From 5679d607e5a4ab121e718c5e9921594baa44b0e8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ricardo=20Montan=CC=83ana?= <rmontanana@gmail.com>
Date: Thu, 6 Jul 2023 16:06:52 +0200
Subject: [PATCH] Add transform method to discretize values using CutPoints

---
 CPPFImdlp.cpp | 12 +++++++++++-
 CPPFImdlp.h   |  2 ++
 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/CPPFImdlp.cpp b/CPPFImdlp.cpp
index 92f3353..8e5f27b 100644
--- a/CPPFImdlp.cpp
+++ b/CPPFImdlp.cpp
@@ -7,7 +7,7 @@
 
 namespace mdlp {
 
-    CPPFImdlp::CPPFImdlp(size_t min_length_, int max_depth_, float proposed): min_length(min_length_),
+    CPPFImdlp::CPPFImdlp(size_t min_length_, int max_depth_, float proposed) : min_length(min_length_),
         max_depth(max_depth_),
         proposed_cuts(proposed)
     {
@@ -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;
+    }
 }
diff --git a/CPPFImdlp.h b/CPPFImdlp.h
index b6066c4..1fb0cab 100644
--- a/CPPFImdlp.h
+++ b/CPPFImdlp.h
@@ -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"; };
     };