Data Visualization

Task 1

First, we load the data

data(CreditCard)

CreditCard <- CreditCard %>% 
  filter(months != 0, card=="yes") %>% 
  mutate(expenses = expenditure / months)

# Create the frequency table
tabela <- Freq(CreditCard$expenses, breaks=seq(0, 500, by=50), na.include = TRUE)

kable(tabela, 
      col.names = c("Avg expen/mth", "Frequency", "Percentage %", "Cumulative frequency", "Cumulative percentage %")) %>%
  kable_styling(bootstrap_options = "striped") %>%
  column_spec(c(3, 5), background = "cornsilk", color="navy")%>%
  column_spec(c(2, 4), background = "navy", color="cornsilk")%>%
  kable_classic(full_width = FALSE, html_font = "Verdana")

Avg expen/mth	Frequency	Percentage %	Cumulative frequency	Cumulative percentage %
[0,50]	937	0.9168297	937	0.9168297
(50,100]	44	0.0430528	981	0.9598826
(100,150]	14	0.0136986	995	0.9735812
(150,200]	12	0.0117417	1007	0.9853229
(200,250]	8	0.0078278	1015	0.9931507
(250,300]	1	0.0009785	1016	0.9941292
(300,350]	0	0.0000000	1016	0.9941292
(350,400]	1	0.0009785	1017	0.9951076
(400,450]	1	0.0009785	1018	0.9960861
(450,500]	4	0.0039139	1022	1.0000000

tabela <- classIntervals(CreditCard$expenses, n=7, style="fixed", fixedBreaks=seq(0,500,by=50))
jenks.tests(tabela)

##        # classes  Goodness of fit Tabular accuracy 
##       10.0000000        0.9490873        0.6426857

Task 2.1

First let’s load the data

download.file("https://raw.githubusercontent.com/kflisikowski/ds/master/netflix-dataset.csv?raw=true", destfile ="dane.csv",mode="wb")
mydata<-read.csv(file="dane.csv",encoding ="UTF-8",header=TRUE,sep = ",")
attach(mydata)

We will consider a movie or series to be polish if it is available in Poland and has Polish subtitles. Now some data wrangling.

movies <- mydata %>% 
  filter(Languages == "Polish")%>%
  filter(Country.Availability == "Poland") %>%
  select( Country.Availability,Languages, Title, IMDb.Score )

ggplot(mydata, aes(IMDb.Score))+
  geom_histogram(binwidth=0.1, fill = "cornsilk", color="navyblue")+
  facet_wrap(vars(Series.or.Movie))

Task 2.2

Now let’s take a look at density.

ggplot(mydata, aes(IMDb.Score), y=after_stat(density), bw=0.5)+
  geom_density( fill = "cornsilk", color="navyblue")+
  facet_wrap(vars(Series.or.Movie))

Task 3.3

new <- mydata %>%
  select(Languages) %>%
  separate_rows(Languages, sep=", ") %>%
  count(Languages, sort=TRUE) %>%
  top_n(10, n)


ggplot(new, aes(x=n, y=fct_reorder(Languages, n)))+
  geom_col()+
  ylab("Language")+
  xlab("How many titles available")

Extra task 1

#Create a chart showing actors starring in the most popular productions.
top_productions<-mydata%>%
  arrange(-IMDb.Votes)%>%
  slice_head(n=50)%>%
  select(Title, Actors)

actors_general<-top_productions%>%
  separate_rows(Actors, sep=", " )%>%
  select(Actors)

top_actors<-actors_general%>%
  count(Actors)%>%
  arrange(-n)%>%
  slice_head(n=10)

top_actors%>%
ggplot(aes(x = Actors, y = n, fill = Actors)) +  
  geom_col(width = 0.7, color = "black") +         
  ylab("Number of Appearances") +
  xlab("Actors") +
  theme_minimal() +                             
  theme(axis.text.x = element_text(angle = 45, hjust = 1, vjust = 1)) +  
  facet_wrap(vars("Top 10 actors starring in the most popular productions(50)"), scales="free")+
  scale_fill_brewer(palette = "Set3")          

Extra task 2

newdata <-mydata %>%
  select(IMDb.Score, Metacritic.Score, Rotten.Tomatoes.Score, Hidden.Gem.Score, Series.or.Movie) %>%

  pivot_longer(cols=c("IMDb.Score", "Metacritic.Score", "Rotten.Tomatoes.Score", "Hidden.Gem.Score"), names_to="Reviewer", values_to="Rating" )
newdata

## # A tibble: 37,700 × 3
##    Series.or.Movie Reviewer              Rating
##    <chr>           <chr>                  <dbl>
##  1 Series          IMDb.Score               7.9
##  2 Series          Metacritic.Score        82  
##  3 Series          Rotten.Tomatoes.Score   98  
##  4 Series          Hidden.Gem.Score         4.3
##  5 Movie           IMDb.Score               5.8
##  6 Movie           Metacritic.Score        69  
##  7 Movie           Rotten.Tomatoes.Score   79  
##  8 Movie           Hidden.Gem.Score         7  
##  9 Movie           IMDb.Score               7.4
## 10 Movie           Metacritic.Score        NA  
## # ℹ 37,690 more rows

ggplot(newdata, aes(x=Rating))+
  geom_histogram()+
  facet_wrap(vars(Reviewer, Series.or.Movie), scales="free")

## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.