In the segment - 3 - Simple Logistic Regression, is the logistic regression model being trained and then tested on the same dataset? I am confused about how that makes sense.
clf.fit(X.T, Y.T);
plot_decision_boundary(lambda x: clf.predict(x), X, Y)
It’s just a simple first example. Using test and validation sets is covered later.
Right! We’re just barely getting started here and there’s a lot more to learn. But the other point is that what they are doing there with the second step is simply showing you the results of the training. Here’s what the model we just trained does on the training data. That’s a perfectly reasonable thing to do, even if it’s not the whole story of how you evaluate a model.
Got it. Thank you. Makes sense