Goal: Build a regression model to predict the average movie rating Click [here for the data] https://github.com/rfordatascience/tidytuesday/tree/master/data/2022/2022-11-01

Import Data

horror_movies <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2022/2022-11-01/horror_movies.csv')

skimr:: skim(horror_movies)
Data summary
Name horror_movies
Number of rows 32540
Number of columns 20
_______________________
Column type frequency:
character 10
Date 1
logical 1
numeric 8
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
original_title 0 1.00 1 191 0 30296 0
title 0 1.00 1 191 0 29563 0
original_language 0 1.00 2 2 0 97 0
overview 1286 0.96 1 1000 0 31020 0
tagline 19835 0.39 1 237 0 12513 0
poster_path 4474 0.86 30 32 0 28048 0
status 0 1.00 7 15 0 4 0
backdrop_path 18995 0.42 29 32 0 13536 0
genre_names 0 1.00 6 144 0 772 0
collection_name 30234 0.07 4 56 0 815 0

Variable type: Date

skim_variable n_missing complete_rate min max median n_unique
release_date 0 1 1950-01-01 2022-12-31 2012-12-09 10999

Variable type: logical

skim_variable n_missing complete_rate mean count
adult 0 1 0 FAL: 32540

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
id 0 1.00 445910.83 305744.67 17 146494.8 426521.00 707534.00 1033095.00 ▇▆▆▅▅
popularity 0 1.00 4.01 37.51 0 0.6 0.84 2.24 5088.58 ▇▁▁▁▁
vote_count 0 1.00 62.69 420.89 0 0.0 2.00 11.00 16900.00 ▇▁▁▁▁
vote_average 0 1.00 3.34 2.88 0 0.0 4.00 5.70 10.00 ▇▂▆▃▁
budget 0 1.00 543126.59 4542667.81 0 0.0 0.00 0.00 200000000.00 ▇▁▁▁▁
revenue 0 1.00 1349746.73 14430479.15 0 0.0 0.00 0.00 701842551.00 ▇▁▁▁▁
runtime 0 1.00 62.14 41.00 0 14.0 80.00 91.00 683.00 ▇▁▁▁▁
collection 30234 0.07 481534.88 324498.16 656 155421.0 471259.00 759067.25 1033032.00 ▇▅▅▅▅

Clean Data

data <- horror_movies %>% 
  
  # Remove unnecessary variables
  
select(-id, -title, -original_language, -overview, -tagline, -release_date, -poster_path, -budget, -revenue, -runtime, -status, -adult, -status, -backdrop_path, -genre_names, -collection, -collection_name) %>%
  
  na.omit() 
  
  skimr:: skim(data)
Data summary
Name data
Number of rows 32540
Number of columns 4
_______________________
Column type frequency:
character 1
numeric 3
________________________
Group variables None

Variable type: character

skim_variable n_missing complete_rate min max empty n_unique whitespace
original_title 0 1 1 191 0 30296 0

Variable type: numeric

skim_variable n_missing complete_rate mean sd p0 p25 p50 p75 p100 hist
popularity 0 1 4.01 37.51 0 0.6 0.84 2.24 5088.58 ▇▁▁▁▁
vote_count 0 1 62.69 420.89 0 0.0 2.00 11.00 16900.00 ▇▁▁▁▁
vote_average 0 1 3.34 2.88 0 0.0 4.00 5.70 10.00 ▇▂▆▃▁

Explore Data

data %>%
  
  ggplot(aes(vote_count, vote_average)) +
  geom_point()

data %>%
  group_by(vote_count, vote_average) %>%
  summarise(mean_group = mean(vote_average)) -> data2

data2 %>%
  ggplot(aes(x= vote_count, y= mean_group,
             color= vote_count, shape= vote_average,
             group = vote_count,
             label = round(mean_group, 2))) +
  scale_shape_binned() +
  geom_point()