Accuracy Visualisation: Supervised Machine Learning Classification Algorithms

Visual report of the classification algorithms result provides a snapshot of the misclassification and accuracy estimation. It is faster to interpret and circumvent the general accuracy score trap.

Measuring the prediction accuracy of any regression or classification algorithm is vital in different stages during modelling and also when the model is live in production.

We have several ways to measure the accuracy of classification algorithms. In the Scikit-learn package, we have several scores like recall score, accuracy score etc. and then we have out of box summarised reports. In my view, most of these metrics have one or more limitations related to verbosity and difficult to understand, potential chance to misinterpret the accuracy in case of imbalance classes in the dataset, need to refer few of the scores to get holistic view etc.

To better understand the limitation, let us consider the example shown in the table. We have few parameters related to a sample of people and whether they are COVID positive. As we have more people who are COVID negative than people who are infected with the virus hence, I have considered a similar distribution in this example.

programming data-science data-visualization machine-learning python

🔵 Intellipaat Data Science with Python course: https://intellipaat.com/python-for-data-science-training/In this Data Science With Python Training video, you...

This article compiles the 38 top Python libraries for data science, data visualization & machine learning,

Practice your skills in Data Science with Python, by learning and then trying all these hands-on, interactive projects, that I have posted for you.

Practice your skills in Data Science with Python, by learning and then trying all these hands-on, interactive projects, that I have posted for you.

Practice your skills in Data Science with Python, by learning and then trying all these hands-on, interactive projects, that I have posted for you.