Train Versus Test Accuracy Gap
~6 mincode completion
Implement accuracy_gap(train_acc, test_acc) returning the array [gap, flag], where flag is 1.0 for likely memorizing and 0.0 otherwise.
Where this shows up
~6 min
••••••••••••••
7 employers weight this skill
2 health and bio companies, 2 quant funds, 2 enterprise vendors, 1 AI product company. Top match scores 50.
Python
import numpy as np
def accuracy_gap(train_acc, test_acc):
"""
How far the training score sits above the test score.
Args:
train_acc: accuracy on the training set, in percent (0 to 100)
test_acc: accuracy on the test set, in percent (0 to 100)
Returns:
array [gap, flag]: gap in percentage points, flag 1.0 if gap > 10 else 0.0
"""
# YOUR CODE HERE
pass