Merge pull request #26 from jenojp/develop

Issue #14 (compound chunk prefixes) and remove patterns bug fix

azure-pipelines.yml

@@ -56,7 +56,7 @@ steps:
     pip install -r requirements.txt
     python -m spacy download en_core_web_sm
     pip install scispacy
-    pip install https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.2.4/en_core_sci_sm-0.2.4.tar.gz
+    pip install https://s3-us-west-2.amazonaws.com/ai2-s2-scispacy/releases/v0.3.0/en_core_sci_sm-0.3.0.tar.gz
   displayName: 'Install dependencies'
 
 - script: |

negspacy/negation.py

@@ -133,7 +133,7 @@ def remove_patterns(
                 for p in following_negations:
                     self.following_negations.remove(p)
             else:
-                self.following_negations.extend(following_negations)
+                self.following_negations.remove(following_negations)
         if termination:
             if isinstance(termination, list):
                 for p in termination:
@@ -306,7 +306,7 @@ def negex(self, doc):
                     continue
                 if self.chunk_prefix:
                     if any(
-                        c.text.lower() == doc[e.start].text.lower()
+                        e.text.lower().startswith(c.text.lower())
                         for c in self.chunk_prefix
                     ):
                         e._.set(self.extension_name, True)

negspacy/test.py

@@ -36,7 +36,7 @@ def build_med_docs():
         (
             "Patient denies cardiovascular disease but has headaches. No history of smoking. Alcoholism unlikely. Smoking not ruled out.",
             [
-                ("Patient denies", False),
+                ("Patient", False),
                 ("cardiovascular disease", True),
                 ("headaches", False),
                 ("No history", True),
@@ -63,7 +63,7 @@ def build_med_docs():
     docs.append(
         (
             "Alcoholism was not the cause of liver disease.",
-            [("Alcoholism", True), ("cause", False), ("liver disease", False)],
+            [("Alcoholism", True), ("liver disease", False)],
         )
     )
 
@@ -213,6 +213,21 @@ def test_add_remove_patterns():
     )
     assert len(patterns_after["pseudo_patterns"]) == len(patterns["pseudo_patterns"])
 
+def test_issue_14():
+    nlp = spacy.load("en_core_sci_sm")
+    negex = Negex(
+        nlp, language="en_clinical", chunk_prefix=["no", "cancer free"]
+    )
+    negex.remove_patterns(following_negations="free")
+    nlp.add_pipe(negex, last=True)
+    print(negex.get_patterns())
+
+    doc = nlp("The patient has a cancer free diagnosis")
+    expected = [False, True]
+    for i, e in enumerate(doc.ents):
+        print(e.text, e._.negex)
+        assert e._.negex == expected[i]
+
 
 if __name__ == "__main__":
     test()
@@ -222,3 +237,4 @@ def test_add_remove_patterns():
     test_get_patterns()
     test_issue7()
     test_add_remove_patterns()
+    test_issue_14()