mlquantify 0.1.12__py3-none-any.whl → 0.1.14__py3-none-any.whl

mlquantify/adjust_counting/_adjustment.py

@@ -104,7 +104,7 @@ class ThresholdAdjustment(SoftLearnerQMixin, BaseAdjustCount):
         thresholds, tprs, fprs = evaluate_thresholds(train_y_values, positive_scores)
         threshold, tpr, fpr = self.get_best_threshold(thresholds, tprs, fprs)
 
-        cc_predictions = CC(threshold).aggregate(predictions)[1]
+        cc_predictions = CC(threshold=threshold).aggregate(predictions, train_y_values)[1]
 
         if tpr - fpr == 0:
             prevalence = cc_predictions
@@ -514,7 +514,7 @@ class X_method(ThresholdAdjustment):
            *ECML*, pp. 564-575.
     """
     def get_best_threshold(self, thresholds, tprs, fprs):
-        idx = np.argmin(np.abs(1 - (tprs + fprs)))
+        idx = np.argmin(np.abs((1-tprs) - fprs))
         return thresholds[idx], tprs[idx], fprs[idx]
 
 
@@ -601,7 +601,7 @@ class MS(ThresholdAdjustment):
         
         prevs = []
         for thr, tpr, fpr in zip(thresholds, tprs, fprs):
-            cc_predictions = CC(thr).aggregate(predictions)
+            cc_predictions = CC(threshold=thr).aggregate(predictions, train_y_values)
             cc_predictions = cc_predictions[1]
             
             if tpr - fpr == 0:

mlquantify/adjust_counting/_base.py

@@ -204,7 +204,7 @@ class BaseAdjustCount(AggregationMixin, BaseQuantifier):
         self.learner = learner
 
     @_fit_context(prefer_skip_nested_validation=True)
-    def fit(self, X, y, learner_fitted=False):
+    def fit(self, X, y, learner_fitted=False, cv=10, stratified=True, random_state=None, shuffle=True):
         """Fit the quantifier using the provided data and learner."""
         X, y = validate_data(self, X, y)
         validate_y(self, y)
@@ -220,10 +220,10 @@ class BaseAdjustCount(AggregationMixin, BaseQuantifier):
                 X,
                 y,
                 function=learner_function,
-                cv=5,
-                stratified=True,
-                random_state=None,
-                shuffle=True
+                cv=cv,
+                stratified=stratified,
+                random_state=random_state,
+                shuffle=shuffle
             )
         
         self.train_predictions = train_predictions
@@ -241,7 +241,6 @@ class BaseAdjustCount(AggregationMixin, BaseQuantifier):
         self.classes_ = check_classes_attribute(self, np.unique(y_train_values))
         
         predictions = validate_predictions(self, predictions)
-        train_predictions = validate_predictions(self, train_predictions)
         
         prevalences = self._adjust(predictions, train_predictions, y_train_values)
         prevalences = validate_prevalences(self, prevalences, self.classes_)

mlquantify/adjust_counting/_counting.py

@@ -75,10 +75,12 @@ class CC(CrispLearnerQMixin, BaseCount):
         super().__init__(learner=learner)
         self.threshold = threshold
 
-    def aggregate(self, predictions):
-        predictions = validate_predictions(self, predictions)
+    def aggregate(self, predictions, train_y_values=None):
+        predictions = validate_predictions(self, predictions, self.threshold)
         
-        self.classes_ = check_classes_attribute(self, np.unique(predictions))
+        if train_y_values is None:
+            train_y_values = np.unique(predictions)
+        self.classes_ = check_classes_attribute(self, np.unique(train_y_values))
         class_counts = np.array([np.count_nonzero(predictions == _class) for _class in self.classes_])
         prevalences = class_counts / len(predictions)
         

mlquantify/meta/_classes.py

@@ -776,9 +776,9 @@ class QuaDapt(MetaquantifierMixin, BaseQuantifier):
         n_neg = n - n_pos
         
         # Scores positivos
-        p_score = np.random.uniform(size=n_pos) ** merging_factor
+        p_score = np.random.uniform(size=n_pos) ** m
         # Scores negativos
-        n_score = 1 - (np.random.uniform(size=n_neg) ** merging_factor)
+        n_score = 1 - (np.random.uniform(size=n_neg) ** m)
         
