/ ## Load tidy Verse
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 3.4.4 ✔ 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
/ ## Load the class playlist data afer we cleaned and then we import the
data into r
read_csv("playlist - data_clean.csv")
## Rows: 144 Columns: 3
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (3): genre, artist, title
##
## 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.
## # A tibble: 144 × 3
## genre artist title
## <chr> <chr> <chr>
## 1 Genre 1 - hiphop/rap Alesso When I'm Gone
## 2 Genre 1 - hiphop/rap Aliyah's Interlude It Girl
## 3 Genre 1 - hiphop/rap Big Sean Beware
## 4 Genre 1 - hiphop/rap Clipse Ma, I don't love her
## 5 Genre 1 - hiphop/rap Common Be
## 6 Genre 1 - hiphop/rap Drake Nice for what
## 7 Genre 1 - hiphop/rap Isaiah Rashad Headshots
## 8 Genre 1 - hiphop/rap Jcole change
## 9 Genre 1 - hiphop/rap Jcole Crooked smile
## 10 Genre 1 - hiphop/rap Jcole Immortal
## # ℹ 134 more rows
/ ## Rename the data to df (data frame) for convience so I dont have to
write the full file name over again
df <-
read.csv("playlist - data_clean.csv")
/ ## Make sure my data is correct if I think some data might be faulty i
could check here
head(df)
## genre artist title
## 1 Genre 1 - hiphop/rap Alesso When I'm Gone
## 2 Genre 1 - hiphop/rap Aliyah's Interlude It Girl
## 3 Genre 1 - hiphop/rap Big Sean Beware
## 4 Genre 1 - hiphop/rap Clipse Ma, I don't love her
## 5 Genre 1 - hiphop/rap Common Be
## 6 Genre 1 - hiphop/rap Drake Nice for what
/ ## This finds the total of the amount of genres there are and how many
there is
df %>% count(genre)
## genre n
## 1 Genre 1 - hiphop/rap 26
## 2 Genre 2 - pop/kpop/Latin 22
## 3 Genre 3 - house/ska 5
## 4 Genre 4 - rnb/soul 43
## 5 Genre 5 - alt/indie/folk 34
## 6 Genre 6 - country/rock 14
/ ## Basic summary of the class playlist data
summary(df)
## genre artist title
## Length:144 Length:144 Length:144
## Class :character Class :character Class :character
## Mode :character Mode :character Mode :character
/ ## This code finds the probability of a certain genre playing inside
of the class playlist
original <- df %>% count(genre) %>% mutate("probability" = n/sum(n))
/ ## This code lets you veiw the class playlist and the probability for
a certain genre to be chosen/played
original
## genre n probability
## 1 Genre 1 - hiphop/rap 26 0.18055556
## 2 Genre 2 - pop/kpop/Latin 22 0.15277778
## 3 Genre 3 - house/ska 5 0.03472222
## 4 Genre 4 - rnb/soul 43 0.29861111
## 5 Genre 5 - alt/indie/folk 34 0.23611111
## 6 Genre 6 - country/rock 14 0.09722222
/ ## This creates the number of genres in the class playlist into its
own data
df2 <- df %>% count(genre)
/ ## This shuffles the playlist into 10 random songs out of the class
playlist data
shuffle10 <- sample_n(df,10)
/ ## View the random playlist with 10 songs
shuffle10 %>% count(genre) %>% mutate("probability" = n/sum(n))
## genre n probability
## 1 Genre 1 - hiphop/rap 4 0.4
## 2 Genre 2 - pop/kpop/Latin 3 0.3
## 3 Genre 4 - rnb/soul 2 0.2
## 4 Genre 5 - alt/indie/folk 1 0.1
/ ## This shuffles the playlist into 25 random songs out of the class
data
shuffle25 <- sample_n(df,25)
/ ## View the random playlist with 25 songs
shuffle25 %>% count(genre) %>% mutate("probability" = n/sum(n))
## genre n probability
## 1 Genre 1 - hiphop/rap 4 0.16
## 2 Genre 2 - pop/kpop/Latin 4 0.16
## 3 Genre 3 - house/ska 2 0.08
## 4 Genre 4 - rnb/soul 7 0.28
## 5 Genre 5 - alt/indie/folk 5 0.20
## 6 Genre 6 - country/rock 3 0.12
/ ## This shuffles the playlist into 50 random songs out of the class
data
shuffle50 <- sample_n(df,50)
/ ## View the random playlist with 50 songs
shuffle50 %>% count(genre) %>% mutate("probability" = n/sum(n))
## genre n probability
## 1 Genre 1 - hiphop/rap 5 0.10
## 2 Genre 2 - pop/kpop/Latin 12 0.24
## 3 Genre 3 - house/ska 1 0.02
## 4 Genre 4 - rnb/soul 13 0.26
## 5 Genre 5 - alt/indie/folk 14 0.28
## 6 Genre 6 - country/rock 5 0.10