Load the necessary libraries
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.1.) Rename(): (4 points) Rename the “Film” column to “movie_title” and “Year” to “release_year”.
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>2. Select(): (4 points) Create a new data-frame with only the columns: movie_title, release_year, Genre, Profitability,
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 3.083. Filter(): (4 points) Filter the data-set to include only movies released after 2000 with a Rotten Tomatoes % higher than 80.
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>4. Mutate(): (4 points) Add a new column called “Profitability_millions” that converts the Profitability to millions of dollars.
Q3_Cleaned <- Q3 %>%
mutate(`Worldwide Gross` = as.numeric(gsub("[$,]", "", `Worldwide Gross`)),
Profitability = as.numeric(Profitability))
Q4 <- Q3_Cleaned %>%
mutate(Profitability_millions = Profitability * `Worldwide Gross`)
print(head(Q4))## # A tibble: 6 × 9
## movie_title Genre `Lead Studio` `Audience score %` Profitability
## <chr> <chr> <chr> <dbl> <dbl>
## 1 WALL-E Animati… Disney 89 2.90
## 2 Waitress Romance Independent 67 11.1
## 3 Tangled Animati… Disney 88 1.37
## 4 Rachel Getting Married Drama Independent 61 1.38
## 5 My Week with Marilyn Drama The Weinstei… 84 0.826
## 6 Midnight in Paris Romence Sony 84 8.74
## # ℹ 4 more variables: `Rotten Tomatoes %` <dbl>, `Worldwide Gross` <dbl>,
## # release_year <dbl>, Profitability_millions <dbl>5. Arrange(): (3 points) Sort the filtered dataset by Rotten Tomatoes % in descending order, and then by Profitability in descending order. five <- four %>% arrange(desc(Rotten Tomatoes %) , desc(Profitability_millions))
Q5 <- Q4 %>%
arrange(desc(`Rotten Tomatoes %`), desc(Profitability_millions))
print(head(Q5))## # A tibble: 6 × 9
## movie_title Genre `Lead Studio` `Audience score %` Profitability
## <chr> <chr> <chr> <dbl> <dbl>
## 1 WALL-E Animation Disney 89 2.90
## 2 Enchanted Comedy Disney 80 4.01
## 3 Midnight in Paris Romence Sony 84 8.74
## 4 Knocked Up Comedy Universal 83 6.64
## 5 Tangled Animation Disney 88 1.37
## 6 Waitress Romance Independent 67 11.1
## # ℹ 4 more variables: `Rotten Tomatoes %` <dbl>, `Worldwide Gross` <dbl>,
## # release_year <dbl>, Profitability_millions <dbl>6. Combining Functions: (3 points) Use the pipe operator (%>%) to chain these operations together, starting with the original dataset and ending with a final dataframe that incorporates all the above transformations.
Q6 <- movies %>%
rename(movie_title = Film, release_year = Year) %>%
select(movie_title, release_year, Genre, Profitability, `Rotten Tomatoes %`, `Worldwide Gross`) %>%
mutate(`Worldwide Gross` = as.numeric(gsub("[$,]", "", `Worldwide Gross`)),
Profitability = as.numeric(Profitability)) %>%
mutate(Profitability_millions = Profitability * `Worldwide Gross`) %>%
filter(release_year > 2000, `Rotten Tomatoes %` > 80) %>%
arrange(desc(`Rotten Tomatoes %`), desc(Profitability_millions))
print(head(Q6))## # A tibble: 6 × 7
## movie_title release_year Genre Profitability `Rotten Tomatoes %`
## <chr> <dbl> <chr> <dbl> <dbl>
## 1 WALL-E 2008 Animation 2.90 96
## 2 Enchanted 2007 Comedy 4.01 93
## 3 Midnight in Paris 2011 Romence 8.74 93
## 4 Knocked Up 2007 Comedy 6.64 91
## 5 Tangled 2010 Animation 1.37 89
## 6 Waitress 2007 Romance 11.1 89
## # ℹ 2 more variables: `Worldwide Gross` <dbl>, Profitability_millions <dbl>7. Interpret question 6 (1 point) From the resulting data, are the best movies the most popular?
#The best movies, although sometimes, are not always the most popular. For example, 500 days of summer is considered a worse movie than Tangled, Waitress, and A Serious Man, but is still more popular. Also, Enchanted and Midnight in Paris are better movies than Knocked Up, but are not as successful.EXTRA CREDIT (4 points) Create a summary data-frame that shows the average rating and Profitability_millions for movies by Genre. Hint: You’ll need to use group_by() and summarize().
XTRA_cleaned <- movies %>%
rename(movie_title = Film, release_year = Year) %>%
mutate(`Worldwide Gross` = as.numeric(gsub("[$,]", "", `Worldwide Gross`)),
Profitability = as.numeric(Profitability)) %>%
mutate(Profitability_millions = Profitability * `Worldwide Gross`)
XTRA <- XTRA_cleaned %>%
group_by(Genre) %>%
summarize(
average_rating = mean(`Rotten Tomatoes %`, na.rm = TRUE),
average_profitability_millions = mean(Profitability_millions, na.rm = TRUE)
)
print(head(XTRA))## # A tibble: 6 × 3
## Genre average_rating average_profitability_millions
## <chr> <dbl> <dbl>
## 1 Action 11 116.
## 2 Animation 74.2 1021.
## 3 Comdy 13 281.
## 4 Comedy 42.7 894.
## 5 Drama 51.5 1082.
## 6 Fantasy 73 509.