Update spaCy pipeline

config.cfg

@@ -10,7 +10,7 @@ seed = 0
 
 [nlp]
 lang = "en"
-pipeline = ["tok2vec","ner"]
+pipeline = ["tok2vec","ner","count_extraction_component"]
 batch_size = 1000
 disabled = []
 before_creation = null
@@ -21,6 +21,10 @@ vectors = {"@vectors":"spacy.Vectors.v1"}
 
 [components]
 
+[components.count_extraction_component]
+factory = "count_extraction_component"
+label = "CONNECTION"
+
 [components.ner]
 factory = "ner"
 incorrect_spans_key = null

count_extraction_component.py

@@ -5,7 +5,7 @@ from spacy.language import Language
 import re
 
 # https://spacy.io/usage/processing-pipelines#custom-components
-@Language.factory("count_extraction")
+@Language.factory("count_extraction_component")
 class CountExtractorComponent(object):
     def __init__(self, nlp, name, label="CONNECTION"):
         self.label = label
@@ -50,3 +50,15 @@ class CountExtractorComponent(object):
             ent._.text = text
             ent._.count = 1
         return doc
+
+    def connections(self, doc):
+        connections = {}
+        for ent in doc.ents:
+            if ent._.count is None:
+                continue
+
+            if ent._.text not in connections:
+                connections[ent._.text] = ent._.count
+                continue
+            connections[ent._.text] += ent._.count
+        return connections

en_setec_mk_tv-any-py3-none-any.whl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edda8abe91cb2274ca61da460b6ccc5f3f80d155d1dd7bae59914e179a475699
-size 5706128
+oid sha256:486bf4e15ccf77ad023ba0362bf1142e833b37e7506d78a7141975d4480ebdd3
+size 5706265

meta.json

@@ -35,11 +35,13 @@
   },
   "pipeline":[
     "tok2vec",
-    "ner"
+    "ner",
+    "count_extraction_component"
   ],
   "components":[
     "tok2vec",
-    "ner"
+    "ner",
+    "count_extraction_component"
   ],
   "disabled":[