improve compatibility (#68)

improve compatibility

.github/workflows/ci.yml

@@ -0,0 +1,74 @@
+name: CI
+
+on: 
+  push:
+    path:
+      - 'ge/*'
+      - 'tests/*'
+  pull_request:
+    path:
+      - 'ge/*'
+      - 'tests/*'
+      
+jobs:
+  build:
+
+    runs-on: ubuntu-latest
+    timeout-minutes: 180
+    strategy:
+      matrix:
+        python-version: [3.6,3.7,3.8]
+        tf-version: [1.4.0,1.15.0,2.5.0,2.6.0,2.7.0,2.8.0,2.9.0]
+        
+        exclude:
+          - python-version: 3.7
+            tf-version: 1.4.0
+          - python-version: 3.7
+            tf-version: 1.15.0
+          - python-version: 3.8
+            tf-version: 1.4.0
+          - python-version: 3.8
+            tf-version: 1.14.0
+          - python-version: 3.8
+            tf-version: 1.15.0
+          - python-version: 3.6
+            tf-version: 2.7.0
+          - python-version: 3.6
+            tf-version: 2.8.0
+          - python-version: 3.6
+            tf-version: 2.9.0
+          - python-version: 3.9
+            tf-version: 1.4.0
+          - python-version: 3.9
+            tf-version: 1.15.0
+          - python-version: 3.9
+            tf-version: 2.2.0
+    steps:
+    
+    - uses: actions/checkout@v3
+    
+    - name: Setup python environment
+      uses: actions/setup-python@v4
+      with:
+        python-version: ${{ matrix.python-version }}
+
+    - name: Install dependencies
+      run: |
+        pip3 install -q tensorflow==${{ matrix.tf-version }}
+        pip install -q protobuf==3.19.0
+        pip install -q requests
+        pip install -e .
+    - name: Test with pytest
+      timeout-minutes: 180
+      run: |
+        pip install -q pytest
+        pip install -q pytest-cov
+        pip install -q python-coveralls
+        pytest --cov=ge --cov-report=xml
+    - name: Upload coverage to Codecov  
+      uses: codecov/codecov-action@v3.1.0
+      with:
+        token: ${{secrets.CODECOV_TOKEN}}
+        file: ./coverage.xml
+        flags: pytest
+        name: py${{ matrix.python-version }}-tf${{ matrix.tf-version }}

README.md

@@ -1,5 +1,14 @@
 # GraphEmbedding
 
+[![GitHub Issues](https://img.shields.io/github/issues/shenweichen/graphembedding.svg
+)](https://github.com/shenweichen/graphembedding/issues)
+![CI status](https://github.com/shenweichen/graphembedding/workflows/CI/badge.svg)
+[![codecov](https://codecov.io/gh/shenweichen/graphembedding/branch/master/graph/badge.svg)](https://codecov.io/gh/shenweichen/graphembedding)
+[![Codacy Badge](https://app.codacy.com/project/badge/Grade/c46407f5931f40048e28860dccf7dabc)](https://www.codacy.com/gh/shenweichen/GraphEmbedding/dashboard?utm_source=github.com&utm_medium=referral&utm_content=shenweichen/GraphEmbedding&utm_campaign=Badge_Grade)
+[![Disscussion](https://img.shields.io/badge/chat-wechat-brightgreen?style=flat)](./README.md#disscussiongroup--related-projects)
+
+[comment]: <> ([![License]&#40;https://img.shields.io/github/license/shenweichen/graphembedding.svg&#41;]&#40;https://github.com/shenweichen/graphembedding/blob/master/LICENSE&#41;)
+
 # Method
 
 
@@ -27,7 +36,7 @@ python deepwalk_wiki.py
     <table style="margin-left: 20px; margin-right: auto;">
         <tr>
             <td>
-                公众号：<b>浅梦的学习笔记</b><br><br>
+                公众号：<b>浅梦学习笔记</b><br><br>
                 <a href="https://github.com/shenweichen/GraphEmbedding">
   <img align="center" src="./pics/code.png" />
 </a>
@@ -101,7 +110,7 @@ embeddings = model.get_embeddings()# get embedding vectors
 ```python
 G = nx.read_edgelist('../data/flight/brazil-airports.edgelist',create_using=nx.DiGraph(),nodetype=None,data=[('weight',int)])#read graph
 
-model = model = Struc2Vec(G, 10, 80, workers=4, verbose=40, ) #init model
+model = Struc2Vec(G, 10, 80, workers=4, verbose=40, ) #init model
 model.train(window_size = 5, iter = 3)# train model
 embeddings = model.get_embeddings()# get embedding vectors
 ```

ge/classify.py

@@ -1,6 +1,5 @@
 from __future__ import print_function
 
-
 import numpy
 from sklearn.metrics import f1_score, accuracy_score
 from sklearn.multiclass import OneVsRestClassifier
@@ -45,7 +44,6 @@ class Classifier(object):
         print('-------------------')
         print(results)
         return results
-        print('-------------------')
 
     def predict(self, X, top_k_list):
         X_ = numpy.asarray([self.embeddings[x] for x in X])

ge/models/deepwalk.py

@@ -6,7 +6,7 @@
 
 Author:
 
