# Load necessary 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, unionlibrary(readr)
# Global options
knitr::opts_chunk$set(echo = TRUE)
# Load 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.question_one <- movies %>%
rename(movie_title = Film,
release_year = Year)
head(question_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>question_two <- question_one %>%
select(movie_title, release_year, Genre, Profitability, `Rotten Tomatoes %`)
head(question_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 60question_three <- question_two %>%
filter(release_year > 2000, `Rotten Tomatoes %` > 80)
head(question_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 93question_four <- question_three %>%
mutate(Profitability_millions = Profitability / 1e6)
head(question_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>question_five <- question_four %>%
arrange(desc(`Rotten Tomatoes %`), desc(Profitability_millions))
head(question_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>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>From the resulting data, high Rotten Tomatoes scores do not always equal high profitability — critical acclaim and box-office/Profitability don’t always align.
library(dplyr)
library(stringr)
### EXTRA CREDIT: summary by Genre
extra <- movies %>%
rename(movie_title = Film,
release_year = Year) %>%
mutate(
Profitability_millions = Profitability / 1e6,
# Clean Genre robustly
Genre_clean = str_to_lower(Genre), # lowercase
Genre_clean = str_replace_all(Genre_clean, "[^a-z ]", ""), # remove non-letter characters
Genre_clean = str_trim(Genre_clean), # remove spaces
Genre_clean = ifelse(Genre_clean == "comdey", "Comedy", Genre_clean)
) %>%
group_by(Genre_clean) %>%
summarize(
avg_rating = mean(`Rotten Tomatoes %`, na.rm = TRUE),
avg_profitability = mean(Profitability_millions, na.rm = TRUE)
)
head(extra)## # A tibble: 6 × 3
## Genre_clean avg_rating avg_profitability
## <chr> <dbl> <dbl>
## 1 action 11 0.00000125
## 2 animation 74.2 0.00000376
## 3 comdy 13 0.00000265
## 4 comedy 43.8 0.00000388
## 5 drama 51.5 0.00000841
## 6 fantasy 73 0.00000178