Feature Importance and Model Explainability

Let's look at the linear models (linear regression, logistic regression, and their regularization extensions). We find a set of coefficients ($\beta$ values) for features in the training dataset, and then the weighted sum (coefficient_1$\times$feature_1$+ \cdots$) helps us to make the predictions.

Regression coefficients

Technically, these coefficients (the $\beta$ values) can provide a basis for a crude way of scoring the respective feature's importance. This guides us to the usefulness of certain features for predicting the target values, given that the features are on the same scale. We can get the coefficients of our trained models and create a beautiful histogram. Let's get one for our model logR and explore how the model worked while training using (X_train_s, y_train).