-    Weichen Shen,wcshen1994@163.com
+    Weichen Shen,weichenswc@163.com
 
 
 
@@ -17,9 +17,9 @@ Reference:
 
 
 """
-from ..walker import RandomWalker
 from gensim.models import Word2Vec
-import pandas as pd
+
+from ..walker import RandomWalker
 
 
 class DeepWalk:
@@ -38,12 +38,12 @@ class DeepWalk:
 
         kwargs["sentences"] = self.sentences
         kwargs["min_count"] = kwargs.get("min_count", 0)
-        kwargs["size"] = embed_size
+        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["iter"] = iter
+        kwargs["epochs"] = iter
 
         print("Learning embedding vectors...")
         model = Word2Vec(**kwargs)

ge/models/line.py

@@ -6,7 +6,7 @@
 
 Author:
 
-    Weichen Shen,wcshen1994@163.com
+    Weichen Shen,weichenswc@163.com
 
 
 
@@ -21,7 +21,7 @@ import math
 import random
 
 import numpy as np
-import tensorflow as tf
+from deepctr.layers.utils import reduce_sum
 from tensorflow.python.keras import backend as K
 from tensorflow.python.keras.layers import Embedding, Input, Lambda
 from tensorflow.python.keras.models import Model
@@ -35,7 +35,6 @@ def line_loss(y_true, y_pred):
 
 
 def create_model(numNodes, embedding_size, order='second'):
-
     v_i = Input(shape=(1,))
     v_j = Input(shape=(1,))
 
@@ -49,9 +48,9 @@ def create_model(numNodes, embedding_size, order='second'):
     v_i_emb_second = second_emb(v_i)
     v_j_context_emb = context_emb(v_j)
 
-    first = Lambda(lambda x: tf.reduce_sum(
+    first = Lambda(lambda x: reduce_sum(
         x[0] * x[1], axis=-1, keep_dims=False), name='first_order')([v_i_emb, v_j_emb])
-    second = Lambda(lambda x: tf.reduce_sum(
+    second = Lambda(lambda x: reduce_sum(
         x[0] * x[1], axis=-1, keep_dims=False), name='second_order')([v_i_emb_second, v_j_context_emb])
 
     if order == 'first':
@@ -168,7 +167,6 @@ class LINE:
                 sign = np.ones(len(h)) * -1
                 t = []
                 for i in range(len(h)):
-
                     t.append(alias_sample(
                         self.node_accept, self.node_alias))
 
@@ -207,7 +205,8 @@ class LINE:
 
     def train(self, batch_size=1024, epochs=1, initial_epoch=0, verbose=1, times=1):
         self.reset_training_config(batch_size, times)
-        hist = self.model.fit_generator(self.batch_it, epochs=epochs, initial_epoch=initial_epoch, steps_per_epoch=self.steps_per_epoch,
+        hist = self.model.fit_generator(self.batch_it, epochs=epochs, initial_epoch=initial_epoch,
+                                        steps_per_epoch=self.steps_per_epoch,
                                         verbose=verbose)
 
         return hist

ge/models/node2vec.py

@@ -6,7 +6,7 @@
 
 Author:
 
-    Weichen Shen,wcshen1994@163.com
+    Weichen Shen,weichenswc@163.com
 
 
 
@@ -19,14 +19,13 @@ Reference:
 """
 
 from gensim.models import 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, walk_length, num_walks, p=1.0, q=1.0, workers=1, use_rejection_sampling=False):
 
         self.graph = graph
         self._embeddings = {}

ge/models/sdne.py

@@ -6,7 +6,7 @@
 
 Author:
 
-    Weichen Shen,wcshen1994@163.com
+    Weichen Shen,weichenswc@163.com
 
 
 
@@ -88,8 +88,7 @@ class SDNE(object):
         self.nu1 = nu1
         self.nu2 = nu2
 
