Import data
# excel file
data <- read_excel("data/Summer Movies.xlsx")
data %>% separate_rows(genres, sep = ",")
## # A tibble: 1,585 × 10
## tconst title_type primary_title original_title year runtime_minutes genres
## <chr> <chr> <chr> <chr> <dbl> <chr> <chr>
## 1 tt00114… movie Midsummer Ma… Midsummer Mad… 1920 60 Drama
## 2 tt00267… movie A Midsummer … A Midsummer N… 1935 133 Comedy
## 3 tt00267… movie A Midsummer … A Midsummer N… 1935 133 Fanta…
## 4 tt00267… movie A Midsummer … A Midsummer N… 1935 133 Roman…
## 5 tt00338… movie The Teachers… Magistrarna p… 1941 86 Comedy
## 6 tt00373… movie Summer Storm Summer Storm 1944 106 Crime
## 7 tt00373… movie Summer Storm Summer Storm 1944 106 Drama
## 8 tt00373… movie Summer Storm Summer Storm 1944 106 Film-…
## 9 tt00384… movie Centennial S… Centennial Su… 1946 102 Histo…
## 10 tt00384… movie Centennial S… Centennial Su… 1946 102 Music
## # ℹ 1,575 more rows
## # ℹ 3 more variables: simple_title <chr>, average_rating <dbl>, num_votes <dbl>
Plot Data
data %>%
ggplot(aes(genres)) +
geom_bar()
