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”.

Question1 <- movies %>%  
  rename(movie_title = Film , release_year = Year)

head(Question1)
## # 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,

Question2 <- Question1 %>% 
  select(movie_title, release_year, Genre, Profitability)

head(Question2)
## # 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.

Question3 <- movies %>%  
  filter(Year > 2000 & `Rotten Tomatoes %` > 80)

print(Question3)
## # A tibble: 12 × 8
##    Film                   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>,
## #   Year <dbl>

4. mutate(): (4 points)

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

Question4 <- movies %>% 
  mutate(Profitability_millions = Profitability * 1000000)

head(select(Question4, Profitability, Profitability_millions))
## # A tibble: 6 × 2
##   Profitability Profitability_millions
##           <dbl>                  <dbl>
## 1          1.75               1747542.
## 2          1.09               1090000 
## 3          1.21               1211818.
## 4          0                        0 
## 5          6.27               6267647.
## 6          3.08               3081421.

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))

Question5 <- movies %>%  
  arrange(desc(`Rotten Tomatoes %`), desc(Profitability))

head(select(Question5, `Rotten Tomatoes %`, Profitability))
## # A tibble: 6 × 2
##   `Rotten Tomatoes %` Profitability
##                 <dbl>         <dbl>
## 1                  96          2.90
## 2                  93          8.74
## 3                  93          4.01
## 4                  91          6.64
## 5                  89         11.1 
## 6                  89          4.38

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.

Question6 <- 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 * 1000000) %>%
  arrange(desc(`Rotten Tomatoes %`), desc(Profitability))

head(Question6)
## # A tibble: 6 × 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
## 4 Knocked Up                2007 Comedy             6.64                  91
## 5 Waitress                  2007 Romance           11.1                   89
## 6 A Serious Man             2009 Drama              4.38                  89
## # ℹ 1 more variable: Profitability_millions <dbl>

7. Interpret question 6 (1 point)

From the data, I would suggest that the best movies according to Rotten Tomatoes aren’t necessarily the most popular. There is no positive correlation between Rotten Tomatoes score and profitability.

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_fixed <- Question6 %>% 
  mutate(Genre = tolower(Genre)) %>% 
  mutate(Genre = recode(Genre, "romence" = "romance", "comedy" = "comedy")) %>% 
  group_by(Genre) %>% summarize( avg_rating = mean(`Rotten Tomatoes %`, na.rm = TRUE), 
  avg_profitability_millions = mean(Profitability_millions, na.rm = TRUE) ) 

  print(summary_fixed)
## # A tibble: 4 × 3
##   Genre     avg_rating avg_profitability_millions
##   <chr>          <dbl>                      <dbl>
## 1 animation       92.5                   2130856.
## 2 comedy          88.8                   5802503.
## 3 drama           85.7                   2197608.
## 4 romance         89                     6611482.