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)
print(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)
print(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)
print(q3)
## # A tibble: 12 × 8
##    movie_title            Genre   `Lead Studio` `Audience score %` Profitability
##    <chr>                  <chr>   <chr>                      <dbl>         <dbl>
##  1 WALL-E                 Animat… Disney                        89         2.90 
##  2 Waitress               Romance Independent                   67        11.1  
##  3 Tangled                Animat… 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 
##  7 Knocked Up             Comedy  Universal                     83         6.64 
##  8 Jane Eyre              Romance Universal                     77         0    
##  9 Enchanted              Comedy  Disney                        80         4.01 
## 10 Beginners              Comedy  Independent                   80         4.47 
## 11 A Serious Man          Drama   Universal                     64         4.38 
## 12 (500) Days of Summer   comedy  Fox                           81         8.10 
## # 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.

q4 <- q3 %>% 
  mutate(Profitability_millions = Profitability * 1000000 )
print(select(q4)) 
## # A tibble: 12 × 0

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'))
print(select(q5))
## # A tibble: 12 × 0

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) %>%
  filter(release_year > 2000 & "Rotten Tomatoes %" > 80) %>% 
  mutate(Profitability_millions = Profitability * 1000000 ) %>%
  arrange(desc('Rotten Tomatoes %'), desc('Profitability_millions'))
print(select(q6))
## # A tibble: 77 × 0

7. Interpret question 6 (1 point)

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().

summary_df <- q5 %>%
  group_by(Genre) %>%
  summarize(
    avg_profitability = mean(Profitability_millions, na.rm = TRUE)
  )