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.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># Load dplyr package
library(dplyr)
# Assuming df is your original dataframe
q2 <- q1 %>% select(movie_title, release_year, Genre, Profitability)
# Print first few rows
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 3.08library(dplyr)
# Assuming df is your original dataframe
filtered_q3 <- q1 %>%
filter(release_year > 2000, `Rotten Tomatoes %` > 80)
# Print first few rows
head(filtered_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>library(dplyr)
q4 <- filtered_q3 %>%
mutate(Profitability_millions = Profitability / 1e6)
head(q4)## # A tibble: 6 × 9
## 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 4 more variables: `Rotten Tomatoes %` <dbl>, `Worldwide Gross` <chr>,
## # release_year <dbl>, Profitability_millions <dbl>q5 <- q4 %>%
mutate(
`Rotten Tomatoes %` = as.numeric(`Rotten Tomatoes %`), # Ensure numeric Rotten Tomatoes %
Profitability_millions = as.numeric(Profitability_millions) # Ensure numeric Profitability
) %>%
arrange(desc(`Rotten Tomatoes %`), desc(Profitability_millions)) # Sort in descending order
# Print first 6 rows
head(q5)## # A tibble: 6 × 9
## 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 4 more variables: `Rotten Tomatoes %` <dbl>, `Worldwide Gross` <chr>,
## # release_year <dbl>, Profitability_millions <dbl>library(dplyr)
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))
# Print first 6 rows of q6 to confirm it exists
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, because some movies with a lower rotten Tomatoes score have a higher profitability, suggesting that a high Rotten Tomatoes score does not guarantee popularity.
# Standardize Genre names
movies_clean <- movies %>%
mutate(Genre = ifelse(Genre == "Romence", "Romance", Genre))
# Create summary dataframe by Genre
genre_summary_full <- movies_clean %>%
group_by(Genre) %>%
summarize(
avg_rating = mean(`Rotten Tomatoes %`, na.rm = TRUE),
avg_profitability_millions = mean(Profitability / 1e6, na.rm = TRUE)
) %>%
arrange(desc(avg_rating)) # Sort by highest avg rating
# Print the summary
print(genre_summary_full)## # A tibble: 9 × 3
## Genre avg_rating avg_profitability_millions
## <chr> <dbl> <dbl>
## 1 comedy 87 0.00000810
## 2 Animation 74.2 0.00000376
## 3 Fantasy 73 0.00000178
## 4 romance 54 0.000000653
## 5 Drama 51.5 0.00000841
## 6 Romance 45.7 0.00000432
## 7 Comedy 42.7 0.00000378
## 8 Comdy 13 0.00000265
## 9 Action 11 0.00000125