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(select(q4, movie_title, Profitability, Profitability_millions))
## # A tibble: 77 × 3
## movie_title Profitability Profitability_millions
## <chr> <dbl> <dbl>
## 1 Zack and Miri Make a Porno 1.75 1747542.
## 2 Youth in Revolt 1.09 1090000
## 3 You Will Meet a Tall Dark Stranger 1.21 1211818.
## 4 When in Rome 0 0
## 5 What Happens in Vegas 6.27 6267647.
## 6 Water For Elephants 3.08 3081421.
## 7 WALL-E 2.90 2896019.
## 8 Waitress 11.1 11089742.
## 9 Waiting For Forever 0.005 5000
## 10 Valentine's Day 4.18 4184038.
## # ℹ 67 more rows
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 <- q1 %>%
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) %>%
filter(release_year > 2000 & `Rotten Tomatoes %` > 80) %>%
arrange (desc(`Rotten Tomatoes %`), desc(Profitability)) %>%
select(movie_title, release_year, Genre, Profitability , `Rotten Tomatoes %`) %>%
mutate(Profitability_millions = Profitability * 1000000)
head(q6)
## # 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>
7. Interpret question 6 (1 point)
From the resulting data, are the best movies the most popular?
- Not necessarily. The fifth best movie has the highest profitability
while the best rated movie has a low profitability compared to other
movies