├── setup.cfg ├── community_detect ├── __init__.py └── community_detect.py ├── setup.py ├── README.md └── License.md /setup.cfg: -------------------------------------------------------------------------------- 1 | [metadata] 2 | description-file = README.md -------------------------------------------------------------------------------- /community_detect/__init__.py: -------------------------------------------------------------------------------- 1 | from community_detect.community_detect import Community -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- 1 | from distutils.core import setup 2 | 3 | setup( 4 | name='community_detect', 5 | version='1.0.0', 6 | packages=['community_detect'], 7 | url = 'https://github.com/asshatter/community-detect', 8 | download_url = 'https://github.com/asshatter/community-detect/tarball/1.0.0', 9 | license='Apache License 2.0', 10 | install_requires=["networkx", "matplotlib"], 11 | author='Ankush Bhatia', 12 | author_email='ankushbhatia02@gmail.com', 13 | description='Community Detector based on algorithm for community detection using structural and attribute similarities' 14 | ) 15 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # community-detect 2 | 3 | Community detection using attribute and structural similarities. 4 | 5 | Installation: 6 | 7 | pip install community_detect 8 | 9 | Dependencies: 10 | 11 | NetworkX 12 | Matplotlib 13 | 14 | Usage: 15 | 16 | Import: 17 | 18 | from community_detect import Community 19 | 20 | 21 | Initialize: 22 | 23 | com = Community(alpha_weight = 0.5) #You can add your own value for Alpha 24 | 25 | 26 | Functions: 27 | 28 | Main method: get_communities(Graph, #Your Graph 29 | Vertices, #List of Vertices 30 | Similarity Matrix, #Similarity matrix for attribute similarities (It should be a N X N matrix where N is the number of vertices 31 | Similarity Matrix Type #Types : cosine, euclidean etc. 32 | ) 33 | 34 | Returns a dictionary with each key containing all the nodes in that community 35 | 36 | 37 | To View Communities : view_communities(Communities, #Output of above function 38 | Graph, #Your Graph 39 | Vertices, #List of Vertices 40 | Similarity Matrix, #Similarity matrix for attribute similarities (It should be a N X N matrix where N is the number of vertices 41 | Similarity Matrix Type #Types : cosine, euclidean etc 42 | ) 43 | Displays a matplotlib window displaying communities on a graph 44 | -------------------------------------------------------------------------------- /License.md: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "{}" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright 2016 Ankush Bhatia 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /community_detect/community_detect.py: -------------------------------------------------------------------------------- 1 | """ Copyright 2016 Ankush Bhatia 2 | 3 | Licensed under the Apache License, Version 2.0 (the "License"); 4 | you may not use this file except in compliance with the License. 5 | You may obtain a copy of the License at 6 | 7 | http://www.apache.org/licenses/LICENSE-2.0 8 | 9 | Unless required by applicable law or agreed to in writing, software 10 | distributed under the License is distributed on an "AS IS" BASIS, 11 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12 | See the License for the specific language governing permissions and 13 | limitations under the License. """ 14 | 15 | 16 | #------------------------------------------------------------------------------- 17 | # Name: community-detect.py 18 | # Purpose: A community detection module based on my research paper : 19 | # *Paper yet to be published* 20 | # 21 | # 22 | # Author: Ankush Bhatia 23 | # 24 | # Created: 28/06/2016 25 | # Copyright: Copyright 2016 Ankush Bhatia 26 | # Licence: Apache License 2.0 27 | #------------------------------------------------------------------------------- 28 | 29 | import networkx as nx 30 | 31 | from itertools import permutations 32 | from itertools import combinations 33 | from collections import defaultdict 34 | 35 | import matplotlib.pyplot as plt 36 | import random 37 | 38 | class Community(object): 39 | def __init__(self, alpha_weight = 0.5): 40 | self.alpha = alpha_weight 41 | random.seed() 42 | self.MIN_VALUE = 0.0000001 43 | self.node_weights = {} 44 | 45 | @classmethod 46 | # Louvain Modularity implementation based on https://github.com/shogo-ma/louvain-python 47 | # Author : Shogo Ma 48 | # Date : 25th Nov 2015 49 | # Name : 'louvain-python' 50 | # Version : "0.0.1" 51 | #To convert an IGraph to NetworkX Graph 52 | def