This project stimulates the shuffle effect on a playlist, such as those used by Spotify or Apple Music. The playlist was made using the favorite songs of students from Ms. Hood’s Period 7 Data Science class, and their respective genres. This data was comprised into a spreadsheet, which will serve as our “playlist.” We will use this data to explore calculating theoretical probability.
The guiding question of this project is: What is the likelihood of a song of each genre being played?
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.5.0 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.1
## ✔ purrr 1.0.2
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
df <- read_csv("Playlist - Clean.csv")
## Rows: 175 Columns: 3
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (3): Genre, Artist, Song
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
head(df)
## # A tibble: 6 × 3
## Genre Artist Song
## <chr> <chr> <chr>
## 1 Genre 1 - hiphop/rap 8k When you call
## 2 Genre 2 - pop/kpop/Latin Yonaguni bad bunny
## 3 Genre 1 - hiphop/rap $uicideboy$ Diemonds
## 4 Genre 1 - hiphop/rap $uicideboy$ Not Even Ghosts Are This Empty
## 5 Genre 1 - hiphop/rap 03 Greedo Trap House
## 6 Genre 5 - alt/indie/folk 10,000 Maniacs Trouble Me
df%>%count(df$Genre)
## # A tibble: 6 × 2
## `df$Genre` n
## <chr> <int>
## 1 Genre 1 - hiphop/rap 58
## 2 Genre 2 - pop/kpop/Latin 25
## 3 Genre 3 - house/ska 5
## 4 Genre 4 - rnb/soul 14
## 5 Genre 5 - alt/indie/folk 45
## 6 Genre 6 - country/rock 28
Genre_Counts <- df%>%count(Genre)
Genre_Counts <- Genre_Counts %>% mutate(prob = n/sum(n))
Genre_Counts
## # A tibble: 6 × 3
## Genre n prob
## <chr> <int> <dbl>
## 1 Genre 1 - hiphop/rap 58 0.331
## 2 Genre 2 - pop/kpop/Latin 25 0.143
## 3 Genre 3 - house/ska 5 0.0286
## 4 Genre 4 - rnb/soul 14 0.08
## 5 Genre 5 - alt/indie/folk 45 0.257
## 6 Genre 6 - country/rock 28 0.16
Genre_Counts$prob <- round(Genre_Counts$prob, 2)
Genre_Counts
## # A tibble: 6 × 3
## Genre n prob
## <chr> <int> <dbl>
## 1 Genre 1 - hiphop/rap 58 0.33
## 2 Genre 2 - pop/kpop/Latin 25 0.14
## 3 Genre 3 - house/ska 5 0.03
## 4 Genre 4 - rnb/soul 14 0.08
## 5 Genre 5 - alt/indie/folk 45 0.26
## 6 Genre 6 - country/rock 28 0.16
This table tells us that the probability of a song playing from each genre is .33% chance for hiphop/rap, .14% chance for pop/kpop/Latin, .03% chance for house/ska, .08% chance for rnb/soul, .26% for alt/indie/folk, and .16% for country/rock.
sample <- sample_n(df, 10)
sample
## # A tibble: 10 × 3
## Genre Artist Song
## <chr> <chr> <chr>
## 1 Genre 1 - hiphop/rap $uicideboy$ Not Even Ghosts Are This Em…
## 2 Genre 1 - hiphop/rap Kendrick Lamar Alright
## 3 Genre 6 - country/rock Billy Joel Summer, Highland Falls
## 4 Genre 6 - country/rock Ferry STRIKE 3
## 5 Genre 2 - pop/kpop/Latin bad bunny kpop
## 6 Genre 1 - hiphop/rap Drake teenage fever
## 7 Genre 1 - hiphop/rap Polo G Martin and Gina
## 8 Genre 6 - country/rock Queens of the Stone Age No One Knows
## 9 Genre 4 - rnb/soul running on e Brent F
## 10 Genre 6 - country/rock Red Hot Chili Peppers Can't Stop
sample_counts <- sample %>% count(Genre) %>% mutate(probability = n/sum(n))
sample_counts
## # A tibble: 4 × 3
## Genre n probability
## <chr> <int> <dbl>
## 1 Genre 1 - hiphop/rap 4 0.4
## 2 Genre 2 - pop/kpop/Latin 1 0.1
## 3 Genre 4 - rnb/soul 1 0.1
## 4 Genre 6 - country/rock 4 0.4
This table tells us the experimental probability of a song playing from each genre. One thing that stands out about this data is the lack of representation from genre 3 & 4. Both of these have an experimental probability of 0%, which is unsurprising as their theoretical probability were both under 10%. Pop/kpop/latin, alt/indie/folk, and country/rock each have a 20% chance of being played, and hiphop/rap has a 40% chance. The biggest suprise probably comes from alt/indie/rock’s data, which had a theoretical probability of 26% (only 4% less than hiphop/rap), but an expirimental probability of just 20%. This data could be improved, and made closer to it’s theoretical data, by using a larger sample size of shuffled songs– think 20 or 30 songs instead of 10.
