Logistic Regression Returning Wrong Prediction - c++

Question

I'm trying to implement logistic regression in C++, but the predictions I'm getting are not even close to what I am expecting. I'm not sure if there is an error in my understanding of logistic regression or the code.
I have reviewed the algorithms and messed with the learning rate, but the results are very inconsistent.
double theta[4] = {0,0,0,0};
double x[2][3] = {
{1,1,1},
{9,9,9},
};
double y[2] = {0,1};
//prediction data
double test_x[1][3] = {
{9,9,9},
};
int test_m = sizeof(test_x) / sizeof(test_x[0]);
int m = sizeof(x) / sizeof(x[0]);
int n = sizeof(theta) / sizeof(theta[0]);
int xn = n - 1;
struct Logistic
{
double sigmoid(double total)
{
double e = 2.71828;
double sigmoid_x = 1 / (1 + pow(e, -total));
return sigmoid_x;
}
double h(int x_row)
{
double total = theta[0] * 1;
for(int c1 = 0; c1 < xn; ++c1)
{
total += theta[c1 + 1] * x[x_row][c1];
}
double final_total = sigmoid(total);
//cout << "final total: " << final_total;
return final_total;
}
double cost()
{
double hyp;
double temp_y;
double error;
for(int c1 = 0; c1 < m; ++c1)
{
//passes row of x to h to calculate sigmoid(xi * thetai)
hyp = h(c1);
temp_y = y[c1];
error += temp_y * log(hyp) + (1 - temp_y) * log(1 - hyp);
}// 1 / m
double final_error = -.5 * error;
return final_error;
}
void gradient_descent()
{
double alpha = .01;
for(int c1 = 0; c1 < n; ++c1)
{
double error = cost();
cout << "final error: " << error << "\n";
theta[c1] = theta[c1] - alpha * error;
cout << "theta: " << c1 << " " << theta[c1] << "\n";
}
}
void train()
{
for(int epoch = 0; epoch <= 10; ++epoch)
{
gradient_descent();
cout << "epoch: " << epoch << "\n";
}
}
vector<double> predict()
{
double temp_total;
double total;
vector<double> final_total;
//hypothesis equivalent function
temp_total = theta[0] * 1;
for(int c1 = 0; c1 < test_m; ++c1)
{
for(int c2 = 0; c2 < xn; ++c2)
{
temp_total += theta[c2 + 1] * test_x[c1][c2];
}
total = sigmoid(temp_total);
//cout << "final total: " << final_total;
final_total.push_back(total);
}
return final_total;
}
};
int main()
{
Logistic test;
test.train();
vector<double> prediction = test.predict();
for(int c1 = 0; c1 < test_m; ++c1)
{
cout << "prediction: " << prediction[c1] << "\n";
}
}

Answer 1

start with a very small learning rate wither larger iteration number at try. Haven`t tested ur code. But I guess the cost/error/energy jumps from hump to hump.

Answer 2

Somewhat unrelated to your question, but rather than computing e^-total using pow, use exp instead (it's a hell of a lot faster!). Also there is no need to make the sigmoid function a member func, make it static or just a normal C func (it doesn't require any member variable from your struct).
static double sigmoid(double total)
{
return 1.0 / (1.0 + exp(-total));
}