convertIGraphToNxGraph(cls, igraph): 53 | nodenames = igraph.vs["name"] 54 | edges = igraph.get_edgelist() 55 | weights = igraph.es["weight"] 56 | nodes = defaultdict(str) 57 | 58 | for idx, node in enumerate(igraph.vs): 59 | nodes[node.index] = nodenames[idx] 60 | 61 | convertlist = [] 62 | for idx in range(len(edges)): 63 | edge = edges[idx] 64 | newedge = (nodes[edge[0]], nodes[edge[1]], weights[idx]) 65 | convertlist.append(newedge) 66 | 67 | convert_graph = nx.Graph() 68 | convert_graph.add_weighted_edges_from(convertlist) 69 | return convert_graph 70 | 71 | #Updating Nodes weight 72 | def updateNodeWeights(self, edgeweights): 73 | nodeweights = defaultdict(float) 74 | for node in edgeweights.keys(): 75 | nodeweights[node] = sum([weight for weight in edgeweights[node].values()]) 76 | return nodeweights 77 | 78 | #Main function of Louvain Algorithm 79 | def getPartition(self, graph, param=1.): 80 | node2com, edge_weights = self._setNode2Com(graph) 81 | node2com = self.runFirstPhase(node2com, edge_weights, param) 82 | best_modularity = self.ComputeModularity(node2com, edge_weights, param) 83 | partition = node2com.copy() 84 | new_node2com, new_edge_weights = self.runSecondPhase(node2com, edge_weights) 85 | while True: 86 | new_node2com = self.runFirstPhase(new_node2com, new_edge_weights, param) 87 | modularity = self.ComputeModularity(new_node2com, new_edge_weights, param) 88 | if abs(best_modularity - modularity) < self.MIN_VALUE: 89 | break 90 | best_modularity = modularity 91 | partition = self._updatePartition(new_node2com, partition) 92 | new_node2com_, new_edge_weights_ = self.runSecondPhase(new_node2com, new_edge_weights) 93 | new_node2com = new_node2com_ 94 | new_edge_weights = new_edge_weights_ 95 | return partition 96 | 97 | #Newmann Modularity 98 | def ComputeModularity(self, node2com, edge_weights, param): 99 | q = 0 100 | all_edge_weights = sum( 101 | [weight for start in edge_weights.keys() for end, weight in edge_weights[start].items()]) / 2 102 | com2node = defaultdict(list) 103 | for node, com_id in node2com.items(): 104 | com2node[com_id].append(node) 105 | for com_id, nodes in com2node.items(): 106 | node_combinations = list(combinations(nodes, 2)) + [(node, node) for node in nodes] 107 | cluster_weight = sum([edge_weights[node_pair[0]][node_pair[1]] for node_pair in node_combinations]) 108 | tot = self.getDegreeOfCluster(nodes, node2com, edge_weights) 109 | q += (cluster_weight / (2 * all_edge_weights)) - param * ((tot / (2 * all_edge_weights)) ** 2) 110 | return q 111 | 112 | def getDegreeOfCluster(self, nodes, node2com, edge_weights): 113 | weight = sum([sum(list(edge_weights[n].values())) for n in nodes]) 114 | return weight 115 | 116 | def _updatePartition(self, new_node2com, partition): 117 | reverse_partition = defaultdict(list) 118 | for node, com_id in partition.items(): 119 | reverse_partition[com_id].append(node) 120 | 121 | for old_com_id, new_com_id in new_node2com.items(): 122 | for old_com in reverse_partition[old_com_id]: 123 | partition[old_com] = new_com_id 124 | return partition 125 | 126 | def runFirstPhase(self, node2com, edge_weights, param): 127 | all_edge_weights = sum( 128 | [weight for start in edge_weights.keys() for end, weight in edge_weights[start].items()]) / 2 129 | self.node_weights = self.updateNodeWeights(edge_weights) 130 | status = True 131 | while status: 132 | statuses = [] 133 | for node in node2com.keys(): 134 | statuses = [] 135 | com_id = node2com[node] 136 | neigh_nodes = [edge[0] for edge in self.getNeighborNodes(node, edge_weights)] 137 | 138 | max_delta = 0. 139 | max_com_id = com_id 140 | communities = {} 141 | for neigh_node in neigh_nodes: 142 | node2com_copy = node2com.copy() 143 | if node2com_copy[neigh_node] in communities: 144 | continue 145 | communities[node2com_copy[neigh_node]] = 1 146 | node2com_copy[node] = node2com_copy[neigh_node] 147 | 148 | delta_q = 2 * self.getNodeWeightInCluster(node, node2com_copy, edge_weights) - (self.getTotWeight( 149 | node, node2com_copy, edge_weights) * self.node_weights[node] / all_edge_weights) * param 150 | if delta_q > max_delta: 151 | max_delta = delta_q 152 | max_com_id = node2com_copy[neigh_node] 153 | 154 | node2com[node] = max_com_id 155 | statuses.append(com_id != max_com_id) 156 | 157 | if sum(statuses) == 0: 158 | break 159 | 160 | return node2com 161 | 162 | def runSecondPhase(self, node2com, edge_weights): 163 | com2node = defaultdict(list) 164 | 165 | new_node2com = {} 166 | new_edge_weights = defaultdict(lambda: defaultdict(float)) 167 | 168 | for node, com_id in node2com.items(): 169 | com2node[com_id].append(node) 170 | if com_id not in new_node2com: 171 | new_node2com[com_id] = com_id 172 | 173 | nodes = list(node2com.keys()) 174 | node_pairs = list(permutations(nodes, 2)) + [(node, node) for node in nodes] 175 | for edge in node_pairs: 176 | new_edge_weights[new_node2com[node2com[edge[0]]]][new_node2com[node2com[edge[1]]]] += edge_weights[edge[0]][ 177 | edge[1]] 178 | return new_node2com, new_edge_weights 179 | 180 | def getTotWeight(self, node, node2com, edge_weights): 181 | nodes = [n for n, com_id in node2com.items() if com_id == node2com[node] and node != n] 182 | 183 | weight = 0. 