Assignment 3

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,

q2 <- q1 %>%
  select(movie_title, release_year, Genre, Profitability)
head(q2)

## # 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            3.08

3. filter(): (4 points)

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

q3 <- q1 %>%
  filter(release_year > 2000, `Rotten Tomatoes %` > 80)
head(q3)

## # 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.

q3_Cleaned <- q3 %>% 
  mutate(`Worldwide Gross` = as.numeric(gsub("[$,]", "", `Worldwide Gross`)), 
         Profitability = as.numeric(Profitability))

q4 <- q3_Cleaned %>% 
  mutate(Profitability_millions = Profitability * `Worldwide Gross`)

(head(q4))

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

q5 <- q4 %>%
  arrange(desc(`Rotten Tomatoes %`), desc(Profitability_millions))

head(q5)

## # A tibble: 6 × 9
##   movie_title       Genre     `Lead Studio` `Audience score %` Profitability
##   <chr>             <chr>     <chr>                      <dbl>         <dbl>
## 1 WALL-E            Animation Disney                        89          2.90
## 2 Enchanted         Comedy    Disney                        80          4.01
## 3 Midnight in Paris Romence   Sony                          84          8.74
## 4 Knocked Up        Comedy    Universal                     83          6.64
## 5 Tangled           Animation Disney                        88          1.37
## 6 Waitress          Romance   Independent                   67         11.1 
## # ℹ 4 more variables: `Rotten Tomatoes %` <dbl>, `Worldwide Gross` <dbl>,
## #   release_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.

q6 <- movies %>% 
  rename(movie_title = Film, release_year = Year) %>% 
  select(movie_title, release_year, Genre, Profitability, `Rotten Tomatoes %`, `Worldwide Gross`) %>%
  mutate(`Worldwide Gross` = as.numeric(gsub("[$,]", "", `Worldwide Gross`)),  
         Profitability = as.numeric(Profitability)) %>% 
  mutate(Profitability_millions = Profitability * `Worldwide Gross`) %>% 
  filter(release_year > 2000, `Rotten Tomatoes %` > 80) %>% 
  arrange(desc(`Rotten Tomatoes %`), desc(Profitability_millions))
(head(q6))

## # 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 Enchanted                 2007 Comedy             4.01                  93
## 3 Midnight in Paris         2011 Romence            8.74                  93
## 4 Knocked Up                2007 Comedy             6.64                  91
## 5 Tangled                   2010 Animation          1.37                  89
## 6 Waitress                  2007 Romance           11.1                   89
## # ℹ 2 more variables: `Worldwide Gross` <dbl>, Profitability_millions <dbl>

7. Interpret question 6 (1 point)

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

The movies with the highest Rotten Tomatoes scores (such as WALL-E and Midnight in Paris) are indeed among the most well-received critically, but they are not always the most profitable. In this dataset, movies like ‘Waitress’ with a lower Rotten Tomatoes score have significantly higher profitability, showing that critical acclaim doesn’t always correlate with commercial success.

EXTRA CREDIT (4 points) Create a summary data-frame that shows the average rating and Profitability_millions for movies by Genre. Hint: You’ll need to use group_by() and summarize().

XTRA_cleaned <- movies %>% rename(movie_title = Film, release_year = Year) %>% mutate(Worldwide Gross = parse_number(Worldwide Gross), # Convert to numeric safely Profitability = as.numeric(Profitability)) %>% mutate(Profitability_millions = Worldwide Gross / 1e6) # Convert to millions

XTRA <- XTRA_cleaned %>% group_by(Genre) %>% summarize( average_rating = mean(Rotten Tomatoes %, na.rm = TRUE), average_profitability_millions = mean(Profitability_millions, na.rm = TRUE) )

head(XTRA)