install.packages("tidyverse")## Installing package into '/cloud/lib/x86_64-pc-linux-gnu-library/4.3'
## (as 'lib' is unspecified)library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.2 ✔ readr 2.1.4
## ✔ forcats 1.0.0 ✔ stringr 1.5.0
## ✔ ggplot2 3.4.2 ✔ tibble 3.2.1
## ✔ lubridate 1.9.2 ✔ tidyr 1.3.0
## ✔ 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 errorsdf <- 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 Medf$Genre<-as.factor(df$Genre)genre_counts <- df %>% count(Genre)genre_counts <- genre_counts %>% mutate(prob = n/sum(n))
genre_counts## # A tibble: 6 × 3
## Genre n prob
## <fct> <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 0.16genre_counts$prob <- round(genre_counts$prob, 2)
genre_counts## # A tibble: 6 × 3
## Genre n prob
## <fct> <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 0.1633% of hiphop 14% Pop 3% house 8% RNB 26% Alt 16% Country/Rock
sample_n(df, 10)## # A tibble: 10 × 3
## Genre Artist Song
## <fct> <chr> <chr>
## 1 Genre 1 - hiphop/rap Drake teenage fever
## 2 Genre 2 - pop/kpop/Latin Seori Running Through the Night
## 3 Genre 6 - country/rock Life on mars david bowie
## 4 Genre 5 - alt/indie/folk Current Joys New Flesh
## 5 Genre 1 - hiphop/rap EBE REEF Trust
## 6 Genre 5 - alt/indie/folk T e l e p a t h バウンス家の中でセックス
## 7 Genre 6 - country/rock Ferry STRIKE 3
## 8 Genre 5 - alt/indie/folk Surf Curse Freaks
## 9 Genre 2 - pop/kpop/Latin bad bunny lo siento bb
## 10 Genre 5 - alt/indie/folk 10,000 Maniacs Trouble Megenre_counts %>% count(Genre)## # A tibble: 6 × 2
## Genre n
## <fct> <int>
## 1 Genre 1 - hiphop/rap 1
## 2 Genre 2 - pop/kpop/Latin 1
## 3 Genre 3 - house/ska 1
## 4 Genre 4 - rnb/soul 1
## 5 Genre 5 - alt/indie/folk 1
## 6 Genre 6 - country/rock 1genre_counts %>% count(Genre) %>% mutate(probability = n/sum(n))## # A tibble: 6 × 3
## Genre n probability
## <fct> <int> <dbl>
## 1 Genre 1 - hiphop/rap 1 0.167
## 2 Genre 2 - pop/kpop/Latin 1 0.167
## 3 Genre 3 - house/ska 1 0.167
## 4 Genre 4 - rnb/soul 1 0.167
## 5 Genre 5 - alt/indie/folk 1 0.167
## 6 Genre 6 - country/rock 1 0.167genre_counts## # A tibble: 6 × 3
## Genre n prob
## <fct> <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 0.16These might not reflect my playlists because i don’t listen to a lot of hiphop/rap or pop. I mostly have indie or rock. But i was correct about the fact that they are more popular and show up more often.
sample_n(df, 40) %>% count(Genre) %>% mutate(probability = round(n/sum(n), 2))## # A tibble: 5 × 3
## Genre n probability
## <fct> <int> <dbl>
## 1 Genre 1 - hiphop/rap 13 0.32
## 2 Genre 2 - pop/kpop/Latin 3 0.07
## 3 Genre 4 - rnb/soul 3 0.07
## 4 Genre 5 - alt/indie/folk 13 0.32
## 5 Genre 6 - country/rock 8 0.2The genres that show up the most on shuffle might represent what most people in our class would listen to. Mostly rap and pop. Every time i simulated shuffle rap and pop were always on the top 2. I learned that if you have a large amount of data there seems to be one group that is larger, you’re most likely going to see it show up more often.
it made the shuffling easier because it done automatically. The hardest ones were the longer ones but they were also the most fulfilling ones to get correct. Do people who code memorize all these inputs? like a language?