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(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
3. filter(): (4 points)
Filter the dataset to include only movies released after 2000 with a
Rotten Tomatoes % higher than 80.
q3 <- q1 %>%
filter(release_year > 2000 & `Rotten Tomatoes %` > 80)
print(q3)
## # A tibble: 12 × 8
## 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 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 <- q1 %>%
mutate(Profitability_millions = Profitability*1000000)
print(q4)
## # A tibble: 77 × 9
## movie_title Genre `Lead Studio` `Audience score %` Profitability
## <chr> <chr> <chr> <dbl> <dbl>
## 1 Zack and Miri Make a Po… Roma… The Weinstei… 70 1.75
## 2 Youth in Revolt Come… The Weinstei… 52 1.09
## 3 You Will Meet a Tall Da… 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
## 7 WALL-E Anim… Disney 89 2.90
## 8 Waitress Roma… Independent 67 11.1
## 9 Waiting For Forever Roma… Independent 53 0.005
## 10 Valentine's Day Come… Warner Bros. 54 4.18
## # ℹ 67 more rows
## # 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 <- q4 %>%
arrange(desc(`Rotten Tomatoes %`), desc(Profitability_millions))
head(q5)
## # 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>
6. Combining functions: (3 points)
7. Interpret question 6 (1 point)
From the resulting data, are the best movies the most popular?
# The best movies are not always the most popular. The movie could be highly rated and not make the most money. An example of this is the movie Wall-E, it is the highest rated movie but did not make as much money as Waitress which happened to have a lower rating.
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 %>%
rename(movie_title = Film, release_year = Year) %>%
mutate(Profitability_millions = Profitability * 1000000) %>%
group_by(Genre) %>% # Group by Genre
summarize(
Average_Rating = mean(`Rotten Tomatoes %`, na.rm = TRUE), # Calculate average rating
Total_Profitability = sum(Profitability_millions, na.rm = TRUE) # Sum profitability
)
# View the summary dataframe
print(summary_df)
## # A tibble: 10 × 3
## Genre Average_Rating Total_Profitability
## <chr> <dbl> <dbl>
## 1 Action 11 1245333.
## 2 Animation 74.2 15037656.
## 3 Comdy 13 2649068.
## 4 Comedy 42.7 154854802.
## 5 Drama 51.5 109293839.
## 6 Fantasy 73 1783944.
## 7 Romance 42.1 51802270.
## 8 Romence 93 8744706.
## 9 comedy 87 8096000
## 10 romance 54 652603.