Hw02

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

library(tidyr)
library(stringr)

netflix <- read.csv("Netflix.csv")

netflix_clean <- netflix %>%
  filter(type == "TV Show") %>%     
  select(type, title, cast) %>%       
  separate_rows(cast, sep = ",") %>%      
  mutate(cast = str_trim(cast)) %>%       
  rename(actor = cast)     

top_actors <- netflix_clean %>%
  group_by(actor) %>%
  summarise(appearances = n()) %>%
  arrange(desc(appearances)) %>%
  slice(-1) %>%                         
  head(6)                                  

top_actors

## # A tibble: 6 × 2
##   actor              appearances
##   <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