// calculate percentile
value_t percentile( double x ) const
{
assert( x >= 0 && x <= 1.0 );
if ( simple )
return 0;
if ( data().empty() )
return 0;
if ( !is_sorted )
return base_t::nan();
// Should be improved to use linear interpolation
return *( sorted_data()[ ( int ) ( x * ( sorted_data().size() - 1 ) ) ] );
}
void test_sorted_data_can_sort_complex_tree(void)
{
TEST_IGNORE();
int tree_data[] = { 2, 1, 3, 6, 7, 5 };
node_t *tree = build_tree(tree_data, ARRAY_SIZE(tree_data));
int expected[] = { 1, 2, 3, 5, 6, 7 };
int *actual = sorted_data(tree);
TEST_ASSERT_EQUAL_INT_ARRAY(expected, actual, ARRAY_SIZE(expected));
free_tree(tree);
free(actual);
}
void test_sorted_data_can_sort_if_second_number_is_greater_than_first(void)
{
TEST_IGNORE();
int tree_data[] = { 2, 3 };
node_t *tree = build_tree(tree_data, ARRAY_SIZE(tree_data));
int expected[] = { 2, 3 };
int *actual = sorted_data(tree);
TEST_ASSERT_EQUAL_INT_ARRAY(expected, actual, ARRAY_SIZE(expected));
free_tree(tree);
free(actual);
}
void test_sorted_data_can_sort_single_number(void)
{
TEST_IGNORE();
int tree_data[] = { 2 };
node_t *tree = build_tree(tree_data, ARRAY_SIZE(tree_data));
int expected[] = { 2 };
int *actual = sorted_data(tree);
TEST_ASSERT_EQUAL_INT_ARRAY(expected, actual, ARRAY_SIZE(expected));
free_tree(tree);
free(actual);
}
int Stump::train(const Mat& data, const Mat& labels, const Mat& weights)
{
CV_Assert(labels.rows == 1 && labels.cols == data.cols);
CV_Assert(weights.rows == 1 && weights.cols == data.cols);
/* Assert that data and labels have int type */
/* Assert that weights have float type */
/* Prepare labels for each feature rearranged according to sorted order */
Mat sorted_labels(data.rows, data.cols, labels.type());
Mat sorted_weights(data.rows, data.cols, weights.type());
Mat indices;
sortIdx(data, indices, cv::SORT_EVERY_ROW | cv::SORT_ASCENDING);
for( int row = 0; row < indices.rows; ++row )
{
for( int col = 0; col < indices.cols; ++col )
{
sorted_labels.at<int>(row, col) =
labels.at<int>(0, indices.at<int>(row, col));
sorted_weights.at<float>(row, col) =
weights.at<float>(0, indices.at<int>(row, col));
}
}
/* Sort feature values */
Mat sorted_data(data.rows, data.cols, data.type());
sort(data, sorted_data, cv::SORT_EVERY_ROW | cv::SORT_ASCENDING);
/* Split positive and negative weights */
Mat pos_weights = Mat::zeros(sorted_weights.rows, sorted_weights.cols,
sorted_weights.type());
Mat neg_weights = Mat::zeros(sorted_weights.rows, sorted_weights.cols,
sorted_weights.type());
for( int row = 0; row < data.rows; ++row )
{
for( int col = 0; col < data.cols; ++col )
{
if( sorted_labels.at<int>(row, col) == +1 )
{
pos_weights.at<float>(row, col) =
sorted_weights.at<float>(row, col);
}
else
{
neg_weights.at<float>(row, col) =
sorted_weights.at<float>(row, col);
}
}
}
/* Compute cumulative sums for fast stump error computation */
Mat pos_cum_weights = Mat::zeros(sorted_weights.rows, sorted_weights.cols,
sorted_weights.type());
Mat neg_cum_weights = Mat::zeros(sorted_weights.rows, sorted_weights.cols,
sorted_weights.type());
cumsum(pos_weights, pos_cum_weights);
cumsum(neg_weights, neg_cum_weights);
/* Compute total weights of positive and negative samples */
float pos_total_weight = pos_cum_weights.at<float>(0, weights.cols - 1);
float neg_total_weight = neg_cum_weights.at<float>(0, weights.cols - 1);
float eps = 1.0f / (4 * labels.cols);
/* Compute minimal error */
float min_err = FLT_MAX;
int min_row = -1;
int min_col = -1;
int min_polarity = 0;
float min_pos_value = 1, min_neg_value = -1;
for( int row = 0; row < sorted_weights.rows; ++row )
{
for( int col = 0; col < sorted_weights.cols - 1; ++col )
{
float err, h_pos, h_neg;
// Direct polarity
float pos_wrong = pos_cum_weights.at<float>(row, col);
float pos_right = pos_total_weight - pos_wrong;
float neg_right = neg_cum_weights.at<float>(row, col);
float neg_wrong = neg_total_weight - neg_right;
h_pos = (float)(.5 * log((pos_right + eps) / (pos_wrong + eps)));
h_neg = (float)(.5 * log((neg_wrong + eps) / (neg_right + eps)));
err = sqrt(pos_right * neg_wrong) + sqrt(pos_wrong * neg_right);
if( err < min_err )
{
min_err = err;
min_row = row;
min_col = col;
min_polarity = +1;
min_pos_value = h_pos;
min_neg_value = h_neg;
}
// Opposite polarity
swap(pos_right, pos_wrong);
swap(neg_right, neg_wrong);
h_pos = -h_pos;
h_neg = -h_neg;
err = sqrt(pos_right * neg_wrong) + sqrt(pos_wrong * neg_right);
if( err < min_err )
{
min_err = err;
min_row = row;
min_col = col;
min_polarity = -1;
min_pos_value = h_pos;
min_neg_value = h_neg;
}
}
}
/* Compute threshold, store found values in fields */
threshold_ = ( sorted_data.at<int>(min_row, min_col) +
sorted_data.at<int>(min_row, min_col + 1) ) / 2;
polarity_ = min_polarity;
pos_value_ = min_pos_value;
neg_value_ = min_neg_value;
return min_row;
}
