renamed_movies <- movies %>%
rename(movie_title = Film, release_year = Year)
print(head(renamed_movies))## # A tibble: 6 × 8
## movie_title Genre `Lead Studio` `Audience score %` Profitability
## <chr> <chr> <chr> <dbl> <dbl>
## 1 Zack and Miri Make a Por… Roma… The Weinstei… 70 1.75
## 2 Youth in Revolt Come… The Weinstei… 52 1.09
## 3 You Will Meet a Tall Dar… Come… Independent 35 1.21
## 4 When in Rome Come… Disney 44 0
## 5 What Happens in Vegas Come… Fox 72 6.27
## 6 Water For Elephants Drama 20th Century… 72 3.08
## # ℹ 3 more variables: `Rotten Tomatoes %` <dbl>, `Worldwide Gross` <chr>,
## # release_year <dbl>new_dataframe <- renamed_movies %>%
select(movie_title, release_year, Genre, Profitability)
print(head(new_dataframe))## # 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 3.08after_2000 <- renamed_movies %>%
filter(release_year > 2000 & `Rotten Tomatoes %` > 80)
head(after_2000)## # A tibble: 6 × 8
## movie_title Genre `Lead Studio` `Audience score %` Profitability
## <chr> <chr> <chr> <dbl> <dbl>
## 1 WALL-E Animati… Disney 89 2.90
## 2 Waitress Romance Independent 67 11.1
## 3 Tangled Animati… Disney 88 1.37
## 4 Rachel Getting Married Drama Independent 61 1.38
## 5 My Week with Marilyn Drama The Weinstei… 84 0.826
## 6 Midnight in Paris Romence Sony 84 8.74
## # ℹ 3 more variables: `Rotten Tomatoes %` <dbl>, `Worldwide Gross` <chr>,
## # release_year <dbl>profitability_ratio <- renamed_movies %>%
mutate(Profitability_millions = Profitability * 1000000)
head(profitability_ratio)## # A tibble: 6 × 9
## movie_title Genre `Lead Studio` `Audience score %` Profitability
## <chr> <chr> <chr> <dbl> <dbl>
## 1 Zack and Miri Make a Por… Roma… The Weinstei… 70 1.75
## 2 Youth in Revolt Come… The Weinstei… 52 1.09
## 3 You Will Meet a Tall Dar… Come… Independent 35 1.21
## 4 When in Rome Come… Disney 44 0
## 5 What Happens in Vegas Come… Fox 72 6.27
## 6 Water For Elephants Drama 20th Century… 72 3.08
## # ℹ 4 more variables: `Rotten Tomatoes %` <dbl>, `Worldwide Gross` <chr>,
## # release_year <dbl>, Profitability_millions <dbl>arranged_movies <- renamed_movies %>%
arrange(desc(`Rotten Tomatoes %`), Profitability)
head(arranged_movies)## # A tibble: 6 × 8
## movie_title Genre `Lead Studio` `Audience score %` Profitability
## <chr> <chr> <chr> <dbl> <dbl>
## 1 WALL-E Animation Disney 89 2.90
## 2 Enchanted Comedy Disney 80 4.01
## 3 Midnight in Paris Romence Sony 84 8.74
## 4 Knocked Up Comedy Universal 83 6.64
## 5 Tangled Animation Disney 88 1.37
## 6 A Serious Man Drama Universal 64 4.38
## # ℹ 3 more variables: `Rotten Tomatoes %` <dbl>, `Worldwide Gross` <chr>,
## # release_year <dbl>conclusion <- 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 %`), Profitability)
head(conclusion)## # 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 Enchanted 2007 Comedy 4.01 93
## 3 Midnight in Paris 2011 Romence 8.74 93
## 4 Knocked Up 2007 Comedy 6.64 91
## 5 Tangled 2010 Animation 1.37 89
## 6 A Serious Man 2009 Drama 4.38 89
## # ℹ 1 more variable: Profitability_millions <dbl>The best movies are not the most popular, the most profitable movie is “Waitress” but got a score of 89 on Rotten Tomatoes.
renamed_movies <- renamed_movies %>%
mutate(Genre = tolower(trimws(Genre))) %>%
mutate(Genre = recode(Genre,
"comdy" = "comedy",
"romence" = "romance"))
summary_df <- renamed_movies %>%
group_by(Genre) %>%
summarize(
avg_rating = mean(`Audience score %`, na.rm = TRUE),
avg_profitability_millions = mean(Profitability * 1000000, na.rm = TRUE)
)
head(summary_df)## # A tibble: 6 × 3
## Genre avg_rating avg_profitability_millions
## <chr> <dbl> <dbl>
## 1 action 45 1245333.
## 2 animation 70.2 3759414.
## 3 comedy 61.4 3851160.
## 4 drama 67.2 8407218.
## 5 fantasy 81 1783944.
## 6 romance 65.6 4079972.