Merge pull request #60 from gmrukwa/dunn-fixes

Release v2.5.3 - Sampled Dunn fix

.github/workflows/deploy.yml

@@ -12,7 +12,7 @@ on:
 env:
   MAJOR: ${{ 2 }}
   MINOR: ${{ 5 }}
-  FIXUP: ${{ 2 }}
+  FIXUP: ${{ 3 }}
   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:2.5.2
+docker pull gmrukwa/divik:2.5.3
 ```
 
 ## Python package
@@ -79,7 +79,7 @@ pip install divik
 or any stable tagged version, e.g.:
 
 ```bash
-pip install divik==2.5.2
+pip install divik==2.5.3
 ```
 
 If you want to have compatibility with

divik/__init__.py

@@ -1,4 +1,4 @@
-__version__ = '2.5.2'
+__version__ = '2.5.3'
 
 from ._summary import plot, reject_split
 

divik/_cli/fit_clusters.py

@@ -35,6 +35,8 @@ def experiment(
     logging.info(str(model))
     data = load_data()
     xy = load_xy()
+    # repeated dump just because the dataset locations are not tracked
+    dump_gin_args(destination)
     model.fit(data)
     save(model, destination, xy=xy)
 

divik/score/_dunn.py

@@ -131,6 +131,6 @@ def sampled_dunn(kmeans: KMeans, data: Data,
         distances = partial(_sample_distances, sampler=d, kmeans=kmeans,
                             inter=inter, intra=intra)
         inter_, intra_ = np.array(pool.map(distances, seeds)).T
-    v_inter = inter_.var()
-    v_intra = intra_.var()
-    return (inter_.min() - v_inter) / (intra_.max() + v_intra)
+    s_inter = inter_.std()
+    s_intra = intra_.std()
+    return (inter_.min() - s_inter) / (intra_.max() + s_intra)

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:2.5.2
+    docker pull gmrukwa/divik:2.5.3
 
 Python package
 --------------
@@ -31,7 +31,7 @@ package::
 
 or any stable tagged version, e.g.::
 
-    pip install divik==2.5.2
+    pip install divik==2.5.3
 
 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__ = '2.5.2'
+__version__ = '2.5.3'
 
 LINUX_OPTS = {
     'extra_link_args': [

test/score/test_dunn.py

@@ -58,7 +58,7 @@ def test_works_with_other_distances(self):
 class TestSamplingDunn(unittest.TestCase):
     def setUp(self):
         self.X, _ = make_blobs(n_samples=10000, n_features=2, centers=3,
-                               random_state=0)
+                               random_state=0, cluster_std=0.1)
         self.kmeans_3 = km.KMeans(n_clusters=3).fit(self.X)
         self.kmeans_7 = km.KMeans(n_clusters=7).fit(self.X)