##
## 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## 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.Rename the “Film” column to “movie_title” and “Year” to “release_year”.
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>Create a new dataframe with only the columns: movie_title, release_year, Genre, Profitability,
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 3.08Filter the dataset to include only movies released after 2000 with a Rotten Tomatoes % higher than 80.
after_2000 <- renamed_movies %>%
filter(release_year > 2000 & `Rotten Tomatoes %` > 80)
print(after_2000)## # A tibble: 12 × 8
## movie_title 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>,
## # release_year <dbl>Add a new column called “Profitability_millions” that converts the Profitability to millions of dollars.
profitability_ratio <- renamed_movies %>%
mutate(profitabilty_millions = Profitability * 1000000)
print(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>, profitabilty_millions <dbl>Sort the filtered dataset by Rotten Tomatoes % in descending order, and then by Profitability in descending order. five <- four %>% arrange(desc(Rotten Tomatoes %) , desc(Profitability_millions))
arranged_movies <- renamed_movies %>%
arrange(desc(`Rotten Tomatoes %`), Profitability)
print(select(arranged_movies, `Rotten Tomatoes %`, Profitability))## # A tibble: 77 × 2
## `Rotten Tomatoes %` Profitability
## <dbl> <dbl>
## 1 96 2.90
## 2 93 4.01
## 3 93 8.74
## 4 91 6.64
## 5 89 1.37
## 6 89 4.38
## 7 89 11.1
## 8 87 8.10
## 9 85 0
## 10 85 1.38
## # ℹ 67 more rowsUse the pipe operator (%>%) to chain these operations together, starting with the original dataset and ending with a final dataframe that incorporates all the above transformations.
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(profitabilty_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: profitabilty_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.
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 Comdy 61 2649068.
## 4 Comedy 61.0 3776946.
## 5 Drama 67.2 8407218.
## 6 Fantasy 81 1783944.