mlquantify 0.1.10__py3-none-any.whl → 0.1.12__py3-none-any.whl

mlquantify/adjust_counting/_adjustment.py

@@ -603,7 +603,12 @@ class MS(ThresholdAdjustment):
         for thr, tpr, fpr in zip(thresholds, tprs, fprs):
             cc_predictions = CC(thr).aggregate(predictions)
             cc_predictions = cc_predictions[1]
-            prevalence = cc_predictions if tpr - fpr == 0 else (cc_predictions - fpr) / (tpr - fpr)
+            
+            if tpr - fpr == 0:
+                prevalence = cc_predictions
+            else:
+                prevalence = np.clip((cc_predictions - fpr) / (tpr - fpr), 0, 1)
+                
             prevs.append(prevalence)
         prevalence = np.median(prevs)
         return np.asarray([1 - prevalence, prevalence])

mlquantify/adjust_counting/_base.py

@@ -239,7 +239,10 @@ class BaseAdjustCount(AggregationMixin, BaseQuantifier):
     def aggregate(self, predictions, train_predictions, y_train_values):
         """Aggregate predictions and apply matrix- or rate-based bias correction."""
         self.classes_ = check_classes_attribute(self, np.unique(y_train_values))
-        predictions = validate_predictions(self, train_predictions)
+        
+        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_)
         return prevalences

mlquantify/meta/_classes.py

@@ -661,7 +661,7 @@ class QuaDapt(MetaquantifierMixin, BaseQuantifier):
     def __init__(self, 
                  quantifier,
                  measure="topsoe", 
-                 merging_factors=(0.1, 1.0, 0.2)):
+                 merging_factors=np.arange(0.1, 1.0, 0.2)):
         self.quantifier = quantifier
         self.measure = measure
         self.merging_factors = merging_factors
@@ -701,10 +701,7 @@ class QuaDapt(MetaquantifierMixin, BaseQuantifier):
         
         self.classes = self.classes if hasattr(self, 'classes') else np.unique(train_y_values)
 
-        moss = QuaDapt.MoSS(1000, 0.5, m)
-
-        moss_scores = moss[:, :2]
-        moss_labels = moss[:, 2]
+        moss_scores, moss_labels = self.MoSS(1000, 0.5, m)
 
         prevalences = self.quantifier.aggregate(predictions,
                                                 moss_scores,
@@ -721,9 +718,9 @@ class QuaDapt(MetaquantifierMixin, BaseQuantifier):
         distances = []
         
         for mf in MF:
-            scores = QuaDapt.MoSS(1000, 0.5, mf)
-            pos_scores = scores[scores[:, 2] == 1][:, :2]
-            neg_scores = scores[scores[:, 2] == 0][:, :2]
+            scores, labels = self.MoSS(1000, 0.5, mf)
+            pos_scores = scores[labels == 1][:, 1]
+            neg_scores = scores[labels == 0][:, 1]
             
             best_distance = self._get_best_distance(predictions, pos_scores, neg_scores)
             
@@ -772,14 +769,27 @@ class QuaDapt(MetaquantifierMixin, BaseQuantifier):
         .. [1] Maletzke, A., Reis, D. dos, Hassan, W., & Batista, G. (2021).
         Accurately Quantifying under Score Variability. 2021 IEEE International Conference on Data Mining (ICDM), 1228-1233. https://doi.org/10.1109/ICDM51629.2021.00149
         """
-        p_score = np.random.uniform(size=int(n * alpha)) ** m
-        n_score = 1 - (np.random.uniform(size=int(round(n * (1 - alpha), 0))) ** m)
-        scores = np.column_stack(
-            (np.concatenate((p_score, n_score)), 
-             np.concatenate((p_score, n_score)), 
-             np.concatenate((
-                 np.ones(len(p_score)), 
-                 np.full(len(n_score), 0))))
+        if isinstance(alpha, list):
+            alpha = float(alpha[1])
+            
+        n_pos = int(n * alpha)
+        n_neg = n - n_pos
+        
+        # Scores positivos
+        p_score = np.random.uniform(size=n_pos) ** merging_factor
+        # Scores negativos
+        n_score = 1 - (np.random.uniform(size=n_neg) ** merging_factor)
+        
+        # Construção dos arrays de features (duas colunas iguais)
+        moss = np.column_stack(
+            ( 
+                1 - np.concatenate((p_score, n_score)),
+                np.concatenate((p_score, n_score)),
+                np.int16(np.concatenate((np.ones(len(p_score)), np.full(len(n_score), 0))))
+            )
         )
-        return scores
+        
+        scores = moss[:, :2]
+        labels = moss[:, 2].astype(np.int16)
+        return scores, labels
         

mlquantify/mixture/_classes.py

@@ -308,8 +308,10 @@ class SMM(AggregativeMixture):
         mean_pos = np.mean(pos_scores)
         mean_neg = np.mean(neg_scores)
         mean_test = np.mean(predictions)
-        
-        alpha = (mean_test - mean_neg) / (mean_pos - mean_neg)
+        if mean_pos - mean_neg == 0:
+            alpha = mean_test
+        else:
+            alpha = np.clip((mean_test - mean_neg) / (mean_pos - mean_neg), 0, 1)
         return alpha, None
 
