mlquantify 0.1.1__tar.gz → 0.1.3__tar.gz

mlquantify-0.1.3/MANIFEST.in

@@ -0,0 +1 @@
+include VERSION.txt

{mlquantify-0.1.1 → mlquantify-0.1.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mlquantify
-Version: 0.1.1
+Version: 0.1.3
 Summary: Quantification Library
 Home-page: https://github.com/luizfernandolj/QuantifyML/tree/master
 Maintainer: Luiz Fernando Luth Junior

mlquantify-0.1.3/VERSION.txt

@@ -0,0 +1 @@
+0.1.3

{mlquantify-0.1.1 → mlquantify-0.1.3}/mlquantify/methods/aggregative.py

@@ -907,10 +907,140 @@ class PCC(AggregativeQuantifier):
 
     
     
+class PACC(AggregativeQuantifier):
+    """
+    Probabilistic Adjusted Classify and Count (PACC). 
+    This method extends the Adjusted Classify and Count (AC) approach 
+    by leveraging the average class-conditional confidences obtained 
+    from a probabilistic classifier instead of relying solely on true 
+    positive and false positive rates.
+
+    Parameters
+    ----------
+    learner : BaseEstimator
+        A scikit-learn compatible classifier to be used for quantification.
+    threshold : float, optional
+        The decision threshold for classification. Default is 0.5.
+
+    Attributes
+    ----------
+    learner : BaseEstimator
+        A scikit-learn compatible classifier.
+    threshold : float
+        Decision threshold for classification. Default is 0.5.
+    tpr : float
+        True positive rate computed during the fitting process.
+    fpr : float
+        False positive rate computed during the fitting process.
+        
+    See Also
+    --------
+    ThresholdOptimization : Base class for threshold-based quantification methods.
+    ACC : Adjusted Classify and Count quantification method.
+    CC : Classify and Count quantification method.
+    
+    References
+    ----------
+    A. Bella, C. Ferri, J. Hernández-Orallo and M. J. Ramírez-Quintana, "Quantification via Probability Estimators," 2010 IEEE International Conference on Data Mining, Sydney, NSW, Australia, 2010, pp. 737-742, doi: 10.1109/ICDM.2010.75. Available at: https://ieeexplore.ieee.org/abstract/document/5694031
     
+    Examples
+    --------
+    >>> from mlquantify.methods.aggregative import PACC
+    >>> from mlquantify.utils.general import get_real_prev
+    >>> from sklearn.datasets import load_breast_cancer
+    >>> from sklearn.svm import SVC
+    >>> from sklearn.model_selection import train_test_split
+    >>>
+    >>> features, target = load_breast_cancer(return_X_y=True)
+    >>>
+    >>> X_train, X_test, y_train, y_test = train_test_split(features, target, test_size=0.2, random_state=42)
+    >>>
+    >>> pacc = PACC(learner=SVC(probability=True))
+    >>> pacc.fit(X_train, y_train)
+    >>> y_pred = pacc.predict(X_test)
+    >>> y_pred
+    {0: 0.4664886119311328, 1: 0.5335113880688672}
+    >>> get_real_prev(y_test)
+    {0: 0.3991228070175439, 1: 0.6008771929824561}
+    """
 
+    def __init__(self, learner: BaseEstimator=None, threshold: float = 0.5):
+        self.learner = learner
+        self.threshold = threshold
+        self.mean_pos = None
+        self.mean_neg = None
+    
+    @property
+    def is_probabilistic(self) -> bool:
+        return True
+    
+    @property
+    def is_multiclass(self) -> bool:
+        return False
 
+    def _fit_method(self, X, y):
+        # Get predicted labels and probabilities
+        if mq.arguments["y_labels"] is not None and mq.arguments["posteriors_train"] is not None:
+            y_labels = mq.arguments["y_labels"]
+            probabilities = mq.arguments["posteriors_train"]
+        else:
+            y_labels, probabilities = get_scores(X, y, self.learner, self.cv_folds, self.learner_fitted)
+        
+        # Adjust thresholds and compute true and false positive rates
+        
+        self.mean_pos = np.mean(probabilities[y_labels == self.classes[1], 1])
+        self.mean_neg = np.mean(probabilities[y_labels != self.classes[1], 1])
+        
+        return self
+
+
+    def _predict_method(self, X):
+        """
+        Predicts the class prevalence using the mean class-conditional 
+        probabilities from a probabilistic classifier.
 
