def k_folds_linear_gd(df_test, df_train, Y):
k = 10
df_test = gd.pandas_to_data(df_test)
k_folds = partition_folds(df_test, k)
model = Model_w()
theta = None
for ki in range(k - 1):
print "k fold is {}".format(k)
data, truth = get_data_and_truth(k_folds[ki])
binary = True
model.update(gd.gradient(data, np.array(truth), 0.00001, max_iterations=5, binary=binary))
print model.w
if theta is None:
theta, max_acc = get_best_theta(data, truth, model.w, binary, False)
predict = gd.predict_data(data, model.w, binary, False, theta)
error = mystats.get_error(predict, truth, binary)
print "Error for fold {} is {} with theta = {}".format(k, error, theta)
test, truth = get_data_and_truth(k_folds[k - 1])
predict = gd.predict_data(test, model.w, binary, False, theta)
test_error = mystats.get_error(predict, truth, binary)
return [error, test_error]
def get_best_theta(data, truth, model, binary, logistic):
best_theta = None
max_acc = 0
modmin = min(model)
modmax = max(model)
for theta_i in range(100):
theta = modmin + float(theta_i) / (modmax - modmin)
predict = gd.predict_data(data, model, binary, False, theta)
acc = mystats.get_error(predict, truth, binary)
if best_theta is None:
best_theta = theta
max_acc = acc
elif acc > max_acc:
best_theta = theta
max_acc = acc
return best_theta, max_acc
