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)
# Load the movies dataset
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”
q1 <- movies %>%
rename (movie_title = Film , release_year = Year)
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>create a new dataframe with only the columns: movie_title, release_year, Genre, Profitability
q2 <- q1 %>%
select(movie_title, release_year, Genre, Profitability)
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 3.08Filter the dataset to include only movies released after 2000 with a Rotten Tomatoes % higher than 80
q3 <- 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>Add a new column called “Profitability_millions” that converts the Profitability to millions of dollars
q4 <- movies %>%
mutate(Profitability_Millions = Profitability*1000000)
head(q4)## # A tibble: 6 × 9
## Film Genre `Lead Studio` `Audience score %` Profitability `Rotten Tomatoes %`
## <chr> <chr> <chr> <dbl> <dbl> <dbl>
## 1 Zack… Roma… The Weinstei… 70 1.75 64
## 2 Yout… Come… The Weinstei… 52 1.09 68
## 3 You … Come… Independent 35 1.21 43
## 4 When… Come… Disney 44 0 15
## 5 What… Come… Fox 72 6.27 28
## 6 Wate… Drama 20th Century… 72 3.08 60
## # ℹ 3 more variables: `Worldwide Gross` <chr>, Year <dbl>,
## # 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))
q5 <- q4 %>%
arrange(desc(`Rotten Tomatoes %`), desc(Profitability_Millions))
head(q5)## # A tibble: 6 × 9
## Film Genre `Lead Studio` `Audience score %` Profitability `Rotten Tomatoes %`
## <chr> <chr> <chr> <dbl> <dbl> <dbl>
## 1 WALL… Anim… Disney 89 2.90 96
## 2 Midn… Rome… Sony 84 8.74 93
## 3 Ench… Come… Disney 80 4.01 93
## 4 Knoc… Come… Universal 83 6.64 91
## 5 Wait… Roma… Independent 67 11.1 89
## 6 A Se… Drama Universal 64 4.38 89
## # ℹ 3 more variables: `Worldwide Gross` <chr>, Year <dbl>,
## # Profitability_Millions <dbl>Use 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.
combo <- movies %>% # then
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 %`), desc(Profitability_Millions))
head(combo)## # 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, are the best movies the most popular?
From the resulting data, we learn that the best movies are not always the most popular. For example, the “Waitress” had the highest popularity, but it has an 89% rotten tomato score, and the movie “WALL-E” has the lowest popularity, and a 96% rotten tomato score.
Create a summary dataframe that shows the average rating and Profitability_millions for movies by Genre. Hint: You’ll need to use group_by() and summarize().
q8 <- q4 %>%
mutate(Genre = tolower(Genre), # Convert all genre names to lowercase
Genre = recode(Genre, # Fix common spelling errors
"romence" = "romance",
"comdy" = "comedy")) %>%
group_by(Genre) %>%
summarize(
avg_rating = mean(`Rotten Tomatoes %`, na.rm = TRUE),
avg_profitability_Millions = mean(Profitability_Millions, na.rm = TRUE)
)
q8## # A tibble: 6 × 3
## Genre avg_rating avg_profitability_Millions
## <chr> <dbl> <dbl>
## 1 action 11 1245333.
## 2 animation 74.2 3759414.
## 3 comedy 43.0 3851160.
## 4 drama 51.5 8407218.
## 5 fantasy 73 1783944.
## 6 romance 46.3 4079972.