fix encoding error when setup; and Parameter error due to the version…

ge/models/__init__.py

@@ -3,6 +3,7 @@
 from .line import LINE
 from .sdne import SDNE
 from .struc2vec import Struc2Vec
+from .bfswalk import BFSWalk
 
 
-__all__ = ["DeepWalk", "Node2Vec", "LINE", "SDNE", "Struc2Vec"]
+__all__ = ["DeepWalk", "Node2Vec", "LINE", "SDNE", "Struc2Vec", "BFSWalk"]

ge/models/alibaba-eges.py

@@ -0,0 +1,67 @@
+# -*- coding:utf-8 -*-
+
+"""
+
+
+
+Author:
+
+    Chengliang Zhao, [email protected]
+
+
+
+Reference:
+
+    [1] Jizhe Wang, Pipei Huang, Huan Zhao, Zhibo Zhang, Binqiang Zhao, and Dik Lun Lee. 2018. Billion-scale Commodity Embedding for E-commerce Recommendation in Alibaba. In <i>Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery &amp; Data Mining</i> (<i>KDD '18</i>). Association for Computing Machinery, New York, NY, USA, 839–848. DOI:https://doi.org/10.1145/3219819.3219869
+
+
+"""
+from ..walker import RandomWalker
+from gensim.models import Word2Vec
+import pandas as pd
+import numpy as np
+
+
+class EGES:
+    def __init__(self, graph, walk_length, num_walks, workers=1):
+
+        self.graph = graph
+        self.w2v_model = None
+        self._embeddings = {}
+
+        self.walker = RandomWalker(
+            graph, p=1, q=1, )
+        self.sentences = self.walker.simulate_walks(
+            num_walks=num_walks, walk_length=walk_length, workers=workers, verbose=1)
+
+    def train(self, embed_size=128, window_size=5, workers=3, iter=5, **kwargs):
+
+        kwargs["sentences"] = self.sentences
+        kwargs["min_count"] = kwargs.get("min_count", 0)
+        kwargs["vector_size"] = embed_size
+        kwargs["sg"] = 1  # skip gram
+        kwargs["hs"] = 1  # deepwalk use Hierarchical Softmax
+        kwargs["workers"] = workers
+        kwargs["window"] = window_size
+        kwargs["epochs"] = iter
+
+        # print("Learning embedding vectors...")
+        # model = Word2Vec(**kwargs)
+        # print("Learning embedding vectors done!")
+
+        # self.w2v_model = model
+        # return model
+
+
+
+
+    def get_embeddings(self,):
+        if self.w2v_model is None:
+            print("model not train")
+            return {}
+
+        self._embeddings = {}
+        for word in self.graph.nodes():
+            self._embeddings[word] = self.w2v_model.wv[word]
+
+        return self._embeddings

ge/models/bfswalk.py

@@ -0,0 +1,67 @@
+# -*- coding:utf-8 -*-
+
+"""
+
+
+
+Author:
+
+    Weichen Shen,[email protected]
+
+
+
+Reference:
+
+    [1] Perozzi B, Al-Rfou R, Skiena S. Deepwalk: Online learning of social representations[C]//Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, 2014: 701-710.(http://www.perozzi.net/publications/14_kdd_deepwalk.pdf)
+
+
+
+"""
+from ..walker import RandomWalker
+from gensim.models import Word2Vec, word2vec
+import pandas as pd
+
+
+class BFSWalk:
+    def __init__(self, graph, outlier, walk_length, num_walks, workers=1, weight = False):
+
+        self.graph = graph
+        self.w2v_model = None
+        self._embeddings = {}
+
+        self.walker = RandomWalker(
+            graph, p=1, q=1, )
+        self.sentences = self.walker.simulate_walks("bfs", outlier,
+            num_walks=num_walks, walk_length=walk_length, workers=workers, verbose=1, weight = weight)
+
+    def train(self, walkfile, embed_size=128, window_size=5, workers=3, iter=5, sg = 1, hs=1, **kwargs):
+
+        kwargs["sentences"] = word2vec.Text8Corpus(walkfile)
+        kwargs["min_count"] = kwargs.get("min_count", 1)
+        kwargs["vector_size"] = embed_size
+        kwargs["sg"] = sg  # skip gram
+        kwargs["hs"] = hs  # deepwalk use Hierarchical Softmax
+        kwargs["workers"] = workers
+        kwargs["window"] = window_size
+        kwargs["epochs"] = iter
+
+        print("Learning embedding vectors...")
+        model = Word2Vec(**kwargs)
+        print("Learning embedding vectors done!")
+
+        self.w2v_model = model
+        return model
+
+    def get_embeddings(self,):
+        if self.w2v_model is None:
+            print("model not train")
+            return {}
+
+        self._embeddings = {}
+        for word in self.graph.nodes():
+            self._embeddings[word] = self.w2v_model.wv[word]
+
+        return self._embeddings
+
+    def get_sentences(self):
+        return self.sentences

ge/models/deepwalk.py

@@ -18,32 +18,32 @@
 
 """
 from ..walker import RandomWalker
-from gensim.models import Word2Vec
+from gensim.models import Word2Vec, word2vec
 import pandas as pd
 
 
 class DeepWalk:
-    def __init__(self, graph, walk_length, num_walks, workers=1):
+    def __init__(self, graph, outlier, walk_length, num_walks, workers=1, weight = False):
 
         self.graph = graph
         self.w2v_model = None
         self._embeddings = {}
 
         self.walker = RandomWalker(
             graph, p=1, q=1, )
-        self.sentences = self.walker.simulate_walks(
-            num_walks=num_walks, walk_length=walk_length, workers=workers, verbose=1)
+        self.sentences = self.walker.simulate_walks("deep", outlier,
+            num_walks=num_walks, walk_length=walk_length, workers=workers, verbose=1, weight = weight)
 
