Wrangling and Visualizing Musical Data - Guided Project
@ Shrishti Vaish · Thursday, Sep 24, 2020 · 14 minute read · Update at Sep 24, 2020

Hey everyone, This is a guided project on gathering, cleaning and transforming musical data and visualizing it. I somehow got the opportunity to get the access to this project on Data Camp. Right now, it is for premium users as in you cannot access it via free account. But, Data Camp does time to time gives free access to such projects, well yeah occasionally. You shoud definitely look out for such opportunities on these platforms if you are really serious about enhancing your core skills. But you need not worry, because for this project, I am here to give you complete access to it.

Let us get started!

1. Introduction

How do musicians choose the chords they use in their songs? Do guitarists, pianists, and singers gravitate towards different kinds of harmony?

We can uncover trends in the kinds of chord progressions used by popular artists by analyzing the harmonic data provided in the McGill Billboard Dataset. This dataset includes professionally tagged chords for several hundred pop/rock songs representative of singles that made the Billboard Hot 100 list between 1958 and 1991. Using the data-wrangling tools available in the dplyr package, and the visualization tools available in the ggplot2 package, we can explore the most common chords and chord progressions in these songs, and contrast the harmonies of some guitar-led and piano-led artists to see where the "affordances" of those instruments may affect the chord choices artists make.

# Loading individual Tidyverse packages
# .... YOUR CODE FOR TASK 1 ....
library(dplyr)
library(readr)
library(ggplot2)

# Reading in the McGill Billboard chord data
bb <- read.csv('datasets/bb_chords.csv')

# Taking a look at the first rows in bb
# .... YOUR CODE FOR TASK 1 ....
head(bb)

A data.frame: 6 x 9
yearchordroot_integerroot_romanqualitytitle_compressedartist_compressedtitleartist
<int><fct><fct><fct><fct><fct><fct><fct><fct>
1961A:min9VIminidon’tmindjamesbrownI Don’t MindJames Brown
1961C:maj0I majidon’tmindjamesbrownI Don’t MindJames Brown
1961A:min9VIminidon’tmindjamesbrownI Don’t MindJames Brown
1961C:maj0I majidon’tmindjamesbrownI Don’t MindJames Brown
1961A:min9VIminidon’tmindjamesbrownI Don’t MindJames Brown
1961C:maj0I majidon’tmindjamesbrownI Don’t MindJames Brown

2. The most common chords

As seen in the previous task, this is a tidy dataset: each row represents a single observation, and each column a particular variable or attribute of that observation. Note that the metadata for each song (title, artist, year) is repeated for each chord -- like "I Don't Mind" by James Brown, 1961 -- while the unique attributes of each chord (chord symbol, chord quality, and analytical designations like integer and Roman-numeral notation) is included once for each chord change.

A key element of the style of any popular musical artist is the kind of chords they use in their songs. But not all chords are created equal! In addition to differences in how they sound, some chords are simply easier to play than others. On top of that, some chords are easier to play on one instrument than they are on another. And while master musicians can play a wide variety of chords and progressions with ease, it's not a stretch to think that even the best musicians may choose more "idiomatic" chords and progressions for their instrument.

To start to explore that, let's look at the most common chords in the McGill Billboard Dataset.

# Counting the most common chords
bb_count <- bb %>% count(chord, sort = T)

# Displaying the top 20 chords
# .... YOUR CODE FOR TASK 2 ....
bb_count[1:20,]
A tibble: 20 x 2
chordn
<fct><int>
C:maj 1183
G:maj 1140
A:maj 1071
D:maj 1054
F:maj 859
E:maj 839
Bb:maj 718
B:maj 503
Ab:maj 375
Eb:maj 360
A:min 328
E:min 298
Db:maj 293
D:min 250
B:min 236
N 201
E:min7 186
C:min 176
D:7 176
A:min7 170

3. Visualizing the most common chords

Of course, it's easier to get a feel for just how common some of these chords are if we graph them and show the percentage of the total chord count represented by each chord. Musicians may notice right away that the most common chords in this corpus are chords that are easy to play on both the guitar and the piano: C, G, A, and D major — and to an extent, F and E major. (They also belong to keys, or scales, that are easy to play on most instruments, so they fit well with melodies and solos, as well.) After that, there is a steep drop off in the frequency with which individual chords appear.

