Apply 1

Goal: The goal of this analysis is to predict the average movie rating (vote_average) Click here for the data.

Import Data

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

• Missing values in overview, collection, and collection name
• Movies with $0 budget

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	▇▂▆▃▁

• How is the target variable distributed?
• Are there any predictors correlated with the target variable?
• Character data should be converted to factor.

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()

# Prepare Data

data_binarized_tbl <- data %>%
  select(-original_title, -popularity) %>%
  binarize()

data_binarized_tbl %>% glimpse()

## Rows: 32,540
## Columns: 6
## $ `vote_count__-Inf_2`   <dbl> 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ vote_count__2_11       <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ vote_count__11_Inf     <dbl> 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,…
## $ `vote_average__-Inf_4` <dbl> 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ vote_average__4_5.7    <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,…
## $ vote_average__5.7_Inf  <dbl> 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,…

#Correlate

data_corr_tbl <- data_binarized_tbl %>%
  correlate( `vote_average__-Inf_4`)

data_corr_tbl

## # A tibble: 6 × 3
##   feature      bin     correlation
##   <fct>        <chr>         <dbl>
## 1 vote_average -Inf_4        1    
## 2 vote_average 4_5.7        -0.588
## 3 vote_average 5.7_Inf      -0.579
## 4 vote_count   -Inf_2        0.575
## 5 vote_count   11_Inf       -0.467
## 6 vote_count   2_11         -0.214

Plot

data_corr_tbl %>%
  plot_correlation_funnel()