{r} sample_n(df, 10)

{r} df %>% count()

{r} df %>% mutate()

In general, the results are representative of the contents of the playlist. An example of this is shown in both of these tables where genre 1 is the genre being pulled up the most. This is the genre that was revealed to be the most common. As for the theoretical and experimental probabilities, the results of the samples prove both to be true.

{r} sample_n(df, 30) %>% count(Genre) %>% mutate(probability = round(n/sum(n), 2))

{r} sample_n(df, 40) %>% count(Genre) %>% mutate(probability = round(n/sum(n), 2))

{r} sample_n(df, 10) %>% count(Genre) %>% mutate(probability = round(n/sum(n), 2))

{r} sample_n(df, 20) %>% count(Genre) %>% mutate(probability = round(n/sum(n), 2))

{r} sample_n(df, 5) %>% count(Genre) %>% mutate(probability = round(n/sum(n), 2))

Analyse and Synthesize

The songs shuffled do adequately represent the totality of the playlist we created and the genres included in it. This is shown consistently by the tables shown in this report.