Merge pull request #32 from gmrukwa/fixup-gap-computation

Release v2.3.12
gmrukwa · Jan 9, 2020 · 7664288 · 7664288
2 parents 92b8427 + d73b474
commit 7664288
Show file tree

Hide file tree

Showing 6 changed files with 9 additions and 11 deletions.
diff --git a/.github/workflows/deploy.yml b/.github/workflows/deploy.yml
@@ -12,7 +12,7 @@ on:
 env:
   MAJOR: ${{ 2 }}
   MINOR: ${{ 3 }}
-  FIXUP: ${{ 11 }}
+  FIXUP: ${{ 12 }}
   PACKAGE_INIT_FILE: ${{ 'divik/__init__.py' }}
   DOCKER_REPO: ${{ 'gmrukwa/divik' }}
   IS_ALPHA: ${{ github.event_name == 'pull_request' }}

diff --git a/README.md b/README.md
@@ -39,7 +39,7 @@ docker pull gmrukwa/divik
 To install specific version, you can specify it in the command, e.g.:
 
 ```bash
-docker pull gmrukwa/divik:2.3.11
+docker pull gmrukwa/divik:2.3.12
 ```
 
 ## Python package
@@ -59,7 +59,7 @@ pip install divik
 or any stable tagged version, e.g.:
 
 ```bash
-pip install divik==2.3.11
+pip install divik==2.3.12
 ```
 
 # References

diff --git a/divik/__init__.py b/divik/__init__.py
@@ -1,4 +1,4 @@
-__version__ = '2.3.11'
+__version__ = '2.3.12'
 
 from ._seeding import seeded
 from ._utils import DivikResult

diff --git a/divik/_score/_gap.py b/divik/_score/_gap.py
@@ -20,10 +20,9 @@ def _dispersion(data: Data, kmeans: KMeans) -> float:
     if kmeans.normalize_rows:
         data = normalize_rows(data)
     clusters = pd.DataFrame(data).groupby(kmeans.labels_)
-    return float(np.sum([
-        np.sum(dist.cdist(kmeans.cluster_centers_[np.newaxis, label],
-                          cluster_members.values, kmeans.distance))
-        for label, cluster_members in clusters
+    return float(np.mean([
+        np.mean(dist.pdist(cluster_members.values, kmeans.distance))
+        for _, cluster_members in clusters
     ]))
 
 

diff --git a/divik/_score/_sampled_gap.py b/divik/_score/_sampled_gap.py
@@ -22,7 +22,6 @@ def sampled_gap(data: Data, kmeans: KMeans,
                 return_deviation: bool = False,
                 max_iter: int = 10) -> float:
     # TODO: Docs
-    # TODO: Tests
     data_ = StratifiedSampler(n_rows=sample_size, n_samples=n_trials
                               ).fit(data, kmeans.labels_)
     reference_ = UniformSampler(n_rows=sample_size, n_samples=n_trials

diff --git a/docs/instructions/installation.rst b/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:2.3.11
+    docker pull gmrukwa/divik:2.3.12
 
 Python package
 --------------
@@ -31,4 +31,4 @@ package::
 
 or any stable tagged version, e.g.::
 
-    pip install divik==2.3.11
+    pip install divik==2.3.12