mlquantify 0.1.2__py3-none-any.whl → 0.1.4__py3-none-any.whl

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/methods/threshold_optimization.py

@@ -659,157 +659,6 @@ class MS2(ThresholdOptimization):
 
         return np.asarray(prevalences)
 
-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}
-    """
-
-    def __init__(self, learner: BaseEstimator=None, threshold: float = 0.5):
-        super().__init__(learner)
-        self.threshold = threshold
-
-    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.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)
-    
-    
-    
-
-
-
 
 
 class T50(ThresholdOptimization):

mlquantify/utils/general.py

@@ -26,12 +26,9 @@ def convert_columns_to_arrays(df, columns:list = ['PRED_PREVS', 'REAL_PREVS']):
     return df
 
 
-
-
-
-def generate_artificial_indexes(y, prevalence: list, sample_size:int, classes:list):
+def get_indexes_with_prevalence(y, prevalence: list, sample_size:int):
     """
-    Generate indexes for a stratified sample based on the prevalence of each class.
+    Get indexes for a stratified sample based on the prevalence of each class.
     
     Parameters
     ----------
@@ -48,10 +45,13 @@ def generate_artificial_indexes(y, prevalence: list, sample_size:int, classes:li
     -------
     list
         List of indexes for the stratified sample.
-    """        
+    """      
+    classes = np.unique(y)
+        
     # Ensure the sum of prevalences is 1
     assert np.isclose(sum(prevalence), 1), "The sum of prevalences must be 1"
     # Ensure the number of prevalences matches the number of classes
+    assert len(prevalence) == len(classes), "The number of prevalences must match the number of classes"
 
     sampled_indexes = []
     total_sampled = 0
@@ -78,6 +78,43 @@ def generate_artificial_indexes(y, prevalence: list, sample_size:int, classes:li
 
 
 
+def kraemer_sampling(n_dim: int, n_prev: int, n_iter: int = 1) -> np.ndarray:
+    """
+    Uniform sampling from the unit simplex using Kraemer's algorithm.
+
+    Parameters
+    ----------
+    n_dim : int
+        Number of dimensions.
+    n_prev : int
+        Size of the sample.
+    n_iter : int
+        Number of iterations.
+
+    Returns
+    -------
+    np.ndarray
+        Array of sampled prevalences.
+    """
+
+    def _sampling(n_dim: int, n_prev: int) -> np.ndarray:
+        if n_dim == 2:
+            u = np.random.rand(n_prev)
+            return np.vstack([1 - u, u]).T
+        else:
+            u = np.random.rand(n_prev, n_dim - 1)
+            u.sort(axis=-1)   # sort each row
+            _0s = np.zeros((n_prev, 1))
+            _1s = np.ones((n_prev, 1))
+            a = np.hstack([_0s, u])
+            b = np.hstack([u, _1s])
+            return b - a
+
+    # repeat n_iter times
+    prevs = _sampling(n_dim, n_prev)
+
+    return np.repeat(prevs, n_iter, axis=0) if n_iter > 1 else prevs
+ 
 
 def generate_artificial_prevalences(n_dim: int, n_prev: int, n_iter: int) -> np.ndarray:
     """Generates n artificial prevalences with n dimensions.

{mlquantify-0.1.2.dist-info → mlquantify-0.1.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: mlquantify
-Version: 0.1.2
+Version: 0.1.4
 Summary: Quantification Library
 Home-page: https://github.com/luizfernandolj/QuantifyML/tree/master
 Maintainer: Luiz Fernando Luth Junior
@@ -40,9 +40,9 @@ ___
 
 ## Latest Release
 
-- **Version 0.0.11.6**: Inicial beta version. For a detailed list of changes, check the [changelog](#).
-- In case you need any help, refer to the [wiki](https://github.com/luizfernandolj/mlquantify/wiki).
-- Explore the [API documentation](#) for detailed developer information.
+- **Version 0.1.3**: 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/)
 
 ___
@@ -70,7 +70,7 @@ ___
 | **21 Quantification Methods** | Methods for quantification, such as classify & Count Correct methods, Threshold Optimization, Mixture Models and more.|
 | **Dynamic class management** | All methods are dynamic, and handles multiclass and binary problems, in case of binary it makes One-Vs-All (OVA) automatically. |
 | **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, BIAS, NAE, SE, KLD, etc.). |
+| **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. |
@@ -82,7 +82,10 @@ ___
 This code first loads the breast cancer dataset from _sklearn_, which is then split into training and testing sets. It uses the _Expectation Maximisation Quantifier (EMQ)_ with a RandomForest classifier to predict class prevalence. After training the model, it evaluates performance by calculating and printing the absolute error and bias between the real and predicted prevalences.
 
 ```python
-import mlquantify as mq
+from mlquantify.methods import EMQ
+from mlquantify.evaluation.measures import absolute_error, mean_absolute_error
+from mlquantify.utils import get_real_prev
+
 from sklearn.ensemble import RandomForestClassifier
 from sklearn.datasets import load_breast_cancer
 from sklearn.model_selection import train_test_split
@@ -94,19 +97,19 @@ features, target = load_breast_cancer(return_X_y=True)
 X_train, X_test, y_train, y_test = train_test_split(features, target, test_size=0.3)
 
 #Create the model, here it is the Expectation Maximisation Quantifier (EMQ) with a classifier
-model = mq.methods.EMQ(RandomForestClassifier())
+model = EMQ(RandomForestClassifier())
 model.fit(X_train, y_train)
 
 #Predict the class prevalence for X_test
 pred_prevalence = model.predict(X_test)
-real_prevalence = mq.utils.get_real_prev(y_test)
+real_prevalence = get_real_prev(y_test)
 
 #Get the error for the prediction
-ae = mq.evaluation.absolute_error(real_prevalence, pred_prevalence)
-bias = mq.evaluation.bias(real_prevalence, pred_prevalence)
+ae = absolute_error(real_prevalence, pred_prevalence)
+mae = mean_absolute_error(real_prevalence, pred_prevalence)
 
-print(f"Mean Squared Error (MSE) -> {ae:.4f}")
-print(f"Bias -> {bias}")
+print(f"Absolute Error -> {ae}")
+print(f"Mean Absolute Error -> {mae}")
 ```
 