To illustrate this, here is a short video demonstrating the relative ease (and difficulty) of some of the most common (and not-so-common) chords in the McGill Billboard dataset.

```R # Creating a bar plot from bb_count bb_count %>% slice(1:20) %>% mutate(share = (n/sum(n))*100, chord = reorder(chord,share)) %>% ggplot(aes(x=chord, y=share, fill=chord)) + geom_col()+ coord_flip() + xlab("Common Chords") + ylab("Frequent Occurence") ``` ![png](/img/output_7_0.png) ## 4. Chord "bigrams"

Just as some chords are more common and more idiomatic than others, not all chord progressions are created equal. To look for common patterns in the structuring of chord progressions, we can use many of the same modes of analysis used in text-mining to analyze phrases. A chord change is simply a bigram — a two-"word" phrase — composed of a starting chord and a following chord. Here are the most common two-chord "phrases" in the McGill Billboard dataset. To help you get your ear around some of these common progressions, here's a short audio clip containing some of the most common chord bigrams.

# Wrangling and counting bigrams
bb_bigram_count <- bb %>% mutate(next_chord = lead(chord), next_title = lead(title), bigram = paste(chord,next_chord)) %>% filter(title == next_title) %>% count(bigram,sort=T)
    # .... YOUR CODE FOR TASK 4 ....

# Displaying the first 20 rows of bb_bigram_count
# .... YOUR CODE FOR TASK 4 ....
bb_bigram_count[1:20, ]
A tibble: 20 x 2
bigramn
<chr><int>
G:maj D:maj 241
C:maj F:maj 234
C:maj G:maj 217
B:maj E:maj 202
F:maj C:maj 195
A:maj E:maj 190
A:maj D:maj 189
D:maj G:maj 185
G:maj C:maj 185
D:maj A:maj 179
E:maj A:maj 175
F:maj Bb:maj143
Bb:maj F:maj134
E:maj B:maj 134
Bb:maj C:maj133
G:maj A:maj 133
A:maj B:maj 112
A:maj G:maj 105
F:maj G:maj 99
D:maj C:maj 93

5. Visualizing the most common chord progressions

We can get a better sense of just how popular some of these chord progressions are if we plot them on a bar graph. Note how the most common chord change, G major to D major, occurs more than twice as often than even some of the other top 20 chord bigrams.

# Creating a column plot from bb_bigram_count
bb_bigram_count %>%
  slice(1:20) %>%
  mutate(share = (n/sum(n)) *100,
         chord =  reorder(bigram,share)) %>%
   ggplot(aes(x=chord, y=share, fill=chord)) +
  geom_col()+
  coord_flip() +
  xlab("Common Next_Chords") +
  ylab("Frequent Occurence")

png

6. Finding the most common artists

As noted above, the most common chords (and chord bigrams) are those that are easy to play on both the guitar and the piano. If the degree to which these chords are idiomatic on guitar or piano (or both) determine how common they are, we would expect to find the more idiomatic guitar chords (C, G, D, A, and E major) to be more common in guitar-driven songs, but we would expect the more idiomatic piano chords (C, F, G, D, and B-flat major) to be more common in piano-driven songs. (Note that there is some overlap between these two instruments.)

The McGill Billboard dataset does not come with songs tagged as "piano-driven" or "guitar-driven," so to test this hypothesis, we'll have to do that manually. Rather than make this determination for every song in the corpus, let's focus on just a few to see if the hypothesis has some validity. If so, then we can think about tagging more artists in the corpus and testing the hypothesis more exhaustively.

Here are the 30 artists with the most songs in the corpus. From this list, we'll extract a few artists who are obviously heavy on guitar or piano to compare.

# Finding 30 artists with the most songs in the corpus
bb_30_artists <- bb %>% select(artist, title) %>% unique() %>% count(artist, sort = T)
    #.... YOUR CODE FOR TASK 6 ....

# Displaying 30 artists with the most songs in the corpus
#.... YOUR CODE FOR TASK 6 ....
bb_30_artists %>% slice(1:30)
