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.Rename the “Film” column to “movie_title” and “Year” to “release_year”.
one <- movies %>%
rename(
movie_title = Film,
release_year = Year
)
head(one)## # 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, Rotten Tomatoes %.
two <- one %>%
select(movie_title, release_year, Genre, Profitability, `Rotten Tomatoes %`)
head(two)## # A tibble: 6 × 5
## movie_title release_year Genre Profitability `Rotten Tomatoes %`
## <chr> <dbl> <chr> <dbl> <dbl>
## 1 Zack and Miri Make a Por… 2008 Roma… 1.75 64
## 2 Youth in Revolt 2010 Come… 1.09 68
## 3 You Will Meet a Tall Dar… 2010 Come… 1.21 43
## 4 When in Rome 2010 Come… 0 15
## 5 What Happens in Vegas 2008 Come… 6.27 28
## 6 Water For Elephants 2011 Drama 3.08 60Filter the dataset to include only movies released after 2000 with a Rotten Tomatoes % higher than 80.
three <- two %>%
filter(release_year > 2000,
`Rotten Tomatoes %` > 80)
head(three)## # A tibble: 6 × 5
## movie_title release_year Genre Profitability `Rotten Tomatoes %`
## <chr> <dbl> <chr> <dbl> <dbl>
## 1 WALL-E 2008 Animati… 2.90 96
## 2 Waitress 2007 Romance 11.1 89
## 3 Tangled 2010 Animati… 1.37 89
## 4 Rachel Getting Married 2008 Drama 1.38 85
## 5 My Week with Marilyn 2011 Drama 0.826 83
## 6 Midnight in Paris 2011 Romence 8.74 93Add a new column called “Profitability_millions”.
four <- three %>%
mutate(Profitability_millions = Profitability)
head(four)## # A tibble: 6 × 6
## movie_title release_year Genre Profitability `Rotten Tomatoes %`
## <chr> <dbl> <chr> <dbl> <dbl>
## 1 WALL-E 2008 Animati… 2.90 96
## 2 Waitress 2007 Romance 11.1 89
## 3 Tangled 2010 Animati… 1.37 89
## 4 Rachel Getting Married 2008 Drama 1.38 85
## 5 My Week with Marilyn 2011 Drama 0.826 83
## 6 Midnight in Paris 2011 Romence 8.74 93
## # ℹ 1 more variable: Profitability_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))
head(five)## # 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
## # ℹ 1 more variable: Profitability_millions <dbl>Use the pipe operator (%>%) to chain these operations together, starting with the original dataset.
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) %>%
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
## # ℹ 1 more variable: Profitability_millions <dbl>From the resulting data, the highest rated movies are not always the most profitable. Some movies with strong Rotten Tomatoes scores also have high profitability, but others do not, showing that critically successful movies are not always the most popular or financially successful.
Create a summary dataframe that shows the average rating and Profitability_millions for movies by Genre.
extra_credit <- movies %>%
rename(
movie_title = Film,
release_year = Year
) %>%
mutate(Profitability_millions = Profitability) %>%
group_by(Genre) %>%
summarize(
avg_rating = mean(`Rotten Tomatoes %`, na.rm = TRUE),
avg_profitability_millions = mean(Profitability_millions, na.rm = TRUE),
number_of_movies = n()
) %>%
arrange(desc(avg_rating))
head(extra_credit)## # A tibble: 6 × 4
## Genre avg_rating avg_profitability_millions number_of_movies
## <chr> <dbl> <dbl> <int>
## 1 Romence 93 8.74 1
## 2 comedy 87 8.10 1
## 3 Animation 74.2 3.76 4
## 4 Fantasy 73 1.78 1
## 5 romance 54 0.653 1
## 6 Drama 51.5 8.41 13