Machine Learning for Beginners - Analyzing Logistic Regression Performance with ROC Curves [Part 17] | Machine Learning for Beginners

Join Bea Stollnitz, a Principal Cloud Advocate at Microsoft, as she teaches you how to analyze the performance of your logistic regression model using ROC (Receiver Operating Characteristic) curves. We'll be using these to evaluate the Logistic regression classifier built in the previous video using our pumpkin data set 🎃. What you'll learn: ✅ What a ROC curve is ✅ How a ROC curve helps in evaluating binary classifiers ✅ How a ROC curve relates to a confusion matrix Bea will guide you through the process of creating an ROC curve using Python in a Juypter Notebook and how to interpret its results to gain insights into your model's performance. Make sure to subscribe and hit the notification bell 🔔 so you won't miss upcoming videos in the ML for Beginners series! 📙 Follow along: The Jupyter Notebook to follow along with this lesson is available here: https://github.com/microsoft/ML-For-Beginners/tree/main/2-Regression/4-Logistic #Python #ScikitLearn #pandas #LogisticRegression #DataScience #MachineLearning #ml 📚 Learn more: This course is based on the free, open source, 26 lesson ML For Beginners curriculum from Microsoft, which can be found at https://aka.ms/ml-beginners. 📇 Connect with Bea: Blog: https://bea.stollnitz.com/blog/ LinkedIn: https://www.linkedin.com/in/beatrizstollnitz/ Twitter: https://twitter.com/beastollnitz 0:00 - Intro 0:17 - What is an ROC curve? 0:37 - The notebook we are working on - https://aka.ms/ml-beginners 0:55 - Definition of an ROC curve 1:29 - Choosing a new threshold for logistic regression 2:21 - Plot ROC using multiple classification thresholds 2:43 - Create an ROC curve in code 3:00 - The shape of an ROC curve 3:38 - Reading an ROC curve 4:10 - Calculate the area under the ROC curve