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.

Question 1

q1 <- movies %>%
#Rename "film" to "movie_title" and "Year" to "release_year"
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>

Question 2

#select only the movie_title, release_year, Genre, Profitability

movies_2 <- q1 %>%
  select(movie_title, release_year, Genre, Profitability)

print(head(movies_2))
## # 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

Question 3

#filter dataset foir movies with an RT over 80

filtered_movies <-  q1 %>%
  select(movie_title, release_year, Genre, Profitability , `Rotten Tomatoes %`) %>%
filter(release_year > 2000, `Rotten Tomatoes %`> 80)

print(head(filtered_movies))
## # A tibble: 6 × 5
##   movie_title            release_year Genre    Profitability `Rotten Tomatoes %`
##   <chr>                         <dbl> <chr>            <dbl>               <dbl>
## 1 WALL-E                         2008 Animati…         2.90                   96
## 2 Waitress                       2007 Romance         11.1                    89
## 3 Tangled                        2010 Animati…         1.37                   89
## 4 Rachel Getting Married         2008 Drama            1.38                   85
## 5 My Week with Marilyn           2011 Drama            0.826                  83
## 6 Midnight in Paris              2011 Romence          8.74                   93

Question 4

filtered_movies <- filtered_movies %>%
  mutate(Profitability_millions=Profitability/1e6 )
print(select(filtered_movies, Profitability_millions))
## # A tibble: 12 × 1
##    Profitability_millions
##                     <dbl>
##  1            0.00000290 
##  2            0.0000111  
##  3            0.00000137 
##  4            0.00000138 
##  5            0.000000826
##  6            0.00000874 
##  7            0.00000664 
##  8            0          
##  9            0.00000401 
## 10            0.00000447 
## 11            0.00000438 
## 12            0.00000810

Question 5

sorted_movies <- filtered_movies %>%
  arrange(desc(`Rotten Tomatoes %`), desc(Profitability_millions))
print(head(sorted_movies))
## # 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>

Question 6

final_movies <- movies %>%
rename(movies_title = Film, release_year= Year) %>%
select(movies_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(final_movies)
## # A tibble: 6 × 6
##   movies_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>

Question 7

The best movies based on Rotten Tomatoe % are not neccessarily the most popular. For example the movie Twlight:Breaking Dawn has a Rotten Tomato Score of 26, but grossed $702.17 million, while Wall-E who has an almost perfect 96 Rotten Tomato score, but only grossed $521.28 million. The Profitability for Twlight was also higher.

Extra Credit

summary_movies <- final_movies %>%
  group_by(Genre) %>%
  summarise(
    avg_rating = mean(`Rotten Tomatoes %`, na.rm = TRUE),  # Calculate average Rotten Tomatoes %
    avg_profitability_millions = mean(Profitability_millions, na.rm = TRUE)  
  )

# Print the summary dataframe
print(summary_movies)
## # A tibble: 6 × 3
##   Genre     avg_rating avg_profitability_millions
##   <chr>          <dbl>                      <dbl>
## 1 Animation       92.5                 0.00000213
## 2 Comedy          89.3                 0.00000504
## 3 Drama           85.7                 0.00000220
## 4 Romance         87                   0.00000554
## 5 Romence         93                   0.00000874
## 6 comedy          87                   0.00000810