HW 2

# Load the dplyr package
library(dplyr)

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

# Load the dataset
df <- read.csv('Netflix.csv')

# Split the cast column into multiple rows using unnest
df <- df %>%
  mutate(actor = strsplit(as.character(cast), ',')) %>%
  tidyr::unnest(actor)

# Drop the original 'cast' column
df <- df %>%
  select(-cast)

# Filter for TV shows and count actor appearances
tv_show_actors <- df %>%
  filter(type == "TV Show") %>%
  count(actor, sort = TRUE) %>%
  head(6)

# Display the top six actors with the most appearances in TV shows
print(tv_show_actors)

## # A tibble: 6 × 2
##   actor                    n
##   <chr>                <int>
## 1 " Takahiro Sakurai"     18
## 2 " Yuki Kaji"            14
## 3 "David Attenborough"    14
## 4 " Tomokazu Sugita"      12
## 5 " Ai Kayano"            11
## 6 " Daisuke Ono"          11