implement preview methods

.gitignore

@@ -141,4 +141,7 @@ dmypy.json
 .pytype/
 
 # Cython debug symbols
-cython_debug/
+cython_debug/
+
+experimental_notebooks
+settings.json

README.md

@@ -42,8 +42,8 @@ for sent in doc.sents:
     sent._.linkedEntities.pretty_print()
 
 # OUTPUT:
-# https://www.wikidata.org/wiki/Q194318     194318     Pirates of the Caribbean        Series of fantasy adventure films                                                                   
-# https://www.wikidata.org/wiki/Q12525597   12525597   Silvester                       the day celebrated on 31 December (Roman Catholic Church) or 2 January (Eastern Orthodox Churches)  
+# https://www.wikidata.org/wiki/Q194318     Pirates of the Caribbean        Series of fantasy adventure films                                                                   
+# https://www.wikidata.org/wiki/Q12525597   Silvester                       the day celebrated on 31 December (Roman Catholic Church) or 2 January (Eastern Orthodox Churches)  
 
 ```
 
@@ -94,16 +94,14 @@ doc = nlp("I follow the New England Patriots")
 patriots_entity = doc._.linkedEntities[0]
 patriots_entity.pretty_print()
 # OUTPUT:
-# https://www.wikidata.org/wiki/Q193390
-# 193390     
+# https://www.wikidata.org/wiki/Q193390     
 # New England Patriots            
 # National Football League franchise in Foxborough, Massachusetts                    
 
 football_team_entity = patriots_entity.get_super_entities()[0]
 football_team_entity.pretty_print()
 # OUTPUT:
-# https://www.wikidata.org/wiki/Q17156793   
-# 17156793   
+# https://www.wikidata.org/wiki/Q17156793 
 # American football team          
 # organization, in which a group of players are organized to compete as a team in American football   
 

setup.py

@@ -1,9 +1,6 @@
 #!/usr/bin/env python
 # -*- coding: utf-8 -*-
 
-# Copyright (c) 2014 SeatGeek
-
-# This file is part of fuzzywuzzy.
 
 import os
 
@@ -22,7 +19,7 @@ with open("README.md", "r") as fh:
 
 setup(
     name='spacy-entity-linker',
-    version='1.0.0',
+    version='1.0.1',
     author='Emanuel Gerber',
     author_email='emanuel.j.gerber@gmail.com',
     packages=['spacy_entity_linker'],

spacy_entity_linker/EntityCandidates.py

@@ -1,3 +1,5 @@
+MAX_ITEMS_PREVIEW=20
+
 class EntityCandidates:
 
     def __init__(self, entity_elements):
@@ -17,6 +19,15 @@ class EntityCandidates:
         for entity in self.entity_elements:
             entity.pretty_print()
 
+    def __repr__(self) -> str:
+        preview_str=""
+        for index,entity_element in enumerate(self):
+            if index>MAX_ITEMS_PREVIEW:
+                break
+            preview_str+="{}\n".format(entity_element.get_preview_string())
+        
+        return preview_str
+
     def __str__(self):
         return str(["entity {}: {} (<{}>)".format(i, entity.get_label(), entity.get_description()) for i, entity in
                     enumerate(self.entity_elements)])

spacy_entity_linker/EntityCollection.py

@@ -1,6 +1,8 @@
 from collections import Counter, defaultdict
 from .DatabaseConnection import get_wikidata_instance
 
+MAX_ITEMS_PREVIEW=20
+
 
 class EntityCollection:
 
@@ -45,6 +47,17 @@ class EntityCollection:
             print("{} ({}) : {}".format(wikidataInstance.get_entity_name(category), frequency,
                                         ','.join([str(e) for e in category_to_entites[category]])))
 
+    def __repr__(self) -> str:
+        preview_str="<EntityCollection ({} entities):".format(len(self))
+        for index,entity_element in enumerate(self):
+            if index>MAX_ITEMS_PREVIEW:
+                preview_str+="\n...{} more".format(len(self)-MAX_ITEMS_PREVIEW)
+                break
+            preview_str+="\n-{}".format(entity_element.get_preview_string())
+        
+        preview_str+=">"
+        return preview_str
+
     def pretty_print(self):
         for entity in self.entities:
             entity.pretty_print()

spacy_entity_linker/EntityElement.py

@@ -20,6 +20,7 @@ class EntityElement:
         if len(row) > 5 and row[5]:
             self.original_alias = row[5]
 
+        self.url="https://www.wikidata.org/wiki/Q{}".format(self.get_id())
         self.span = span
 
         self.chain = None
@@ -101,11 +102,16 @@ class EntityElement:
         }
 
     def pretty_print(self):
-        print(
-            "https://www.wikidata.org/wiki/Q{0:<10} {1:<10} {2:<30}  {3:<100}".format(self.get_id(),
-                                                                                      self.get_id(),
-                                                                                      self.get_label(),
-                                                                                      self.get_description()[:100]))
+        print(self.__repr__())
+    
+    def get_url(self):
+        return self.url
+
+    def __repr__(self):
+        return "<EntityElement: {}>".format(self.get_preview_string())
+
+    def get_preview_string(self):
+        return "{0:<10} {1:<25} {2:<50}".format(self.get_url(),self.get_label(),self.get_description()[:100])
 
     def pretty_string(self, description=False):
         if description: