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.

1. rename(): (4 points)

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

q1  <- movies %>%
  rename(movie_title = Film , release_year = Year)

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>

2. select(): (4 points)

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

movies_selected <- movies %>%
  select(Film, Year, Genre, Profitability )

head(movies_selected)

## # A tibble: 6 × 4
##   Film                                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

3. filter(): (4 points)

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

movies_filtered <- movies %>%
  filter(Year > 2000 ,  `Rotten Tomatoes %` > 80)

head(movies_filtered)

## # A tibble: 6 × 8
##   Film  Genre `Lead Studio` `Audience score %` Profitability `Rotten Tomatoes %`
##   <chr> <chr> <chr>                      <dbl>         <dbl>               <dbl>
## 1 WALL… Anim… Disney                        89         2.90                   96
## 2 Wait… Roma… Independent                   67        11.1                    89
## 3 Tang… Anim… Disney                        88         1.37                   89
## 4 Rach… Drama Independent                   61         1.38                   85
## 5 My W… Drama The Weinstei…                 84         0.826                  83
## 6 Midn… Rome… Sony                          84         8.74                   93
## # ℹ 2 more variables: `Worldwide Gross` <chr>, Year <dbl>

4. mutate(): (4 points)

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

q4 <- movies %>%
  mutate(Profitability_millions = Profitability * 1000)

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>

5. arrange(): (3 points)

Sort the filtered dataset by Rotten Tomatoes % in descending order, and then by Profitability in descending order.

five <- q4 %>%
  arrange(desc(`Rotten Tomatoes %`), desc(Profitability_millions))

head(five)

## # A tibble: 6 × 9
##   Film  Genre `Lead Studio` `Audience score %` Profitability `Rotten Tomatoes %`
##   <chr> <chr> <chr>                      <dbl>         <dbl>               <dbl>
## 1 WALL… Anim… Disney                        89          2.90                  96
## 2 Midn… Rome… Sony                          84          8.74                  93
## 3 Ench… Come… Disney                        80          4.01                  93
## 4 Knoc… Come… Universal                     83          6.64                  91
## 5 Wait… Roma… Independent                   67         11.1                   89
## 6 A Se… Drama Universal                     64          4.38                  89
## # ℹ 3 more variables: `Worldwide Gross` <chr>, Year <dbl>,
## #   Profitability_millions <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.

final_movies <- movies %>%
  filter(Year > 2000 ,  `Rotten Tomatoes %` > 80) %>%
  select(Film, Year, Genre, Profitability, `Rotten Tomatoes %`) %>%
  mutate(Profitability_millions = Profitability * 1000) %>%
  arrange(desc('Rotten Tomatoes %'), desc(Profitability_millions))

head(final_movies)

## # A tibble: 6 × 6
##   Film       Year Genre Profitability `Rotten Tomatoes %` Profitability_millions
##   <chr>     <dbl> <chr>         <dbl>               <dbl>                  <dbl>
## 1 Waitress   2007 Roma…         11.1                   89                 11090.
## 2 Midnight…  2011 Rome…          8.74                  93                  8745.
## 3 (500) Da…  2009 come…          8.10                  87                  8096 
## 4 Knocked …  2007 Come…          6.64                  91                  6636.
## 5 Beginners  2011 Come…          4.47                  84                  4472.
## 6 A Seriou…  2009 Drama          4.38                  89                  4383.

7. Interpret question 6 (1 point)

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

No, the best movies are not always the most popular. Based on the data there are movies that are more profitable with a lower rotten tomatoes score than movies that are less profitable.

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().

Assignment 3

Ronan Curry and Tom Short

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.

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().