test.py works

OptimizedEntityLinking/search.py

@@ -36,7 +36,6 @@ def runLocalSearch(self, alpha, iterations):
                     candidateDocumentRelevances = []
                     currentLinkDocumentRelevances = []
                     context = [v[0] for k, v in state.items() if k != keyword]
-                    print "entering loop"
                     for otherAssignedLink in context:
                         # get cached page
                         otherAssignedPage = self.retrieveCachedPage(candidateLink)

test.py

@@ -28,10 +28,6 @@
             totalKeywords = len(result.keys())
             correctKeywords = 0
             for k in result:
-                print result[k][0]
-                print currentSolution[k]
-                print type(result[k][0])
-                print type(currentSolution[k])
                 if result[k][0] == currentSolution[k]:
                     correctKeywords += 1
 
@@ -40,3 +36,38 @@
         avg_accuracies.append(np.mean(accuracies))
 
 print avg_accuracies
+
+
+
+# import nltk 
+# with open('sample.txt', 'r') as f:
+#     sample = f.read()
+
+
+# sentences = nltk.sent_tokenize(sample)
+# tokenized_sentences = [nltk.word_tokenize(sentence) for sentence in sentences]
+# tagged_sentences = [nltk.pos_tag(sentence) for sentence in tokenized_sentences]
+# chunked_sentences = nltk.ne_chunk_sents(tagged_sentences, binary=True)
+
+# def extract_entity_names(t):
+#     entity_names = []
+#     if hasattr(t, 'label') and t.label:
+#         if t.label() == 'NE':
+#             entity_names.append(' '.join([child[0] for child in t]))
+#         else:
+#             for child in t:
+#                 entity_names.extend(extract_entity_names(child))
+#     return entity_names
+
+# entity_names = []
+# for tree in chunked_sentences:
+#     # Print results per sentence
+#     # print extract_entity_names(tree)
+#     print chunked_sentences
+#     entity_names.extend(extract_entity_names(tree))
+
+# # Print all entity names
+# # print entity_names
+
+# # Print unique entity names
+# print set(entity_names)

test/solutions.txt

@@ -1,3 +1,3 @@
 {"Thermodynamics":('Thermodynamics', 1), "study":('Study', 1), "heat":('Heat', 1)}
 {"Airplane!":('Airplane!', 1), "movie":('movie', 1)}
-{"China":('China', 1), "GDP":('Gross domestic product', 1)}
+{"China":('China', 1), "country":('Country', 1), "GDP":('Gross domestic product', 1)}