FeatureHasher issue dask#963

brian-methodical · Feb 9, 2023 · 91daec6 · 91daec6
1 parent c59fc98
commit 91daec6
Showing 1 changed file with 3 additions and 1 deletion.
diff --git a/tests/feature_extraction/test_text.py b/tests/feature_extraction/test_text.py
@@ -32,7 +32,9 @@
 )
 def test_basic(vect, container):
     b = db.from_sequence(JUNK_FOOD_DOCS, npartitions=2)
-    if container == "series":
+    if type(vect) == dask_ml.feature_extraction.text.FeatureHasher:
+        b = b.str.split()
+    elif container == "series":
         b = b.to_dataframe(columns=["text"])["text"]
     elif container == "array":
         b = b.to_dataframe(columns=["text"])["text"].values