Refactor some methods

fimdlp/CPPFImdlp.cpp

@@ -32,17 +32,17 @@ namespace mdlp {
     {
         return xDiscretized;
     }
-    void CPPFImdlp::fit(samples& X_, labels& y_)
+    CPPFImdlp& CPPFImdlp::fit(samples& X_, labels& y_)
     {
         X = X_;
         y = y_;
         if (X.size() != y.size()) {
             std::cerr << "X and y must have the same size" << std::endl;
-            return;
+            return *this;
         }
         if (X.size() == 0) {
             std::cerr << "X and y must have at least one element" << std::endl;
-            return;
+            return *this;
         }
         this->indices = sortIndices(X_);
         this->xDiscretized = labels(X.size(), -1);
@@ -55,6 +55,7 @@ namespace mdlp {
         }
         filterCutPoints();
         applyCutPoints();
+        return *this;
     }
     labels& CPPFImdlp::transform(samples& X_)
     {

fimdlp/CPPFImdlp.h

@@ -31,7 +31,7 @@ namespace mdlp {
         cutPoints_t getCutPoints();
         labels getDiscretizedValues();
         void debugPoints(samples&, labels&);
-        void fit(samples&, labels&);
+        CPPFImdlp& fit(samples&, labels&);
         labels& transform(samples&);
     };
 }

fimdlp/cfimdlp.pyx

@@ -11,7 +11,7 @@ cdef extern from "CPPFImdlp.h" namespace "mdlp":
     cdef cppclass CPPFImdlp:
         CPPFImdlp() except + 
         CPPFImdlp(bool, int, bool) except + 
-        void fit(vector[float]&, vector[int]&)
+        CPPFImdlp& fit(vector[float]&, vector[int]&)
         vector[int] transform(vector[float]&)
         vector[int] getDiscretizedValues()
         vector[CutPointBody] getCutPoints()
@@ -34,12 +34,13 @@ cdef class CFImdlp:
         del self.thisptr
     def fit(self, X, y):
         self.thisptr.fit(X, y)
+        return self
     def transform(self, X):
         return self.thisptr.transform(X)
     def get_discretized_values(self):
         return self.thisptr.getDiscretizedValues()
     def get_cut_points(self):
-        return  self.thisptr.getCutPoints()
+        return self.thisptr.getCutPoints()
     def debug_points(self, X, y):
         return self.thisptr.debugPoints(X, y)
  

sample.py

@@ -66,28 +66,28 @@ features = data.feature_names
 # test.transform(X)
 # test.get_cut_points()
 
-test = CFImdlp(debug=True, proposed=False)
+test = CFImdlp(debug=False, proposed=False)
 # # k = test.cut_points(X[:, 0], y)
 # # print(k)
 # # k = test.cut_points_ant(X[:, 0], y)
 # # print(k)
 # # test.debug_points(X[:, 0], y)
-X = [5.7, 5.3, 5.2, 5.1, 5.0, 5.6, 5.1, 6.0, 5.1, 5.9]
-indices = [4, 3, 6, 8, 2, 1, 5, 0, 9, 7]
-y = [1, 1, 1, 1, 1, 2, 2, 2, 2, 2]
+# X = [5.7, 5.3, 5.2, 5.1, 5.0, 5.6, 5.1, 6.0, 5.1, 5.9]
+# indices = [4, 3, 6, 8, 2, 1, 5, 0, 9, 7]
+# y = [1, 1, 1, 1, 1, 2, 2, 2, 2, 2]
 # # To check
 # indices2 = np.argsort(X)
 # Xs = np.array(X)[indices2]
 # ys = np.array(y)[indices2]
 
-# test.fit(X[:, 0], y)
-test.fit(X, y)
+test.fit(X[:, 0], y)
+# test.fit(X, y)
 result = test.get_cut_points()
-for item in result:
-    print(
-        f"*Class={item['classNumber']} - ({item['start']:3d}, {item['end']:3d})"
-        f" -> ({item['fromValue']:3.1f}, {item['toValue']:3.1f}]"
-    )
+# for item in result:
+#     print(
+#         f"Class={item['classNumber']} - ({item['start']:3d}, {item['end']:3d})"
+#         f" -> ({item['fromValue']:3.1f}, {item['toValue']:3.1f}]"
+#     )
 print(test.get_discretized_values())
 
 # print(Xs, ys)
@@ -102,13 +102,13 @@ print(test.get_discretized_values())
 # print(indices)
 # print(np.array(X)[indices])
 
-# X = np.array(
-#     [
-#         [5.1, 3.5, 1.4, 0.2],
-#         [5.2, 3.0, 1.4, 0.2],
-#         [5.3, 3.2, 1.3, 0.2],
-#         [5.3, 3.1, 1.5, 0.2],
-#     ]
-# )
-# y = np.array([0, 0, 0, 1])
-# test.fit(X, y).transform(X)
+X = np.array(
+    [
+        [5.1, 3.5, 1.4, 0.2],
+        [5.2, 3.0, 1.4, 0.2],
+        [5.3, 3.2, 1.3, 0.2],
+        [5.3, 3.1, 1.5, 0.2],
+    ]
+)
+y = np.array([0, 0, 0, 1])
+print(test.fit(X[:, 0], y).transform(X[:, 0]))