-        self.A, self.L = self._create_A_L(
-            self.graph, self.node2idx)  # Adj Matrix,L Matrix
+        self.A, self.L = _create_A_L(self.graph, self.node2idx)  # Adj Matrix,L Matrix
         self.reset_model()
         self.inputs = [self.A, self.L]
         self._embeddings = {}
@@ -151,7 +150,8 @@ class SDNE(object):
 
         return self._embeddings
 
-    def _create_A_L(self, graph, node2idx):
+
+def _create_A_L(graph, node2idx):
     node_size = graph.number_of_nodes()
     A_data = []
     A_row_index = []

ge/models/struc2vec.py

@@ -6,7 +6,7 @@
 
 Author:
 
-    Weichen Shen,wcshen1994@163.com
+    Weichen Shen,weichenswc@163.com
 
 
 
@@ -28,7 +28,6 @@ import pandas as pd
 from fastdtw import fastdtw
 from gensim.models import Word2Vec
 from joblib import Parallel, delayed
-from tqdm import tqdm
 
 from ..alias import create_alias_table
 from ..utils import partition_dict, preprocess_nxgraph
@@ -36,7 +35,8 @@ from ..walker import BiasedWalker
 
 
 class Struc2Vec():
-    def __init__(self, graph, walk_length=10, num_walks=100, workers=1, verbose=0, stay_prob=0.3, opt1_reduce_len=True, opt2_reduce_sim_calc=True, opt3_num_layers=None, temp_path='./temp_struc2vec/', reuse=False):
+    def __init__(self, graph, walk_length=10, num_walks=100, workers=1, verbose=0, stay_prob=0.3, opt1_reduce_len=True,
+                 opt2_reduce_sim_calc=True, opt3_num_layers=None, temp_path='./temp_struc2vec/', reuse=False):
         self.graph = graph
         self.idx2node, self.node2idx = preprocess_nxgraph(graph)
         self.idx = list(range(len(self.idx2node)))
@@ -112,8 +112,9 @@ class Struc2Vec():
         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
 
@@ -220,7 +221,8 @@ class Struc2Vec():
                     vertices[v] = [vd for vd in degreeList.keys() if vd > v]
 
             results = Parallel(n_jobs=workers, verbose=verbose, )(
-                delayed(compute_dtw_dist)(part_list, degreeList, dist_func) for part_list in partition_dict(vertices, workers))
+                delayed(compute_dtw_dist)(part_list, degreeList, dist_func) for part_list in
+                partition_dict(vertices, workers))
             dtw_dist = dict(ChainMap(*results))
 
             structural_dist = convert_dtw_struc_dist(dtw_dist)
@@ -406,7 +408,6 @@ def get_vertices(v, degree_v, degrees, n_nodes):
 
 
 def verifyDegrees(degrees, degree_v_root, degree_a, degree_b):
-
     if (degree_b == -1):
         degree_now = degree_a
     elif (degree_a == -1):

ge/walker.py

@@ -2,17 +2,15 @@ import itertools
 import math
 import random
 
-import numpy as np
 import pandas as pd
 from joblib import Parallel, delayed
-from tqdm import trange
 
 from .alias import alias_sample, create_alias_table
 from .utils import partition_num
 
 
 class RandomWalker:
-    def __init__(self, G, p=1, q=1, use_rejection_sampling=0):
+    def __init__(self, G, p=1, q=1, use_rejection_sampling=False):
         """
         :param G:
         :param p: Return parameter,controls the likelihood of immediately revisiting a node in the walk.
@@ -213,13 +211,12 @@ class BiasedWalker:
         layers_alias = pd.read_pickle(self.temp_path + 'layers_alias.pkl')
         layers_accept = pd.read_pickle(self.temp_path + 'layers_accept.pkl')
         gamma = pd.read_pickle(self.temp_path + 'gamma.pkl')
-        walks = []
-        initialLayer = 0
 
         nodes = self.idx  # list(self.g.nodes())
 
         results = Parallel(n_jobs=workers, verbose=verbose, )(
-            delayed(self._simulate_walks)(nodes, num, walk_length, stay_prob, layers_adj, layers_accept, layers_alias, gamma) for num in
+            delayed(self._simulate_walks)(nodes, num, walk_length, stay_prob, layers_adj, layers_accept, layers_alias,
+                                          gamma) for num in
             partition_num(num_walks, workers))
 
         walks = list(itertools.chain(*results))
@@ -267,7 +264,6 @@ class BiasedWalker:
 
 
 def chooseNeighbor(v, graphs, layers_alias, layers_accept, layer):
-
     v_list = graphs[layer][v]
 
     idx = alias_sample(layers_accept[layer][v], layers_alias[layer][v])

setup.py

@@ -7,16 +7,17 @@ with open("README.md", "r") as fh:
 
