Merge branch 'develop'

Author: rememberYou

examples/mutag.py

@@ -35,7 +35,12 @@
     # generated for the entities without hashing as MUTAG is a short KG.
     walkers=[
         HALKWalker(
-            2, None, n_jobs=2, random_state=RANDOM_STATE, md5_bytes=None
+            2,
+            None,
+            n_jobs=2,
+            sampler=WideSampler(),
+            random_state=RANDOM_STATE,
+            md5_bytes=None,
         )
     ],
     verbose=1,

pyrdf2vec/embedders/word2vec.py

@@ -19,7 +19,7 @@ class Word2Vec(Embedder):
         _model: The gensim.models.word2vec model.
             Defaults to None.
         kwargs: The keyword arguments dictionary.
-            Defaults to { min_count=0, negative=20, vector_size=500 }.
+            Defaults to { min_count=0 }.
 
     """
 
@@ -29,8 +29,6 @@ class Word2Vec(Embedder):
     def __init__(self, **kwargs):
         self.kwargs = {
             "min_count": 0,
-            "negative": 20,
-            "vector_size": 500,
             **kwargs,
         }
         self._model = W2V(**self.kwargs)

pyrdf2vec/rdf2vec.py

@@ -160,8 +160,6 @@ def get_walks(self, kg: KG, entities: Entities) -> List[List[SWalk]]:
             ValueError: If the provided entities aren't in the Knowledge Graph.
 
         """
-        # Avoids duplicate entities for unnecessary walk extractions.
-        entities = list(set(entities))
         if kg.skip_verify is False and not kg.is_exist(entities):
             if kg.mul_req:
                 asyncio.run(kg.connector.close())

pyrdf2vec/walkers/anonymous.py

@@ -29,7 +29,8 @@ class AnonymousWalker(RandomWalker):
             Defaults to UniformSampler.
         with_reverse: True to extracts parents and children hops from an
             entity, creating (max_walks * max_walks) more walks of 2 * depth,
-            allowing also to centralize this entity in the walks. False otherwise.
+            allowing also to centralize this entity in the walks. False
+            otherwise.
             Defaults to False.
 
     """

pyrdf2vec/walkers/community.py

@@ -275,7 +275,7 @@ def _dfs(
                         sub_walk += (pred_obj[0], pred_obj[1])
                 d = len(sub_walk) - 1
             walks.append(sub_walk)
-        return list(set(walks))
+        return list(walks)
 
     def extract(
         self, kg: KG, entities: Entities, verbose: int = 0

pyrdf2vec/walkers/halk.py

@@ -114,6 +114,7 @@ def _extract(self, kg: KG, entity: Vertex) -> EntityWalks:
         """
         return super()._extract(kg, entity)
 
+    # flake8: noqa: C901
     def _post_extract(self, res: List[EntityWalks]) -> List[List[SWalk]]:
         """Post processed walks.
 

pyrdf2vec/walkers/random.py

@@ -115,7 +115,7 @@ def _dfs(
                     sub_walk += (pred_obj[0], pred_obj[1])
                 d = len(sub_walk) - 1
             walks.append(sub_walk)
-        return list(set(walks))
+        return list(walks)
 
     def extract_walks(self, kg: KG, entity: Vertex) -> List[Walk]:
         """Extracts random walks for an entity based on Knowledge Graph using

pyrdf2vec/walkers/split.py

@@ -1,4 +1,3 @@
-import os
 import re
 from typing import Set
 
@@ -50,6 +49,7 @@ def __attrs_post_init__(self):
         if self.func_split is None:
             self.func_split = self.basic_split
 
+    # flake8: noqa: C901
     def basic_split(self, walks: List[Walk]) -> Set[SWalk]:
         """Splits vertices of random walks for an entity based. To achieve
         this, each vertex (except the root node) is split according to symbols
@@ -77,8 +77,10 @@ def basic_split(self, walks: List[Walk]) -> Set[SWalk]:
         """
         canonical_walks: Set[SWalk] = set()
         for walk in walks:
-            tmp_vertices = []
-            canonical_walk = [] if self.with_reverse else [walk[0].name]
+            tmp_vertices = []  # type: ignore
+            canonical_walk = []
+            if self.with_reverse:
+                canonical_walk = [walk[0].name]
             for i, _ in enumerate(walk[1::], 1):
                 vertices = []
                 if "http" in walk[i].name:

tests/walkers/test_anonymous.py

@@ -69,8 +69,7 @@ def test_extract(
             else:
                 assert len(walks) <= max_walks
         for walk in walks:
-            assert not walk[0].isnumeric()
-            for obj in walk[2::2]:
+            for obj in walk[1::2]:
                 assert obj.isnumeric()
             if not with_reverse:
                 assert walk[0] == root

tests/walkers/test_halk.py

@@ -28,7 +28,7 @@
 
 MAX_DEPTHS = range(15)
 KGS = [KG_LOOP, KG_CHAIN]
-MAX_WALKS = [None, 0, 1, 2, 3, 4, 5]
+MAX_WALKS = [None, 1, 2, 3, 4, 5]
 ROOTS_WITHOUT_URL = ["Alice", "Bob", "Dean"]
 WITH_REVERSE = [False, True]