A tibble: 30 x 2
artistn
<fct><int>
Elvis Presley 13
Brenda Lee 9
Dion 8
Bob Seger 7
James Brown 7
Kenny Rogers 7
The Beatles 7
Chicago 6
Dr. Hook 6
Eric Clapton 6
John Denver 6
Johnny Tillotson 6
The Beach Boys 6
Abba 5
Billy Idol 5
Cliff Richard 5
Glen Campbell 5
The Rolling Stones 5
Billy Joel 4
Cheap Trick 4
Cyndi Lauper 4
David Bowie 4
Elton John 4
Genesis 4
Heart 4
Jackson Browne 4
Little River Band 4
Michael Jackson 4
Pat Benatar 4
Stevie Wonder 4

7. Tagging the corpus

There are relatively few artists in this list whose music is demonstrably "piano-driven," but we can identify a few that generally emphasize keyboards over guitar: Abba, Billy Joel, Elton John, and Stevie Wonder — totaling 17 songs in the corpus. There are many guitar-centered artists in this list, so for our test, we'll focus on three well known, guitar-heavy artists with a similar number of songs in the corpus: The Rolling Stones, The Beatles, and Eric Clapton (18 songs).

Once we've subset the corpus to only songs by these seven artists and applied the "piano" and "guitar" tags, we can compare the chord content of piano-driven and guitar-driven songs.

tags <- tibble(
  artist = c('Abba', 'Billy Joel', 'Elton John', 'Stevie Wonder', 'The Rolling Stones', 'The Beatles', 'Eric Clapton'),
  instrument = c('piano', 'piano', 'piano', 'piano', 'guitar', 'guitar', 'guitar'))

# Creating a new dataframe bb_tagged that includes a new column instrument from tags
bb_tagged <- bb %>% inner_join(tags)
    # .... YOUR CODE FOR TASK 7 ....
    
# Displaying the new data frame
# .... YOUR CODE FOR TASK 7 ....
bb_tagged
A data.frame: 1101 x 10
yearchordroot_integerroot_romanqualitytitle_compressedartist_compressedtitleartistinstrument
<int><fct><fct><fct><fct><fct><fct><fct><chr><chr>
1984C:maj 0 I maj aninnocentmanbillyjoel An Innocent ManBilly Joel piano
1984D:min 2 II min aninnocentmanbillyjoel An Innocent ManBilly Joel piano
1984F:maj 5 IV maj aninnocentmanbillyjoel An Innocent ManBilly Joel piano
1984G:maj 7 V maj aninnocentmanbillyjoel An Innocent ManBilly Joel piano
1984C:maj 0 I maj aninnocentmanbillyjoel An Innocent ManBilly Joel piano
1984D:min 2 II min aninnocentmanbillyjoel An Innocent ManBilly Joel piano
1984F:maj 5 IV maj aninnocentmanbillyjoel An Innocent ManBilly Joel piano
1984G:maj 7 V maj aninnocentmanbillyjoel An Innocent ManBilly Joel piano
1984C:maj 0 I maj aninnocentmanbillyjoel An Innocent ManBilly Joel piano
1984G:min7 7 V min7 aninnocentmanbillyjoel An Innocent ManBilly Joel piano
1984C:maj/5 0 I maj/5aninnocentmanbillyjoel An Innocent ManBilly Joel piano
1984Bb:maj/510bVIImaj/5aninnocentmanbillyjoel An Innocent ManBilly Joel piano
1984F:maj 5 IV maj aninnocentmanbillyjoel An Innocent ManBilly Joel piano
1984G:maj 7 V maj aninnocentmanbillyjoel An Innocent ManBilly Joel piano
1984C:maj 0 I maj aninnocentmanbillyjoel An Innocent ManBilly Joel piano
1984D:min 2 II min aninnocentmanbillyjoel An Innocent ManBilly Joel piano
1984F:maj 5 IV maj aninnocentmanbillyjoel An Innocent ManBilly Joel piano
1984G:maj 7 V maj aninnocentmanbillyjoel An Innocent ManBilly Joel piano
1984C:maj 0 I maj aninnocentmanbillyjoel An Innocent ManBilly Joel piano
1984D:min 2 II min aninnocentmanbillyjoel An Innocent ManBilly Joel piano
1984F:maj 5 IV maj aninnocentmanbillyjoel An Innocent ManBilly Joel piano
1984G:maj 7 V maj aninnocentmanbillyjoel An Innocent ManBilly Joel piano
1972A:maj 7 V maj letitrain ericclaptonLet It Rain Eric Claptonguitar
1972G:maj/9 5 IV maj/9letitrain ericclaptonLet It Rain Eric Claptonguitar
1972A:maj 7 V maj letitrain ericclaptonLet It Rain Eric Claptonguitar
1972G:maj/9 5 IV maj/9letitrain ericclaptonLet It Rain Eric Claptonguitar
1972A:maj 7 V maj letitrain ericclaptonLet It Rain Eric Claptonguitar
1972D:maj 0 I maj letitrain ericclaptonLet It Rain Eric Claptonguitar
