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.
Q1
one <- movies %>%
rename(movie_title = Film, release_year = Year)
print("Results for Question 1")
## [1] "Results for Question 1"
print(head(one))
## # 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
two <- one %>%
select(movie_title, release_year, Genre, Profitability, `Rotten Tomatoes %`)
print("Results for Question 2")
## [1] "Results for Question 2"
print(head(two))
## # 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 60
Q3
three <- two %>%
filter(release_year > 2000 & `Rotten Tomatoes %` > 80)
print("Results for Question 3")
## [1] "Results for Question 3"
print(head(three))
## # 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 93
four <- three %>%
mutate(Profitability_millions = Profitability * 1000000)
print("Results for Question 4")
## [1] "Results for Question 4"
print(head(four))
## # 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>
five <- four %>%
arrange(desc(`Rotten Tomatoes %`), desc(Profitability_millions))
print("Results for Question 5")
## [1] "Results for Question 5"
print(head(five))
## # 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>
final <- 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 * 1000000) %>%
arrange(desc(`Rotten Tomatoes %`), desc(Profitability_millions))
print("Results for Question 6")
## [1] "Results for Question 6"
print(head(final))
## # 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>
print("Results for Question 7")
## [1] "Results for Question 7"
based on the data it is common that the best movies based on rotten
tomatoes % are not necessarily the most profitable
extra_credit_summary <- movies %>%
# 1. RENAME columns for clarity (as in original Q1)
rename(movie_title = Film, release_year = Year) %>%
# 2. **DATA CLEANING STEP: CONSOLIDATE GENRES**
# Use mutate + recode to fix the spelling error 'Romence' to 'Romance'
mutate(Genre = recode(Genre, "Romence" = "Romance")) %>%
# 3. CALCULATE Profitability in Millions (as in original Q4)
mutate(Profitability_millions = Profitability * 1000000) %>%
# 4. GROUP by the corrected Genre column
group_by(Genre) %>%
# 5. SUMMARIZE average rating and profitability for each consolidated Genre
summarize(
average_rotten_tomatoes = mean(`Rotten Tomatoes %`, na.rm = TRUE),
average_profitability_millions = mean(Profitability_millions, na.rm = TRUE)
) %>%
# 6. ARRANGE the final output
arrange(desc(average_rotten_tomatoes))
# Print the resulting summary table (first 6 rows)
print(head(extra_credit_summary))
## # A tibble: 6 × 3
## Genre average_rotten_tomatoes average_profitability_millions
## <chr> <dbl> <dbl>
## 1 comedy 87 8096000
## 2 Animation 74.2 3759414.
## 3 Fantasy 73 1783944.
## 4 romance 54 652603.
## 5 Drama 51.5 8407218.
## 6 Romance 45.7 4324784.
print("Results for EXTRA CREDIT (Summary Table):")
## [1] "Results for EXTRA CREDIT (Summary Table):"
print(extra_credit_summary)
## # A tibble: 9 × 3
## Genre average_rotten_tomatoes average_profitability_millions
## <chr> <dbl> <dbl>
## 1 comedy 87 8096000
## 2 Animation 74.2 3759414.
## 3 Fantasy 73 1783944.
## 4 romance 54 652603.
## 5 Drama 51.5 8407218.
## 6 Romance 45.7 4324784.
## 7 Comedy 42.7 3776946.
## 8 Comdy 13 2649068.
## 9 Action 11 1245333.