wizualizacja-danych/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("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")


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()