sample_n(df, 20) %>% count(Genre) %>% mutate(probability = round(n/sum(n), 2))
## # A tibble: 5 × 3
## Genre n probability
## <chr> <int> <dbl>
## 1 Genre 1 - hiphop/rap 8 0.4
## 2 Genre 2 - pop/kpop/Latin 3 0.15
## 3 Genre 4 - rnb/soul 1 0.05
## 4 Genre 5 - alt/indie/folk 5 0.25
## 5 Genre 6 - country/rock 3 0.15
sample_n(df, 30) %>% count(Genre) %>% mutate(probability = round(n/sum(n), 2))
## # A tibble: 5 × 3
## Genre n probability
## <chr> <int> <dbl>
## 1 Genre 1 - hiphop/rap 9 0.3
## 2 Genre 2 - pop/kpop/Latin 7 0.23
## 3 Genre 4 - rnb/soul 2 0.07
## 4 Genre 5 - alt/indie/folk 7 0.23
## 5 Genre 6 - country/rock 5 0.17
sample_n(df, 40) %>% count(Genre) %>% mutate(probability = round(n/sum(n), 2))
## # A tibble: 5 × 3
## Genre n probability
## <chr> <int> <dbl>
## 1 Genre 1 - hiphop/rap 13 0.32
## 2 Genre 2 - pop/kpop/Latin 8 0.2
## 3 Genre 4 - rnb/soul 4 0.1
## 4 Genre 5 - alt/indie/folk 6 0.15
## 5 Genre 6 - country/rock 9 0.22
sample_n(df, 60) %>% count(Genre) %>% mutate(probability = round(n/sum(n), 2))
## # A tibble: 6 × 3
## Genre n probability
## <chr> <int> <dbl>
## 1 Genre 1 - hiphop/rap 24 0.4
## 2 Genre 2 - pop/kpop/Latin 8 0.13
## 3 Genre 3 - house/ska 1 0.02
## 4 Genre 4 - rnb/soul 4 0.07
## 5 Genre 5 - alt/indie/folk 14 0.23
## 6 Genre 6 - country/rock 9 0.15
sample_n(df, 80) %>% count(Genre) %>% mutate(probability = round(n/sum(n), 2))
## # A tibble: 6 × 3
## Genre n probability
## <chr> <int> <dbl>
## 1 Genre 1 - hiphop/rap 31 0.39
## 2 Genre 2 - pop/kpop/Latin 13 0.16
## 3 Genre 3 - house/ska 1 0.01
## 4 Genre 4 - rnb/soul 5 0.06
## 5 Genre 5 - alt/indie/folk 20 0.25
## 6 Genre 6 - country/rock 10 0.12
sample_n(df, 100) %>% count(Genre) %>% mutate(probability = round(n/sum(n), 2))
## # A tibble: 6 × 3
## Genre n probability
## <chr> <int> <dbl>
## 1 Genre 1 - hiphop/rap 36 0.36
## 2 Genre 2 - pop/kpop/Latin 14 0.14
## 3 Genre 3 - house/ska 4 0.04
## 4 Genre 4 - rnb/soul 5 0.05
## 5 Genre 5 - alt/indie/folk 26 0.26
## 6 Genre 6 - country/rock 15 0.15
As each shuffle simulation grows larger, they become more representative of the theoretical probability. In the largest simulation– containing 100 songs– the experimental probability of each genre was no more than 3% off from the theoretical probability.
The earlier simulations were less accurate, each having discrepancies of between 8-10% for at least one of the genres. However this is still a fairly small number, and only occurred in one or two genres per simulation. This pattern indicates that these tests are accurate, and the shuffles are representative of the overall playlist.
In this study I have learned about the differences between theoretical and experimental probability. I find it fascinating that mathematically something might be supposed to happen, but because of the many ever changing factors of life it doesn’t. I also learned that if you have a larger sample size, your experimental probability is more likely to be near the theoretical probability.
Coding this simulation helped me to quickly understand data without complex math equations. One way to use simulations (or a simulation-like product) is to create a seating arrangement for a wedding dinner or the Hunger Games simulation games I played as a kid.
The hardest part of coding for this assignment was at the beginning when I had absolutely no idea what I was doing! I didn’t even know how to ask for help I was so lost. That meant that one I finally finished the first coding project in this unit I was so so proud!
In the future, I want to learn more about how and why code works. I felt like I was just memorizing phrases of a language, rather than taking the time to understand the meaning and the nuance. I think if I were to do this project again I would have procrastinated less. I ended up really enjoying the material, and wish I could have set aside more time to fully understand it.