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

one <- movies %>%
  rename(movie_title = Film,
         release_year = Year)
head(one, 3)

## # A tibble: 3 × 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
## # ℹ 3 more variables: `Rotten Tomatoes %` <dbl>, `Worldwide Gross` <chr>,
## #   release_year <dbl>

2. Select

two <- one %>%
  select(movie_title, release_year, Genre, Profitability)
head(two, 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

three <- one %>%
  select(movie_title, release_year, Genre, Profitability, `Rotten Tomatoes %`) %>%
  filter(release_year > 2000, `Rotten Tomatoes %` > 80) 
head(three, 3)

## # A tibble: 3 × 5
##   movie_title release_year Genre     Profitability `Rotten Tomatoes %`
##   <chr>              <dbl> <chr>             <dbl>               <dbl>
## 1 WALL-E              2008 Animation          2.90                  96
## 2 Waitress            2007 Romance           11.1                   89
## 3 Tangled             2010 Animation          1.37                  89

4. Mutate

four <- three %>%
  mutate(Profitability_millions = Profitability / 1e6)
head(four, 3)

## # A tibble: 3 × 6
##   movie_title release_year Genre     Profitability `Rotten Tomatoes %`
##   <chr>              <dbl> <chr>             <dbl>               <dbl>
## 1 WALL-E              2008 Animation          2.90                  96
## 2 Waitress            2007 Romance           11.1                   89
## 3 Tangled             2010 Animation          1.37                  89
## # ℹ 1 more variable: Profitability_millions <dbl>

5. Arrange

five <- four %>%
  arrange(desc(`Rotten Tomatoes %`), desc(Profitability_millions))
head(five, 3)

## # A tibble: 3 × 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
## # ℹ 1 more variable: Profitability_millions <dbl>

6. Combining Functions

six <- 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(six, 3)

## # A tibble: 3 × 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
## # ℹ 1 more variable: Profitability_millions <dbl>

Interpret

The best movies are not always the most popular. Some movies with good ratings generate moderate profits compared to lower-rated films. Popularity and quality are not always correlated.

Extra Credit

six <- six %>%
  mutate(
    Genre = ifelse(Genre == "Romence", "Romance", Genre),
    Genre = ifelse(Genre == "romance", "Romance", Genre),
    Genre = ifelse(Genre == "comedy", "Comedy", Genre)
  )

extra_credit <- six %>%
  group_by(Genre) %>%
  summarize(
    avg_rating = mean(`Rotten Tomatoes %`, na.rm = TRUE),
    avg_profitability_millions = mean(Profitability_millions, na.rm = TRUE)
  )
head(extra_credit)

## # A tibble: 4 × 3
##   Genre     avg_rating avg_profitability_millions
##   <chr>          <dbl>                      <dbl>
## 1 Animation       92.5                 0.00000213
## 2 Comedy          88.8                 0.00000580
## 3 Drama           85.7                 0.00000220
## 4 Romance         89                   0.00000661