Logistic Regression Model in 9 Steps with Python

In this ML model series, Logistic Regression is the first classification model. Logistic regression is used to classify the two-classes dataset. In our practice, we have a dataset about the people watching a social network advertisement. The dataset includes the people’s userId, gender, age, estimated salary and whether these people purchased SUV type car. We try to build a model that classifies the points into the people purchasing or not purchasing the SUV. The independent variables are age and estimated salary and the dependent variable is a boolean variable of 0 or 1.

Data Preprocessing:

Red points are the ones not purchasing the SUV and the blue points are the ones purchasing the SUV. The goal of this model is to classify the right users into the right categories. Prediction regions are the two sides of the graph and the red region represents 0 and the blue region represents 1. The division line between these regions called the prediction boundary. This line is a straight line because our model defined a linear classifier. The dataset in the upper case is the training set thus the model learned how to classify based on this information.

We could observe the correct and incorrect predictions in the confusion matrix.

References:

Related posts:

The Indian Rebellion of 1857 ended the Mughal Empire and the British East India Company. It also heralded the beginning of the British Raj.

We have this race for a 100 dollars and we have rules before they run this race I saw this on YouTube and it made me open my eyes to how privileged some people really are. So there rules that you…

Git is a version control system by which a single person or a large group of contributors can work on a project simultaneously while maintaining organization and tracking throughout version changes…