# Load required 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 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.
# Q1: Rename "Film" to "movie_title" and "Year" to "release_year"
Q1 <- movies %>%
rename(movie_title = Film, release_year = Year)
# Print first 6 rows
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: Select only movie_title, release_year, Genre, Profitability
Q2 <- Q1 %>%
select(movie_title, release_year, Genre, Profitability, `Rotten Tomatoes %`)
# Print first 6 rows
head(Q2)
## # 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 60
# Filter dataset based on release year > 2000 and Rotten Tomatoes % > 80
Q3 <- Q2 %>%
filter(release_year > 2000, `Rotten Tomatoes %` > 80)
# Print first 6 rows
head(Q3)
## # 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 93
# Add a new column "Profitability_millions" (convert to millions)
Q4 <- Q3 %>%
mutate(Profitability_millions = Profitability / 1e6)
# Print first 6 rows
head(Q4)
## # 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 by Rotten Tomatoes % (descending) and then by Profitability (descending)
Q5 <- Q4 %>%
arrange(desc(`Rotten Tomatoes %`), desc(Profitability_millions))
# Print first 6 rows
head(Q5)
## # 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>
# Apply all transformations in one pipeline
Q6 <- 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))
# Print first 6 rows
head(Q6)
## # 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>
# Interpretation
"Based on the resulting dataset, the best-rated movies (high Rotten Tomatoes scores) are not necessarily the most profitable.
Some critically acclaimed films may have lower box office success, while highly profitable films may have mixed reviews."
## [1] "Based on the resulting dataset, the best-rated movies (high Rotten Tomatoes scores) are not necessarily the most profitable. \nSome critically acclaimed films may have lower box office success, while highly profitable films may have mixed reviews."
# Create a summary dataframe that shows the average rating and Profitability_millions for movies by Genre
ExtraCredit <- Q6 %>%
group_by(Genre) %>%
summarize(
avg_rating = mean(`Rotten Tomatoes %`, na.rm = TRUE),
avg_profitability_millions = mean(Profitability_millions, na.rm = TRUE)
)
# Print summary dataframe
ExtraCredit
## # A tibble: 6 × 3
## Genre avg_rating avg_profitability_millions
## <chr> <dbl> <dbl>
## 1 Animation 92.5 0.00000213
## 2 Comedy 89.3 0.00000504
## 3 Drama 85.7 0.00000220
## 4 Romance 87 0.00000554
## 5 Romence 93 0.00000874
## 6 comedy 87 0.00000810