##INTRODUCTION ##in

playlistdata <- 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.
head(playlistdata)
## # A tibble: 6 × 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
genre <- playlistdata %>% count(genre)
genre
## # A tibble: 6 × 2
##   genre                        n
##   <chr>                    <int>
## 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
chance <- genre %>% mutate(prob = n/144)
chance
## # A tibble: 6 × 3
##   genre                        n   prob
##   <chr>                    <int>  <dbl>
## 1 Genre 1 - hiphop/rap        26 0.181 
## 2 Genre 2 - pop/kpop/Latin    22 0.153 
## 3 Genre 3 -  house/ska         5 0.0347
## 4 Genre 4 -  rnb/soul         43 0.299 
## 5 Genre 5 - alt/indie/folk    34 0.236 
## 6 Genre 6 - country/rock      14 0.0972
sample1<- sample_n(playlistdata,10) %>% count(genre) %>% mutate(prob = n/sum(n))
sample1
## # A tibble: 3 × 3
##   genre                        n  prob
##   <chr>                    <int> <dbl>
## 1 Genre 2 - pop/kpop/Latin     2   0.2
## 2 Genre 4 -  rnb/soul          6   0.6
## 3 Genre 6 - country/rock       2   0.2

##From the first set of data we see that every genre is included in the first set of songs except a hip hop/rap song. i feel thats because of hip hop having one of the lesser songs in the playlist.

sample2 <- sample_n(playlistdata,5) %>% count(genre) %>% mutate(prob = n/sum(n))
sample2
## # A tibble: 2 × 3
##   genre                        n  prob
##   <chr>                    <int> <dbl>
## 1 Genre 1 - hiphop/rap         3   0.6
## 2 Genre 5 - alt/indie/folk     2   0.4

##looking at the second set, i see there are only three genres that were chosen. what makes it more interesting is that the songs chosen were from genres that had the least probability of being chosen.

sample3 <- sample_n(playlistdata,15) %>% count(genre) %>% mutate(prob = n/sum(n))
sample3
## # A tibble: 5 × 3
##   genre                        n   prob
##   <chr>                    <int>  <dbl>
## 1 Genre 1 - hiphop/rap         3 0.2   
## 2 Genre 2 - pop/kpop/Latin     3 0.2   
## 3 Genre 3 -  house/ska         1 0.0667
## 4 Genre 4 -  rnb/soul          7 0.467 
## 5 Genre 5 - alt/indie/folk     1 0.0667

##While making these last two samples ive decided to make my last two samples songs a little more to find more probabability.

sample4 <- sample_n(playlistdata,25) %>% count(genre) %>% mutate(prob = n/sum(n))
sample4
## # A tibble: 5 × 3
##   genre                        n  prob
##   <chr>                    <int> <dbl>
## 1 Genre 1 - hiphop/rap         6  0.24
## 2 Genre 2 - pop/kpop/Latin     3  0.12
## 3 Genre 4 -  rnb/soul          8  0.32
## 4 Genre 5 - alt/indie/folk     6  0.24
## 5 Genre 6 - country/rock       2  0.08
full_join(sample1, sample2, by = "genre")
## # A tibble: 5 × 5
##   genre                      n.x prob.x   n.y prob.y
##   <chr>                    <int>  <dbl> <int>  <dbl>
## 1 Genre 2 - pop/kpop/Latin     2    0.2    NA   NA  
## 2 Genre 4 -  rnb/soul          6    0.6    NA   NA  
## 3 Genre 6 - country/rock       2    0.2    NA   NA  
## 4 Genre 1 - hiphop/rap        NA   NA       3    0.6
## 5 Genre 5 - alt/indie/folk    NA   NA       2    0.4
sample10 <- sample1 %>% select(genre)