Merge pull request #54 from gmrukwa/fixup-percentiles-normalization

Fixup percentiles normalization

.github/workflows/deploy.yml

@@ -12,7 +12,7 @@ on:
 env:
   MAJOR: ${{ 2 }}
   MINOR: ${{ 4 }}
-  FIXUP: ${{ 7 }}
+  FIXUP: ${{ 8 }}
   PACKAGE_INIT_FILE: ${{ 'divik/__init__.py' }}
   PACKAGE_INIT_FILE_VERSION_LINE: ${{ 1 }}
   PACKAGE_SETUP_FILE: ${{ 'setup.py' }}

README.md

@@ -40,7 +40,7 @@ docker pull gmrukwa/divik
 To install specific version, you can specify it in the command, e.g.:
 
 ```bash
-docker pull gmrukwa/divik:2.4.7
+docker pull gmrukwa/divik:2.4.8
 ```
 
 ## Python package
@@ -79,7 +79,7 @@ pip install divik
 or any stable tagged version, e.g.:
 
 ```bash
-pip install divik==2.4.7
+pip install divik==2.4.8
 ```
 
 If you want to have compatibility with

divik/__init__.py

@@ -1,4 +1,4 @@
-__version__ = '2.4.7'
+__version__ = '2.4.8'
 
 from ._summary import plot, reject_split
 

divik/cluster/_kmeans/_initialization.py

@@ -244,7 +244,7 @@ def __call__(self, data: Data, number_of_centroids: int) -> Centroids:
         leaves = get_leaves(tree)
         box_centroids = np.vstack([l.centroid for l in leaves])
         box_weights = np.array([l.count for l in leaves])
-        normalized_weights = box_weights / np.sum(box_weights)
+        normalized_weights = 100 * box_weights / np.sum(box_weights)
 
         residuals = _find_residuals(box_centroids, box_weights)
         centroids = np.nan * np.zeros((number_of_centroids, data.shape[1]))

docs/instructions/installation.rst

@@ -14,7 +14,7 @@ To install latest stable version use::
 
 To install specific version, you can specify it in the command, e.g.::
 
-    docker pull gmrukwa/divik:2.4.7
+    docker pull gmrukwa/divik:2.4.8
 
 Python package
 --------------
@@ -31,7 +31,7 @@ package::
 
 or any stable tagged version, e.g.::
 
-    pip install divik==2.4.7
+    pip install divik==2.4.8
 
 If you want to have compatibility with
 `gin-config <https://github.com/google/gin-config>`_, you can install

setup.py

@@ -6,7 +6,7 @@
 import sys
 import numpy
 
-__version__ = '2.4.7'
+__version__ = '2.4.8'
 
 LINUX_OPTS = {
     'extra_link_args': [

test/cluster/kmeans/test_initialization.py

@@ -47,3 +47,13 @@ class PercentileInitializationTest(ExtremeInitializationTest):
     def setUp(self):
         self.number_of_clusters = 2
         self.initialize = km.PercentileInitialization('euclidean')
+
+
+class KDTreePercentileInitializationTest(unittest.TestCase):
+    def setUp(self):
+        self.number_of_clusters = 2
+        self.initialize = km.KDTreePercentileInitialization(
+            'euclidean', 0.1, 99.)
+
+    def test_works_for_sample_data(self):
+        self.initialize(data, self.number_of_clusters)