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(): (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 (q2)

## # A tibble: 77 × 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 
##  7 WALL-E                                     2008 Animation         2.90 
##  8 Waitress                                   2007 Romance          11.1  
##  9 Waiting For Forever                        2011 Romance           0.005
## 10 Valentine's Day                            2010 Comedy            4.18 
## # ℹ 67 more rows

3. filter(): (4 points)

Filter the dataset to include only movies released after 2000 with a Rotten Tomatoes % higher than 80.

q3 <- q1 %>%
filter(`Rotten Tomatoes %` > 80, release_year > 2000)

head(q3)

## # 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.

q4 <- q3
q4 $Profitability <- as.numeric(gsub("[^0-9.-]", "", q4$Profitability))
q4 $Profitability_millions <- q4$Profitability / 1e+06
print (q4)

## # A tibble: 12 × 9
##    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 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))

q5<-q3 %>% arrange(desc(`Rotten Tomatoes %`), desc(Profitability))
head(q5)

## # A tibble: 6 × 8
##   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 3 more variables: `Rotten Tomatoes %` <dbl>, `Worldwide Gross` <chr>,
## #   release_year <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.

q6 <- movies %>%  
  rename(movie_title = Film, release_year = Year) %>% 
  select(movie_title, release_year, Genre, Profitability, `Rotten Tomatoes %`) %>% 
  filter(`Rotten Tomatoes %` > 80, release_year > 2000) %>% 
  arrange(desc(`Rotten Tomatoes %`), desc(Profitability))
head(q6)

## # A tibble: 6 × 5
##   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

7. Interpret question 6 (1 point)

From the resulting data, are the best movies the most popular?

From the resulting data, Fireproof seems to be the most popular, followed by High School Musical 3: Senior Year, then followed by the Twilight Saga: New Moon. Based off rotten tomatoes, “WALL-E” was the “best” movie, having the highest rating, but it was ranked 35th on profitability. All things considered, the best movies are not the most popular.

8. 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 <- movies %>%
  group_by(Genre) %>%
  summarize(
    avg_Audience_score_pct = mean(`Audience score %`, na.rm = TRUE),
    avg_profitability_millions = mean(Profitability / 1e6, na.rm = TRUE)
  ) %>%
  arrange(desc(avg_Audience_score_pct))

print(summary_df)

## # A tibble: 10 × 3
##    Genre     avg_Audience_score_pct avg_profitability_millions
##    <chr>                      <dbl>                      <dbl>
##  1 Romence                     84                  0.00000874 
##  2 romance                     84                  0.000000653
##  3 Fantasy                     81                  0.00000178 
##  4 comedy                      81                  0.00000810 
##  5 Animation                   70.2                0.00000376 
##  6 Drama                       67.2                0.00000841 
##  7 Romance                     62.8                0.00000398 
##  8 Comdy                       61                  0.00000265 
##  9 Comedy                      61.0                0.00000378 
## 10 Action                      45                  0.00000125