Last updated: 2020-07-17

Checks: 7 0

Knit directory: project/

This reproducible R Markdown analysis was created with workflowr (version 1.6.2). 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.

Environment: empty

Great job! The global environment was empty. Objects defined in the global environment can affect the analysis in your R Markdown file in unknown ways. For reproduciblity it’s best to always run the code in an empty environment.

Seed: set.seed(20200723)

The command set.seed(20200723) was run prior to running the code in the R Markdown file. Setting a seed ensures that any results that rely on randomness, e.g. subsampling or permutations, are reproducible.

Session information: recorded

Great job! Recording the operating system, R version, and package versions is critical for reproducibility.

Cache: none

Nice! There were no cached chunks for this analysis, so you can be confident that you successfully produced the results during this run.

File paths: relative

Great job! Using relative paths to the files within your workflowr project makes it easier to run your code on other machines.

Repository version: 2eb4639

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 2eb4639. 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/spotify.Rmd) and HTML (docs/spotify.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 2eb4639 John Blischak 2020-07-17 Update Spotify analysis so that it matches how it will appear on the day of the tutorial.
html 80f7ef5 John Blischak 2020-07-02 Build site.
Rmd 6c85c34 John Blischak 2020-07-02 Add spotify analysis

This analysis attempts to classify songs into their correct musical genre using audio features. It is inspired by the original analysis by Kaylin Pavlik (@kaylinquest) in her 2019 blog post Understanding + classifying genres using Spotify audio features.

spotify <- read.csv("data/spotify.csv", stringsAsFactors = FALSE)
dim(spotify)
[1] 32833    15
head(spotify)
  genre danceability energy key loudness mode speechiness acousticness
1   pop        0.748  0.916   6   -2.634    1      0.0583       0.1020
2   pop        0.726  0.815  11   -4.969    1      0.0373       0.0724
3   pop        0.675  0.931   1   -3.432    0      0.0742       0.0794
4   pop        0.718  0.930   7   -3.778    1      0.1020       0.0287
5   pop        0.650  0.833   1   -4.672    1      0.0359       0.0803
6   pop        0.675  0.919   8   -5.385    1      0.1270       0.0799
  instrumentalness liveness valence   tempo duration_ms           artist
1         0.00e+00   0.0653   0.518 122.036      194754       Ed Sheeran
2         4.21e-03   0.3570   0.693  99.972      162600         Maroon 5
3         2.33e-05   0.1100   0.613 124.008      176616     Zara Larsson
4         9.43e-06   0.2040   0.277 121.956      169093 The Chainsmokers
5         0.00e+00   0.0833   0.725 123.976      189052    Lewis Capaldi
6         0.00e+00   0.1430   0.585 124.982      163049       Ed Sheeran
                               song
1 I Don't Care (with Justin Bieber)
2                          Memories
3                      All the Time
4                     Call You Mine
5                 Someone You Loved
6   Beautiful People (feat. Khalid)
table(spotify[, 1])

  edm latin   pop   r&b   rap  rock 
 6043  5155  5507  5431  5746  4951 
spotify <- spotify[, 1:13]

Split the data into training and testing sets. The training set should have 3/4 of the samples.

numTrainingSamples <- nrow(spotify) * 3/4
trainingSet <- sample(seq_len(nrow(spotify)), size = numTrainingSamples)
spotifyTraining <- spotify[trainingSet, ]
spotifyTesting <- spotify[-trainingSet, ]

Build classification model with decision tree from the rpart package.

library(rpart)
model <- rpart(genre ~ ., data = spotifyTraining)
plot(model)
text(model)

Version Author Date
80f7ef5 John Blischak 2020-07-02

Calculate prediction accuracy of the model on the training and testing sets.

predictTraining <- predict(model, type = "class")
(accuracyTraining <- mean(spotifyTraining[, 1] == predictTraining))
[1] 0.4036712
predictTesting <- predict(model, newdata = spotifyTesting[, -1], type = "class")
(accuracyTesting <- mean(spotifyTesting[, 1] == predictTesting))
[1] 0.4000487

Evaluate prediction performance using a confusion matrix.

table(predicted = predictTesting, observed = spotifyTesting[, 1])
         observed
predicted  edm latin  pop  r&b  rap rock
    edm    615   129  220   62   33   67
    latin   70   292  135  111   74   19
    pop     77   120  224   86   36   94
    r&b     71   171  165  359  140  157
    rap    397   439  341  535 1047  178
    rock   254    92  306  230  116  747

How does the model compare to random guessing?

predictRandom <- sample(unique(spotifyTesting[, 1]),
                        size = nrow(spotifyTesting),
                        replace = TRUE,
                        prob = table(spotifyTesting[, 1]))
(accuracyRandom <- mean(spotifyTesting[, 1] == predictRandom))
[1] 0.1612864

sessionInfo()
R version 4.0.0 (2020-04-24)
Platform: x86_64-pc-linux-gnu (64-bit)
Running under: Ubuntu 16.04.6 LTS

Matrix products: default
BLAS:   /usr/lib/atlas-base/atlas/libblas.so.3.0
LAPACK: /usr/lib/atlas-base/atlas/liblapack.so.3.0

locale:
 [1] LC_CTYPE=C.UTF-8       LC_NUMERIC=C           LC_TIME=C.UTF-8       
 [4] LC_COLLATE=C.UTF-8     LC_MONETARY=C.UTF-8    LC_MESSAGES=C.UTF-8   
 [7] LC_PAPER=C.UTF-8       LC_NAME=C              LC_ADDRESS=C          
[10] LC_TELEPHONE=C         LC_MEASUREMENT=C.UTF-8 LC_IDENTIFICATION=C   

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
[1] rpart_4.1-15    workflowr_1.6.2

loaded via a namespace (and not attached):
 [1] Rcpp_1.0.4.6    rprojroot_1.3-2 digest_0.6.25   later_1.1.0.1  
 [5] R6_2.4.1        backports_1.1.8 git2r_0.27.1    magrittr_1.5   
 [9] evaluate_0.14   stringi_1.4.6   rlang_0.4.6     fs_1.4.2       
[13] promises_1.1.1  whisker_0.4     rmarkdown_2.3   tools_4.0.0    
[17] stringr_1.4.0   glue_1.4.1      httpuv_1.5.4    xfun_0.15      
[21] yaml_2.2.1      compiler_4.0.0  htmltools_0.5.0 knitr_1.29