linearReg.R

linearReg.R

library(ggplot2)

# Price, Age, KM(kilometers driven), Fuel Type, 
# HP(horsepower), Automatic or Manual, Number of Doors, 
# and Weight in pounds are the data collected in this file for
# Toyota Corollas.

toyota <- read.csv("https://raw.githubusercontent.com/datailluminations/PredictingToyotaPricesBlog/master/ToyotaCorolla.csv")

g <- ggplot(toyota, aes(Price)) 
g <- g + geom_histogram(
                   # binwidth = 25, 
                   bins = 30,
                   col="black", 
                   size=.1)  + 
  labs(
    y="Count", 
    x="Price", 
    caption = "Source: Toyota")

plot(g)

head(toyota)
sapply(toyota, class)
summary(toyota$FuelType)

# Price vs Age

ggplot(toyota,aes(x=Age,y=Price))+
  geom_point()  +
#  geom_smooth(method="loess", se=T) + 
  labs(
    y="Price", 
    x="Age", 
    caption = "Source: toyota")


# Price vs KM
ggplot(toyota,aes(x=KM,y=Price))+
  geom_point()  +
  #  geom_smooth(method="loess", se=T) + 
  labs(
    y="Price", 
    x="KM", 
    caption = "Source: toyota")

# Price vs Metalizado (factor)
ggplot(toyota, aes(x=MetColor, y=Price,color=factor(MetColor))) +
  geom_point(shape=1)

# Price vs HorsePower
ggplot(toyota, aes(x=HP, y=Price)) +
  geom_point(shape=1)


# Price vs Doors
ggplot(toyota, aes(x=Doors, y=Price)) +
  geom_point(shape=1)


linReg <- lm(formula = Price ~ ., data = toyota) 
summary(linReg)


corAgePrice <- cor(toyota$Age, toyota$Price)
corAgePrice

cors <- cor(subset(toyota, select = c(Price, Age, KM, HP, Weight)))
class(cors)

library(ggcorrplot)
# Plot
ggcorrplot(cors, hc.order = TRUE, 
           type = "lower", 
           lab = TRUE, 
           lab_size = 3, 
           method="circle", 
           colors = c("tomato2", "white", "springgreen3"), 
           title="Correlogram of toyota", 
           ggtheme=theme_bw)