mlquantify 0.1.19__py3-none-any.whl → 0.1.20__py3-none-any.whl

mlquantify/meta/_classes.py

@@ -696,59 +696,67 @@ class QuaDapt(MetaquantifierMixin, BaseQuantifier):
     
     def aggregate(self, predictions, train_y_values):
 
-        pos_predictions = predictions[:, 1]
-        m = self._get_best_merging_factor(pos_predictions)
+        prevalence, _, _ = self.best_mixture(predictions)
+        prevalences = np.asarray([1-prevalence, prevalence])
         
         self.classes = self.classes if hasattr(self, 'classes') else np.unique(train_y_values)
-
-        moss_scores, moss_labels = self.MoSS(1000, 0.5, m)
-
-        prevalences = self.quantifier.aggregate(predictions,
-                                                moss_scores,
-                                                moss_labels)
         
-        prevalences = {self.classes[i]: v for i, v in enumerate(prevalences.values())}
+        prevalences = validate_prevalences(self, prevalences, self.classes)
         return prevalences
 
         
-    def _get_best_merging_factor(self, predictions):
+    def best_mixture(self, predictions):
+        predictions = predictions[:, 1]
         
         MF = np.atleast_1d(np.round(self.merging_factors, 2)).astype(float)
         
         distances = []
+        alphas = []
         
         for mf in MF:
-            scores, labels = self.MoSS(1000, 0.5, mf)
+            scores, labels = self.MoSS(n=1000, alpha=0.5, merging_factor=mf)
             pos_scores = scores[labels == 1][:, 1]
             neg_scores = scores[labels == 0][:, 1]
+
+            if self.measure in ["hellinger", "topsoe", "probsymm"]:
+                method = DyS(measure=self.measure)
+            elif self.measure == "sord":
+                method = SORD()
             
-            best_distance = self._get_best_distance(predictions, pos_scores, neg_scores)
+            alpha, distance = method.best_mixture(predictions, pos_scores, neg_scores)
             
-            distances.append(best_distance)
+            distances.append(distance)
+            alphas.append(alpha)
         
         best_m = MF[np.argmin(distances)]
-        return best_m
+        best_alpha = alphas[np.argmin(distances)]
+        best_distance = np.min(distances)
+        return best_alpha, best_distance, best_m
     
-    def _get_best_distance(self, predictions, pos_scores, neg_scores):
-        
-        if self.measure in ["hellinger", "topsoe", "probsymm"]:
-            method = DyS(measure=self.measure)
-        elif self.measure == "sord":
-            method = SORD()
+    def get_best_distance(self, predictions):
         
-        best_distance = method.get_best_distance(predictions, pos_scores, neg_scores)
-        return best_distance
+        _, distance, _= self.get_best_merging_factor(predictions)
+
+        return distance
         
 
     @classmethod
-    def MoSS(cls, n, alpha, m):
+    def MoSS(cls, n, alpha, merging_factor):
         r"""Model for Score Simulation
 
-        MoSS has three key parameters:
-        (I) the number of observations `n`;
-        (II) the class proportion `\alpha`, which defines the prevalence of the positive class;
-        (III) the merging factor :math:`m`, which controls the overlap between positive and negative score distributions 
-        (where :math:`m=0` represents easily separable classes and :math:`m=1` represents highly overlapping ones).
+        Parameters
+        ----------
+        n : int
+            Number of observations.
+        alpha : float
+            Class proportion, which defines the prevalence of the positive class.
+        m : float
+            Merging factor, which controls the overlap between positive and negative score distributions.
+
+        Returns
+        -------
+        tuple
+            Tuple of score and label arrays.
 
