Data Visualization

Exercise 1.

Using data on credit card applications’ status please present the frequency table with the nice, kable format for average monthly credit card expenditures of applicants.

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


tabela4<-Freq(CreditCard$monthly_expenditure,useNA="ifany")

#using frequency_df to make sure that every second column/row will look diffrently
frequency_df <- as.data.frame(tabela4)

tabela4 %>%
kable(col.names = c("Avg Mon_Exp in kUSD  ","Frequency  ","Percentage %  ","Cumulative frequency  ","Cumulative percentage %  ")) %>%
kable_styling(bootstrap_options = "bordered") %>% 
column_spec(seq(1, ncol(frequency_df), by = 2), italic = T, background = "lightgray") %>%
row_spec(seq(1, nrow(frequency_df), by = 2), italic = T, bold = TRUE, background = "darkgray")

Avg Mon_Exp in kUSD	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

Exercise 2.

The data comes from https://flixgem.com/ (dataset version as of March 12, 2021). The data contains information on 9425 movies and series available on Netlix.

Answer with the most appropriate data visualization for the following questions:

1.What is the distribution of Imdb scores for Polish movies and movie-series?

#Reading the database
netflix_data <- read.csv("https://raw.githubusercontent.com/kflisikowski/ds/master/netflix-dataset.csv")

polish <- netflix_data[netflix_data$Languages == "Polish", ]

# Distribution of IMDb scores for Polish movies and movie-series
ggplot(polish) +
  geom_histogram(aes(x = IMDb.Score), fill = "lightgreen", color = "black") +
  scale_x_continuous(breaks = seq(0, 10, by = 0.5)) +
  labs(title = "Distribution of IMDb Scores for Polish Movies and Movie-Series",
       x = "IMDb Scores",
       y = "Amount")

2.What is the density function of Imdb scores for Polish movies and movie-series?

# Filter Polish movies and series
polish_movies <- polish[polish$`Series.or.Movie` == "Movie", ]
polish_series <- polish[polish$`Series.or.Movie` == "Series", ]

# Plot density function separately for movies and series
ggplot() +
  geom_density(data = polish_movies, aes(x = IMDb.Score, fill = "Movie"), alpha = 0.5) +
  geom_density(data = polish_series, aes(x = IMDb.Score, fill = "Series"), alpha = 0.5) +
  labs(title = "Density Function of IMDb Scores for Polish Movies and Series",
       x = "IMDb Scores",
       y = "Density") +
  scale_fill_manual(values = c("darkred", "lightblue"), labels = c("Movie", "Series")) +
  guides(fill = guide_legend(title = "Type"))

3.What are the most popular languages available on Netflix?

# Spliting the data, becouse there can be two or more languages
netflix_data <- netflix_data %>%
  separate_rows(Languages, sep = ", ") %>%
  filter(!is.na(Languages))

# Count occurences of each language
language_counts <- netflix_data %>%
  group_by(Languages) %>%
  summarize(count = n()) %>%
  arrange(desc(count))

# Creating visual reprezentation
ggplot(language_counts[1:10, ], aes(x = reorder(Languages, -count), y = count)) +
  geom_bar(stat = "identity", fill = "pink", color = "black") +
  labs(title = "Top 10 Most Popular Languages on Netflix",
       x = "Language",
       y = "Count") +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

Extra challenge 1

Create a chart showing actors starring in the most popular productions.

#top 25 film by IMDb.Votes
top_films <- netflix_data %>%
  arrange(desc(`IMDb.Votes`)) %>%
  head(25)

# Count occurences of each actor in the top films
actor_counts <- top_films %>%
  filter(!is.na(Actors)) %>%
  separate_rows(Actors, sep = ", ") %>%
  group_by(Actors) %>%
  summarize(count = n()) %>%
  arrange(desc(count))

# create data visualization
ggplot(actor_counts[1:10, ], aes(x = reorder(Actors, -count), y = count)) +
  geom_bar(stat = "identity", fill = "gold", color = "black") +
  labs(title = "Top 10 Actors with most apparencess in 25 most popular productions",
       x = "Actor",
       y = "Count") +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

Extra challenge 2

For movies and series, create rating charts from the various portals (Hidden Gem, IMDb, Rotten Tomatoes, Metacritic). Hint: it’s a good idea to reshape the data to long format.

#resheping data in long format
ratings_long <- netflix_data %>%
  select(-Title, -Languages, -Genre, -TMDb.Trailer, -Trailer.Site, -Poster, -Tags, -Country.Availability, -Runtime, -Director, -Writer, -Actors, -View.Rating, -Awards.Received, -Awards.Nominated.For, -Boxoffice, -Release.Date, -Netflix.Release.Date, -Production.House, -Netflix.Link, -IMDb.Link, -Summary, -IMDb.Votes, -Image) %>%
  pivot_longer(cols = ends_with("Score"), names_to = "Portal", values_to = "Rating") %>%
  mutate(Portal = gsub("Rating.", "", Portal),
         Portal = gsub("\\.", " ", Portal)) %>%  # Replace periods with spaces
  group_by(`Series.or.Movie`, Portal) %>%
  summarize(mean_rating = mean(Rating, na.rm = TRUE)) 

# Create data Visualization
ggplot(ratings_long, aes(x = Portal, y = mean_rating, color = `Series.or.Movie`, group = `Series.or.Movie`)) +
  geom_line() +
  labs(title = "Rating Charts from Various Portals for Movies and Series",
       x = "Portal",
       y = "Mean Rating") +
  theme(axis.text.x = element_text(angle = 45, hjust = 1))

Extra challenge 3

Which film studios produce the most and how has this changed over the years?

netflix_data$Release_Year <- as.integer(format(as.Date(netflix_data$`Release.Date`, format = "%m/%d/%Y"), "%Y"))

filtered_data <- netflix_data %>%
  filter(Production.House != "")

# Group the data by film studio and year, count the number of movies
studio_year_counts <- filtered_data %>%
  filter(!is.na(Release_Year)) %>%  # Filter out rows with missing release year
  group_by(`Production.House`, Release_Year) %>%
  summarize(num_movies = n()) %>%
  ungroup()

# Find the top film studios by total number of movies produced
top_studios <- studio_year_counts %>%
  group_by(`Production.House`) %>%
  summarize(total_movies = sum(num_movies)) %>%
  top_n(10, total_movies)  # Select top 10 studios

# Filter data for top film studios
top_studio_data <- studio_year_counts %>%
  filter(`Production.House` %in% top_studios$`Production.House`)

# Creating data visaulization
ggplot(top_studio_data, aes(x = Release_Year, y = num_movies, color = `Production.House`)) +
  geom_line() +
  labs(title = "Trend of Movie Production by Top Film Studios Over the Years",
       x = "Release Year",
       y = "Number of Movies") +
  theme(legend.position = "right", legend.title = element_blank())

The top studio

total_studio_movies <- studio_year_counts %>%
  group_by(Production.House) %>%
  summarize(total_movies = sum(num_movies)) %>%
  arrange(desc(total_movies))

# Select the top studio
top_studio <- total_studio_movies$Production.House[1]

# Filter data for the top studio
top_studio_data <- studio_year_counts %>%
  filter(Production.House == top_studio)

# Creating data visaulization
ggplot(top_studio_data, aes(x = Release_Year, y = num_movies)) +
  geom_line(color = "purple", size = 1.5) +  # Increase line thickness
  labs(title = paste("Trend of Movie Production for", top_studio, "Over the Years"),
       x = "Release Year",
       y = "Number of Movies") +
  scale_y_continuous(breaks = seq(0, max(top_studio_data$num_movies), by = 0.5))