         # Construção dos arrays de features (duas colunas iguais)
         moss = np.column_stack(

mlquantify/multiclass.py

@@ -337,7 +337,7 @@ class BinaryQuantifier(MetaquantifierMixin, BaseQuantifier):
         classes = np.unique(args_dict["y_train"])
         qtf.strategy = getattr(qtf, "strategy", "ovr")
 
-        if hasattr(qtf, "binary") and qtf.binary:
+        if (hasattr(qtf, "binary") and qtf.binary) or len(classes) <= 2:
             return qtf._original_aggregate(*args_dict.values())
 
         if qtf.strategy == "ovr":

mlquantify/utils/_validation.py

@@ -97,22 +97,22 @@ def validate_y(quantifier: Any, y: np.ndarray) -> None:
 def _get_valid_crisp_predictions(predictions, threshold=0.5):
     predictions = np.asarray(predictions)
 
-    dimensions = predictions.shape[1] if len(predictions.shape) > 1 else 1
+    dimensions = predictions.ndim
 
     if dimensions > 2:
         predictions = np.argmax(predictions, axis=1)
     elif dimensions == 2:
-        predictions = (predictions[:, 1] > threshold).astype(int)
+        predictions = (predictions[:, 1] >= threshold).astype(int)
     elif dimensions == 1:
         if np.issubdtype(predictions.dtype, np.floating):
-            predictions = (predictions > threshold).astype(int)
+            predictions = (predictions >= threshold).astype(int)
     else:
         raise ValueError(f"Predictions array has an invalid number of dimensions. Expected 1 or more dimensions, got {predictions.ndim}.")
 
     return predictions
 
 
-def validate_predictions(quantifier: Any, predictions: np.ndarray) -> None:
+def validate_predictions(quantifier: Any, predictions: np.ndarray, threshold: float = 0.5) -> np.ndarray:
     """
     Validate predictions using the quantifier's declared output tags.
     Raises InputValidationError if inconsistent with tags.
@@ -132,7 +132,7 @@ def validate_predictions(quantifier: Any, predictions: np.ndarray) -> None:
             f"Soft predictions for {quantifier.__class__.__name__} must be float, got dtype {predictions.dtype}."
         )
     elif estimator_type == "crisp" and np.issubdtype(predictions.dtype, np.floating):
-        predictions = _get_valid_crisp_predictions(predictions) 
+        predictions = _get_valid_crisp_predictions(predictions, threshold) 
     return predictions   
     
     

{mlquantify-0.1.12.dist-info → mlquantify-0.1.14.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mlquantify
-Version: 0.1.12
+Version: 0.1.14
 Summary: Quantification Library
 Home-page: https://github.com/luizfernandolj/QuantifyML/tree/master
 Maintainer: Luiz Fernando Luth Junior

