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”.
movies1  <- movies %>%  
  rename(movie_title = Film , release_year = Year)

head(movies1)
## # 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
movies2 <- movies1 %>% 
  select(movie_title, release_year, Genre, Profitability)
head(movies2)
## # 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.
movies3 <- movies1 %>%
  filter(release_year > 2000 & `Rotten Tomatoes %` > 80)
head(movies3)
## # 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.
movies4 <- movies3 %>% 
  mutate(Profitability_millions = Profitability * 1000000)
head(movies4)
## # 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` <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))
movies5 <- movies4 %>%
  arrange(desc(`Rotten Tomatoes %`), desc(Profitability_millions))
head(movies5)
## # 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 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 4 more variables: `Rotten Tomatoes %` <dbl>, `Worldwide Gross` <chr>,
## #   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.
movies1 %>%
  filter(release_year > 2000 & `Rotten Tomatoes %` > 80) %>%
  select(movie_title, release_year, Genre, Profitability , `Rotten Tomatoes %`) %>%
  mutate(Profitability_millions = Profitability * 1000000) %>%
  arrange(desc(`Rotten Tomatoes %`), desc(Profitability_millions)) 
## # A tibble: 12 × 6
##    movie_title            release_year Genre   Profitability `Rotten Tomatoes %`
##    <chr>                         <dbl> <chr>           <dbl>               <dbl>
##  1 WALL-E                         2008 Animat…         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
##  7 Tangled                        2010 Animat…         1.37                   89
##  8 (500) Days of Summer           2009 comedy          8.10                   87
##  9 Rachel Getting Married         2008 Drama           1.38                   85
## 10 Jane Eyre                      2011 Romance         0                      85
## 11 Beginners                      2011 Comedy          4.47                   84
## 12 My Week with Marilyn           2011 Drama           0.826                  83
## # ℹ 1 more variable: Profitability_millions <dbl>
  head(movies1)
## # 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>

7. Interpret question 6 (1 point)

First, let’s define the “best movies” as those with the highest Rotten Tomatoes %, and “most popular” as movies with the highest audience score. Given this, it can be concluded that not all of the movies with the highest Rotten Tomatoes % have the highest Audience Score, apart from WALL-E. This means that generally speaking, no - typically the best movies aren’t 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().
movies_extracredit <- movies5 %>%
  mutate(Genre = case_when(Genre == "Romence" ~ "Romance",TRUE ~ Genre)) %>%
  group_by(Genre) %>%
  summarize(average_rating = mean(`Rotten Tomatoes %`, na.rm = TRUE), average_profitability = mean(Profitability_millions, na.rm = TRUE))