wizualizacja-danych/proj1/projekt.R

# Projekt 1: Przygotowanie wizualnej analizy danych z wykorzystaniem podstawowej biblioteki graficznej R i/lub biblioteki ggplot2
# zaladowanie bibliotek
library(Hmisc)
library(dplyr)
library(ggplot2)
library(RColorBrewer)

# zaladowanie danych
german_credit_risk <- read.csv("proj1/german_credit_data.csv", header = TRUE)

# sprawdzenie danych
head(german_credit_risk)
tail(german_credit_risk)
str(german_credit_risk)
summary(german_credit_risk)
describe(german_credit_risk)

# zmiana nazwy pierwszej kolumny
colnames(german_credit_risk)[1] <- "index"

min(german_credit_risk$Age)
na.omit(german_credit_risk)

# violin plot
ggplot(german_credit_risk, aes(x=Purpose, y=Age, fill=Sex)) +
  geom_violin(trim=TRUE, position=position_dodge(1)) +
  stat_summary(fun = mean, geom="point", shape=25, size=2) + #position=position_dodge(.9)
  labs(title="Credit purpose by age", x="Purpose", y = "Age") +
  scale_fill_brewer(palette="Accent") +
  theme_minimal() +
  theme(legend.position="bottom")

# ridge plot
german_credit_risk <- na.omit(german_credit_risk)
ggplot(german_credit_risk, aes(x=Credit.amount,y=Checking.account,fill=Checking.account))+
  geom_density_ridges_gradient(scale = 8, show.legend = TRUE, rel_min_height = 0.00) + theme_ridges() +
  scale_fill_brewer(palette = 4)+
  scale_y_discrete(expand = c(0.01, 0)) +
  scale_x_continuous(expand = c(0.01, 0)) +
  labs(x = "Credit amount [DM]",y = "Checking account", fill="Checking account status") +
  ggtitle("Credit amount density estimation by checking account status ") +
  theme(plot.title = element_text(hjust = 0.5))


ggplot(german_credit_risk, aes(x = Duration, y = Credit.amount, color = Sex)) + 
  geom_point(size = 1.5) + 
  geom_smooth(se = FALSE, size = 1.5) +
  labs(title="Credit amount for credit duration", x="Duration", y = "Amount") +
  theme_minimal() +
  theme(legend.position="bottom")

ggplot(german_credit_risk , aes(x = factor(Job), fill = Purpose)) + 
  geom_bar() +
  scale_x_discrete(breaks = 0:3, labels=c("Unskilled, non-resident", "Unskilled, resident","Skilled","Highly skilled")) +
  labs(title="Credit count and purpose for different job statuses", x="Job status", y = "Credit count") +
  theme_minimal()

#Wykres pudełkowy przedstawiający jakiej wielkości  najczęściej ludzie biorą kredyty na poszczególne cele.
stat_box_data <- function(y) {
  return( 
    data.frame(
      y = max(german_credit_risk$Credit.amount),
      label = paste('count =', length(y), '\n',
                    'sum =', sum(y), '\n')
    )
  )
}

german_credit_risk %>%
  mutate(Purpose = reorder(Purpose, Credit.amount, sum)) %>%
  ggplot(aes(x = Purpose, y = Credit.amount, fill = Purpose)) +
  geom_boxplot(alpha = .7) +
  guides(fill = "none") +
  scale_y_continuous(breaks = scales::pretty_breaks(n = 10)) +
  stat_summary(
    fun.data = stat_box_data,
    geom = "text",
    vjust = 1
  ) +
  ylab("Credit amount") +
  theme_bw()
  
#Histogram przedstawiający ilość wziętych kredytów w zależności od wieku i z przeznaczeniem na co z linią gęstości
german_credit_risk %>%
  ggplot(aes(x=Age, fill = Purpose)) +
  geom_histogram(color = 'white', binwidth = 1) +
  scale_x_continuous(name="Age", breaks = scales::pretty_breaks(n = 10)) +
  ylab('Number of credits') +
  stat_density(aes(x=Age, y=..count..), geom = "line", inherit.aes = FALSE, size = 1.10, color = '#555555', adjust = 1)