Subwords as parameter.

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__ = '0.0.3'
+__version__ = '0.0.4'
 
 from dialectid.text_repr import BoW
 from dialectid.model import DialectId

dialectid/tests/test_text_repr.py

@@ -30,9 +30,18 @@ def test_bow():
     """Test BoW"""
     from b4msa.textmodel import TextModel
 
-    bow = BoW(lang='es')
+    bow = BoW(lang='es', voc_size_exponent=13)
     assert isinstance(bow.bow, TextModel)
     X = bow.transform(['Buenos dias'])
-    bow2 = BoW(lang='es', loc='mx')
+    bow2 = BoW(lang='es', loc='mx', voc_size_exponent=13)
     X2 = bow2.transform(['Buenos dias'])
-    assert (X - X2).sum() != 0
+    assert (X - X2).sum() != 0
+
+
+def test_subwords():
+    """Test subwords"""
+
+    bow = BoW(lang='es', voc_size_exponent=13,
+              subwords=True)
+    bow.transform(['Hola'])
+

dialectid/text_repr.py

@@ -39,10 +39,14 @@ def __init__(self, pretrain: bool=True,
                  v1: bool=False,
                  estimator_kwargs: dict=None,
                  loc: str=None,
+                 subwords: bool=False,
                  **kwargs):
         assert pretrain
         assert not v1
         self._bow = None
+        if subwords:
+            assert loc is None
+            loc = 'qgrams'
         self.loc = loc
         if estimator_kwargs is None:
             estimator_kwargs = {'dual': True, 'class_weight': 'balanced'}