Merge branch 'develop'

IBCNServices · Jun 9, 2021 · c40c52b · c40c52b
2 parents 5b75c7d + 9603fa5
commit c40c52b
Show file tree

Hide file tree

Showing 25 changed files with 767 additions and 455 deletions.
diff --git a/examples/literals.py b/examples/literals.py
@@ -9,7 +9,8 @@
 from pyrdf2vec import RDF2VecTransformer
 from pyrdf2vec.embedders import Word2Vec
 from pyrdf2vec.graphs import KG
-from pyrdf2vec.walkers import RandomWalker
+from pyrdf2vec.samplers import WideSampler
+from pyrdf2vec.walkers import HALKWalker
 
 # Ensure the determinism of this script by initializing a pseudo-random number.
 RANDOM_STATE = 22
@@ -32,8 +33,17 @@
     Word2Vec(workers=1, epochs=10),
     # Extract all walks with a maximum depth of 2 for each entity using two
     # processes and use a random state to ensure that the same walks are
-    # generated for the entities.
-    walkers=[RandomWalker(2, None, n_jobs=2, random_state=RANDOM_STATE)],
+    # generated for the entities without hashing as MUTAG is a short KG.
+    walkers=[
+        HALKWalker(
+            2,
+            None,
+            n_jobs=2,
+            sampler=WideSampler(),
+            random_state=RANDOM_STATE,
+            md5_bytes=None,
+        )
+    ],
     verbose=1,
 ).fit_transform(
     KG(

diff --git a/examples/mutag.py b/examples/mutag.py
@@ -8,7 +8,8 @@
 from pyrdf2vec import RDF2VecTransformer
 from pyrdf2vec.embedders import Word2Vec
 from pyrdf2vec.graphs import KG
-from pyrdf2vec.walkers import RandomWalker
+from pyrdf2vec.samplers import WideSampler
+from pyrdf2vec.walkers import HALKWalker
 
 # Ensure the determinism of this script by initializing a pseudo-random number.
 RANDOM_STATE = 22
@@ -31,8 +32,12 @@
     Word2Vec(workers=1, epochs=10),
     # Extract all walks with a maximum depth of 2 for each entity using two
     # processes and use a random state to ensure that the same walks are
-    # generated for the entities.
-    walkers=[RandomWalker(2, None, n_jobs=1, random_state=RANDOM_STATE)],
+    # 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
+        )
+    ],
     verbose=1,
 ).fit_transform(
     KG(

diff --git a/poetry.lock b/poetry.lock
diff --git a/pyproject.toml b/pyproject.toml
@@ -57,7 +57,6 @@ scikit-learn = "^0.23.2"
 tomlkit = "^0.7.0"
 torch = "^1.7.1"
 tqdm = "^4.48.2"
-transformers = "^4.3.2"
 
 [tool.poetry.dev-dependencies]
 black = "^20.8b1"

diff --git a/pyrdf2vec/samplers/__init__.py b/pyrdf2vec/samplers/__init__.py
@@ -5,6 +5,7 @@
 from .uniform import UniformSampler
 from .frequency import ObjFreqSampler, ObjPredFreqSampler, PredFreqSampler
 from .pagerank import PageRankSampler
+from .wide import WideSampler
 
 __all__ = [
     "ObjFreqSampler",
@@ -13,4 +14,5 @@
     "PredFreqSampler",
     "Sampler",
     "UniformSampler",
+    "WideSampler",
 ]