Removing all the features with a high correlation. Keeping those which correlate with target value better.

drop_corr_features.py

to_drop = list()

# Iterating over rows starting from the second one, because position [0, 0] will be self-correlation which is 1
for i in range(1, len(corr_matrix)):
    # Iterating over columns of the row. Only going under the diagonal.
    for j in range(i):
        # See if the correlation between two features are more than a selected threshold
        if corr_matrix.iloc[i, j] >= 0.98:
            # Then keep the one from thos two which correlates with target better
            if abs(pd.concat([X[corr_matrix.index[i]], y], axis=1).corr().iloc[0][1]) > abs(pd.concat([X[corr_matrix.columns[j]], y], axis=1).corr().iloc[0][1]):
                to_drop.append(corr_matrix.columns[j])
            else:
                to_drop.append(corr_matrix.index[i])

to_drop = list(set(to_drop))