Project 2

To find the variables to form clusters on
The first default attribute is the price since that is the prime attribute when considering buying cars
In relation to price, city mpg,highway mpg and peak rpm are negatively related but we select highway mpg since it has the highest negative correlation

Then we find the optimal no of clusters

It comes out to be 3

We then implement clustering and plot to scatter plots

The findings are as follows-

We can clearly see that cars in the red cluster have low prices whereas cars in the green cluster have high price

We can clearly see from the graph that cars in the green cluster have high highway mileage whereas cars in the yellow cluster
have average mileage and cars in the red cluster have low mileage