Checks: 2 0

Knit directory: workflowr-useR2020/

This reproducible R Markdown analysis was created with workflowr (version 1.6.2.9000). The Checks tab describes the reproducibility checks that were applied when the results were created. The Past versions tab lists the development history.

R Markdown file: up-to-date

Great! Since the R Markdown file has been committed to the Git repository, you know the exact version of the code that produced these results.

Repository version: 28e7671

Great! You are using Git for version control. Tracking code development and connecting the code version to the results is critical for reproducibility.

The results in this page were generated with repository version 28e7671. See the Past versions tab to see a history of the changes made to the R Markdown and HTML files.

Note that you need to be careful to ensure that all relevant files for the analysis have been committed to Git prior to generating the results (you can use wflow_publish or wflow_git_commit). workflowr only checks the R Markdown file, but you know if there are other scripts or data files that it depends on. Below is the status of the Git repository when the results were generated: 


Ignored files:
    Ignored:    .Rhistory
    Ignored:    .Rproj.user/

Note that any generated files, e.g. HTML, png, CSS, etc., are not included in this status report because it is ok for generated content to have uncommitted changes.

These are the previous versions of the repository in which changes were made to the R Markdown (analysis/challenge.Rmd) and HTML (docs/challenge.html) files. If you’ve configured a remote Git repository (see ?wflow_git_remote), click on the hyperlinks in the table below to view the files as they were in that past version.

File Version Author Date Message
Rmd ecbe1e6 John Blischak 2020-06-11 Add the challenge instructions

Introduction

For the reproducibility challenge, you will attempt to re-run an analysis of Spotify song genres that was inspired by the blog post Understanding + classifying genres using Spotify audio features by Kaylin Pavlik (@kaylinquest).

The code includes a minimal machine learning style analysis with the following steps:

  • Import the songs data
  • Split the songs data into training and test sets
  • Build a tree model to classify songs into genres based on the song characteristics
  • Assess accuracy of the model on the training and test sets
  • Compute the accuracy of a model based on random guessing

Getting started

The analysis purposefully contains various issues that make it difficult to reproduce. Open the file spotify.Rmd by clicking on it in the RStudio Files pane. Click the Knit button to re-run the analysis and find the first issue.

File paths

The first error you will encounter is below:

Quitting from lines 16-21 (spotify.Rmd) 
Error in file(file, "rt") : cannot open the connection
Calls: <Anonymous> ... withVisible -> eval -> eval -> read.csv -> read.table -> file
Execution halted

The function read.csv() is unable to open the data file. What’s wrong with the path to the file? Apply what you know about absolute and relative paths to update the path and re-run the analysis.

Undefined variable

The next error you encounter is:

Quitting from lines 27-30 (spotify.Rmd) 
Error in sample.int(length(x), size, replace, prob) : 
  object 'numTrainingSamples' not found
Calls: <Anonymous> ... withVisible -> eval -> eval -> sample -> sample.int
Execution halted

It looks like the variable numTrainingSamples isn’t defined in the Rmd file. This error often occurs when a variable is interactively created in the R console, but you forget to define it in the script.

Based on the description above the code chunk, can you define the variable numTrainingSamples? Hint: You can obtain the number of samples with nrow(spotify).

Missing package

The next error you encounter is:

Quitting from lines 36-39 (spotify.Rmd) 
Error in rpart(genre ~ ., data = spotifyTraining) : 
  could not find function "rpart"
Calls: <Anonymous> ... handle -> withCallingHandlers -> withVisible -> eval -> eval
Execution halted

The function rpart() can’t be found. This can occur when you load a package in the current R session, but forget to put the call to library() in the script.

Based on the text above the code chunk, can you figure out which package needs to be loaded?

Renamed variable

The next error you encounter is:

Quitting from lines 61-66 (spotify.Rmd) 
Error in mean(spotifyTesting[, 1] == predict_random) : 
  object 'predict_random' not found
Calls: <Anonymous> ... withCallingHandlers -> withVisible -> eval -> eval -> mean

Execution halted

R can’t find the variable named predict_random. Look at the surrounding code: what do you think the name of this variable should be?

Renaming variables during an analysis can lead to these subtle errors. Since both the original and updated versions of the variable are defined in the current R session, the code will continue to run. But when you or someone else tries to run the code in a clean R session, the code will unexpectedly fail.

Compare results

Success! The analysis now runs. Compare your prediction results to that of your partners’ and/or re-run the analysis again. Are the results always identical? Why not? What could you do if you wanted to publish these results and allow others to exactly reproduce your findings?