mlquantify 0.0.11.3__tar.gz → 0.0.11.5__tar.gz

{mlquantify-0.0.11.3 → mlquantify-0.0.11.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mlquantify
-Version: 0.0.11.3
+Version: 0.0.11.5
 Summary: Quantification Library
 Home-page: https://github.com/luizfernandolj/QuantifyML/tree/master
 Maintainer: Luiz Fernando Luth Junior
@@ -12,6 +12,14 @@ Classifier: Operating System :: Unix
 Classifier: Operating System :: MacOS :: MacOS X
 Classifier: Operating System :: Microsoft :: Windows
 Description-Content-Type: text/markdown
+Requires-Dist: scikit-learn
+Requires-Dist: numpy
+Requires-Dist: scipy
+Requires-Dist: joblib
+Requires-Dist: tqdm
+Requires-Dist: pandas
+Requires-Dist: xlrd
+Requires-Dist: matplotlib
 
 <h1 align="center">MLQuantify</h1>
 <h4 align="center">A Python Package for Quantification</h4>
@@ -45,7 +53,7 @@ ___
 
 | Section | Description |
 |---|---|
-| **Quantification Methods** | Methods for quantification, such as classify & Count Correct methods, Threshold Optimization, Mixture Models and more.|
+| **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.). |

{mlquantify-0.0.11.3 → mlquantify-0.0.11.5}/README.md

@@ -30,7 +30,7 @@ ___
 
 | Section | Description |
 |---|---|
-| **Quantification Methods** | Methods for quantification, such as classify & Count Correct methods, Threshold Optimization, Mixture Models and more.|
+| **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.). |

{mlquantify-0.0.11.3 → mlquantify-0.0.11.5}/mlquantify/evaluation/measures/bias.py

@@ -11,6 +11,6 @@ def bias(prev_real:np.any, prev_pred:np.any):
     abs_errors = abs(prev_pred - prev_real)
     
     if classes:
-        return {class_:abs_error for class_, abs_error in zip(classes, abs_errors)}
+        return {class_:float(abs_error) for class_, abs_error in zip(classes, abs_errors)}
 
     return abs_errors

{mlquantify-0.0.11.3 → mlquantify-0.0.11.5}/mlquantify/methods/aggregative/gac.py

@@ -2,7 +2,7 @@ import numpy as np
 import pandas as pd
 from sklearn.base import BaseEstimator
 from sklearn.metrics import confusion_matrix
-from sklearn.model_selection import StratifiedKFold
+from sklearn.model_selection import train_test_split
 
 from ...base import AggregativeQuantifier
 
@@ -13,10 +13,12 @@ class GAC(AggregativeQuantifier):
     and solve it via constrained least-squares regression.
     """
     
-    def __init__(self, learner: BaseEstimator):
+    def __init__(self, learner: BaseEstimator, train_size:float=0.6, random_state:int=None):
         assert isinstance(learner, BaseEstimator), "learner object is not an estimator"
         self.learner = learner
         self.cond_prob_matrix = None
+        self.train_size = train_size
+        self.random_state = random_state
     
     def _fit_method(self, X, y):
         # Ensure X and y are DataFrames
@@ -29,26 +31,17 @@ class GAC(AggregativeQuantifier):
             y_pred = self.learner.predict(X)
             y_label = y
         else:
-            # Cross-validation for generating predictions
-            skf = StratifiedKFold(n_splits=self.cv_folds)
-            y_pred = []
-            y_label = []
+            X_train, X_val, y_train, y_val = train_test_split(
+                X, y, train_size=self.train_size, stratify=y, random_state=self.random_state
+            )
             
-            for train_index, valid_index in skf.split(X, y):
-                
-                train_data = pd.DataFrame(X.iloc[train_index])
-                train_label = y.iloc[train_index]
-                
-                valid_data = pd.DataFrame(X.iloc[valid_index])
-                valid_label = y.iloc[valid_index]
-                
-                self.learner.fit(train_data, train_label)
-                
-                y_pred.extend(self.learner.predict(valid_data))
-                y_label.extend(valid_label)
+            self.learner.fit(X_train, y_train)
+            
+            y_label = y_val
+            y_pred = self.learner.predict(X_val)
         
         # Compute conditional probability matrix
-        self.cond_prob_matrix = self.get_cond_prob_matrix(self.classes, y, y_pred)
+        self.cond_prob_matrix = GAC.get_cond_prob_matrix(self.classes, y_label, y_pred)
         
         return self
     
@@ -66,11 +59,11 @@ class GAC(AggregativeQuantifier):
         return adjusted_prevalences
     
     @classmethod
-    def get_cond_prob_matrix(cls, classes:list, true_labels:np.ndarray, predictions:np.ndarray) -> np.ndarray:
+    def get_cond_prob_matrix(cls, classes:list, y_labels:np.ndarray, predictions:np.ndarray) -> np.ndarray:
         """ Estimate the conditional probability matrix P(yi|yj)"""
 
-        CM = confusion_matrix(true_labels, predictions, labels=classes).T
-        CM = CM.astype(np.float32)
+        CM = confusion_matrix(y_labels, predictions, labels=classes).T
+        CM = CM.astype(float)
         class_counts = CM.sum(axis=0)
         for i, _ in enumerate(classes):
             if class_counts[i] == 0:
@@ -91,6 +84,6 @@ class GAC(AggregativeQuantifier):
             adjusted_prevalences = np.linalg.solve(A, B)
             adjusted_prevalences = np.clip(adjusted_prevalences, 0, 1)
             adjusted_prevalences /= adjusted_prevalences.sum()
-        except (np.linalg.LinAlgError, ValueError):
+        except (np.linalg.LinAlgError):
             adjusted_prevalences = predicted_prevalences  # No way to adjust them
         return adjusted_prevalences