 
 REQUIRED_PACKAGES = [
-    # 'tensorflow>=1.4.0,<=1.12.0',
-    'gensim==3.6.0',
-    'networkx==2.1',
-    'joblib==0.13.0',
-    'fastdtw==0.3.2',
+    # 'tensorflow>=1.4.0',
+    'gensim>=4.0.0',
+    'networkx',
+    'joblib',
+    'fastdtw',
     'tqdm',
     'numpy',
     'scikit-learn',
     'pandas',
     'matplotlib',
+    'deepctr'
 ]
 
 
@@ -28,13 +29,13 @@ setuptools.setup(
 
     author="Weichen Shen",
 
-    author_email="wcshen1994@163.com",
+    author_email="weichenswc@163.com",
 
     url="https://github.com/shenweichen/GraphEmbedding",
 
     packages=setuptools.find_packages(exclude=[]),
 
-    python_requires='>=3.4',  # 3.4.6
+    python_requires='>=3.5',  # 3.4.6
 
     install_requires=REQUIRED_PACKAGES,
 

tests/Wiki_edgelist.txt

@@ -0,0 +1,5 @@
+0 1
+0 2
+0 3
+1 2
+2 3

tests/deepwalk_test.py

@@ -0,0 +1,16 @@
+import networkx as nx
+
+from ge import DeepWalk
+
+
+def test_DeepWalk():
+    G = nx.read_edgelist('./tests/Wiki_edgelist.txt',
+                         create_using=nx.DiGraph(), nodetype=None, data=[('weight', int)])
+
+    model = DeepWalk(G, walk_length=3, num_walks=2, workers=1)
+    model.train(window_size=3, iter=1)
+    embeddings = model.get_embeddings()
+
+
+if __name__ == "__main__":
+    pass

tests/line_test.py

@@ -0,0 +1,16 @@
+import networkx as nx
+
+from ge import LINE
+
+
+def test_LINE():
+    G = nx.read_edgelist('./tests/Wiki_edgelist.txt',
+                         create_using=nx.DiGraph(), nodetype=None, data=[('weight', int)])
+
+    model = LINE(G, embedding_size=2, order='second')
+    model.train(batch_size=2, epochs=1, verbose=2)
+    embeddings = model.get_embeddings()
+
+
+if __name__ == "__main__":
+    pass

tests/node2vec_test.py

@@ -0,0 +1,22 @@
+import networkx as nx
+import pytest
+
+from ge import Node2Vec
+
+
+@pytest.mark.parametrize(
+    'use_rejection_sampling',
+    [True, False
+     ]
+)
+def test_Node2Vec(use_rejection_sampling):
+    G = nx.read_edgelist('./tests/Wiki_edgelist.txt',
+                         create_using=nx.DiGraph(), nodetype=None, data=[('weight', int)])
+    model = Node2Vec(G, walk_length=10, num_walks=80,
+                     p=0.25, q=4, workers=1, use_rejection_sampling=use_rejection_sampling)
+    model.train(window_size=5, iter=3)
+    embeddings = model.get_embeddings()
+
+
+if __name__ == "__main__":
+    pass

tests/sdne_test.py

@@ -0,0 +1,19 @@
+import networkx as nx
+import tensorflow as tf
+
+from ge import SDNE
+
+
+def test_SDNE():
+    if tf.__version__ >= '1.15.0':
+        return #todo
+    G = nx.read_edgelist('./tests/Wiki_edgelist.txt',
+                         create_using=nx.DiGraph(), nodetype=None, data=[('weight', int)])
+
+    model = SDNE(G, hidden_size=[8, 4], )
+    model.train(batch_size=2, epochs=1, verbose=2)
+    embeddings = model.get_embeddings()
+
+
+if __name__ == "__main__":
+    pass

tests/struct2vec_test.py

@@ -0,0 +1,16 @@
+import networkx as nx
+
+from ge import Struc2Vec
+
+
+def test_Struc2Vec():
+    G = nx.read_edgelist('./tests/Wiki_edgelist.txt', create_using=nx.DiGraph(), nodetype=None,
+                         data=[('weight', int)])
+
+    model = Struc2Vec(G, 3, 1, workers=1, verbose=40, )
+    model.train()
+    embeddings = model.get_embeddings()
+
+
+if __name__ == "__main__":
+    pass