├── DBSCAN_Martingale.r ├── LICENSE ├── README.md └── topic_detection_module.r /DBSCAN_Martingale.r: -------------------------------------------------------------------------------- 1 | 2 | library(dbscan) 3 | minpts = 50 4 | eps_max = 0.5 5 | T = 5 6 | realizations = 10 7 | 8 | ### realizations of the DBSCAN-Martingale ### 9 | ### requires as input a matrix x with the dataset to be clustered ### 10 | 11 | realizations.DBSCAN_martingale = matrix(0, nrow = realizations, ncol = T) 12 | 13 | principal.clustering.all = matrix(0, nrow = realizations, ncol = dim(x)[1]) 14 | 15 | 16 | for(r in 1:realizations) { 17 | 18 | number.of.clusters = c() 19 | 20 | ### generate 10 random numbers from the uniform distribution in [0, eps_max] ### 21 | random.epsilon = runif(T, min=0, max = eps_max) 22 | random.epsilon = sort(random.epsilon, decreasing = FALSE) 23 | 24 | dbscan.results.all = matrix(0,nrow=dim(x)[1],ncol=T) 25 | for(j in 1:T) dbscan.results.all[,j] = dbscan(x, random.epsilon[j], minpts)$cluster 26 | 27 | principal.clustering = dbscan.results.all[,1] 28 | 29 | for(j in 1:T) { 30 | if((principal.clustering%*%dbscan.results.all[,j])[1,1]==0) { 31 | b = max(principal.clustering) 32 | for(i in 1:length(dbscan.results.all[,j])) if(dbscan.results.all[i,j]!=0) dbscan.results.all[i,j] = dbscan.results.all[i,j] + b 33 | principal.clustering = principal.clustering + dbscan.results.all[,j] 34 | } else { 35 | h = c() 36 | clh = c() 37 | for(i in 1:length(principal.clustering)) { 38 | h = c(h,0) 39 | clh = c(clh,0) 40 | } 41 | for(i in 1:length(principal.clustering)) if(principal.clustering[i]==0 && dbscan.results.all[i,j] != 0) h[i]=dbscan.results.all[i,j] 42 | b = max(principal.clustering) 43 | u = 0 44 | if(max(h)>0) { 45 | for(j in 1:max(h)) if(sum(h==j)>=minpts+1) { 46 | u = u + 1 47 | clh[which(h==j)]= u 48 | } 49 | for(i in 1:length(principal.clustering)) if(clh[i]!=0) clh[i] = clh[i] + b 50 | principal.clustering = principal.clustering + clh 51 | } 52 | } 53 | number.of.clusters = c(number.of.clusters,max(principal.clustering)) 54 | } 55 | 56 | principal.clustering.all[r,] = principal.clustering 57 | 58 | print(max(principal.clustering)) 59 | print(r) 60 | 61 | realizations.DBSCAN_martingale[r,] = number.of.clusters 62 | } 63 | 64 | #realizations.DBSCAN_martingale[,T] 65 | 66 | ### number of clusters probability ### 67 | table(realizations.DBSCAN_martingale[,T])/realizations 68 | 69 | 70 | ### probability distribution - barplot ### 71 | barplot(table(realizations.DBSCAN_martingale[,T])/realizations, col = "blue", xlab = "clusters", ylab = "probability") 72 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 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 {yyyy} {name of copyright owner} 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. -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # topic-detection 2 | 3 | Provides the implementation of a topic detection framework developed for the MULTISENSOR project. In this framework, topic detection is tackled as a clustering problem and a hybrid clustering approach for assigning news articles into topics is realized. In this approach, prior knowledge of the correct number of clusters/topics is not required, as this number is automatically estimated by means of a novel methodology named DBSCAN-Martingale. The assignment of news articles into topics is done using Latent Dirichlet Allocation (LDA). 4 | 5 | #Description 6 | 7 | The ```DBSCAN_Martingale.r``` script has been developed in R, version 3.2.3 and requires the “dbscan” R package. The input is a data matrix to be clustered. The output is a probability distribution over the number of clusters and a barplot, showing the number of clusters that is more probable to describe the optimal partitioning of a dataset. 8 | 9 | The ```topic_detection_module.r``` script requires as input a folder, which contains a list of text documents. The output is a JSON file with a list of topics. The requirements are the R packages “tm”, “dbscan”, “topicmodels” and “rjson”. 