Akansha YadavData Science & Coding (Python) | MySQL

precision in machine learning #pandas #mlwithakansha

14 Apr 2024 · 1 min

Watch on YouTube

0:39

In this tutorial, Akansha Yadav explains the precision metric for binary classification. She defines precision as the proportion of correct positive predictions, describes the four entries of a confusion matrix (true positives, false positives, true negatives, false negatives), and shows how to compute precision using the formula TP / (TP + FP). While noting that Python libraries can compute precision automatically, she emphasizes manually verifying the result by printing the confusion matrix and applying the formula.

Chapters

So let's see what precision is and how to calculate it using the confusion matrix. So confusion matrix gives us the 4 parameters, and on the basis of these 4 parameters, we are going to evaluate the precision. Let's first see what precision is. Precision is— it basically, it will tell us how accurate our positive predictions are. So all the positive prediction accuracy, it will tell you. So to calculate it, we have to do is true positive divided by true positive plus false positive. So this will give you the precision value. Although you can do it using the Python libraries, but if you wanted to evaluate it whether it is giving us the good precision and not manually, then you can use this method by printing the confusion matrix.