1972A:min 7 V min letitrain ericclaptonLet It Rain Eric Claptonguitar
1972C:maj 10bVIImaj letitrain ericclaptonLet It Rain Eric Claptonguitar
..............................
1965F#:min 9 VI min help! thebeatles Help! The Beatles guitar
1965D:maj 5 IV maj help! thebeatles Help! The Beatles guitar
1965G:maj 10 bVII maj help! thebeatles Help! The Beatles guitar
1965A:maj 0 I maj help! thebeatles Help! The Beatles guitar
1965C#:min 4 III min help! thebeatles Help! The Beatles guitar
1965F#:maj 9 VI maj help! thebeatles Help! The Beatles guitar
1965D:maj 5 IV maj help! thebeatles Help! The Beatles guitar
1965G:maj 10 bVII maj help! thebeatles Help! The Beatles guitar
1965A:maj 0 I maj help! thebeatles Help! The Beatles guitar
1965B:min 2 II min help! thebeatles Help! The Beatles guitar
1965B:min/b72 II min/b7 help! thebeatles Help! The Beatles guitar
1969N NonHarmonicNonHarmonicNonHarmonichonkytonkwomentherollingstonesHonky Tonk WomenThe Rolling Stonesguitar
1969G:maj 0 I maj honkytonkwomentherollingstonesHonky Tonk WomenThe Rolling Stonesguitar
1969C:maj 5 IV maj honkytonkwomentherollingstonesHonky Tonk WomenThe Rolling Stonesguitar
1969C:sus4 5 IV sus4 honkytonkwomentherollingstonesHonky Tonk WomenThe Rolling Stonesguitar
1969C:maj 5 IV maj honkytonkwomentherollingstonesHonky Tonk WomenThe Rolling Stonesguitar
1969G:maj 0 I maj honkytonkwomentherollingstonesHonky Tonk WomenThe Rolling Stonesguitar
1969A:maj 2 II maj honkytonkwomentherollingstonesHonky Tonk WomenThe Rolling Stonesguitar
1969D:maj 7 V maj honkytonkwomentherollingstonesHonky Tonk WomenThe Rolling Stonesguitar
1969D:sus4 7 V sus4 honkytonkwomentherollingstonesHonky Tonk WomenThe Rolling Stonesguitar
1969D:maj 7 V maj honkytonkwomentherollingstonesHonky Tonk WomenThe Rolling Stonesguitar
1969G:maj 0 I maj honkytonkwomentherollingstonesHonky Tonk WomenThe Rolling Stonesguitar
1969C:maj 5 IV maj honkytonkwomentherollingstonesHonky Tonk WomenThe Rolling Stonesguitar
1969C:sus4 5 IV sus4 honkytonkwomentherollingstonesHonky Tonk WomenThe Rolling Stonesguitar
1969C:maj 5 IV maj honkytonkwomentherollingstonesHonky Tonk WomenThe Rolling Stonesguitar
1969G:maj 0 I maj honkytonkwomentherollingstonesHonky Tonk WomenThe Rolling Stonesguitar
1969D:maj 7 V maj honkytonkwomentherollingstonesHonky Tonk WomenThe Rolling Stonesguitar
1969G:maj 0 I maj honkytonkwomentherollingstonesHonky Tonk WomenThe Rolling Stonesguitar
1969D:maj 7 V maj honkytonkwomentherollingstonesHonky Tonk WomenThe Rolling Stonesguitar
1969G:maj 0 I maj honkytonkwomentherollingstonesHonky Tonk WomenThe Rolling Stonesguitar

8. Comparing chords in piano-driven and guitar-driven songs

Let's take a look at any difference in how common chords are in these two song groups. To clean things up, we'll just focus on the 20 chords most common in the McGill Billboard dataset overall.

While we want to be careful about drawing any conclusions from such a small set of songs, we can see that the chords easiest to play on the guitar do dominate the guitar-driven songs, especially G, D, E, and C major, as well as A major and minor. Similarly, "flat" chords (B-flat, E-flat, A-flat major) occur frequently in piano-driven songs, though they are nearly absent from the guitar-driven songs. In fact, the first and fourth most frequent piano chords are "flat" chords that occur rarely, if at all, in the guitar songs.

So with all the appropriate caveats, it seems like the instrument-based-harmony hypothesis does have some merit and is worth further examination.

# The top 20 most common chords
top_20 <- bb_count$chord[1:20]

# Comparing the frequency of the 20 most common chords in piano- and guitar-driven songs
bb_tagged %>%
  filter(chord %in% top_20) %>%
  count(chord, instrument, sort = T) %>%
  ggplot(aes(chord,n, fill = chord)) +
  geom_bar(stat = "identity") +
  facet_grid(~instrument) +
  coord_flip() +
