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”.

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

head(one)

## # 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,

two <- one %>%
  select(movie_title, release_year, Genre, Profitability, 'Rotten Tomatoes %')


head(two)

## # A tibble: 6 × 5
##   movie_title               release_year Genre Profitability `Rotten Tomatoes %`
##   <chr>                            <dbl> <chr>         <dbl>               <dbl>
## 1 Zack and Miri Make a Por…         2008 Roma…          1.75                  64
## 2 Youth in Revolt                   2010 Come…          1.09                  68
## 3 You Will Meet a Tall Dar…         2010 Come…          1.21                  43
## 4 When in Rome                      2010 Come…          0                     15
## 5 What Happens in Vegas             2008 Come…          6.27                  28
## 6 Water For Elephants               2011 Drama          3.08                  60



# 3. filter(): (4 points)
# Filter the dataset to include only movies released after 2000 with a Rotten Tomatoes % higher than 80.


``` r
three <- movies %>% 
  rename(movie_title = Film, release_year = Year) %>% 
  filter(release_year > 2000, 
        `Rotten Tomatoes %`  >80)

head(three)

## # 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.

four <- three %>%
  mutate(Profitability_millions = Profitability / 1e6)

head(four)

## # A tibble: 6 × 9
##   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 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))

five <- four %>%
  arrange(desc(`Rotten Tomatoes %`), desc(Profitability_millions))

head(five)

## # A tibble: 6 × 9
##   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 4 more variables: `Rotten Tomatoes %` <dbl>, `Worldwide Gross` <chr>,
## #   release_year <dbl>, Profitability_millions <dbl>

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(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_df)

## # 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>

Interpret question 6 (1 point)

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

# # The best movies, based on rotten tomato score, are not necessarily the most popular, 
# # based on profitability.For example, the top rated movie "WALL-E" has the highest 
# # rotten tomato score with a low profitability compared to others. This indicates that the best 
# movies critically aren't necessarily the most popular.

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 <-final_df %>%
  group_by(Genre) %>%
  summarize(avg_rating = mean(`Rotten Tomatoes %`, na.rm = TRUE), avg_profitability_millions = mean(Profitability_millions, na.rm = TRUE))
  
summary_df

## # 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

Assignment 3

Billy

2025-02-13

1. rename(): (4 points)

Rename the “Film” column to “movie_title” and “Year” to “release_year”.

2. select(): (4 points)

Create a new dataframe with only the columns: movie_title, release_year, Genre, Profitability,

4. mutate(): (4 points)

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

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))

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.

Interpret question 6 (1 point)

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

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().