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(): (4 points)
Rename the “Film” column to “movie_title” and “Year” to
“release_year”.
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>
2. select(): (4 points)
Create a new dataframe with only the columns: movie_title,
release_year, Genre, Profitability,
q2 <- movies %>%
select(Film, Year, Genre, Profitability)
head(q2)
## # A tibble: 6 × 4
## Film 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(): (4 points)
Filter the dataset to include only movies released after 2000 with a
Rotten Tomatoes % higher than 80.
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.5.1 ✔ tibble 3.2.1
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1
## ✔ purrr 1.0.4
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
q3 <- movies %>% #then
filter(Year > 2000 & `Rotten Tomatoes %` > 80)
head(q3)
## # A tibble: 6 × 8
## Film Genre `Lead Studio` `Audience score %` Profitability `Rotten Tomatoes %`
## <chr> <chr> <chr> <dbl> <dbl> <dbl>
## 1 WALL… Anim… Disney 89 2.90 96
## 2 Wait… Roma… Independent 67 11.1 89
## 3 Tang… Anim… Disney 88 1.37 89
## 4 Rach… Drama Independent 61 1.38 85
## 5 My W… Drama The Weinstei… 84 0.826 83
## 6 Midn… Rome… Sony 84 8.74 93
## # ℹ 2 more variables: `Worldwide Gross` <chr>, Year <dbl>
4. mutate(): (4 points)
Add a new column called “Profitability_millions” that converts the
Profitability to millions of dollars.
q4 <- movies %>%
mutate(Profitability_millions = 'millions of dollars')
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 <chr>
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 <- movies %>%
arrange(desc(`Rotten Tomatoes %`), desc(Profitability))
6. Combining functions: (3 points)
7. Interpret question 6 (1 point)
From the resulting data, are the best movies the most popular?
no the best movies are not always the most popular
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().
q7 <- movies %>%
mutate(Profitability_millions = Profitability) %>%
group_by(Genre) %>%
summarize(
avg_rating = mean(`Rotten Tomatoes %`, na.rm = TRUE),
avg_profitability_millions = mean(Profitability_millions, na.rm = TRUE))
head(q7)
## # A tibble: 6 × 3
## Genre avg_rating avg_profitability_millions
## <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