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.
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>
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
q3 <- q1 %>%
filter(release_year > 2000 & `Rotten Tomatoes %` > 80)
print(head(q3))
## # A tibble: 6 × 8
## movie_title Genre `Lead Studio` `Audience score %` Profitability
## <chr> <chr> <chr> <dbl> <dbl>
## 1 WALL-E Animati… Disney 89 2.90
## 2 Waitress Romance Independent 67 11.1
## 3 Tangled Animati… 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
## # ℹ 3 more variables: `Rotten Tomatoes %` <dbl>, `Worldwide Gross` <chr>,
## # release_year <dbl>
q4 <- movies %>%
mutate(Profitability_millions = Profitability / 1e6)
print(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>
q5 <- q4 %>%
arrange(desc(`Rotten Tomatoes %`), Profitability_millions)
print(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 Ench… Come… Disney 80 4.01 93
## 3 Midn… Rome… Sony 84 8.74 93
## 4 Knoc… Come… Universal 83 6.64 91
## 5 Tang… Anim… Disney 88 1.37 89
## 6 A Se… Drama Universal 64 4.38 89
## # ℹ 3 more variables: `Worldwide Gross` <chr>, Year <dbl>,
## # Profitability_millions <dbl>
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 %`), Profitability_millions)
#From the resulting data, are the best movies the most popular? yes the highest movie Wall e has a high audience rate and rotton tomatoes % ### EXTRA CREDIT (4 points) # 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 %>%
group_by(Genre) %>%
summarize(avg_rating = mean(`Rotten Tomatoes %`, na.rm = TRUE),
avg_profitability = mean(Profitability, na.rm = TRUE))
print(head(summary_df))
## # A tibble: 6 × 3
## Genre avg_rating avg_profitability
## <chr> <dbl> <dbl>
## 1 Action 11 1.25
## 2 Animation 74.2 3.76
## 3 Comdy 13 2.65
## 4 Comedy 42.7 3.78
## 5 Drama 51.5 8.41
## 6 Fantasy 73 1.78