184 | for n in nodes: 185 | weight += sum(list(edge_weights[n].values())) 186 | return weight 187 | 188 | def getNeighborNodes(self, node, edgeweights): 189 | if node not in edgeweights: 190 | return 0 191 | return edgeweights[node].items() 192 | 193 | def getNodeWeightInCluster(self, node, node2com, edge_weights): 194 | neigh_nodes = self.getNeighborNodes(node, edge_weights) 195 | node_com = node2com[node] 196 | weights = 0. 197 | for neigh_node in neigh_nodes: 198 | if node_com == node2com[neigh_node[0]]: 199 | weights += neigh_node[1] 200 | return weights 201 | 202 | def _setNode2Com(self, graph): 203 | node2com = {} 204 | edge_weights = defaultdict(lambda: defaultdict(float)) 205 | for idx, node in enumerate(graph.nodes()): 206 | node2com[node] = idx 207 | for edge in graph[node].items(): 208 | edge_weights[node][edge[0]] = edge[1]["weight"] 209 | return node2com, edge_weights 210 | 211 | 212 | def make_k_nearest_neighbour_graph(self, Graph, vertices, k, similarity_matrix, similarity_matrix_type='cosine'): 213 | #Directed Graph 214 | knng = nx.DiGraph() 215 | 216 | #Iteration over all vertices 217 | for i in vertices: 218 | 219 | #Similarity list of i with all other vertices 220 | sim_i = [] 221 | for j in range(len(similarity_matrix[i])): 222 | if j != i: 223 | if similarity_matrix_type == 'cosine': 224 | g = 0 225 | else: 226 | g = 1 227 | if j in Graph[i]: 228 | g = abs(g-1) 229 | sim = self.alpha * g + (1 - self.alpha) * float(similarity_matrix[i][j]) 230 | sim_i.append((sim, j)) 231 | sim_i.sort(reverse=True) 232 | for j in range(k): 233 | # print (sim_i[j][1]) 234 | knng.add_edge(int(i), int(sim_i[j][1]), weight=sim_i[j][0]) 235 | return knng 236 | 237 | def get_communities(self, Graph, vertices, similarity_matrix, similarity_matrix_type='cosine'): 238 | #try: 239 | #Total Edges 240 | m = len(Graph.edges()) 241 | # Setting k for knn graph 242 | k = (m // len(vertices)) 243 | #Making a k-nearest-neighbour-graph 244 | knng = self.make_k_nearest_neighbour_graph(Graph=Graph, vertices=vertices, k=k, 245 | similarity_matrix=similarity_matrix, 246 | similarity_matrix_type=similarity_matrix_type) 247 | 248 | #Getting communities 249 | partition = self.getPartition(knng) 250 | communities = defaultdict(list) 251 | for node, com_id in partition.items(): 252 | communities[com_id].append(node) 253 | return communities 254 | #except Exception as err: 255 | # print(err) 256 | 257 | #Requires Matplotlib 258 | def view_communities(self, communities, Graph, vertices, similarity_matrix, similarity_matrix_type): 259 | try: 260 | # Total Edges 261 | m = len(Graph.edges()) 262 | # Setting k for knn graph 263 | k = (m // len(vertices)) 264 | # Making a k-nearest-neighbour-graph 265 | knngraph = self.make_k_nearest_neighbour_graph(Graph=Graph, vertices=vertices, k=k, 266 | similarity_matrix=similarity_matrix, 267 | similarity_matrix_type=similarity_matrix_type) 268 | #Viewing Graph 269 | pos = nx.spring_layout(knngraph) 270 | red_edges = [] 271 | blue_edges = [] 272 | 273 | colors = ['r', 'b', 'g', '#FF0099', '#660066', '#FFFFFF', '#000000', '#123456', '#00FFFF', '#A056F2', '#888888', 274 | '#AABBCC', 275 | '#BFCFDF', '#500000', '#EFFEEF'] 276 | i = 0 277 | for com, nodes in communities.items(): 278 | nx.draw_networkx_nodes(knngraph, pos, cmap=plt.get_cmap('jet'), nodelist=nodes, 279 | node_size=100, node_color=colors[(i-1)%len(communities)]) 280 | i+=1 281 | 282 | for edge in knngraph.edges(): 283 | found = False 284 | for com, nodes in p.items(): 285 | if edge[0] in nodes and edge[1] in nodes: 286 | blue_edges.append(edge) 287 | found = True 288 | if found == False: 289 | red_edges.append(edge) 290 | 291 | nx.draw_networkx_edges(knngraph, pos, edgelist=red_edges, edge_color='r', arrows=True) 292 | nx.draw_networkx_edges(knngraph, pos, edgelist=blue_edges, edge_color='b', arrows=True) 293 | return plt 294 | except Exception as err: 295 | print(err) 296 | 297 | --------------------------------------------------------------------------------