linearrf 1.2.2__tar.gz → 1.2.4__tar.gz

{linearrf-1.2.2/src/linearrf.egg-info → linearrf-1.2.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: linearrf
-Version: 1.2.2
+Version: 1.2.4
 Summary: A python libary to build Random Forests with Linear Models at the leaves.
 Author-email: Marian Biermann <marianbiermann@gmx.de>
 Project-URL: homepage, https://github.com/marianbiermann/lrf

{linearrf-1.2.2 → linearrf-1.2.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "linearrf"
-version = "1.2.2"
+version = "1.2.4"
 description = "A python libary to build Random Forests with Linear Models at the leaves."
 readme = "README.md"
 authors = [{ name = "Marian Biermann", email = "marianbiermann@gmx.de" }]

{linearrf-1.2.2 → linearrf-1.2.4/src/linearrf.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: linearrf
-Version: 1.2.2
+Version: 1.2.4
 Summary: A python libary to build Random Forests with Linear Models at the leaves.
 Author-email: Marian Biermann <marianbiermann@gmx.de>
 Project-URL: homepage, https://github.com/marianbiermann/lrf

{linearrf-1.2.2 → linearrf-1.2.4}/src/lrf/_criterion.py

@@ -82,43 +82,61 @@ def neg_mcc(y_true: np.ndarray, y_pred: np.ndarray):
 
 
 def neg_roc_auc(y_true: np.ndarray, y_pred: np.ndarray):
-    # Rank-based ROC AUC in O(n log n). Sort by descending score and sweep:
-    # each step adds the next sample to "predicted positive", so cumulative
-    # positives / negatives give TPR / FPR at every distinct cutoff.
+    # Rank-based ROC AUC in O(n log n). Sort by descending score, then evaluate
+    # TPR/FPR only at distinct-score endpoints — collapsing each tied group
+    # into a single point. Without this, tied predictions produce results that
+    # depend on the (arbitrary) within-tie sort order.
     y_true = np.asarray(y_true)
     y_pred = np.asarray(y_pred)
 
     order = np.argsort(-y_pred, kind='stable')
     y_sorted = y_true[order].astype(np.float64)
+    pred_sorted = y_pred[order]
 
-    positives = y_sorted.sum()
-    negatives = y_sorted.size - positives
+    tps_full = np.cumsum(y_sorted)
+    fps_full = np.arange(1, y_sorted.size + 1, dtype=np.float64) - tps_full
+
+    # End of each tied group: positions where the next prediction differs,
+    # plus the very last position.
+    endpoints = np.concatenate((np.where(np.diff(pred_sorted))[0],
+                                [y_sorted.size - 1]))
+    tps = tps_full[endpoints]
+    fps = fps_full[endpoints]
+
+    positives, negatives = tps[-1], fps[-1]
     if positives == 0 or negatives == 0:
         return 0.0
 
-    tpr = np.concatenate(([0.0], np.cumsum(y_sorted) / positives))
-    fpr = np.concatenate(([0.0], np.cumsum(1.0 - y_sorted) / negatives))
+    tpr = np.concatenate(([0.0], tps / positives))
+    fpr = np.concatenate(([0.0], fps / negatives))
 
     # negated so the caller minimizes AUC (matches the previous convention)
     return -_trapz(tpr, fpr)
 
 
 def neg_pr_auc(y_true: np.ndarray, y_pred: np.ndarray):
-    # Rank-based PR AUC in O(n log n) — same idea as neg_roc_auc above.
+    # Rank-based PR AUC in O(n log n). Same tie-collapsing as neg_roc_auc.
     y_true = np.asarray(y_true)
     y_pred = np.asarray(y_pred)
 
     order = np.argsort(-y_pred, kind='stable')
     y_sorted = y_true[order].astype(np.float64)
+    pred_sorted = y_pred[order]
+
+    tps_full = np.cumsum(y_sorted)
+    fps_full = np.arange(1, y_sorted.size + 1, dtype=np.float64) - tps_full
+
+    endpoints = np.concatenate((np.where(np.diff(pred_sorted))[0],
+                                [y_sorted.size - 1]))
+    tps = tps_full[endpoints]
+    fps = fps_full[endpoints]
 
-    positives = y_sorted.sum()
+    positives = tps[-1]
     if positives == 0:
         return 0.0
 
-    pos_cum = np.cumsum(y_sorted)
-    ranks = np.arange(1, y_sorted.size + 1, dtype=np.float64)
-    precision = pos_cum / ranks
-    recall = pos_cum / positives
+    precision = tps / (tps + fps)
+    recall = tps / positives
 
     return -_trapz(precision, recall)
 

{linearrf-1.2.2 → linearrf-1.2.4}/src/lrf/lrf.py

@@ -21,6 +21,9 @@ class LRFRegressor(_LinearRandomForest):
         self.preprocessing = preprocessing
         self._estimator_type = 'regressor'
 
+        if criterion not in ('mse', 'rmse', 'mae', 'mape', 'wape', 'neg_explained_variance', 'neg_r2'):
+            print(' Metric "{}" is not implemented, MSE is used instead.'.format(criterion))
+
         if linear_model is None:
             linear_model = Regressor(alpha=self.alpha, preprocessing=self.preprocessing, intercept_in_input=True)
         else:
@@ -83,7 +86,6 @@ class LRFRegressor(_LinearRandomForest):
         elif self.criterion == 'neg_r2':
             val = neg_r2(y_true=y_true, y_pred=y_pred)
         else:
-            print(' Metric "{}" is not implemented, MSE is used instead.'.format(self.criterion))
             val = mse(y_true=y_true, y_pred=y_pred)
 
         return val
@@ -114,6 +116,10 @@ class LRFClassifier(_LinearRandomForest):
         self.preprocessing = preprocessing
         self._estimator_type = 'classifier'
 
+        if criterion not in ('hamming', 'cross_entropy', 'neg_mcc', 'neg_roc_auc', 'neg_pr_auc'):
+            print(' Metric "{}" is not implemented, negative Matthews Correlation Coefficient is used instead.'
+                  .format(criterion))
+
         if linear_model is None:
             linear_model = Classifier(C=self.C, preprocessing=self.preprocessing, intercept_in_input=True)
         else:
@@ -157,7 +163,8 @@ class LRFClassifier(_LinearRandomForest):
             x = x.to_numpy()
 
         # add intercept here and not inside linear model for performance reasons
-        x = np.insert(x, 0, 1, axis=1)
+        if self.linear_model is None:
+            x = np.insert(x, 0, 1, axis=1)
 
         # add columns with row index for sorting after multiprocessing
         x = np.insert(x, 0, np.arange(x.shape[0]), axis=1)
@@ -213,8 +220,6 @@ class LRFClassifier(_LinearRandomForest):
         elif self.criterion == 'neg_roc_auc':
             val = neg_roc_auc(y_true=y_true, y_pred=y_pred)
         else:
-            print(' Metric "{}" is not implemented, the negative Matthews Correlation Coefficient is used '
-                  'instead.'.format(self.criterion))
             val = neg_mcc(y_true=y_true, y_pred=y_pred)
 
         return val