toyota-mlr.R

###########################
# Identify the question
###########################
Identify the question you are trying to solve

# Which car is the most undervalued?
# Are we trying to maximize or minimize a variable?

###########################
# Understand the data
###########################

# Understand what they variables mean

# Variable          = Description
# Id                = Record_ID
# Model             = Model Description
# Price	            = Offer Price in EUROs
# Age_08_04	        = Age in months as in August 2004
# Mfg_Month         =	Manufacturing month (1-12)
# Mfg_Year	        = Manufacturing Year
# KM	              = Accumulated Kilometers on odometer
# Fuel_Type	        = Fuel Type (Petrol, Diesel, CNG)
# HP	              = Horse Power
# Met_Color	        = Metallic Color?  (Yes=1, No=0)
# Color	            = Color (Blue, Red, Grey, Silver, Black, etc.)
# Automatic	        = Automatic ( (Yes=1, No=0)
# CC	              = Cylinder Volume in cubic centimeters
# Doors	            = Number of doors
# Cylinders	        = Number of cylinders
# Gears	            = Number of gear positions
# Quarterly_Tax	    = Quarterly road tax in EUROs
# Weight	          = Weight in Kilograms
# Mfr_Guarantee	    = Within Manufacturer's Guarantee period  (Yes=1, No=0)
# BOVAG_Guarantee	  = BOVAG (Dutch dealer network) Guarantee  (Yes=1, No=0)
# Guarantee_Period	= Guarantee period in months
# ABS	              = Anti-Lock Brake System (Yes=1, No=0)
# Airbag_1          = Driver_Airbag  (Yes=1, No=0)
# Airbag_2	        = Passenger Airbag  (Yes=1, No=0)
# Airco	            = Airconditioning  (Yes=1, No=0)
# Automatic_airco	  = Automatic Airconditioning  (Yes=1, No=0)
# Boardcomputer	    = Boardcomputer  (Yes=1, No=0)
# CD_Player	        = CD Player  (Yes=1, No=0)
# Central_Lock	    = Central Lock  (Yes=1, No=0)
# Powered_Windows	  = Powered Windows  (Yes=1, No=0)
# Power_Steering	  = Power Steering  (Yes=1, No=0)
# Radio	            = Radio  (Yes=1, No=0)
# Mistlamps	        = Mistlamps  (Yes=1, No=0)
# Sport_Model	      = Sport Model  (Yes=1, No=0)
# Backseat_Divider	= Backseat Divider  (Yes=1, No=0)
# Metallic_Rim	    = Metallic Rim  (Yes=1, No=0)
# Radio_cassette	  = Radio Cassette  (Yes=1, No=0)
# Parking_Assistant	= Parking assistance system  (Yes=1, No=0)
# Tow_Bar	          = Tow Bar  (Yes=1, No=0)

###########################
# Explore the data
###########################

# set working directory to be next to data
raw.data <- read.csv('toyota-corolla.csv')

View(raw.data)
# What types of variables are in this data set?
str(raw.data)

# We won't be able to use all of these variables why?
plot(raw.data$Price ~ raw.data$Mfg_Year)
subset <- raw.data[,c(3:7)]
plot(subset)
plot(subset$KM ~ subset$Age_08_04)
# What can we learn from this correlation?
plot(subset$Price ~ subset$KM)
# What can we learn from this?
plot(subset)
plot(subset$Age_08_04 ~ subset$Mfg_Year)
plot(subset$Age_08_04 ~ subset$Mfg_Month)
# can we learn anything from this data?
plot(subset)

subset <- raw.data[,c(3:4,7,9,13:18)]
plot(subset)

# Run one linear regression
plot(subset$Price ~ subset$KM)
price_km_linear_regression <- lm(subset$Price ~ subset$KM)
# Plot this line on the graph
abline(price_km_linear_regression, col = "red")
summary(price_km_linear_regression)
# What do all of these numbers mean?
# Intercept?
# subset$KM Estimate
# Multiple R-squared
# 32% explained by 

plot(price_km_linear_regression)

mlr.2factors <- lm(subset$Price ~ subset$KM + subset$Weight)
summary(mlr.2factors)

mlr.2factors <- lm(subset$Price ~ subset$KM + subset$Age_08_04)
summary(mlr.2factors)

mlr.3factors <- lm(subset$Price ~ subset$KM + subset$Age_08_04 + subset$Weight)
summary(mlr.3factors)
# Why weight?

# Run an MLR
mlr.allfactors <- lm(subset$Price ~ 
                  subset$KM + 
                  subset$Age_08_04 + 
                  subset$HP + 
                  subset$CC + 
                  subset$Doors + 
                  subset$Cylinders +
                  subset$Gears + 
                  subset$Quarterly_Tax + 
                  subset$Weight
                )
summary(mlr.allfactors)

# How many factors do we need to get the most accurate MLR?
# How do we identify which ones give the most predictive power?

mlr.4factors <- lm(subset$Price ~ subset$KM + subset$Age_08_04 + subset$HP + subset$Weight)
summary(mlr.4factors)

# Are the extra factors worth it? 
# .8614 - 4 factors
# .863  - All factors

# How do we calculate the predicted vs actual

coef(mlr.4factors)
plot(density(resid(mlr.4factors)))
resid(mlr.4factors)
subset["residual"] <- resid(mlr.4factors)
new_data = data.frame(KM=1000, Age_08_04=15, HP=100, Weight=1200)