         .. math::
             
@@ -776,9 +784,9 @@ class QuaDapt(MetaquantifierMixin, BaseQuantifier):
         n_neg = n - n_pos
         
         # Scores positivos
-        p_score = np.random.uniform(size=n_pos) ** m
+        p_score = np.random.uniform(size=n_pos) ** merging_factor
         # Scores negativos
-        n_score = 1 - (np.random.uniform(size=n_neg) ** m)
+        n_score = 1 - (np.random.uniform(size=n_neg) ** merging_factor)
         
         # Construção dos arrays de features (duas colunas iguais)
         moss = np.column_stack(

{mlquantify-0.1.19.dist-info → mlquantify-0.1.20.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mlquantify
-Version: 0.1.19
+Version: 0.1.20
 Summary: Quantification Library
 Home-page: https://github.com/luizfernandolj/QuantifyML/tree/master
 Maintainer: Luiz Fernando Luth Junior

{mlquantify-0.1.19.dist-info → mlquantify-0.1.20.dist-info}/RECORD

@@ -13,7 +13,7 @@ mlquantify/likelihood/__init__.py,sha256=3dC5uregNmquUKz0r0-3aPspfjZjKGn3TRBoZPO
 mlquantify/likelihood/_base.py,sha256=seu_Vb58QttcGbFjHKAplMYGZcVbIHqkyTXEK2cax9A,5830
 mlquantify/likelihood/_classes.py,sha256=PZ31cAwO8q5X3O2_oSmQ1FM6bY4EsB8hWEcAgcEmWXQ,14731
 mlquantify/meta/__init__.py,sha256=GzdGw4ky_kmd5VNWiLBULy06IdN_MLCDAuJKbnMOx4s,62
-mlquantify/meta/_classes.py,sha256=RKEVghPMBlyv516xrUtTyUkHvC2-5IsTUO_oVwAt3Gw,30930
+mlquantify/meta/_classes.py,sha256=0o3LBPGc-8znwJL0_TFo9zXjHrXqXc0QIPpzwaghFKQ,30898
 mlquantify/metrics/__init__.py,sha256=3bzzjSYTgrZIJsfAgJidQlB-bnjInwVYUvJ34bPhZxY,186
 mlquantify/metrics/_oq.py,sha256=koXDKeHWksl_vHpZuhc2pAps8wvu_MOgEztlSr04MmE,3544
 mlquantify/metrics/_rq.py,sha256=3yiEmGaRAGpzL29Et3tNqkJ3RMsLXwUX3uL9RoIgi40,3034
@@ -47,7 +47,7 @@ mlquantify/utils/_sampling.py,sha256=3W0vUuvLvoYrt-BZpSM0HM1XJEZr0XYIdkOcUP5hp-8
 mlquantify/utils/_tags.py,sha256=Rz78TLpxgVxBKS0mKTlC9Qo_kn6HaEwVKNXh8pxFT7M,1095
 mlquantify/utils/_validation.py,sha256=zn4OHfa704YBaPKskhiThUG7wS5fvDoHBpcEgb1i8qM,18078
 mlquantify/utils/prevalence.py,sha256=LG-KXJ5Eb4w26WMpu4PoBpxMSHaqrmTQqdRlyqNRJ1o,2020
-mlquantify-0.1.19.dist-info/METADATA,sha256=nQ0BqrdrpxbBTHhFh6p2M9qXqQsehRAdqIB5cpNbr1s,4701
-mlquantify-0.1.19.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-mlquantify-0.1.19.dist-info/top_level.txt,sha256=tGEkYkbbFElwULvqENjam3u1uXtyC1J9dRmibsq8_n0,11
-mlquantify-0.1.19.dist-info/RECORD,,
+mlquantify-0.1.20.dist-info/METADATA,sha256=VTVfeUzcWUpxdiPLHxr1wlkzfpyRAZ5ABhuAJksBg9E,4701
+mlquantify-0.1.20.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+mlquantify-0.1.20.dist-info/top_level.txt,sha256=tGEkYkbbFElwULvqENjam3u1uXtyC1J9dRmibsq8_n0,11
+mlquantify-0.1.20.dist-info/RECORD,,