Correlation Feature Selection

Problem

Select the feature most correlated with y by absolute Pearson correlation.

Return the index of the feature with the largest |corr|, breaking ties by the smallest index; a constant feature or constant y gives correlation 0.0. Empty X returns -1.

Hint

Pearson correlation is the covariance of the column and y divided by the product of their standard deviations.

Test cases

case 1

in: [[[1,10],[2,9],[3,8],[4,7]],[2,4,6,8]]

expected: 0

case 2

in: [[[1,1],[2,3],[3,2],[4,5]],[1,2,3,4]]

expected: 0

case 3

in: [[[2,2],[2,2]],[1,2]]

expected: 0

case 4

in: [[],[]]

expected: -1

Starter codePython

def select_feature_by_correlation(X, y):
    # Your code here
    pass

4 test cases · run your code against them in the editor