{r} install.packages("tidyverse")
{r} library(tidyverse)
{r} df <- read_csv("Playlist - Clean.csv") #check
first few rows of data {r} head(df) # change variable type
to factor {r} as.factor(df$Genre) # get the counts for each
genre {r} df %>% count(Genre) ###Now I’m going to save
this data frame so I can easily access it again later.
{r} Genre_counts <- df %>% count(Genre)
{r} Genre_counts #Modeling ##Calculate Theoretical
Probabilities ###Next I need to find the theoretical probabilities of
getting each genre by creating a new column in my genre counts table.
{r} Genre_counts <- Genre_counts %>% mutate(prob = n/sum(n)) Genre_counts
###I don’t like all those long decimal numbers, so I’m going to round
them to 2 decimal places.
{r} Genre_counts$prob <- round(Genre_counts$prob, 2) Genre_counts
###This new table tells me that there is an 33% chance of getting a
hiphop/rap song, a 14% chance of getting a pop/kpop/Latin song, a 3%
chance of getting a house/ska song, a 8% chance of getting an rnb/soul
song, a 26% chance of getting an alt/indie/folk song, and a 16% chance
of getting a country/rock song.