{mlquantify-0.0.11.3 → mlquantify-0.0.11.5}/mlquantify/methods/aggregative/gpac.py

@@ -1,7 +1,7 @@
 import numpy as np
 import pandas as pd
 from sklearn.base import BaseEstimator
-from sklearn.model_selection import StratifiedKFold
+from sklearn.model_selection import train_test_split
 
 from .gac import GAC
 from ...base import AggregativeQuantifier
@@ -14,10 +14,12 @@ class GPAC(AggregativeQuantifier):
     """
     
     
-    def __init__(self, learner: BaseEstimator):
+    def __init__(self, learner: BaseEstimator, train_size:float=0.6, random_state:int=None):
         assert isinstance(learner, BaseEstimator), "learner object is not an estimator"
         self.learner = learner
         self.cond_prob_matrix = None
+        self.train_size = train_size
+        self.random_state = random_state
     
     def _fit_method(self, X, y):
         # Convert X and y to DataFrames if they are numpy arrays
@@ -28,31 +30,20 @@ class GPAC(AggregativeQuantifier):
             
         if self.learner_fitted:
             # Use existing model to predict
-            predictions = self.learner.predict(X)
-            true_labels = y
+            y_pred = self.learner.predict(X)
+            y_labels = y
         else:
-            # Perform cross-validation to generate predictions
-            skf = StratifiedKFold(n_splits=self.cv_folds)
-            predictions = []
-            true_labels = []
+            X_train, X_val, y_train, y_val = train_test_split(
+                X, y, train_size=self.train_size, stratify=y, random_state=self.random_state
+            )
             
-            for train_index, valid_index in skf.split(X, y):
-                # Split data into training and validation sets
-                train_data = pd.DataFrame(X.iloc[train_index])
-                train_labels = y.iloc[train_index]
-                
-                valid_data = pd.DataFrame(X.iloc[valid_index])
-                valid_labels = y.iloc[valid_index]
-                
-                # Train the learner
-                self.learner.fit(train_data, train_labels)
-                
-                # Predict and collect results
-                predictions.extend(self.learner.predict(valid_data))
-                true_labels.extend(valid_labels)
+            self.learner.fit(X_train, y_train)
+            
+            y_labels = y_val
+            y_pred = self.learner.predict(X_val)
         
         # Compute conditional probability matrix using GAC
-        self.cond_prob_matrix = GAC.get_cond_prob_matrix(self.classes, true_labels, predictions)
+        self.cond_prob_matrix = GAC.get_cond_prob_matrix(self.classes, y_labels, y_pred)
         
         return self
     
@@ -73,15 +64,15 @@ class GPAC(AggregativeQuantifier):
         return adjusted_prevalences
     
     @classmethod
-    def get_cond_prob_matrix(cls, classes:list, true_labels:np.ndarray, predictions:np.ndarray) -> np.ndarray:
+    def get_cond_prob_matrix(cls, classes:list, y_labels:np.ndarray, y_pred:np.ndarray) -> np.ndarray:
         """Estimate the matrix where entry (i,j) is the estimate of P(yi|yj)"""
         
         n_classes = len(classes)
         cond_prob_matrix = np.eye(n_classes)
         
         for i, class_ in enumerate(classes):
-            class_indices = true_labels == class_
+            class_indices = y_labels == class_
             if class_indices.any():
-                cond_prob_matrix[i] = predictions[class_indices].mean(axis=0)
+                cond_prob_matrix[i] = y_pred[class_indices].mean(axis=0)
         
         return cond_prob_matrix.T

{mlquantify-0.0.11.3 → mlquantify-0.0.11.5}/mlquantify.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: mlquantify
-Version: 0.0.11.3
+Version: 0.0.11.5
 Summary: Quantification Library
 Home-page: https://github.com/luizfernandolj/QuantifyML/tree/master
 Maintainer: Luiz Fernando Luth Junior
@@ -12,6 +12,14 @@ Classifier: Operating System :: Unix
 Classifier: Operating System :: MacOS :: MacOS X
 Classifier: Operating System :: Microsoft :: Windows
 Description-Content-Type: text/markdown
+Requires-Dist: scikit-learn
+Requires-Dist: numpy
+Requires-Dist: scipy
+Requires-Dist: joblib
+Requires-Dist: tqdm
+Requires-Dist: pandas
+Requires-Dist: xlrd
+Requires-Dist: matplotlib
 
 <h1 align="center">MLQuantify</h1>
 <h4 align="center">A Python Package for Quantification</h4>
@@ -45,7 +53,7 @@ ___
 
 | Section | Description |
 |---|---|
-| **Quantification Methods** | Methods for quantification, such as classify & Count Correct methods, Threshold Optimization, Mixture Models and more.|
+| **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.). |

{mlquantify-0.0.11.3 → mlquantify-0.0.11.5}/setup.py

@@ -6,7 +6,7 @@ here = pathlib.Path(__file__).parent.resolve()
 
 long_description = (here / 'README.md').read_text(encoding='utf-8')
 
-VERSION = '0.0.11.3'
+VERSION = '0.0.11.5'
 DESCRIPTION = 'Quantification Library'
 
 # Setting up