 

mlquantify/utils/_validation.py

@@ -274,7 +274,7 @@ def validate_data(quantifier,
         else:
             out = X, y
     elif not no_val_X and no_val_y:
-        out = check_array(X, input_name="X", **check_params)
+        out = check_array(X, input_name="X", dtype=None, **check_params)
     elif no_val_X and not no_val_y:
         out = _check_y(y, **check_params)
     else:
@@ -286,12 +286,12 @@ def validate_data(quantifier,
             check_X_params, check_y_params = validate_separately
             if "estimator" not in check_X_params:
                 check_X_params = {**default_check_params, **check_X_params}
-            X = check_array(X, input_name="X", **check_X_params)
+            X = check_array(X, input_name="X", dtype=None, **check_X_params)
             if "estimator" not in check_y_params:
                 check_y_params = {**default_check_params, **check_y_params}
             y = check_array(y, input_name="y", **check_y_params)
         else:
-            X, y = check_X_y(X, y, **check_params)
+            X, y = check_X_y(X, y, dtype=None, **check_params)
         out = X, y
         
     return out

{mlquantify-0.1.10.dist-info → mlquantify-0.1.12.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mlquantify
-Version: 0.1.10
+Version: 0.1.12
 Summary: Quantification Library
 Home-page: https://github.com/luizfernandolj/QuantifyML/tree/master
 Maintainer: Luiz Fernando Luth Junior
@@ -30,7 +30,7 @@ Dynamic: maintainer
 Dynamic: requires-dist
 Dynamic: summary
 
-<h1 align="center">MLQuantify</h1>
+<img src="assets/logo_mlquantify-white.svg" alt="mlquantify logo">
 <h4 align="center">A Python Package for Quantification</h4>
 
 ___
@@ -41,7 +41,7 @@ ___
 
 ## Latest Release
 
-- **Version 0.1.3**: Inicial beta version. For a detailed list of changes, check the [changelog](#).
+- **Version 0.1.11**: Inicial beta version. For a detailed list of changes, check the [changelog](#).
 - In case you need any help, refer to the [User Guide](https://luizfernandolj.github.io/mlquantify/user_guide.html).
 - Explore the [API documentation](https://luizfernandolj.github.io/mlquantify/api/index.html) for detailed developer information.
 - See also the library in the pypi site in [pypi mlquantify](https://pypi.org/project/mlquantify/)
@@ -73,7 +73,6 @@ ___
 | **Model Selection** | Criteria and processes used to select the best model, such as grid-search for the case of quantification|
 | **Evaluation Metrics** | Specific metrics used to evaluate quantification performance, (e.g., AE, MAE, NAE, SE, KLD, etc.). |
 | **Evaluation Protocols** | Evaluation protocols used, based on sampling generation (e.g., APP, NPP, etc.).. |
-| **Plotting Results** | Tools and techniques used to visualize results, such as the protocol results.|
 | **Comprehensive Documentation** | Complete documentation of the project, including code, data, and results. |
 
 ___
@@ -84,8 +83,8 @@ This code first loads the breast cancer dataset from _sklearn_, which is then sp
 
 ```python
 from mlquantify.methods import EMQ
-from mlquantify.evaluation.measures import absolute_error, mean_absolute_error
-from mlquantify.utils import get_real_prev
+from mlquantify.metrics import MAE, NRAE
+from mlquantify.utils import get_prev_from_labels
 
 from sklearn.ensemble import RandomForestClassifier
 from sklearn.datasets import load_breast_cancer
@@ -103,14 +102,14 @@ model.fit(X_train, y_train)
 
 #Predict the class prevalence for X_test
 pred_prevalence = model.predict(X_test)
-real_prevalence = get_real_prev(y_test)
+real_prevalence = get_prev_from_labels(y_test)
 
 #Get the error for the prediction
-ae = absolute_error(real_prevalence, pred_prevalence)
-mae = mean_absolute_error(real_prevalence, pred_prevalence)
+mae = MAE(real_prevalence, pred_prevalence)
+nrae = NRAE(real_prevalence, pred_prevalence)
 
-print(f"Absolute Error -> {ae}")
 print(f"Mean Absolute Error -> {mae}")
+print(f"Normalized Relative Absolute Error -> {nrae}")
 ```
 
 ___
@@ -129,13 +128,6 @@ ___
 
 ## Documentation
 
-##### API is avaliable [here](https://luizfernandolj.github.io/mlquantify/api/index.html)
-
-- [Methods](https://github.com/luizfernandolj/mlquantify/wiki/Methods)
-- [Model Selection](https://github.com/luizfernandolj/mlquantify/wiki/Model-Selection)
-- [Evaluation](https://github.com/luizfernandolj/mlquantify/wiki/Evaluation)
-- [Plotting](https://github.com/luizfernandolj/mlquantify/wiki/Plotting)
-- [Utilities](https://github.com/luizfernandolj/mlquantify/wiki/Utilities)
-
+##### API is avaliable [here](https://luizfernandolj.github.io/mlquantify/api/)
 
 ___

{mlquantify-0.1.10.dist-info → mlquantify-0.1.12.dist-info}/RECORD

@@ -5,22 +5,22 @@ mlquantify/calibration.py,sha256=chG3GNX2BBDTWIuSVfZUJ_YF_ZVBSoel2d_AN0OChS0,6
 mlquantify/confidence.py,sha256=QkEWr6s-Su3Nbinia_TRQbBeTM6ymDPe7Bv204XBKKA,10799
 mlquantify/multiclass.py,sha256=Jux0fvL5IBZA3DXLCuqUEE77JYYBGAcW6GaEH9srmu4,11747
 mlquantify/adjust_counting/__init__.py,sha256=AWio99zeaUULQq9vKggkFhnq-tqgXxasQt167NdcNVY,307
-mlquantify/adjust_counting/_adjustment.py,sha256=JYfPj-x0tw6aLt6m3YehsuKXF6FMUIIvjXImbiqXkGI,23130
-mlquantify/adjust_counting/_base.py,sha256=-nxH0seDXmEW9eGoqrH69JaIUCeNjFKBa8pDDH8u0Tg,9342
+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/_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=3twKSrm4mF_AXZ1FP0V0hoOo-ceJulGKKgSEBvU8Vt0,30631
+mlquantify/meta/_classes.py,sha256=JAnMS4bu2XHXI_sSZUfcW_uIXRanoA0NIS3uN6dWSv4,30956
 mlquantify/metrics/__init__.py,sha256=3bzzjSYTgrZIJsfAgJidQlB-bnjInwVYUvJ34bPhZxY,186
 mlquantify/metrics/_oq.py,sha256=koXDKeHWksl_vHpZuhc2pAps8wvu_MOgEztlSr04MmE,3544
 mlquantify/metrics/_rq.py,sha256=3yiEmGaRAGpzL29Et3tNqkJ3RMsLXwUX3uL9RoIgi40,3034
 mlquantify/metrics/_slq.py,sha256=JZceO2LR3mjbT_0zVcl9xI6jf8pn3tIcpP3vP3Luf9I,6817
 mlquantify/mixture/__init__.py,sha256=_KKhpFuvi3vYwxydm5nOy9MKwmIU4eyZDN9Pe00hqtk,70
 mlquantify/mixture/_base.py,sha256=1-yW64FPQXB_d9hH9KjSlDnmFtW9FY7S2hppXAd1DBg,5645
-mlquantify/mixture/_classes.py,sha256=uYtWh6oTx0M3rTG71gfO6RWt3QVXH6KN5F-J4YKN0TM,16329
+mlquantify/mixture/_classes.py,sha256=Dx0KWS-RtVVmJwXvPKIVWitsJhgcYRRiypLYrgE66x4,16420
 mlquantify/mixture/_utils.py,sha256=CKlC081nrkJ8Pil7lrPZvNZC_xfpXV8SsuQq3M_LHgA,4037
 mlquantify/model_selection/__init__.py,sha256=98I0uf8k6lbWAjazGyGjbOdPOvzU8aMRLqC3I7D3jzk,113
 mlquantify/model_selection/_protocol.py,sha256=2k0M_7YwZf7YLoQ8ElR2xMvLySVgtE_EvWieMXTIzTA,12499
@@ -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=dE7NYLy6C5UWf8tXIhQeWLTz2-rej_gr8-aAIwgJTPk,16762
+mlquantify/utils/_validation.py,sha256=yR5zqh_c7OHPnuMFBgKbrdU1bG-oXL2thojFEzydzWs,16798
 mlquantify/utils/prevalence.py,sha256=FXLCJViQb2yDbyTXeGZt8WsPPnSZINhorQYZTKXOn14,1772
-mlquantify-0.1.10.dist-info/METADATA,sha256=qvy3E7u4daj9ZSZnrza7ZtNHcs46xx63wMWbeq4R3T8,5193
-mlquantify-0.1.10.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-mlquantify-0.1.10.dist-info/top_level.txt,sha256=tGEkYkbbFElwULvqENjam3u1uXtyC1J9dRmibsq8_n0,11
-mlquantify-0.1.10.dist-info/RECORD,,
+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,,