Merge pull request #6532 from noahnovsak/dask-fix-removenancolumns

RemoveNaNColumns - compute nans in advance
biolab · Aug 16, 2023 · 5ae6389 · 5ae6389
2 parents 32e0a15 + e0a3988
commit 5ae6389
Showing 1 changed file with 2 additions and 1 deletion.
diff --git a/Orange/preprocess/preprocess.py b/Orange/preprocess/preprocess.py
@@ -307,7 +307,8 @@ def __call__(self, data, threshold=None):
                         self.threshold
         if isinstance(threshold, float):
             threshold = threshold * data.X.shape[0]
-        nans = np.sum(np.isnan(data.X), axis=0)
+        # compute nans in advance, otherwise dask will do it for every attribute
+        nans = np.asarray(np.sum(np.isnan(data.X), axis=0))
         att = [a for a, n in zip(data.domain.attributes, nans) if n < threshold]
         domain = Orange.data.Domain(att, data.domain.class_vars,
                                     data.domain.metas)