Quiz · What Machine Learning Is · lesson 9 of 9Quiz — fit, predict and the training scoreWhat do fit and predict do, and what does a score on the training rows tell you?[A]fit only checks and stores the training rows, and predict(X_new) retrains the model on those rows plus the new ones on every call, so the training score is exactly what you get on new data.[B]fit(X_train, y_train) learns the parameters and predict(X_new) applies them. A high score on the training rows proves the model will also work on new data, since it was already measured on real rows with their real targets.[C]fit(X_train, y_train) learns the model parameters from rows with a known target, and predict(X_new) applies them to rows without one. A high score on the training rows says little about how the model does on new data.[D]fit only picks hyperparameters such as tree depth, and predict learns the weights from X_new itself, so the model adapts to each new batch and does every bit as well on it as on the training rows.Subscribe to take the courseThe course is free. Sign in with Telegram and subscribe to the channel to open every lesson.Continue with TelegramSign in another way← BackTraining, testing and predictionNext module →02 · NumPy and pandas
