library(tidyverse)

## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.1     ✔ tibble    3.2.1
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.0.4     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

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.

1. rename(): (4 points)

Rename the “Film” column to “movie_title” and “Year” to “release_year”.

renamed_movies <- movies %>%
  rename(movie_title = Film , release_year = Year)

head(renamed_movies)

## # 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>

2. select(): (4 points)

Create a new dataframe with only the columns: movie_title, release_year, Genre, Profitability

selected_movies <- renamed_movies %>%
  select(movie_title, release_year, Genre, Profitability)
print(head(selected_movies , 3))

## # A tibble: 3 × 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

3. filter(): (4 points)

Filter the dataset to include only movies released after 2000 with a Rotten Tomatoes % higher than 80.

filtered_movies <- renamed_movies %>%
  filter(`Rotten Tomatoes %` > 80 ,
         release_year > 2000)

head(filtered_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>

4. mutate(): (4 points)

Add a new column called “Profitability_millions” that converts the Profitability to millions of dollars.

mutated_movies <- renamed_movies %>%
  mutate(Profitability_millions = Profitability*1000000)

print(head(mutated_movies))

## # A tibble: 6 × 9
##   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 4 more variables: `Rotten Tomatoes %` <dbl>, `Worldwide Gross` <chr>,
## #   release_year <dbl>, Profitability_millions <dbl>

5. arrange(): (3 points)

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))

arranged_movies <- renamed_movies %>%
  arrange(desc(`Rotten Tomatoes %`),desc(Profitability))

print(head(arranged_movies))

## # A tibble: 6 × 8
##   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 A Serious Man     Drama     Universal                     64          4.38
## # ℹ 3 more variables: `Rotten Tomatoes %` <dbl>, `Worldwide Gross` <chr>,
## #   release_year <dbl>

6. Combining functions: (3 points)

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 <- movies %>%
  rename(movie_title = Film , release_year = Year) %>%
  select(movie_title, release_year, Genre, Profitability, `Rotten Tomatoes %`) %>%
  filter(`Rotten Tomatoes %` > 80 ,
         release_year > 2000) %>%
  mutate(Profitability_millions = Profitability*1000000) %>%
  arrange(desc(`Rotten Tomatoes %`),desc(Profitability))

print(head(combo_movies))

## # 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>

7. Interpret question 6 (1 point)

From the resulting data, are the best movies the most popular?

Based on the data from combo_movies, the movie with the greatest profitability is “Waitress” at $11,089,742. However, it is only the 5th most popular movie in terms of it’s Rotten Tomato percentage of 89%. This shows that the “best movies” (in terms of profitability) do not have to be the most popular (in terms of Rotten Tomatoes).

EXTRA CREDIT (4 points)

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()

summarized_movies <- renamed_movies %>%
  mutate(Genre = str_replace_all(Genre, "Comdy", "Comedy") ,
         Genre = str_replace_all(Genre, "comedy", "Comedy"),
         Genre = str_replace_all(Genre, "Romence", "Romance") ,
         Genre = str_replace_all(Genre, "romance", "Romance") ,
         Profitability_millions = Profitability*1000000) %>% #Replace "Comdy" Romence
  group_by(Genre) %>%
  summarise(avg_rating = mean(`Rotten Tomatoes %`) ,
            avg_profit_millions = mean(Profitability_millions))

summarized_movies

## # A tibble: 6 × 3
##   Genre     avg_rating avg_profit_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.

Assignment 3

Gwendolyn Kardos, Raquel DeLeo

2025-02-10

1. rename(): (4 points)

Rename the “Film” column to “movie_title” and “Year” to “release_year”.

2. select(): (4 points)

Create a new dataframe with only the columns: movie_title, release_year, Genre, Profitability

3. filter(): (4 points)

Filter the dataset to include only movies released after 2000 with a Rotten Tomatoes % higher than 80.

4. mutate(): (4 points)

Add a new column called “Profitability_millions” that converts the Profitability to millions of dollars.

5. arrange(): (3 points)

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))

6. Combining functions: (3 points)

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.

7. Interpret question 6 (1 point)

From the resulting data, are the best movies the most popular?

EXTRA CREDIT (4 points)

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()