mirror of
https://github.com/rmontanana/mdlp.git
synced 2025-08-15 23:45:57 +00:00
Add transform method to discretize values using CutPoints
This commit is contained in:
@@ -37,6 +37,7 @@ namespace mdlp {
|
||||
y = y_;
|
||||
num_cut_points = compute_max_num_cut_points();
|
||||
depth = 0;
|
||||
discretizedData.clear();
|
||||
cutPoints.clear();
|
||||
if (X.size() != y.size()) {
|
||||
throw invalid_argument("X and y must have the same size");
|
||||
@@ -208,4 +209,13 @@ namespace mdlp {
|
||||
}
|
||||
cutPoints.erase(cutPoints.begin() + static_cast<long>(maxEntropyIdx));
|
||||
}
|
||||
labels_t& CPPFImdlp::transform(const samples_t& data)
|
||||
{
|
||||
discretizedData.reserve(data.size());
|
||||
for (const precision_t& item : data) {
|
||||
auto upper = upper_bound(cutPoints.begin(), cutPoints.end(), item);
|
||||
discretizedData.push_back(upper - cutPoints.begin());
|
||||
}
|
||||
return discretizedData;
|
||||
}
|
||||
}
|
||||
|
@@ -20,6 +20,7 @@ namespace mdlp {
|
||||
Metrics metrics = Metrics(y, indices);
|
||||
cutPoints_t cutPoints;
|
||||
size_t num_cut_points = numeric_limits<size_t>::max();
|
||||
labels_t discretizedData = labels_t();
|
||||
|
||||
static indices_t sortIndices(samples_t&, labels_t&);
|
||||
|
||||
@@ -36,6 +37,7 @@ namespace mdlp {
|
||||
~CPPFImdlp();
|
||||
void fit(samples_t&, labels_t&);
|
||||
inline cutPoints_t getCutPoints() const { return cutPoints; };
|
||||
labels_t& transform(const samples_t&);
|
||||
inline int get_depth() const { return depth; };
|
||||
static inline string version() { return "1.1.2"; };
|
||||
};
|
||||
|
Reference in New Issue
Block a user