Section Recap
Introduction
In this section, you learned about logistic regression, how to evaluate classifiers, and how to deal with class imbalance problems.
Objectives
You will be able to:
- Understand and explain what was covered in this section
- Understand and explain why this section will help you become a data scientist
Key Takeaways
The key takeaways from this section include:
- Logistic regression uses a sigmoid function which helps to plot an "s" like curve that enables a linear function to act as a binary classifier
- Like other classifiers, you can evaluate logistic regression models using some combination of precision, recall and accuracy
- A confusion matrix is another common way to visualize the performance of a classification model
- Receiver Operating Characteristic (ROC) curves and the Area Under the Curve (AUC) can be used to help determine the best precision-recall tradeoff for a given classifier
- Class weights, under/oversampling, and SMOTE can be used to deal with class imbalance problems