movies <- read_csv("https://gist.githubusercontent.com/tiangechen/b68782efa49a16edaf07dc2cdaa855ea/raw/0c794a9717f18b094eabab2cd6a6b9a226903577/movies.csv")
head(movies)## # A tibble: 6 × 8
## Film Genre `Lead Studio`
## <chr> <chr> <chr>
## 1 Zack and Miri Make a Porno Romance The Weinstein Company
## 2 Youth in Revolt Comedy The Weinstein Company
## 3 You Will Meet a Tall Dark Stranger Comedy Independent
## 4 When in Rome Comedy Disney
## 5 What Happens in Vegas Comedy Fox
## 6 Water For Elephants Drama 20th Century Fox
## `Audience score %` Profitability `Rotten Tomatoes %` `Worldwide Gross` Year
## <dbl> <dbl> <dbl> <chr> <dbl>
## 1 70 1.75 64 $41.94 2008
## 2 52 1.09 68 $19.62 2010
## 3 35 1.21 43 $26.66 2010
## 4 44 0 15 $43.04 2010
## 5 72 6.27 28 $219.37 2008
## 6 72 3.08 60 $117.09 2011one <- movies %>%
rename(movie_title = Film,
release_year = Year)
head(one)## # A tibble: 6 × 8
## movie_title Genre `Lead Studio`
## <chr> <chr> <chr>
## 1 Zack and Miri Make a Porno Romance The Weinstein Company
## 2 Youth in Revolt Comedy The Weinstein Company
## 3 You Will Meet a Tall Dark Stranger Comedy Independent
## 4 When in Rome Comedy Disney
## 5 What Happens in Vegas Comedy Fox
## 6 Water For Elephants Drama 20th Century Fox
## `Audience score %` Profitability `Rotten Tomatoes %` `Worldwide Gross`
## <dbl> <dbl> <dbl> <chr>
## 1 70 1.75 64 $41.94
## 2 52 1.09 68 $19.62
## 3 35 1.21 43 $26.66
## 4 44 0 15 $43.04
## 5 72 6.27 28 $219.37
## 6 72 3.08 60 $117.09
## release_year
## <dbl>
## 1 2008
## 2 2010
## 3 2010
## 4 2010
## 5 2008
## 6 2011two <- one %>%
select(movie_title, release_year, Genre, Profitability)
head(two)## # A tibble: 6 × 4
## movie_title release_year Genre Profitability
## <chr> <dbl> <chr> <dbl>
## 1 Zack and Miri Make a Porno 2008 Romance 1.75
## 2 Youth in Revolt 2010 Comedy 1.09
## 3 You Will Meet a Tall Dark Stranger 2010 Comedy 1.21
## 4 When in Rome 2010 Comedy 0
## 5 What Happens in Vegas 2008 Comedy 6.27
## 6 Water For Elephants 2011 Drama 3.08three <- one %>%
filter(release_year > 2000, `Rotten Tomatoes %` > 80)
head(three)## # A tibble: 6 × 8
## movie_title Genre `Lead Studio` `Audience score %`
## <chr> <chr> <chr> <dbl>
## 1 WALL-E Animation Disney 89
## 2 Waitress Romance Independent 67
## 3 Tangled Animation Disney 88
## 4 Rachel Getting Married Drama Independent 61
## 5 My Week with Marilyn Drama The Weinstein Company 84
## 6 Midnight in Paris Romence Sony 84
## Profitability `Rotten Tomatoes %` `Worldwide Gross` release_year
## <dbl> <dbl> <chr> <dbl>
## 1 2.90 96 $521.28 2008
## 2 11.1 89 $22.18 2007
## 3 1.37 89 $355.01 2010
## 4 1.38 85 $16.61 2008
## 5 0.826 83 $8.26 2011
## 6 8.74 93 $148.66 2011four <- three %>%
mutate(Profitability_millions = Profitability * 1000000)
