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”.
renamed_film <- movies %>%
rename(movie_title= Film, release_year = Year)
head(renamed_film)## # 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,
select_data <- renamed_film %>%
select(movie_title, release_year, Genre, Profitability )
head(select_data)## # 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 tha
filter_movies <- renamed_film %>%
filter(release_year > 2000 & `Rotten Tomatoes %` > 80)
head(filter_movies)## # 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.
profitability_millions <- renamed_film %>%
mutate(Profitability*1,000,000)
head(profitability_millions)## # A tibble: 6 × 10
## 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 5 more variables: `Rotten Tomatoes %` <dbl>, `Worldwide Gross` <chr>,
## # release_year <dbl>, `Profitability * 1` <dbl>, `0` <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))
sorted_movies <- profitability_millions %>%
arrange(desc(`Rotten Tomatoes %`) , desc(profitability_millions))
head(sorted_movies)## # A tibble: 6 × 10
## movie_title Genre `Lead Studio` `Audience score %` Profitability
## <chr> <chr> <chr> <dbl> <dbl>
## 1 WALL-E Animation Disney 89 2.90
## 2 Midnight in Paris Romence Sony 84 8.74
## 3 Enchanted Comedy Disney 80 4.01
## 4 Knocked Up Comedy Universal 83 6.64
## 5 Waitress Romance Independent 67 11.1
## 6 Tangled Animation Disney 88 1.37
## # ℹ 5 more variables: `Rotten Tomatoes %` <dbl>, `Worldwide Gross` <chr>,
## # release_year <dbl>, `Profitability * 1` <dbl>, `0` <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.
final_movies <- 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 * 1,000,000) %>%
arrange(desc(`Rotten Tomatoes %`), desc(Profitability_millions))
head(final_movies)## # A tibble: 6 × 7
## 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 2 more variables: Profitability_millions <dbl>, `0` <dbl>From the resulting data, are the best movies the most popular?
No, not necessarily. Many of the movies with a high rotten tomatoes % do not have a high profitability. Waitress had the highest profitability but an average rotten tomatoes score.
summary_by_genre <- final_movies %>%
group_by(Genre) %>%
summarize(
avg_rating = mean(`Rotten Tomatoes %`, na.rm = TRUE), # Calculate average rating
avg_profitability_millions = mean(Profitability_millions, na.rm = TRUE) # Calculate average profitability in millions
) %>%
arrange(desc(avg_rating)) # Sort by average rating in descending order
# Load necessary libraries
library(dplyr)
library(stringr) # For str_to_title() and str_trim()
# Ensure Profitability_millions exists
final_movies <- final_movies %>%
mutate(Profitability_millions = Profitability * 1000000)
# Clean and standardize Genre names
final_movies_cleaned <- final_movies %>%
mutate(Genre = str_trim(Genre)) %>% # Remove leading/trailing spaces
mutate(Genre = case_when(
tolower(Genre) == "romence" ~ "Romance", # Fix common typos
tolower(Genre) == "romace" ~ "Romance",
tolower(Genre) == "comedy" ~ "Comedy", # Standardize comedy
TRUE ~ str_to_title(Genre) # Capitalize first letter of each word
))
# Create the summary by Genre with cleaned data
summary_by_genre <- final_movies_cleaned %>%
group_by(Genre) %>%
summarize(
avg_rating = mean(`Rotten Tomatoes %`, na.rm = TRUE), # Calculate average rating
avg_profitability_millions = mean(Profitability_millions, na.rm = TRUE) # Calculate average profitability in millions
) %>%
arrange(desc(avg_rating)) # Sort by average rating in descending order
# View the summary dataframe
head(summary_by_genre)## # A tibble: 4 × 3
## Genre avg_rating avg_profitability_millions
## <chr> <dbl> <dbl>
## 1 Animation 92.5 2130856.
## 2 Romance 89 6611482.
## 3 Comedy 88.8 5802503.
## 4 Drama 85.7 2197608.