+        Parameters
+        ----------
+        X : array-like or sparse matrix of shape (n_samples, n_features)
+            The input data for prediction.
+
+        Returns
+        -------
+        dict
+            A dictionary with class labels as keys and their respective 
+            prevalence estimates as values.
+
+        Notes
+        -----
+        The prevalence is adjusted using the formula:
+            prevalence = |mean_score - FPR| / (TPR - FPR), 
+        where mean_score is the average probability for the positive class.
+
+        Raises
+        ------
+        ZeroDivisionError
+            If `TPR - FPR` equals zero, indicating that the classifier's 
+            performance does not vary across the threshold range.
+        """
+        prevalences = {}
+
+        # Calculate probabilities for the positive class
+        probabilities = self.predict_learner(X)[:, 1]
+
+        # Compute the mean score for the positive class
+        mean_scores = np.mean(probabilities)
+
+        # Adjust prevalence based on TPR and FPR
+        if self.mean_pos - self.mean_neg == 0:
+            prevalence = mean_scores
+        else:
+            prevalence = np.clip(abs(mean_scores - self.mean_neg) / (self.mean_pos - self.mean_neg), 0, 1)
+
+        # Map the computed prevalence to the class labels
+        prevalences[self.classes[0]] = 1 - prevalence
+        prevalences[self.classes[1]] = prevalence
+
+        return prevalences
 
 
 class PWK(AggregativeQuantifier):
@@ -1012,7 +1142,6 @@ class PWK(AggregativeQuantifier):
 from . import threshold_optimization
 
 ACC = threshold_optimization.ACC
-PACC = threshold_optimization.PACC
 T50 = threshold_optimization.T50
 MAX = threshold_optimization.MAX
 X_method  = threshold_optimization.X_method

{mlquantify-0.1.1 → mlquantify-0.1.3}/mlquantify/methods/threshold_optimization.py

@@ -447,9 +447,8 @@ class MS(ThresholdOptimization):
     {0: 0.3991228070175439, 1: 0.6008771929824561}
     """
 
-    def __init__(self, learner: BaseEstimator=None, threshold: float = 0.5):
+    def __init__(self, learner: BaseEstimator=None):
         super().__init__(learner)
-        self.threshold = threshold
 
     def best_tprfpr(self, thresholds: np.ndarray, tprs: np.ndarray, fprs: np.ndarray) -> tuple:
         """
@@ -482,11 +481,42 @@ class MS(ThresholdOptimization):
         ValueError
             If `thresholds`, `tprs`, or `fprs` are empty or have mismatched lengths.
         """
-        # Compute median TPR and FPR
-        tpr = np.median(tprs)
-        fpr = np.median(fprs)
 
-        return (self.threshold, tpr, fpr)
+        return (thresholds, tprs, fprs)
+
+    def _predict_method(self, X) -> dict:
+        """
+        Predicts class prevalences using the adjusted threshold.
+
+        Parameters
+        ----------
+        X : pd.DataFrame or np.ndarray
+            The input features for prediction.
+
+        Returns
+        -------
+        np.ndarray
+            An array of predicted prevalences for the classes.
+        """
+        # Get predicted probabilities for the positive class
+        probabilities = self.predict_learner(X)[:, 1]
+        
+        prevs = []
+        
+        for thr, tpr, fpr in zip(self.threshold, self.tpr, self.fpr):
+            cc_output = len(probabilities[probabilities >= thr]) / len(probabilities)
+            
+            if tpr - fpr == 0:
+                prevalence = cc_output
+            else:
+                prev = np.clip((cc_output - fpr) / (tpr - fpr), 0, 1)
+                prevs.append(prev)
+        
+        prevalence = np.median(prevs)
+        
+        prevalences = [1 - prevalence, prevalence]
+
+        return np.asarray(prevalences)
 
     
 
