bias and variance calculation for linear regression

Question

If we have 4 parameters of X_train, y_train, X_test, and y_test, how can we calculate the bias and variance of a machine learning algorithm like linear regression?

I have searched a lot but I could not find a single code for this.

Answer 1

Evaluation of Variance:

variance = np.var(prediction) # Where prediction is a variable obtained after  predict() function of any Classifier or algorithm

sse= np.mean((np.mean(prediction) - y)** 2) # Where y refers to dependent variable. # sse : Sum of squared errors.

bias = sse - variance

Bias and Variance are errors and need to be balanced. Bias leads to an underfit model that means it does not understand the patterns and fails to generalize, whereas

Variance leads to overfitting of the data, the model learns the data so well even the noises that does not generalize well on unseen data. Variance is the spread of the data, how far are the data points from the central points like mean or median