# Load libraries
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, union
library(readr)
# Load 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.
head(movies)
## # A tibble: 6 × 8
## 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 2 more variables: `Worldwide Gross` <chr>, Year <dbl>
# Q1 - Rename the "Film" column to "movie_title" and "Year" to "release_year"
one <- movies %>%
rename(movie_title = Film, release_year = Year)
head(movies)
## # A tibble: 6 × 8
## 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 2 more variables: `Worldwide Gross` <chr>, Year <dbl>
# Q2 - Select only the columns: movie_title, release_year, Genre, Profitability
two <- one %>%
select(movie_title, release_year, Genre, Profitability)
head(two)
## # 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 3.08
# Q3 - Filter 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 × 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
# Q4 - Add a new column "Profitability_millions" converting Profitability to millions of dollars
four <- three %>%
mutate(Profitability_millions = Profitability * 1e6)
head(four)
## # A tibble: 6 × 5
## movie_title release_year Genre Profitability Profitability_millions
## <chr> <dbl> <chr> <dbl> <dbl>
## 1 Zack and Miri Make a … 2008 Roma… 1.75 1747542.
## 2 Youth in Revolt 2010 Come… 1.09 1090000
## 3 You Will Meet a Tall … 2010 Come… 1.21 1211818.
## 4 When in Rome 2010 Come… 0 0
## 5 What Happens in Vegas 2008 Come… 6.27 6267647.
## 6 Water For Elephants 2011 Drama 3.08 3081421.
# Q5 - Sort the filtered dataset by Rotten Tomatoes % (descending) and then by Profitability (descending)
five <- four %>%
arrange(desc("Rotten Tomatoes %"), desc(Profitability_millions))
head(five)
## # A tibble: 6 × 5
## movie_title release_year Genre Profitability Profitability_millions
## <chr> <dbl> <chr> <dbl> <dbl>
## 1 Fireproof 2008 Drama 66.9 66934000
## 2 High School Musical 3… 2008 Come… 22.9 22913136.
## 3 The Twilight Saga: Ne… 2009 Drama 14.2 14196400
## 4 Waitress 2007 Roma… 11.1 11089742.
## 5 Twilight 2008 Roma… 10.2 10180027.
## 6 Mamma Mia! 2008 Come… 9.23 9234454.
# Q6 - Combine all operations into a single pipeline
final <- 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))
head(final)
## # 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>
# Q7 - From the resulting data, the best movies (highest Rotten Tomatoes %) are not necessarily the most profitable. While highly-rated movies may attract critical praise, profitability is driven by multiple factors such as production budget, marketing, and audience reach.
# EXTRA CREDIT - Create a summary dataframe with average rating and Profitability_millions by Genre
extra_credit <- movies %>%
rename(movie_title = Film, release_year = Year) %>%
mutate(Profitability_millions = Profitability * 1e6) %>%
group_by(Genre) %>%
summarize(
average_rating = mean(`Rotten Tomatoes %`, na.rm = TRUE),
average_profitability_millions = mean(Profitability_millions, na.rm = TRUE)
)
head(extra_credit)
## # A tibble: 6 × 3
## Genre average_rating average_profitability_millions
## <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.