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, unionlibrary(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.Rename the “Film” column to “movie_title” and “Year” to “release_year”.
q1 <- movies %>%
rename( movie_title = Film,
release_year = Year)
head(q1 , 3)## # A tibble: 3 × 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
## # ℹ 3 more variables: `Rotten Tomatoes %` <dbl>, `Worldwide Gross` <chr>,
## # release_year <dbl>Create a new dataframe with only the columns: movie_title, release_year, Genre, Profitability,
q2 <- q1 %>%
select(movie_title, release_year, Genre, Profitability, `Rotten Tomatoes %`)
head(q2, 6)## # 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 60Filter the dataset to include only movies released after 2000 with a Rotten Tomatoes % higher than 80.
q3 <- q2 %>%
filter(release_year > 2000 ,
`Rotten Tomatoes %` > 80)
head(q3, 6)## # 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 93Add a new column called “Profitability_millions” that converts the Profitability to millions of dollars.
q4 <- q3 %>%
mutate(Profitability_millions = Profitability * 1000000)
head(q4, 6)## # 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>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, 6)## # 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>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 %>%
# 1. rename columns
rename(
movie_title = Film,
release_year = Year
) %>%
# 2. select columns (including Rotten Tomatoes)
select(movie_title, release_year, Genre, Profitability, `Rotten Tomatoes %`) %>%
# 3. filter for movies after 2000 with Rotten Tomatoes > 80
filter(release_year > 2000, `Rotten Tomatoes %` > 80) %>%
# 4. add Profitability in millions
mutate(Profitability_millions = Profitability * 1000000) %>%
# 5. arrange by Rotten Tomatoes % descending, then Profitability descending
arrange(desc(`Rotten Tomatoes %`), desc(Profitability_millions))
head(final_df, 6)## # 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>From the resulting data, are the best movies the most popular?
The highest-rated movies (by Rotten Tomatoes %) are not always the most profitable, so the “best” movies are not necessarily the most popular.