q1 <- movies %>%
rename(movie_title = Film, release_year = Year)
print(head(q1))## # 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>q2 <- q1 %>%
select(movie_title , release_year , Genre , Profitability)
print(head(q2))## # 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 3.08q3 <- q1 %>%
filter(release_year > 2000 & `Rotten Tomatoes %` > 80)
head(q3)## # 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>q4 <- q3 %>%
mutate(Profitability_millions = Profitability* 1e6 )
head(q4)## # A tibble: 6 × 9
## 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 4 more variables: `Rotten Tomatoes %` <dbl>, `Worldwide Gross` <chr>,
## # release_year <dbl>, Profitability_millions <dbl>q5 <- q4 %>%
arrange(desc(`Rotten Tomatoes %`), desc(Profitability_millions))
head(q5)## # 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
## # ℹ 4 more variables: `Rotten Tomatoes %` <dbl>, `Worldwide Gross` <chr>,
## # release_year <dbl>, Profitability_millions <dbl>q6 <- 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* 1e6 ) %>%
arrange(desc(`Rotten Tomatoes %`), desc(Profitability_millions))#The most profitable movies are not considered the most popular as seen from the data. When filtering the data to show the most profitable movies, they aren’t the highest rotten tomatoes ratings. Same thing goes with worldwide gross. The movies with the highest gross aren’t the highest rating per rotten tomatoes.
summary_df <- movies %>%
group_by(Genre) %>%
summarize(
Avg_Rating = mean(`Rotten Tomatoes %`, na.rm = TRUE),
Avg_Profitability_millions = mean(Profitability, na.rm = TRUE)
)
print(summary_df)## # A tibble: 10 × 3
## Genre Avg_Rating Avg_Profitability_millions
## <chr> <dbl> <dbl>
## 1 Action 11 1.25
## 2 Animation 74.2 3.76
## 3 Comdy 13 2.65
## 4 Comedy 42.7 3.78
## 5 Drama 51.5 8.41
## 6 Fantasy 73 1.78
## 7 Romance 42.1 3.98
## 8 Romence 93 8.74
## 9 comedy 87 8.10
## 10 romance 54 0.653