Empty str

INGEOTEC · Oct 8, 2024 · dab9056 · dab9056
1 parent c3a1f82
commit dab9056
Show file tree

Hide file tree

Showing 3 changed files with 17 additions and 2 deletions.
diff --git a/dialectid/__init__.py b/dialectid/__init__.py
@@ -20,7 +20,7 @@
 # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 # SOFTWARE.
 
-__version__ = '0.0.5'
+__version__ = '0.0.6'
 
 from dialectid.text_repr import BoW, SeqTM
 from dialectid.model import DialectId
diff --git a/dialectid/model.py b/dialectid/model.py
@@ -152,4 +152,7 @@ def encode(self, text):
             except KeyError:
                 continue
         W = self.weights
+        if len(seq) == 0:
+            dtype = getattr(np, f'float{self.precision}') 
+            return np.ones((W.shape[0], 1), dtype=dtype)
         return np.vstack([W[:, x] for x in seq]).T
diff --git a/dialectid/tests/test_model.py b/dialectid/tests/test_model.py
@@ -91,4 +91,16 @@ def test_DenseBoW_encode():
 
     from dialectid.model import DenseBoW
     dense = DenseBoW(precision=16)
-    assert dense.encode('buenos días').shape[1] == 2
+    assert dense.encode('buenos días').shape[1] == 2
+
+
+def test_DenseBoW_encode_empty():
+    """Test DenseBoW for empty"""
+
+    # 'ᗩᒪᒪ ᒪIᐯEᔕ ᗰᗩTTEᖇ!!!!!'
+
+    from dialectid.model import DenseBoW
+    dense = DenseBoW(precision=16)
+    X = dense.encode('')
+    assert X.shape[1] == 1
+    assert X.sum() == len(dense.names)