Netflix TV Show Actor Analysis

library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.1     ✔ stringr   1.5.2
## ✔ ggplot2   4.0.0     ✔ tibble    3.3.0
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.1.0     
## ── 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

Netflix <- read_csv("Netflix.csv")

## Rows: 6234 Columns: 12
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (10): type, title, director, cast, country, date_added, rating, duration...
## dbl  (2): show_id, release_year
## 
## 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.

Netflix_Actor <- Netflix %>% 
  separate_rows(cast, sep = ", ") %>% 
  drop_na(cast) %>% 
  rename(actor = cast)

Top_Actors <- Netflix_Actor %>%
  select(type, actor) %>% 
  filter(type == "TV Show") %>% 
  group_by(actor) %>% 
  count(sort = TRUE) %>% 
  ungroup() %>% 
  head(6)

Top_Actors

## # A tibble: 6 × 2
##   actor                  n
##   <chr>              <int>
## 1 Takahiro Sakurai      18
## 2 Yuki Kaji             16
## 3 Daisuke Ono           14
## 4 David Attenborough    14
## 5 Ashleigh Ball         12
## 6 Hiroshi Kamiya        12

Top_Actors %>% 
  ggplot(aes(x = reorder(actor, n), y = n, fill = actor)) +
  geom_col(show.legend = FALSE) +
  coord_flip() +
  labs(
    title = "Top 6 Most Frequent TV Show Actors on Netflix",
    x = "Actor",
    y = "Number of Appearances"
  ) +
  theme_minimal()