10 | 11 | # Version 12 | 1.0.0 13 | 14 | 15 | 16 | 17 | 18 | 19 | 20 | -------------------------------------------------------------------------------- /topic_detection_module.r: -------------------------------------------------------------------------------- 1 | 2 | input_folder = "" 3 | 4 | 5 | library(tm) 6 | corp = VCorpus(DirSource(input_folder, encoding = "UTF-8", mode = "text")) 7 | dtm1 = DocumentTermMatrix(corp, control=list(bounds = list(global = c(20,Inf)))) 8 | dtm1_forLDA = DocumentTermMatrix(corp, control=list(bounds = list(global = c(3,Inf)))) 9 | rowTotals = apply(dtm1_forLDA , 1, sum) 10 | dtm1_forLDA = dtm1_forLDA[rowTotals> 0, ] 11 | dtm1_forDBSCAN = as.matrix(dtm1) 12 | 13 | # l1 normalization 14 | for(j in 1:dim(dtm1_forDBSCAN)[2]) dtm1_forDBSCAN[,j] = dtm1_forDBSCAN[,j]/sum(dtm1_forDBSCAN[,j]) 15 | 16 | 17 | ### DBSCAN-Martingale 18 | library(dbscan) 19 | minpts = 5 20 | T = 5 21 | 22 | 23 | ### generate 10 random numbers from the uniform distribution in [0, 0.1] 24 | random.epsilon = runif(T, min=0, max = 0.1) 25 | random.epsilon = sort(random.epsilon, decreasing = FALSE) 26 | dbscan.results.all = matrix(0, nrow = dim(dtm1)[1], ncol=T) 27 | 28 | for(j in 1:T) dbscan.results.all[,j] = dbscan(dtm1_forDBSCAN, random.epsilon[j], minpts)$cluster 29 | # giant cluster removal 30 | for(j in 1:T) { 31 | for(i in 1:length(dbscan.results.all[,j])) dbscan.results.all[i,j]= dbscan.results.all[i,j] - 1 32 | for(i in 1:length(dbscan.results.all[,j])) if(dbscan.results.all[i,j]==-1) dbscan.results.all[i,j]=0 33 | } 34 | principal.clustering = dbscan.results.all[,1] 35 | for(j in 1:T) { 36 | if((principal.clustering%*%dbscan.results.all[,j])[1,1]==0) { 37 | b = max(principal.clustering) 38 | for(i in 1:length(dbscan.results.all[,j])) if(dbscan.results.all[i,j]!=0) dbscan.results.all[i,j] = dbscan.results.all[i,j] + b 39 | principal.clustering = principal.clustering + dbscan.results.all[,j] 40 | } else { 41 | h = c() 42 | clh = c() 43 | for(i in 1:length(principal.clustering)) { 44 | h = c(h,0) 45 | clh = c(clh,0) 46 | } 47 | for(i in 1:length(principal.clustering)) if(principal.clustering[i]==0 && dbscan.results.all[i,j] != 0) h[i]=dbscan.results.all[i,j] 48 | b = max(principal.clustering) 49 | u = 0 50 | if(max(h)>0) { 51 | for(j in 1:max(h)) if(sum(h==j)>=minpts) { 52 | u = u + 1 53 | clh[which(h==j)]= u 54 | } 55 | for(i in 1:length(principal.clustering)) if(clh[i]!=0) clh[i] = clh[i] + b 56 | principal.clustering = principal.clustering + clh 57 | } 58 | } 59 | } 60 | num_of_topics = max(principal.clustering) 61 | 62 | ### LDA using the num_of_topics 63 | library(topicmodels) 64 | 65 | k = if(num_of_topics<2) 2 else num_of_topics 66 | LDA.results = LDA(dtm1_forLDA, k) 67 | LDA.clustering.vector = rep(0, dtm1_forLDA$nrow) 68 | for(i in 1:dtm1_forLDA$nrow) LDA.clustering.vector[i] = which.max(LDA.results@gamma[i,]) 69 | 70 | 71 | ### assign the documents in each topic 72 | topics.list.IDs = vector("list", k+1) 73 | names(topics.list.IDs) = as.character(0:k) 74 | 75 | for(i in 1:k) { 76 | topics.list.IDs[[i+1]] = vector("list", 3) 77 | names(topics.list.IDs[[i+1]]) = c("labels", "scores", "articles") 78 | topics.list.IDs[[i+1]][[1]] = paste(LDA.results@terms[sort(LDA.results@beta[i,], decreasing = TRUE, index.return = TRUE)$ix[1:8]], collapse = " ") 79 | topics.list.IDs[[i+1]][[2]] = abs(sort(LDA.results@beta[i,], decreasing = TRUE)[1:8]) 80 | topics.list.IDs[[i+1]][[3]] = dtm1_forLDA$dimnames$Docs[which(LDA.clustering.vector==i)] 81 | } 82 | 83 | 84 | ### create a collection of "noise"-empty documents 85 | if(length(which(rowTotals==0))>0) { 86 | topics.list.IDs[[1]] = vector("list", 2) 87 | names(topics.list.IDs[[1]]) = c("labels", "articles") 88 | topics.list.IDs[[1]][[1]] = "noise" 89 | topics.list.IDs[[1]][[2]] = dtm1$dimnames$Docs[which(rowTotals==0)] 90 | } else topics.list.IDs = topics.list.IDs[-1] 91 | 92 | 93 | ### write the results to a JSON file 94 | library(rjson) 95 | exportJSON = toJSON(topics.list.IDs) 96 | 97 | write(exportJSON, file = "topics.json") 98 | --------------------------------------------------------------------------------