@@ -586,166 +616,48 @@ class MS2(ThresholdOptimization):
         # Identify indices where the condition is satisfied
         indices = np.where(np.abs(tprs - fprs) > 0.25)[0]
         if len(indices) == 0:
-            raise ValueError("No cases meet the condition |TPR - FPR| > 0.25.")
-
-        # Compute medians for the selected cases
-        threshold = np.median(thresholds[indices])
-        tpr = np.median(tprs[indices])
-        fpr = np.median(fprs[indices])
-
-        return (threshold, tpr, fpr)
-
-
-class PACC(ThresholdOptimization):
-    """
-    Probabilistic Adjusted Classify and Count (PACC). 
-    This method extends the Adjusted Classify and Count (AC) approach 
-    by leveraging the average class-conditional confidences obtained 
-    from a probabilistic classifier instead of relying solely on true 
-    positive and false positive rates.
-
-    Parameters
-    ----------
-    learner : BaseEstimator
-        A scikit-learn compatible classifier to be used for quantification.
-    threshold : float, optional
-        The decision threshold for classification. Default is 0.5.
-
-    Attributes
-    ----------
-    learner : BaseEstimator
-        A scikit-learn compatible classifier.
-    threshold : float
-        Decision threshold for classification. Default is 0.5.
-    tpr : float
-        True positive rate computed during the fitting process.
-    fpr : float
-        False positive rate computed during the fitting process.
-        
-    See Also
-    --------
-    ThresholdOptimization : Base class for threshold-based quantification methods.
-    ACC : Adjusted Classify and Count quantification method.
-    CC : Classify and Count quantification method.
-    
-    References
-    ----------
-    A. Bella, C. Ferri, J. Hernández-Orallo and M. J. Ramírez-Quintana, "Quantification via Probability Estimators," 2010 IEEE International Conference on Data Mining, Sydney, NSW, Australia, 2010, pp. 737-742, doi: 10.1109/ICDM.2010.75. Available at: https://ieeexplore.ieee.org/abstract/document/5694031
-    
-    Examples
-    --------
-    >>> from mlquantify.methods.aggregative import PACC
-    >>> from mlquantify.utils.general import get_real_prev
-    >>> from sklearn.datasets import load_breast_cancer
-    >>> from sklearn.svm import SVC
-    >>> from sklearn.model_selection import train_test_split
-    >>>
-    >>> features, target = load_breast_cancer(return_X_y=True)
-    >>>
-    >>> X_train, X_test, y_train, y_test = train_test_split(features, target, test_size=0.2, random_state=42)
-    >>>
-    >>> pacc = PACC(learner=SVC(probability=True))
-    >>> pacc.fit(X_train, y_train)
-    >>> y_pred = pacc.predict(X_test)
-    >>> y_pred
-    {0: 0.4664886119311328, 1: 0.5335113880688672}
-    >>> get_real_prev(y_test)
-    {0: 0.3991228070175439, 1: 0.6008771929824561}
-    """
+            warnings.warn("No cases satisfy the condition |TPR - FPR| > 0.25.")
+            indices = np.where(np.abs(tprs - fprs) >= 0)[0]
+            
+        thresholds_ = thresholds[indices]
+        tprs_ = tprs[indices]
+        fprs_ = fprs[indices]
 
-    def __init__(self, learner: BaseEstimator=None, threshold: float = 0.5):
-        super().__init__(learner)
-        self.threshold = threshold
+        return (thresholds_, tprs_, fprs_)
 
-    def _predict_method(self, X):
+    def _predict_method(self, X) -> dict:
         """
-        Predicts the class prevalence using the mean class-conditional 
-        probabilities from a probabilistic classifier.
+        Predicts class prevalences using the adjusted threshold.
 
         Parameters
         ----------
-        X : array-like or sparse matrix of shape (n_samples, n_features)
-            The input data for prediction.
+        X : pd.DataFrame or np.ndarray
+            The input features for prediction.
 
         Returns
         -------
-        dict
-            A dictionary with class labels as keys and their respective 
-            prevalence estimates as values.
-
-        Notes
-        -----
-        The prevalence is adjusted using the formula:
-            prevalence = |mean_score - FPR| / (TPR - FPR), 
-        where mean_score is the average probability for the positive class.
-
-        Raises
-        ------
-        ZeroDivisionError
-            If `TPR - FPR` equals zero, indicating that the classifier's 
-            performance does not vary across the threshold range.
+        np.ndarray
+            An array of predicted prevalences for the classes.
         """
-        prevalences = {}
-
-        # Calculate probabilities for the positive class
+        # Get predicted probabilities for the positive class
         probabilities = self.predict_learner(X)[:, 1]
+        
+        prevs = []
+        
+        for thr, tpr, fpr in zip(self.threshold, self.tpr, self.fpr):
+            cc_output = len(probabilities[probabilities >= thr]) / len(probabilities)
+            
+            if tpr - fpr == 0:
+                prevalence = cc_output
+            else:
+                prev = np.clip((cc_output - fpr) / (tpr - fpr), 0, 1)
+                prevs.append(prev)
+        
+        prevalence = np.median(prevs)
+        
+        prevalences = [1 - prevalence, prevalence]
 
