Fixed k-means widget to new clustering

Orange/evaluation/clustering.py

@@ -110,7 +110,7 @@ def __init__(self, data, learners, k=1,
                     fold_models.append(model)
 
                 labels = model(data)
-                self.predicted[i, k, :] = labels.X.flatten()
+                self.predicted[i, k, :] = labels.flatten()
 
 
 

Orange/widgets/unsupervised/owkmeans.py

@@ -6,9 +6,11 @@
     pyqtSlot as Slot
 from AnyQt.QtGui import QIntValidator
 from AnyQt.QtWidgets import QGridLayout, QTableView
+from sklearn.metrics import silhouette_samples, silhouette_score
 
+import Orange.preprocess
 from Orange.clustering import KMeans
-from Orange.clustering.kmeans import KMeansModel, SILHOUETTE_MAX_SAMPLES
+from Orange.clustering.kmeans import KMeansModel
 from Orange.data import Table, Domain, DiscreteVariable, ContinuousVariable
 from Orange.data.util import get_unique_names, array_equal
 from Orange.preprocess.impute import ReplaceUnknowns
@@ -23,6 +25,10 @@
 
 
 RANDOM_STATE = 0
+SILHOUETTE_MAX_SAMPLES = 5000
+# those two preprocessors are required for clustering and silhouette
+preprocessors = [Orange.preprocess.Continuize(),
+                 Orange.preprocess.SklImpute()]
 
 
 class ClusterTableModel(QAbstractTableModel):
@@ -275,7 +281,7 @@ def _compute_clustering(data, k, init, n_init, max_iter, silhouette, random_stat
 
         return KMeans(
             n_clusters=k, init=init, n_init=n_init, max_iter=max_iter,
-            compute_silhouette_score=silhouette, random_state=random_state,
+            random_state=random_state
         )(data)
 
     @Slot(int, int)
@@ -432,10 +438,9 @@ def invalidate(self):
         self.commit()
 
     def update_results(self):
-        scores = [
-            mk if isinstance(mk, str) else mk.silhouette for mk in (
-                self.clusterings[k] for k in range(self.k_from, self.k_to + 1))
-        ]
+        scores = [mk if isinstance(mk, str) else silhouette_score(
+            self.data.X, mk(self.data)) for mk in (
+            self.clusterings[k] for k in range(self.k_from, self.k_to + 1))]
         best_row = max(
             range(len(scores)), default=0,
             key=lambda x: 0 if isinstance(scores[x], str) else scores[x]
@@ -454,6 +459,16 @@ def selected_row(self):
     def select_row(self):
         self.send_data()
 
+    def preproces(self, data):
+        for preprocessor in preprocessors:
+            data = preprocessor(data)
+        return data
+
+    def samples_scores(self, clust_ids):
+        d = self.preproces(self.data)
+        return np.arctan(
+            silhouette_samples(d.X, clust_ids)) / np.pi + 0.5
+
     def send_data(self):
         if self.optimize_k:
             row = self.selected_row()
@@ -473,12 +488,12 @@ def send_data(self):
             values=["C%d" % (x + 1) for x in range(km.k)]
         )
         clust_ids = km(self.data)
-        clust_col = clust_ids.X.ravel()
+        clust_col = clust_ids
         silhouette_var = ContinuousVariable(
             get_unique_names(domain, "Silhouette"))
-        if km.silhouette_samples is not None:
+        if len(self.data) <= SILHOUETTE_MAX_SAMPLES :
             self.Warning.no_silhouettes.clear()
-            scores = np.arctan(km.silhouette_samples) / np.pi + 0.5
+            scores = self.samples_scores(clust_ids)
             clust_scores = []
             for i in range(km.k):
                 in_clust = clust_col == i