small fixes

bin/ud/conll17_ud_eval.py

@@ -292,8 +292,8 @@ def evaluate(gold_ud, system_ud, deprel_weights=None, check_parse=True):
 
     def spans_score(gold_spans, system_spans):
         correct, gi, si = 0, 0, 0
-        undersegmented = list()
-        oversegmented = list()
+        undersegmented = []
+        oversegmented = []
         combo = 0
         previous_end_si_earlier = False
         previous_end_gi_earlier = False

bin/wiki_entity_linking/kb_creator.py

@@ -42,9 +42,9 @@ def create_kb(nlp, max_entities_per_alias, min_entity_freq, min_occ,
 
     # filter the entities for in the KB by frequency, because there's just too much data (8M entities) otherwise
     filtered_title_to_id = dict()
-    entity_list = list()
-    description_list = list()
-    frequency_list = list()
+    entity_list = []
+    description_list = []
+    frequency_list = []
     for title, entity in title_to_id.items():
         freq = entity_frequencies.get(title, 0)
         desc = id_to_descr.get(entity, None)
@@ -131,8 +131,8 @@ def _add_aliases(kb, title_to_id, max_entities_per_alias, min_occ, prior_prob_in
         line = prior_file.readline()
         previous_alias = None
         total_count = 0
-        counts = list()
-        entities = list()
+        counts = []
+        entities = []
         while line:
             splits = line.replace('\n', "").split(sep='|')
             new_alias = splits[0]
@@ -142,8 +142,8 @@ def _add_aliases(kb, title_to_id, max_entities_per_alias, min_occ, prior_prob_in
             if new_alias != previous_alias and previous_alias:
                 # done reading the previous alias --> output
                 if len(entities) > 0:
-                    selected_entities = list()
-                    prior_probs = list()
+                    selected_entities = []
+                    prior_probs = []
                     for ent_count, ent_string in zip(counts, entities):
                         if ent_string in wp_titles:
                             wd_id = title_to_id[ent_string]
@@ -157,8 +157,8 @@ def _add_aliases(kb, title_to_id, max_entities_per_alias, min_occ, prior_prob_in
                         except ValueError as e:
                             print(e)
                 total_count = 0
-                counts = list()
-                entities = list()
+                counts = []
+                entities = []
 
             total_count += count
 

bin/wiki_entity_linking/training_set_creator.py

@@ -343,7 +343,7 @@ def read_training(nlp, training_dir, dev, limit):
                                 # currently feeding the gold data one entity per sentence at a time
                                 gold_start = int(start) - found_ent.sent.start_char
                                 gold_end = int(end) - found_ent.sent.start_char
-                                gold_entities = list()
+                                gold_entities = []
                                 gold_entities.append((gold_start, gold_end, wp_title))
                                 gold = GoldParse(doc=sent, links=gold_entities)
                                 data.append((sent, gold))

examples/pipeline/wikidata_entity_linking.py

@@ -147,7 +147,7 @@ def run_pipeline():
     if train_pipe:
         print("STEP 6: training Entity Linking pipe", datetime.datetime.now())
         # define the size (nr of entities) of training and dev set
-        train_limit = 10000
+        train_limit = 5000
         dev_limit = 5000
 
         train_data = training_set_creator.read_training(nlp=nlp_2,
@@ -332,7 +332,7 @@ def _measure_baselines(data, kb):
                     best_candidate = ""
                     random_candidate = ""
                     if candidates:
-                        scores = list()
+                        scores = []
 
                         for c in candidates:
                             scores.append(c.prior_prob)

spacy/pipeline/pipes.pyx

@@ -1131,8 +1131,8 @@ class EntityLinker(Pipe):
             docs = [docs]
             golds = [golds]
 
-        context_docs = list()
-        entity_encodings = list()
+        context_docs = []
+        entity_encodings = []
 
         for doc, gold in zip(docs, golds):
             for entity in gold.links:
@@ -1198,8 +1198,8 @@ class EntityLinker(Pipe):
         self.require_model()
         self.require_kb()
 
-        final_entities = list()
-        final_kb_ids = list()
+        final_entities = []
+        final_kb_ids = []
 
         if not docs:
             return final_entities, final_kb_ids
@@ -1214,7 +1214,7 @@ class EntityLinker(Pipe):
                 for ent in doc.ents:
                     candidates = self.kb.get_candidates(ent.text)
                     if candidates:
-                        scores = list()
+                        scores = []
                         for c in candidates:
                             prior_prob = c.prior_prob * self.prior_weight
                             kb_id = c.entity_
@@ -1259,11 +1259,10 @@ class EntityLinker(Pipe):
         return self
 
     def rehearse(self, docs, sgd=None, losses=None, **config):
-        # TODO
-        pass
+        raise NotImplementedError
 
     def add_label(self, label):
-        pass
+        raise NotImplementedError
 
 
 class Sentencizer(object):