void FScore::calculate_from_confusion_matrix(const MatrixXi &cmat) {
// Sometimes a class is never predicted, leading to a sum that is 0.
// When dividing later, there can be a nan. Avoid setting the value to 1.
// Setting to 1 is correct because the value to divide will be 0.
VectorXi sums = cmat.colwise().sum().unaryExpr(std::ptr_fun(avoid_zero));
recall_ = cmat.cast<double>().diagonal().array() / sums.cast<double>().array();
sums = cmat.rowwise().sum().unaryExpr(std::ptr_fun(avoid_zero));
precision_ = cmat.cast<double>().diagonal().array() / sums.cast<double>().array();
// Apply the same fix to the sum of the recall and precision arrays.
VectorXd s = (recall_ + precision_).unaryExpr(std::ptr_fun(avoid_zero_double));
fscore_ = 2 * recall_.array() * precision_.array() / s.array();
}
double nominal_gini_gain(const VectorXi &values, const VectorXi &classes) {
MatrixXi T = get_cross_table(values, classes);
// total_per_value(k) is the number of times that value k appears
MatrixXi total_per_value = T.rowwise().sum();
VectorXd probability_of_value = total_per_value.cast<double>() /values.rows();
// Fraction of each class per value
MatrixXd fractions_yx = divide_colwise( T.cast<double>(),
total_per_value.cast<double>());
// Gini impurity for each value: sum fractions^2 over the rows
VectorXd G = fractions_yx.array().square().rowwise().sum();
double total_gini = 1 - probability_of_value.transpose() * G;
VectorXi counts = T.colwise().sum();
double gain = gini(counts.cast<double>()) - total_gini;
return gain;
}
double nominal_entropy_gain(const VectorXi &values, const VectorXi &classes) {
MatrixXi T = get_cross_table(values, classes);
MatrixXi total_per_value = T.rowwise().sum();
VectorXd probability_of_value = total_per_value.cast<double>() /values.rows();
MatrixXd fractions_yx = divide_colwise( T.cast<double>(),
total_per_value.cast<double>());
double epsilon = std::numeric_limits<double>::epsilon();
double invlog = 1 / std::log(2);
MatrixXd H = (- invlog) * fractions_yx.array() *
(fractions_yx.array() + epsilon).log().array();
double total_entropy = probability_of_value.transpose() * H.rowwise().sum();
VectorXi counts = T.colwise().sum();
double gain = entropy(counts.cast<double>()) - total_entropy;
return gain;
}
int main(int, char**)
{
cout.precision(3);
MatrixXi m = MatrixXi::Random(3,4);
cout << "Here is the matrix m:" << endl << m << endl;
cout << "Here is the rowwise reverse of m:" << endl << m.rowwise().reverse() << endl;
cout << "Here is the colwise reverse of m:" << endl << m.colwise().reverse() << endl;
cout << "Here is the coefficient (1,0) in the rowise reverse of m:" << endl
<< m.rowwise().reverse()(1,0) << endl;
cout << "Let us overwrite this coefficient with the value 4." << endl;
//m.colwise().reverse()(1,0) = 4;
cout << "Now the matrix m is:" << endl << m << endl;
return 0;
}
