library(dplyr) library(readr)

movies <- read_csv(“https://gist.githubusercontent.com/tiangechen/b68782efa49a16edaf07dc2cdaa855ea/raw/0c794a9717f18b094eabab2cd6a6b9a226903577/movies.csv”)

  1. rename(): (4 points) Rename the “Film” column to “movie_title” and “Year” to “release_year”.
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)

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.
q1 <- movies %>%
  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>

2. (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)

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
  1. filter(): (4 points) # Filter the dataset to include only movies released after 2000 with a Rotten Tomatoes % higher than 80.
q3 <- movies %>%  
  filter(Year>2000 & `Rotten Tomatoes %`>80)

4. mutate(): (4 points)

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

q4 <- movies %>% 
  mutate(profitability_millions = Profitability*1000000)
head(select(q4, 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))

q5 <- q4 %>% 
  arrange(desc(`Rotten Tomatoes %`),desc(profitability_millions))

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.

final_df <- 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_millions))

head(final_df) 
## # 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>
  1. Interpret question 6 (1 point) # From the resulting data, are the best movies the most popular? # No since the best movie based on profitability was 11089742 but it was the fifth popular movie