Implementing linear regression with Python

Let's now go ahead and try to make a simple linear regression model and see what are the issues that we face and how can they be resolved to make the model more robust. We will use the advertising data that we used earlier for illustrating the correlation.

The following two methods implement linear regression in Python:

• The ols method and the statsmodel.formula.api library

• The scikit-learn package

Let's implement a simple linear regression using the first method and then build upon a multiple-linear regression model. We will then also look at how the second method is used to do the same.

Linear regression using the statsmodel library

Let's first import the Advertising data, as shown:

import pandas as pd
advert=pd.read_csv('E:/Personal/Learning/Predictive Modeling Book/Book Datasets/Linear Regression/Advertising.csv')
advert.head()

To reiterate, this dataset contains data about the advertising budget spent on TV, Radio, and Newspapers, for a particular product...