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)