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, unionlibrary(readr)
movies <- read_csv("https://gist.githubusercontent.com/tiangechen/b68782efa49a16edaf07dc2cdaa855ea/raw/0c794a9717f18b094eabab2cd6a6b9a226903577/movies.csv")## Rows: 77 Columns: 8## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (4): Film, Genre, Lead Studio, Worldwide Gross
## dbl (4): Audience score %, Profitability, Rotten Tomatoes %, Year
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.Q1
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
selected_movies <- q1 %>%
select(movie_title, release_year, Genre, Profitability)
print(selected_movies)## # A tibble: 77 × 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 3.08
## 7 WALL-E 2008 Animation 2.90
## 8 Waitress 2007 Romance 11.1
## 9 Waiting For Forever 2011 Romance 0.005
## 10 Valentine's Day 2010 Comedy 4.18
## # ℹ 67 more rowsQ3
filtered_movies <- movies %>%
filter(Year > 2000, `Rotten Tomatoes %` > 80)
print(filtered_movies)## # A tibble: 12 × 8
## Film Genre `Lead Studio` `Audience score %` Profitability
## <chr> <chr> <chr> <dbl> <dbl>
## 1 WALL-E Animat… Disney 89 2.90
## 2 Waitress Romance Independent 67 11.1
## 3 Tangled Animat… 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
## 7 Knocked Up Comedy Universal 83 6.64
## 8 Jane Eyre Romance Universal 77 0
## 9 Enchanted Comedy Disney 80 4.01
## 10 Beginners Comedy Independent 80 4.47
## 11 A Serious Man Drama Universal 64 4.38
## 12 (500) Days of Summer comedy Fox 81 8.10
## # ℹ 3 more variables: `Rotten Tomatoes %` <dbl>, `Worldwide Gross` <chr>,
## # Year <dbl>Q4
movies_with_profitability <- movies %>%
mutate(Profitability_millions = Profitability * 1000000)
print(movies_with_profitability)## # A tibble: 77 × 9
## Film Genre `Lead Studio` `Audience score %` Profitability
## <chr> <chr> <chr> <dbl> <dbl>
## 1 Zack and Miri Make a Po… Roma… The Weinstei… 70 1.75
## 2 Youth in Revolt Come… The Weinstei… 52 1.09
## 3 You Will Meet a Tall Da… 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
## 7 WALL-E Anim… Disney 89 2.90
## 8 Waitress Roma… Independent 67 11.1
## 9 Waiting For Forever Roma… Independent 53 0.005
## 10 Valentine's Day Come… Warner Bros. 54 4.18
## # ℹ 67 more rows
## # ℹ 4 more variables: `Rotten Tomatoes %` <dbl>, `Worldwide Gross` <chr>,
## # Year <dbl>, Profitability_millions <dbl>Q5
sorted_movies <- movies_with_profitability %>%
arrange(desc(`Rotten Tomatoes %`), desc(Profitability_millions))
print(sorted_movies)## # A tibble: 77 × 9
## Film Genre `Lead Studio` `Audience score %` Profitability
## <chr> <chr> <chr> <dbl> <dbl>
## 1 WALL-E Animat… 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
## 7 Tangled Animat… Disney 88 1.37
## 8 (500) Days of Summer comedy Fox 81 8.10
## 9 Rachel Getting Married Drama Independent 61 1.38
## 10 Jane Eyre Romance Universal 77 0
## # ℹ 67 more rows
## # ℹ 4 more variables: `Rotten Tomatoes %` <dbl>, `Worldwide Gross` <chr>,
## # Year <dbl>, Profitability_millions <dbl>Q6
final_dataframe <- movies %>%
rename(
movie_title = Film,
release_year = Year
) %>%
filter(release_year > 2000, `Rotten Tomatoes %` > 80) %>%
mutate(Profitability_millions = Profitability * 1000000) %>%
arrange(desc(`Rotten Tomatoes %`), desc(Profitability_millions))
print(final_dataframe)## # A tibble: 12 × 9
## movie_title Genre `Lead Studio` `Audience score %` Profitability
## <chr> <chr> <chr> <dbl> <dbl>
## 1 WALL-E Animat… 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
## 7 Tangled Animat… Disney 88 1.37
## 8 (500) Days of Summer comedy Fox 81 8.10
## 9 Rachel Getting Married Drama Independent 61 1.38
## 10 Jane Eyre Romance Universal 77 0
## 11 Beginners Comedy Independent 80 4.47
## 12 My Week with Marilyn Drama The Weinstei… 84 0.826
## # ℹ 4 more variables: `Rotten Tomatoes %` <dbl>, `Worldwide Gross` <chr>,
## # release_year <dbl>, Profitability_millions <dbl>Q7
while some of the movies with high rotten tomatoes % have high audience score %, there are also movies with low rotten tomatoes % and high audience score (like twilight). some also have high rotten tomatoes % and low audience score % (rachel getting married)
Extra Credit
``` r
summary_dataframe <- movies %>%
rename(
movie_title = Film,
release_year = Year
) %>%
mutate(Profitability_millions = Profitability * 1000000) %>%
group_by(Genre) %>%
summarize(
average_rating = mean(`Rotten Tomatoes %`, na.rm = TRUE),
average_profitability = mean(Profitability_millions, na.rm = TRUE)
)
print(summary_dataframe)## # A tibble: 10 × 3
## Genre average_rating average_profitability
## <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.
## 7 Romance 42.1 3984790.
## 8 Romence 93 8744706.
## 9 comedy 87 8096000
## 10 romance 54 652603.