From the course: Python for AI Projects: From Data Exploration to Impact

Unlock the full course today

Join today to access over 24,900 courses taught by industry experts.

Model metrics

Model metrics - Python Tutorial

From the course: Python for AI Projects: From Data Exploration to Impact

Start my 1-month free trial Buy for my team

Model metrics

“

- [Instructor] After we've trained and tuned multiple models, it's time to answer the big question, how well are they actually performing? We'll start by reviewing the standard classification report from scikit-learn. This report includes a few key metrics: accuracy, the overall percentage of correct predictions,; precision, out of all of the predicted positive events, how many were actually correct; recall, out of all the actual positives, again, how many were correctly identified; and F1 score, the harmonic mean of precision and recall. This is especially useful when classes are imbalanced. Each of these metrics tell a different story depending on your business goal. Whether you're trying to reduce false positives or avoid missing key opportunities, you might choose to focus on one over the others, but sometimes standard metrics aren't enough. By default, most models output probability scores, and we often apply a fixed…

Contents