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.
1. rename(): (4 points)
Rename the “Film” column to “movie_title” and “Year” to
“release_year”.
question1 <- movies %>%
rename(movie_title = Film , release_year = Year)
head(question1)
## # 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,
question2 <- question1 %>%
select(movie_title, release_year, Genre, Profitability)
head(question2)
## # 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.
question3 <- question1 %>%
select(movie_title, release_year, Genre, Profitability , `Rotten Tomatoes %`) %>%
filter(release_year > 2000, `Rotten Tomatoes %`> 80)
head(question3)
## # A tibble: 6 × 5
## movie_title release_year Genre Profitability `Rotten Tomatoes %`
## <chr> <dbl> <chr> <dbl> <dbl>
## 1 WALL-E 2008 Animati… 2.90 96
## 2 Waitress 2007 Romance 11.1 89
## 3 Tangled 2010 Animati… 1.37 89
## 4 Rachel Getting Married 2008 Drama 1.38 85
## 5 My Week with Marilyn 2011 Drama 0.826 83
## 6 Midnight in Paris 2011 Romence 8.74 93
4. mutate(): (4 points)
Add a new column called “Profitability_millions” that converts the
Profitability to millions of dollars.
question4 <- question3 %>%
mutate(Profitability_millions = Profitability / 1e6)
head(question4)
## # A tibble: 6 × 6
## movie_title release_year Genre Profitability `Rotten Tomatoes %`
## <chr> <dbl> <chr> <dbl> <dbl>
## 1 WALL-E 2008 Animati… 2.90 96
## 2 Waitress 2007 Romance 11.1 89
## 3 Tangled 2010 Animati… 1.37 89
## 4 Rachel Getting Married 2008 Drama 1.38 85
## 5 My Week with Marilyn 2011 Drama 0.826 83
## 6 Midnight in Paris 2011 Romence 8.74 93
## # ℹ 1 more variable: 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))
question5 <- question4 %>%
arrange(desc(`Rotten Tomatoes %`), desc(Profitability_millions))
head(question5)
## # 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>
6. Combining functions: (3 points)
7. Interpret question 6 (1 point)
From the resulting data, are the best movies the most popular?
# The results of the data set show that high Rotten Tomatoes do not align
# with the highest profitability. Qualtiy and profitability do not necessarily
# align. Some of the best films are not always the most financially successful.
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().
extra <- final %>%
group_by(Genre) %>%
summarize(avg_rating = mean(`Rotten Tomatoes %`, na.rm = TRUE), avg_profitability_millions = mean(Profitability_millions, na.rm = TRUE), n_movies = n()) %>% arrange(desc(avg_rating)) %>% ungroup()
head(extra)
## # A tibble: 6 × 4
## Genre avg_rating avg_profitability_millions n_movies
## <chr> <dbl> <dbl> <int>
## 1 Romence 93 0.00000874 1
## 2 Animation 92.5 0.00000213 2
## 3 Comedy 89.3 0.00000504 3
## 4 Romance 87 0.00000554 2
## 5 comedy 87 0.00000810 1
## 6 Drama 85.7 0.00000220 3