-    def train(self, embed_size=128, window_size=5, workers=3, iter=5, **kwargs):
+    def train(self, walkfile, embed_size=128, window_size=5, workers=3, iter=5, sg = 1, hs=1, **kwargs):
 
-        kwargs["sentences"] = self.sentences
-        kwargs["min_count"] = kwargs.get("min_count", 0)
-        kwargs["size"] = embed_size
-        kwargs["sg"] = 1  # skip gram
-        kwargs["hs"] = 1  # deepwalk use Hierarchical Softmax
+        kwargs["sentences"] = word2vec.Text8Corpus(walkfile)
+        kwargs["min_count"] = kwargs.get("min_count", 1)
+        kwargs["vector_size"] = embed_size
+        kwargs["sg"] = sg  # skip gram
+        kwargs["hs"] = hs  # deepwalk use Hierarchical Softmax
         kwargs["workers"] = workers
         kwargs["window"] = window_size
-        kwargs["iter"] = iter
+        kwargs["epochs"] = iter
 
         print("Learning embedding vectors...")
         model = Word2Vec(**kwargs)
@@ -62,3 +62,6 @@ def get_embeddings(self,):
             self._embeddings[word] = self.w2v_model.wv[word]
 
         return self._embeddings
+
+    def get_sentences(self):
+        return self.sentences

ge/models/line.py

@@ -92,7 +92,7 @@ def __init__(self, graph, embedding_size=8, negative_ratio=5, order='second',):
         self.node_size = graph.number_of_nodes()
         self.edge_size = graph.number_of_edges()
         self.samples_per_epoch = self.edge_size*(1+negative_ratio)
-
+        
         self._gen_sampling_table()
         self.reset_model()
 

ge/models/node2vec.py

@@ -18,15 +18,15 @@
 
 """
 
-from gensim.models import Word2Vec
+from gensim.models import Word2Vec, word2vec
 import pandas as pd
 
 from ..walker import RandomWalker
 
 
 class Node2Vec:
 
-    def __init__(self, graph, walk_length, num_walks, p=1.0, q=1.0, workers=1, use_rejection_sampling=0):
+    def __init__(self, graph, outlier, walk_length, num_walks, p=1.0, q=1.0, workers=1, use_rejection_sampling=0):
 
         self.graph = graph
         self._embeddings = {}
@@ -36,19 +36,19 @@ def __init__(self, graph, walk_length, num_walks, p=1.0, q=1.0, workers=1, use_r
         print("Preprocess transition probs...")
         self.walker.preprocess_transition_probs()
 
-        self.sentences = self.walker.simulate_walks(
-            num_walks=num_walks, walk_length=walk_length, workers=workers, verbose=1)
+        self.sentences = self.walker.simulate_walks("node", outlier,
+            num_walks=num_walks, walk_length=walk_length, workers=workers, verbose=1, weight=False)
 
-    def train(self, embed_size=128, window_size=5, workers=3, iter=5, **kwargs):
+    def train(self, walkfile, embed_size=128, window_size=5, workers=3, iter=5, sg = 1, hs = 1, **kwargs):
 
-        kwargs["sentences"] = self.sentences
-        kwargs["min_count"] = kwargs.get("min_count", 0)
-        kwargs["size"] = embed_size
-        kwargs["sg"] = 1
-        kwargs["hs"] = 0  # node2vec not use Hierarchical Softmax
+        kwargs["sentences"] = word2vec.Text8Corpus(walkfile)
+        kwargs["min_count"] = kwargs.get("min_count", 1)
+        kwargs["vector_size"] = embed_size
+        kwargs["sg"] = sg
+        kwargs["hs"] = hs  # node2vec not use Hierarchical Softmax
         kwargs["workers"] = workers
         kwargs["window"] = window_size
-        kwargs["iter"] = iter
+        kwargs["epochs"] = iter
 
         print("Learning embedding vectors...")
         model = Word2Vec(**kwargs)
@@ -68,3 +68,6 @@ def get_embeddings(self,):
             self._embeddings[word] = self.w2v_model.wv[word]
 
         return self._embeddings
+
+    def get_sentences(self):
+        return self.sentences

ge/models/struc2vec.py

@@ -112,8 +112,8 @@ def train(self, embed_size=128, window_size=5, workers=3, iter=5):
         sentences = self.sentences
 
         print("Learning representation...")
-        model = Word2Vec(sentences, size=embed_size, window=window_size, min_count=0, hs=1, sg=1, workers=workers,
-                         iter=iter)
+        model = Word2Vec(sentences, vector_size=embed_size, window=window_size, min_count=0, hs=1, sg=1, workers=workers,
+                         epochs=iter)
         print("Learning representation done!")
         self.w2v_model = model