ABOUT THE DATA
The data had been taken from AutoMobile Company.
​
We have two datasets, “FE2010.csv” and “FE2011.csv”.
The FE2010 data set contains 1107 rows and 10 columns,while FE2011 data set contains 245 rows and 10 columns where Each observation of the data set represents an vehicle giving various characteristics about the vehicle .
Both the data set contains both categorical
and numerical variables.
4 of the 10 variables are numerical where as 6 are considers as categorical variables.
The response variable is
"FE",
representing the Fuel Economy of Vehicles.The datasets contain different estimates of fuel economy for passenger cars and trucks.
​
We will use 2010 dataset for model building.
All our work will be validated on 2011 dataset.
The training data consists of model year 2010 data and the test set is comprised of cars from 2011 that are not in the 2010 data set.