  xlab("Common Chords") +
  ylab("No. of Occurence") 

png

9. Comparing chord bigrams in piano-driven and guitar-driven songs

Since chord occurrence and chord bigram occurrence are naturally strongly tied to each other, it would not be a reach to expect that a difference in chord frequency would be reflected in a difference in chord bigram frequency. Indeed that is what we find.

# The top 20 most common bigrams
top_20_bigram <- bb_bigram_count$bigram[1:20]

# Creating a faceted plot comparing guitar- and piano-driven songs for bigram frequency
bb_tagged %>%
  mutate(next_chord = lead(chord),
         next_title = lead(title),
         bigram = paste(chord, next_chord)) %>%
  filter(title == next_title) %>%
  count(bigram, instrument, sort = TRUE) %>%
  filter(bigram %in% top_20_bigram) %>%
  ggplot(aes(bigram, n, fill = bigram)) +
  geom_col() +
  facet_grid(~instrument) +
  coord_flip() +
  ylab('Total bigrams') +
  xlab('Bigram') +
  theme(legend.position="none")

  # .... MODIFIED CODE FROM TASK 4 .... 
  # .... MODIFIED CODE FROM TASK 8 ....

png

10. Conclusion

We set out asking if the degree to which a chord is "idiomatic" on an instrument affects how frequently it is used by a songwriter. It seems that is indeed the case. In a large representative sample of pop/rock songs from the historical Billboard charts, the chords most often learned first by guitarists and pianists are the most common. In fact, chords commonly deemed easy or beginner-friendly on both piano and guitar are far and away the most common in the corpus.

We also examined a subset of 35 songs from seven piano- and guitar-heavy artists and found that guitarists and pianists tend to use different sets of chords for their songs. This was an extremely small (and likely not representative) sample, so we can do nothing more than hypothesize that this trend might carry over throughout the larger dataset. But it seems from this exploration that it's worth a closer look.

There are still more questions to explore with this dataset. What about band-driven genres like classic R&B and funk, where artists like James Brown and Chicago build chords from a large number of instruments each playing a single note? What about "progressive" bands like Yes and Genesis, where "easy" and "idiomatic" may be less of a concern during the songwriting process? And what if we compared this dataset to a collection of chords from classical songs, jazz charts, folk songs, liturgical songs?

There's only one way to find out!

# Set to TRUE or FALSE to reflect your answer
hypothesis_valid <- TRUE

# Set to TRUE or FALSE to reflect your answer
more_data_needed <- TRUE

Outro

This project involves all the basic techniques but are really crucial for data collection and cleaning. All the visualizations were made here.

Till then, any feedbacks, queries or recommendations are appreciated on any of my social media handles.

Refer to my Github Profile for solutions!

Stay tuned for more tutorials!
Thank You!

About Me

Hey Folks! I’m Shrishti Vaish and I’m delighted that you visited my page. Currently pursuing Bachelors in Computer Science with Honours from the University of Delhi, India. During my final year at college, I had developed keen interest in Data Science knowing its worth and demand in the coming future.

No better tool that I can find other than R is for statistical analysis. I use R extensively for any of my data science projects.

Well, I am new to blogging and will be posting about a lot of it.

Thank You!

Case Study

Hey everyone, I am working on a project, a case study on the Work Status and Condition of Women during the Pandemic. This is a project in R for analysis and visualization. Kindly fill the form.

The details are provided in the form itself. Kindly support and share the link with your connections as well.

Thank you!