Homework No.3

Describe Your Data:

  1. Chose 4 simple visualization methods (boxplot must be included) for your data visualization.
  2. Present and upload your results.

1. Boxplots

ggplot(insurance_data, aes(x = CAR_TYPE, y = BLUEBOOK, fill = CAR_TYPE)) +  
  ggtitle("Distribution of Value of  Vechles by Vechles types") + 
  geom_boxplot(outlier.colour="black",outlier.shape=16,outlier.size=3, notch=F) + 
  labs(x = "", y = "Value, $", fill = "Car type") +
  theme_minimal()


Komentaras

2. Scater plot

ggplot(insurance_data, aes(x=HOME_VAL, y=INCOME)) +
  geom_point() +  labs(title = "Relation between Home value, Year Income",  x = "Home value, $", y = "Yeary Income, $") + 
  theme_light()

ggplot(insurance_data, aes(x=HOME_VAL, y=INCOME, color=URBANICITY)) +
  geom_point()  + geom_smooth(method=lm, se=FALSE, fullrange=TRUE) + labs(title = "Relation between Home value, Year Income and Urbanicity",  x = "Home value, $", y = "Yeary Income, $")
## `geom_smooth()` using formula 'y ~ x'


Komentaras

3. Pie chart

data2 <- as.data.frame(table(insurance_data$URBANICITY))
data2 <- data2 %>% 
  arrange(desc(Var1)) %>%
  mutate(prop = Freq / sum(data2$Freq) *100) %>%
  mutate(ypos = cumsum(Freq)- 0.5*Freq )
data2$proc <- paste0(round(data2$prop,1),"%")

ggplot(data2, aes(x="", y=Freq, fill=Var1)) +
  geom_bar(stat="identity", width=1, color="white") +
  coord_polar("y", start=0) +
  theme_void() + 
  geom_text(aes(y = ypos, label = Freq), color = "white", size=6) +
  scale_fill_brewer(palette="Dark2", name = "URBANICITY") + 
  labs(title = "Percentage of CUSTUMERS who did  car accidents form Urban or Rural areas") 

data1 <- as.data.frame(table(insurance_data$URBANICITY))
data1 <- data1 %>% 
  arrange(desc(Var1)) %>%
  mutate(prop = Freq / sum(data1$Freq) *100) %>%
  mutate(ypos = cumsum(prop)- 0.5*prop )
data1$proc <- paste0(round(data1$prop,1),"%")

ggplot(data1, aes(x="", y=prop, fill=Var1)) +
  geom_bar(stat="identity", width=1, color="white") +
  coord_polar("y", start=0) +
  theme_void() + 
  geom_text(aes(y = ypos, label = proc), color = "white", size=6) +
  scale_fill_brewer(palette="Dark2", name = "URBANICITY") + 
  labs(title = "Percentage of CUSTUMERS who did  car accidents form Urban or Rural areas")


Komentaras

4. Bar plot

ggplot(insurance_data, aes(x=EDUCATION, y=REPEAT5, fill=EDUCATION)) +
  geom_bar(stat="identity") + 
  labs(title = "Number of drivers by different groups of Education",
       x = "Education level", y = "Count") + 
  theme_light()

ggplot(insurance_data, aes(x=reorder(EDUCATION, -table(EDUCATION)[EDUCATION]), y=REPEAT5, fill=EDUCATION)) +
  geom_bar(stat="identity") + 
  labs(title = "Number of drivers by different groups of Education",
       x = "Education level", y = "Count") + 
  theme_light()


Komentaras