Update README

BinDisc.cpp

@@ -58,7 +58,7 @@ namespace mdlp {
         results.reserve(percentiles.size());
         for (auto percentile : percentiles) {
             const size_t i = static_cast<size_t>(std::floor(static_cast<double>(data.size() - 1) * percentile / 100.));
-            const auto indexLower = clip(i, 0, data.size() - 1);
+            const auto indexLower = clip(i, 0, data.size() - 2);
             const double percentI = static_cast<double>(indexLower) / static_cast<double>(data.size() - 1);
             const double fraction =
                 (percentile / 100.0 - percentI) /

Discretizer.h

@@ -18,7 +18,7 @@ namespace mdlp {
         void fit_t(torch::Tensor& X_, torch::Tensor& y_);
         torch::Tensor transform_t(torch::Tensor& X_);
         torch::Tensor fit_transform_t(torch::Tensor& X_, torch::Tensor& y_);
-        static inline std::string version() { return "1.2.1"; };
+        static inline std::string version() { return "1.2.2"; };
     protected:
         labels_t discretizedData = labels_t();
         cutPoints_t cutPoints;

README.md

@@ -14,9 +14,17 @@ The implementation tries to mitigate the problem of different label values with
 Other features:
 
 - Intervals with the same value of the variable are not taken into account for cutpoints.
-- Intervals have to have more than two examples to be evaluated.
+- Intervals have to have more than two examples to be evaluated (mdlp).
 
-The algorithm returns the cut points for the variable.
+- The algorithm returns the cut points for the variable.
+
+- The transform method uses the cut points returning its index in the following way:
+
+        cut[i - 1] <= x < cut[i]
+
+    using the [std::upper_bound](https://en.cppreference.com/w/cpp/algorithm/upper_bound) method
+
+- K-Bins discretization is also implemented, and "quantile" and "uniform" strategies are available.
 
 ## Sample