In-depth understanding of Logistic Regression and Python combat

Author: Zen and the Art of Computer Programming

1 Introduction

Machine learning (ML) is a hot subject and the most popular technical field at the moment. In the past 100 years, machine learning has gone through many stages from data mining, classification, regression to supervised learning, and has become a major way to process massive data. With the development of deep learning, machine learning has taken another important step forward and achieved greater breakthroughs. This article will describe Logistic Regression and its related algorithms in detail, and implement an efficient Logistic Regression model based on python. The article includes the following sections:

1. Basic Concepts and Terminology of Logistic Regression
2. Model form and loss function
3. Python code to implement Logistic Regression
4. Improve and optimize the model
5. Case analysis and extended reading
   Welcome more technical people to participate in writing this article, and discuss with us how to use Python to implement the Logistic Regression model in machine learning.

2. Basic concepts and terminology of Logistic Regression

2.1 Overview of Logistic Regression

Logistic Regression is a classification model that can be used to predict the likelihood of an event occurring. In general, Logistic Regression is applied to problems other than regression tasks. like:

1. Determine whether a user will subscribe to a product, such as a recommendation engine;
2. Spam filtering, disease diagnosis, cancer detection;
3. checking for credit card fraud;
4. Predict the risk of disease and so on through the patient's body data.

The Logistic Regression model consists of the following key elements