{mlquantify-0.1.12.dist-info → mlquantify-0.1.14.dist-info}/RECORD

@@ -3,17 +3,17 @@ mlquantify/base.py,sha256=o7IaKODocyi4tEmCvGmHKQ8F4ZJsaEh4kymsNcLyHAg,5077
 mlquantify/base_aggregative.py,sha256=uqfhpUmgv5pNLLvqgROCWHfjs3sj_2jfwOTyzUySuGo,7545
 mlquantify/calibration.py,sha256=chG3GNX2BBDTWIuSVfZUJ_YF_ZVBSoel2d_AN0OChS0,6
 mlquantify/confidence.py,sha256=QkEWr6s-Su3Nbinia_TRQbBeTM6ymDPe7Bv204XBKKA,10799
-mlquantify/multiclass.py,sha256=Jux0fvL5IBZA3DXLCuqUEE77JYYBGAcW6GaEH9srmu4,11747
+mlquantify/multiclass.py,sha256=wFbbXKqGsFVSsI9zC0EHGYyyx1JRxFpzMi_q8l80TUM,11770
 mlquantify/adjust_counting/__init__.py,sha256=AWio99zeaUULQq9vKggkFhnq-tqgXxasQt167NdcNVY,307
-mlquantify/adjust_counting/_adjustment.py,sha256=x0i_jAWCw2UP9Gt20EteYxLmCr1Xh_AbISwFRbOVoI8,23234
-mlquantify/adjust_counting/_base.py,sha256=tbYq2Efaxsub_vzXoMOR-J6SZlK6K8oRr5UvSSsjVvs,9428
-mlquantify/adjust_counting/_counting.py,sha256=7Ip7-XHQJcTWcWVDaLzEIM6WYcp8k5axsCIyD3QPWZE,5572
+mlquantify/adjust_counting/_adjustment.py,sha256=aQ92-wfRF1TT_d3kQecFleSWE8CdGBJiZx3bbePuXM0,23284
+mlquantify/adjust_counting/_base.py,sha256=MjBsNG7wE0Z_KToXX8WbthhVvz-yc0-d2zIqPo1CB9g,9429
+mlquantify/adjust_counting/_counting.py,sha256=6PKea54xvsga8spNEbsngKNQPyGUXzOkCRyXQR8rTdo,5699
 mlquantify/adjust_counting/_utils.py,sha256=DEPNzvcr0KszCnfUJaRzBilwWzuNVMSdy5eV7aQ_JPE,2907
 mlquantify/likelihood/__init__.py,sha256=3dC5uregNmquUKz0r0-3aPspfjZjKGn3TRBoZPO1uFs,53
 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=JAnMS4bu2XHXI_sSZUfcW_uIXRanoA0NIS3uN6dWSv4,30956
+mlquantify/meta/_classes.py,sha256=RKEVghPMBlyv516xrUtTyUkHvC2-5IsTUO_oVwAt3Gw,30930
 mlquantify/metrics/__init__.py,sha256=3bzzjSYTgrZIJsfAgJidQlB-bnjInwVYUvJ34bPhZxY,186
 mlquantify/metrics/_oq.py,sha256=koXDKeHWksl_vHpZuhc2pAps8wvu_MOgEztlSr04MmE,3544
 mlquantify/metrics/_rq.py,sha256=3yiEmGaRAGpzL29Et3tNqkJ3RMsLXwUX3uL9RoIgi40,3034
@@ -45,9 +45,9 @@ mlquantify/utils/_parallel.py,sha256=XotpX9nsj6nW-tNCmZ-ahTcRztgnn9oQKP2cl1rLdYM
 mlquantify/utils/_random.py,sha256=7F3nyy7Pa_kN8xP8P1L6MOM4WFu4BirE7bOfGTZ1Spk,1275
 mlquantify/utils/_sampling.py,sha256=QQxE2WKLdiCFUfPF6fKgzyrsOUIWYf74w_w8fbYVc2c,8409
 mlquantify/utils/_tags.py,sha256=Rz78TLpxgVxBKS0mKTlC9Qo_kn6HaEwVKNXh8pxFT7M,1095
-mlquantify/utils/_validation.py,sha256=yR5zqh_c7OHPnuMFBgKbrdU1bG-oXL2thojFEzydzWs,16798
+mlquantify/utils/_validation.py,sha256=TGGnfv7F5rnQmVeSqGMuS9AP76O974b1TPishKCCWls,16800
 mlquantify/utils/prevalence.py,sha256=FXLCJViQb2yDbyTXeGZt8WsPPnSZINhorQYZTKXOn14,1772
-mlquantify-0.1.12.dist-info/METADATA,sha256=qMZWMClRDNjUuFjuiAGhC7aDA3r9hlECzSbyoSLlQ-4,4701
-mlquantify-0.1.12.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-mlquantify-0.1.12.dist-info/top_level.txt,sha256=tGEkYkbbFElwULvqENjam3u1uXtyC1J9dRmibsq8_n0,11
-mlquantify-0.1.12.dist-info/RECORD,,
+mlquantify-0.1.14.dist-info/METADATA,sha256=-uPQqaXhgbXEq9M4EWYGKK9t3RRGNpbZY436DCL3bog,4701
+mlquantify-0.1.14.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+mlquantify-0.1.14.dist-info/top_level.txt,sha256=tGEkYkbbFElwULvqENjam3u1uXtyC1J9dRmibsq8_n0,11
+mlquantify-0.1.14.dist-info/RECORD,,