Building a Logistic Regression model from scratch

Building a Logistic Regression model from scratch.

Do you understand how does logistic regression work? If your answer is yes, I have a challenge for you to solve. Here is an extremely simple logistic problem. Here is the catch : YOU CANNOT USE ANY PREDEFINED LOGISTIC FUNCTION! Why am I asking you to build a Logistic Regression from scratch? Here is a small survey which I did with professionals with 1-3 years of experience in analytics industry (my sample size is. I was amazed to see such low percent of analyst who actually knows what goes behind the scene. We have now moved towards a generation where we are comfortable to see logistic regression also as a black box. In this article, I aim to kill this problem for once and all. The objective of the article is to bring out how logistic regression can be made without using inbuilt functions and not to give an introduction on Logistic regression. Refreshers of mathematics terminology. Logistic regression is an estimation of Logit function. Logit function is simply a log of odds in favor of the event. This function creates a s-shaped curve with the probability estimate, which is very similar to the required step wise function. Here goes the first definition : Logit Function: Logistic regression is an estimate of a logit function. Here is how the logit function looks like: Now that you know what we are trying to estimate, next is the definition of the function we are trying to optimize to get the estimates of coefficient. This function is analogous to the square of error in linear regression and is known as the likelihood function. Here goes our next definition. Likelihood Function. Given the complicated derivative of the likelihood function, we consider a monotonic function which can replicate the likelihood function and simplify derivative. This is the log of likelihood function. Here goes the next definition. Log Likelihood. Finally we have the derivatives of log likelihood function.

Following are the first and second derivative of log likelihood function. Derivative of Likelihood Function. Hessian Matrix (second derivative) Finally, we are looking to solve the following equation. As we now have all the derivative, we will finally apply the Newton Raphson method to converge to optimal solution. Here is a recap of Newton Raphson method. Newton Raphson Method. Here is a R code which can help you make your own logistic function. Let’s get our functions right. This might seem like a simple exercise, but I feel that this is extremely important before you start using Logistic as a black box. As an exercise you should try making these calculations using a gradient descent method. Also, for people conversant with Python, here is a small challenge to you – can you write a Python code for the larger community and share it in comments below? If you like what you just read & want to continue your analytics learning, subscribe to our emails, follow us on twitter or like our facebook page. Data Scientist/Senior Data Scientist – Bangalore (2+ years of experience) Beginner’s guide to Design of Experiments (with case study on banner advertisement) Tavish Srivastava. Related Articles. Model Performance metrics: How well does my model perform? – Part 2. 40 Questions to test a Data Scientist on Clustering Techniques (Skill test Solution) 40 Questions to ask a Data Scientist on Ensemble Modeling Techniques (Skilltest Solution) 8 Interesting Data Science Games to break the ice & Monday Blues! 19 Data Science and Machine Learning Tools for people who Don’t Know Programming. Taking a new job in Analytics? Ask these 5 questions first! 3 Comments. Excellent Write up Tavish. Finally the most hurting thorn for a beginner has been pricked out… Thank you Tavish for such a simple and useful explanation of Logistic regression. This is good stuff. I took up your challenge to build a logistic regression from scratch in Python. Here is my attempt. It seems to work fine. Let me know your thoughts.