This dataset is been taken from Kaggle and contains 81 Features.
In this is case study, we will use Linear Regression to predict house prices, based on the various different independent variables.
Here we start with cleaning the data. Firstly, it shows large null values in various different features, but as we read the description file, we come to know that these are actually non-null values. Thus, we treat these values and replace them accordingly.
Then we scale our data and start with model building. First, we start with Linear Regression Stats Model and then finally reach to Regularization. We will use all three types of Regularization (Lasso, Ridge & Elastic Net), and then find out the best one.