-        # Compute the mean score for the positive class
-        mean_scores = np.mean(probabilities)
-
-        # Adjust prevalence based on TPR and FPR
-        if self.tpr - self.fpr == 0:
-            prevalence = mean_scores
-        else:
-            prevalence = np.clip(abs(mean_scores - self.fpr) / (self.tpr - self.fpr), 0, 1)
-
-        # Map the computed prevalence to the class labels
-        prevalences[self.classes[0]] = 1 - prevalence
-        prevalences[self.classes[1]] = prevalence
-
-        return prevalences
-
-    def best_tprfpr(self, thresholds: np.ndarray, tprs: np.ndarray, fprs: np.ndarray) -> tuple:
-        """
-        Finds the true positive rate (TPR) and false positive rate (FPR) 
-        corresponding to the specified decision threshold.
-
-        Parameters
-        ----------
-        thresholds : np.ndarray
-            An array of threshold values.
-        tprs : np.ndarray
-            An array of true positive rates corresponding to the thresholds.
-        fprs : np.ndarray
-            An array of false positive rates corresponding to the thresholds.
-
-        Returns
-        -------
-        tuple
-            A tuple containing the specified threshold, TPR, and FPR.
-
-        Raises
-        ------
-        IndexError
-            If the specified threshold is not found in the `thresholds` array.
-        """
-        # Locate TPR and FPR for the specified threshold
-        tpr = tprs[thresholds == self.threshold][0]
-        fpr = fprs[thresholds == self.threshold][0]
-        return (self.threshold, tpr, fpr)
-
-    
-    
-    
-    def best_tprfpr(self, thresholds:np.ndarray, tprs: np.ndarray, fprs: np.ndarray) -> tuple:
-        tpr = tprs[thresholds == self.threshold][0]
-        fpr = fprs[thresholds == self.threshold][0]
-        return (self.threshold, tpr, fpr)
-    
-    
-    
-
-
+        return np.asarray(prevalences)
 
 
 

{mlquantify-0.1.1 → mlquantify-0.1.3}/mlquantify.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mlquantify
-Version: 0.1.1
+Version: 0.1.3
 Summary: Quantification Library
 Home-page: https://github.com/luizfernandolj/QuantifyML/tree/master
 Maintainer: Luiz Fernando Luth Junior

{mlquantify-0.1.1 → mlquantify-0.1.3}/mlquantify.egg-info/SOURCES.txt

@@ -1,4 +1,6 @@
+MANIFEST.in
 README.md
+VERSION.txt
 setup.py
 mlquantify/__init__.py
 mlquantify/base.py

{mlquantify-0.1.1 → mlquantify-0.1.3}/setup.py

@@ -1,20 +1,20 @@
 from setuptools import setup, find_packages
-
 import pathlib
 
 here = pathlib.Path(__file__).parent.resolve()
-
 long_description = (here / 'README.md').read_text(encoding='utf-8')
 
-VERSION = '0.1.1'
+# Lê a versão do arquivo VERSION.txt
+version_file = here / 'VERSION.txt'
+VERSION = version_file.read_text(encoding='utf-8').strip()
+
 DESCRIPTION = 'Quantification Library'
 
-# Setting up
 setup(
     name="mlquantify",
     version=VERSION,
     url="https://github.com/luizfernandolj/QuantifyML/tree/master",
-    maintainer="Luiz Fernando Luth Junior",    
+    maintainer="Luiz Fernando Luth Junior",
     description=DESCRIPTION,
     long_description=long_description,
     long_description_content_type="text/markdown",
@@ -30,4 +30,4 @@ setup(
         "Operating System :: MacOS :: MacOS X",
         "Operating System :: Microsoft :: Windows",
     ]
-)
+)