Prepare release

Author: SandroMartens

dbgsom/BaseSom.py

@@ -9,6 +9,8 @@
 
 from typing_extensions import Self
 
+from line_profiler import profile
+
 # from matplotlib import pyplot as plt
 # import matplotlib
 
@@ -938,10 +940,11 @@ def exponential_decay(
     return sigma
 
 
-@nb.njit(
-    # parallel=True,
-    fastmath=True
-)
+# @nb.njit(
+#     # parallel=True,
+#     fastmath=True
+# )
+@profile
 def numba_voronoi_set_centers(winners: npt.NDArray, data: npt.NDArray, shape: tuple):
     """
     Calculates the centers of the Voronoi regions based on the winners and data arrays.
@@ -968,7 +971,9 @@ def numba_voronoi_set_centers(winners: npt.NDArray, data: npt.NDArray, shape: tu
     return voronoi_set_centers
 
 
-@nb.njit(fastmath=True)
+@nb.njit(fastmath=True, 
+        #  parallel=True,
+    )
 def numba_quantization_error(
     data: npt.NDArray, winners: npt.NDArray, length, weights: npt.NDArray
 ):

dbgsom/SomClassifier.py

@@ -12,7 +12,7 @@
     check_is_fitted,
     check_X_y,
 )
-from dbgsom.BaseSom import BaseSom
+from .BaseSom import BaseSom
 
 
 class SomClassifier(BaseSom, TransformerMixin, ClassifierMixin):
@@ -206,12 +206,13 @@ def predict_proba(self, X: npt.ArrayLike) -> np.ndarray:
             sample_probabilities = np.array(probabilities_rows)
 
         else:
-            X_transformed = self.transform(X)
-            node_probabilities = self._extract_values_from_graph("probabilities")
-            # Sample Probabilities do not sum to 1
-            sample_probabilities_unnormalized = X_transformed @ node_probabilities
-            sample_probabilities = sample_probabilities_unnormalized / (
-                sample_probabilities_unnormalized.sum(axis=1)[np.newaxis].T
-            )
+            pass
+            # X_transformed = self.transform(X)
+            # node_probabilities = self._extract_values_from_graph("probabilities")
+            # # Sample Probabilities do not sum to 1
+            # sample_probabilities_unnormalized = X_transformed @ node_probabilities
+            # sample_probabilities = sample_probabilities_unnormalized / (
+            #     sample_probabilities_unnormalized.sum(axis=1)[np.newaxis].T
+            # )
 
         return sample_probabilities

setup.py

@@ -4,14 +4,14 @@
     long_description = f.read()
 
 setup(
-    name="dbgsom",
-    version="1.0.1",
+    name="DBGSOM",
+    version="1.1.0",
     description="A directed batch growing approach to enhance the topology preservation of self-organizing maps ",
     long_description=long_description,
     author="Sandro Martens",
     author_email="sandro.martens@web.de",
     license="MIT",
-    packages=["dbgsom"],
+    packages=["DBGSOM"],
     install_requires=[
         "numpy",
         "networkx",