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.“Year” to “release_year”.
q1 <- movies %>%
rename(movie_title = Film, release_year = Year)
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>movie_title, release_year, Genre, Profitability,
q2 <- movies %>%
select(Film, Year, Genre, Profitability)
head(q2)## # A tibble: 6 × 4
## Film 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 3.08released after 2000 with a Rotten Tomatoes % higher than 80.
q3 <- movies %>%
filter(Year > 2000, `Rotten Tomatoes %` > 80)
head(q3)## # A tibble: 6 × 8
## Film Genre `Lead Studio` `Audience score %` Profitability `Rotten Tomatoes %`
## <chr> <chr> <chr> <dbl> <dbl> <dbl>
## 1 WALL… Anim… Disney 89 2.90 96
## 2 Wait… Roma… Independent 67 11.1 89
## 3 Tang… Anim… Disney 88 1.37 89
## 4 Rach… Drama Independent 61 1.38 85
## 5 My W… Drama The Weinstei… 84 0.826 83
## 6 Midn… Rome… Sony 84 8.74 93
## # ℹ 2 more variables: `Worldwide Gross` <chr>, Year <dbl>“Profitability_millions” that converts the Profitability to millions of dollars.
q4 <- movies %>%
mutate(Profitability_millions = Profitability * 1e6)
head (q4)## # A tibble: 6 × 9
## Film Genre `Lead Studio` `Audience score %` Profitability `Rotten Tomatoes %`
## <chr> <chr> <chr> <dbl> <dbl> <dbl>
## 1 Zack… Roma… The Weinstei… 70 1.75 64
## 2 Yout… Come… The Weinstei… 52 1.09 68
## 3 You … Come… Independent 35 1.21 43
## 4 When… Come… Disney 44 0 15
## 5 What… Come… Fox 72 6.27 28
## 6 Wate… Drama 20th Century… 72 3.08 60
## # ℹ 3 more variables: `Worldwide Gross` <chr>, Year <dbl>,
## # Profitability_millions <dbl>% 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
## Film Genre `Lead Studio` `Audience score %` Profitability `Rotten Tomatoes %`
## <chr> <chr> <chr> <dbl> <dbl> <dbl>
## 1 WALL… Anim… Disney 89 2.90 96
## 2 Midn… Rome… Sony 84 8.74 93
## 3 Ench… Come… Disney 80 4.01 93
## 4 Knoc… Come… Universal 83 6.64 91
## 5 Wait… Roma… Independent 67 11.1 89
## 6 A Se… Drama Universal 64 4.38 89
## # ℹ 3 more variables: `Worldwide Gross` <chr>, Year <dbl>,
## # Profitability_millions <dbl>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) %>%
select(movie_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(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>No, The movies with the highest Rotten Tomatos scores are not the most profitable. Therefore the best movies are are not the most
average rating and Profitability_millions for movies by Genre. Hint: You’ll need to use group_by() and summarize().
library(dplyr)
library(stringr)
movies_cleaned <- movies %>%
mutate(
Genre = str_trim(Genre),
Genre = str_to_title(Genre)
) %>%
mutate(
Genre = case_when(
Genre == "Comdy" ~ "Comedy",
Genre == "comedy" ~ "Comedy",
Genre == "Romence" ~ "Romance",
Genre == "romance" ~ "Romance",
TRUE ~ Genre
)
)
q8_cleaned <- movies_cleaned %>%
group_by(Genre) %>%
summarize(
avg_rating = mean(`Rotten Tomatoes %`, na.rm = TRUE),
avg_profitability_millions = mean(Profitability, na.rm = TRUE) / 1e6
)
print(q8_cleaned)## # A tibble: 6 × 3
## Genre avg_rating avg_profitability_millions
## <chr> <dbl> <dbl>
## 1 Action 11 0.00000125
## 2 Animation 74.2 0.00000376
## 3 Comedy 43.0 0.00000385
## 4 Drama 51.5 0.00000841
## 5 Fantasy 73 0.00000178
## 6 Romance 46.3 0.00000408