head(four)## # A tibble: 6 × 9
## movie_title Genre `Lead Studio` `Audience score %`
## <chr> <chr> <chr> <dbl>
## 1 WALL-E Animation Disney 89
## 2 Waitress Romance Independent 67
## 3 Tangled Animation Disney 88
## 4 Rachel Getting Married Drama Independent 61
## 5 My Week with Marilyn Drama The Weinstein Company 84
## 6 Midnight in Paris Romence Sony 84
## Profitability `Rotten Tomatoes %` `Worldwide Gross` release_year
## <dbl> <dbl> <chr> <dbl>
## 1 2.90 96 $521.28 2008
## 2 11.1 89 $22.18 2007
## 3 1.37 89 $355.01 2010
## 4 1.38 85 $16.61 2008
## 5 0.826 83 $8.26 2011
## 6 8.74 93 $148.66 2011
## Profitability_millions
## <dbl>
## 1 2896019.
## 2 11089742.
## 3 1365692.
## 4 1384167.
## 5 825800
## 6 8744706.five <- four %>%
arrange(desc(`Rotten Tomatoes %`), desc(Profitability_millions))
head(five)## # A tibble: 6 × 9
## movie_title Genre `Lead Studio` `Audience score %` Profitability
## <chr> <chr> <chr> <dbl> <dbl>
## 1 WALL-E Animation Disney 89 2.90
## 2 Midnight in Paris Romence Sony 84 8.74
## 3 Enchanted Comedy Disney 80 4.01
## 4 Knocked Up Comedy Universal 83 6.64
## 5 Waitress Romance Independent 67 11.1
## 6 A Serious Man Drama Universal 64 4.38
## `Rotten Tomatoes %` `Worldwide Gross` release_year Profitability_millions
## <dbl> <chr> <dbl> <dbl>
## 1 96 $521.28 2008 2896019.
## 2 93 $148.66 2011 8744706.
## 3 93 $340.49 2007 4005737.
## 4 91 $219 2007 6636402.
## 5 89 $22.18 2007 11089742.
## 6 89 $30.68 2009 4382857.six <- movies %>%
rename(movie_title = Film, release_year = Year) %>%
select(movie_title, release_year, Genre, Profitability, `Rotten Tomatoes %`) %>%
filter(release_year > 2000, `Rotten Tomatoes %` > 80) %>%
mutate(Profitability_millions = Profitability * 1000000) %>%
arrange(desc(`Rotten Tomatoes %`), desc(Profitability_millions))
head(six)## # A tibble: 6 × 6
## movie_title release_year Genre Profitability `Rotten Tomatoes %`
## <chr> <dbl> <chr> <dbl> <dbl>
## 1 WALL-E 2008 Animation 2.90 96
## 2 Midnight in Paris 2011 Romence 8.74 93
## 3 Enchanted 2007 Comedy 4.01 93
## 4 Knocked Up 2007 Comedy 6.64 91
## 5 Waitress 2007 Romance 11.1 89
## 6 A Serious Man 2009 Drama 4.38 89
## Profitability_millions
## <dbl>
## 1 2896019.
## 2 8744706.
## 3 4005737.
## 4 6636402.
## 5 11089742.
## 6 4382857.not necessarily. even among movies with very high Rotten Tomatoes scores, profitability varies a lot. Some highly rated movies are very profitable, but others are not, so higher ratings (“best”) do not always mean higher profitability (“most popular”).
extra <- movies %>%
rename(movie_title = Film, release_year = Year) %>%
mutate(Profitability_millions = Profitability * 1000000) %>%
group_by(Genre) %>%
summarize(
avg_rating = mean(`Rotten Tomatoes %`),
avg_profitability_millions = mean(Profitability_millions)
)
head(extra)## # A tibble: 6 × 3
## Genre avg_rating avg_profitability_millions
## <chr> <dbl> <dbl>
## 1 Action 11 1245333.
## 2 Animation 74.2 3759414.
## 3 Comdy 13 2649068.
## 4 Comedy 42.7 3776946.
## 5 Drama 51.5 8407218.
## 6 Fantasy 73 1783944.