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.
1 (Rename) the “Film” column to “movie_title” and “Year” to
“release_year”.
Rename_movies <- movies %>%
rename(movie_title = Film,
release_year = Year)
head(Rename_movies)
## # 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) Create a new dataframe with only the columns:
movie_title, release_year, Genre, Profitability,
selected_movies <- Rename_movies %>%
select(movie_title, release_year, Genre, Profitability)
head(selected_movies)
## # 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
3 Filter the dataset to include only movies released after 2000 with
a Rotten Tomatoes % higher than 80.
filter_movies <- Rename_movies%>%
filter(release_year > 2000, `Rotten Tomatoes %`>80 )
altered_Filtered <- filter_movies %>%
select(`Rotten Tomatoes %`, release_year)
print(altered_Filtered)
## # A tibble: 12 × 2
## `Rotten Tomatoes %` release_year
## <dbl> <dbl>
## 1 96 2008
## 2 89 2007
## 3 89 2010
## 4 85 2008
## 5 83 2011
## 6 93 2011
## 7 91 2007
## 8 85 2011
## 9 93 2007
## 10 84 2011
## 11 89 2009
## 12 87 2009
##used select because these two variables werent showing up in markup
4 Mutate Add a new column called “Profitability_millions” converts
the Profitability to millions of dollars.
mutate_movies <- movies %>%
mutate(Profitability_millions= Profitability * 1000000)
head(mutate_movies)
## # 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>
5 (arrange) by Rotten Tomatoes % in descending order, then
Profitability in descending order. five <- four %>%
arrange(desc(Rotten Tomatoes %) , desc(Profitability_millions))
arrange_movies <- mutate_movies %>%
arrange(desc(`Rotten Tomatoes %`), desc(Profitability_millions))
head(arrange_movies)
## # 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>
6 Combine all
combine_movies <- movies%>%
rename(movie_title = Film,
release_year = Year) %>%
select(movie_title, release_year, Genre, Profitability,`Rotten Tomatoes %`, `Worldwide Gross`)%>%
filter(release_year > 2000, `Rotten Tomatoes %`>80 )%>%
mutate(Profitability_millions= Profitability * 1000000)%>%
arrange(desc(`Rotten Tomatoes %`), desc(Profitability_millions))
head(combine_movies)
## # 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 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 2 more variables: `Worldwide Gross` <chr>, Profitability_millions <dbl>
7 From the resulting data, are the best movies the most
popular?
Ans: There seems to be a correlation based on worldwide gross, as
Walle is number one with the highest gross, but the second highest gross
is in the bottom half of the resulting data.
XC) Create a summary dataframe that shows the average rating and
Profitability_millions for movies by Genre.
summary_movies <- movies%>%
mutate(Genre = recode(Genre,
"Comdy" = "Comedy",
"comedy" = "Comedy",
"Romence" = "Romance",
"romance" = "Romance")) %>%
group_by(Genre)%>%
summarize( AvgRating= mean(`Rotten Tomatoes %`),
AvgProfitability_millions= mean(Profitability * 1000000))
print((summary_movies))
## # A tibble: 6 × 3
## Genre AvgRating AvgProfitability_millions
## <chr> <dbl> <dbl>
## 1 Action 11 1245333.
## 2 Animation 74.2 3759414.
## 3 Comedy 43.0 3851160.
## 4 Drama 51.5 8407218.
## 5 Fantasy 73 1783944.
## 6 Romance 46.3 4079972.