Merge remote-tracking branch 'origin/master'

TutteInstitute · Jun 25, 2020 · 5c67a32 · 5c67a32
2 parents c01ddc7 + 3d655a8
commit 5c67a32
Show file tree

Hide file tree

Showing 2 changed files with 7 additions and 7 deletions.
diff --git a/vectorizers/_vectorizers.py b/vectorizers/_vectorizers.py
@@ -1225,7 +1225,7 @@ def __init__(
         window_function="fixed",
         kernel_function="flat",
         window_radius=5,
-        window_orientation="symmetric",
+        window_orientation="directional",
         validate_data=True,
     ):
         self.token_dictionary = token_dictionary
@@ -1317,12 +1317,12 @@ def fit_transform(self, X, y=None, **fit_params):
             self.column_index_dictionary_ = self.token_index_dictionary_
         elif self.window_orientation == "directional":
             self.column_label_dictionary_ = {
-                "pre_" + token: index
+                "pre_" + str(token): index
                 for token, index in self.token_label_dictionary_.items()
             }
             self.column_label_dictionary_.update(
                 {
-                    "post_" + token: index + len(self.token_label_dictionary_)
+                    "post_" + str(token): index + len(self.token_label_dictionary_)
                     for token, index in self.token_label_dictionary_.items()
                 }
             )
@@ -1472,7 +1472,7 @@ def __init__(
         kernel_function="flat",
         window_radius=5,
         token_dictionary=None,
-        window_orientation="symmetric",
+        window_orientation="directional",
         validate_data=True,
     ):
         self.token_dictionary = token_dictionary

diff --git a/vectorizers/tests/test_common.py b/vectorizers/tests/test_common.py
@@ -159,7 +159,7 @@ def test_LabeledTreeCooccurrenceVectorizer_reduced_vocab():
 @pytest.mark.parametrize("max_token_occurrences", [None, 2])
 @pytest.mark.parametrize("min_document_occurrences", [None, 1])
 @pytest.mark.parametrize("max_document_frequency", [None, 0.7])
-@pytest.mark.parametrize("window_orientation", ["before", "after", "symmetric"])
+@pytest.mark.parametrize("window_orientation", ["before", "after", "symmetric", "directional"])
 @pytest.mark.parametrize("window_radius", [1, 2])
 @pytest.mark.parametrize("kernel_function", ["harmonic", "flat"])
 def test_equality_of_CooccurrenceVectorizers(
@@ -315,7 +315,7 @@ def test_find_boundaries_all_dupes():
 
 
 def test_token_cooccurrence_vectorizer_basic():
-    vectorizer = TokenCooccurrenceVectorizer()
+    vectorizer = TokenCooccurrenceVectorizer(window_orientation='symmetric')
     result = vectorizer.fit_transform(token_data)
     transform = vectorizer.transform(token_data)
     assert (result != transform).nnz == 0
@@ -365,7 +365,7 @@ def test_token_cooccurrence_vectorizer_column_order():
 
 
 def test_token_cooccurrence_vectorizer_transform():
-    vectorizer = TokenCooccurrenceVectorizer()
+    vectorizer = TokenCooccurrenceVectorizer(window_orientation='symmetric')
     result = vectorizer.fit_transform(text_token_data_subset)
     transform = vectorizer.transform(text_token_data)
     assert result.shape == transform.shape