 ___
@@ -125,7 +128,7 @@ ___
 
 ## Documentation
 
-##### API is avaliable [here](#)
+##### 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)

{mlquantify-0.1.2.dist-info → mlquantify-0.1.4.dist-info}/RECORD

@@ -6,17 +6,17 @@ mlquantify/classification/__init__.py,sha256=3FGf-F4SOM3gByUPsWdnBzjyC_31B3Mtzuo
 mlquantify/classification/methods.py,sha256=yDSbpoqM3hfF0a9ATzKqfG9S-44x-0Rq0lkAVJKTIEs,5006
 mlquantify/evaluation/__init__.py,sha256=x1grng0n_QeZpVBU8-pwagYdBMkbMRILtrp1qk_bLvk,447
 mlquantify/evaluation/measures.py,sha256=fIKyxxlD8em3oaj4u_BeXmNyUQG_A0vXWY8APPgNoJ0,6579
-mlquantify/evaluation/protocol.py,sha256=OsOXm_vf7sYlw9pQv08WxAvvgzo10bAqiDM-1cpz7nQ,24020
+mlquantify/evaluation/protocol.py,sha256=__tzRyqW4cJz4Fl87TInf7dXxIJ6bSaYaSaw-SdkNmM,10365
 mlquantify/methods/__init__.py,sha256=ya3Mn7bcz2r3oaIT7yVR4iJkAfgEAwF4xDK54C0rZ7U,536
-mlquantify/methods/aggregative.py,sha256=rL_xlX2nYECrxFSjBJNlxj6h3b-iIs7l_XgxIRSYHpw,34164
+mlquantify/methods/aggregative.py,sha256=F5Z-tGA9OcZgMBLKOeaos6wIgvvnDeriZ4y0TyMpDrc,39051
 mlquantify/methods/meta.py,sha256=sZWQHUGkm6iiqujmIpHDL_8tDdKQ161bzD5mcpXLWEY,19066
 mlquantify/methods/mixture_models.py,sha256=si2Pzaka5Kbva4QKBzLolvb_8V0ZEjp68UBAiOwl49s,35166
 mlquantify/methods/non_aggregative.py,sha256=xaBu21TUtiYkOEUKO16NaNMwdNa6-SNjfBsc5PpIMyI,4815
-mlquantify/methods/threshold_optimization.py,sha256=-iOcP5YcXZd0XZHGvbmcoE72hXR6D9YCoTnr1l80-9k,35796
+mlquantify/methods/threshold_optimization.py,sha256=NYGKbYvtfmiBeU8wpTiFCdURkijcPRZtybPOt6vtXbY,30489
 mlquantify/utils/__init__.py,sha256=logWrL6B6mukP8tvYm_UPEdO9eNA-J-ySILr7-syDoc,44
-mlquantify/utils/general.py,sha256=Li5ix_dy19dUhYNgiUsNHdqqnSVYvznUBUuyr-zYSPI,7554
+mlquantify/utils/general.py,sha256=wKJSmwF1KfSlSrDm0KTf92FMvB62BBOxf2Se9HyeWYE,8668
 mlquantify/utils/method.py,sha256=RL4vBJGl5_6DZ59Bs62hdNXI_hnoDIWilMMyMPiOjBg,12631
-mlquantify-0.1.2.dist-info/METADATA,sha256=2j3pqrm5djMAPm7bKTIjBjtg71OzAbFpwC-_ofOoSlc,4940
-mlquantify-0.1.2.dist-info/WHEEL,sha256=CmyFI0kx5cdEMTLiONQRbGQwjIoR1aIYB7eCAQ4KPJ0,91
-mlquantify-0.1.2.dist-info/top_level.txt,sha256=tGEkYkbbFElwULvqENjam3u1uXtyC1J9dRmibsq8_n0,11
-mlquantify-0.1.2.dist-info/RECORD,,
+mlquantify-0.1.4.dist-info/METADATA,sha256=UtNxYnZnSt6HS0B8JsW5A5tvxlxFUH_GODjF1AXXsSY,5166
+mlquantify-0.1.4.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+mlquantify-0.1.4.dist-info/top_level.txt,sha256=tGEkYkbbFElwULvqENjam3u1uXtyC1J9dRmibsq8_n0,11
+mlquantify-0.1.4.dist-info/RECORD,,

{mlquantify-0.1.2.dist-info → mlquantify-0.1.4.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (78.1.0)
+Generator: setuptools (80.9.0)
 Root-Is-Purelib: true
 Tag: py3-none-any