├── .gitignore ├── LICENSE ├── MTM ├── MultiTerm.java └── MultiTermModel.java ├── README.md ├── data └── stackoverflow ├── output └── stackoverflow │ └── stackoverflow_K20 └── preprocess_multiTerm.py /.gitignore: -------------------------------------------------------------------------------- 1 | *.class 2 | *.log 3 | *.pyc 4 | 5 | -------------------------------------------------------------------------------- /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. 202 | -------------------------------------------------------------------------------- /MTM/MultiTerm.java: -------------------------------------------------------------------------------- 1 | package MTM; 2 | 3 | import java.util.ArrayList; 4 | 5 | public class MultiTerm{ 6 | ArrayList words; 7 | int word_z; 8 | 9 | public static void main(String[] args){ 10 | 11 | } 12 | 13 | public MultiTerm(Integer[] words){ 14 | this.words = new ArrayList(); 15 | for(int i=0; i get_words(){ 22 | return words; 23 | } 24 | 25 | public void set_topic(int z){ 26 | word_z = z; 27 | } 28 | 29 | public int get_topic(){ 30 | return word_z; 31 | } 32 | 33 | public void reset_topic(){ 34 | word_z = -1; 35 | } 36 | } -------------------------------------------------------------------------------- /MTM/MultiTermModel.java: -------------------------------------------------------------------------------- 1 | package MTM; 2 | 3 | import java.util.ArrayList; 4 | import java.util.Arrays; 5 | import java.util.HashMap; 6 | import java.util.HashSet; 7 | import java.util.Collections; 8 | import java.util.Random; 9 | import java.io.BufferedReader; 10 | import java.io.FileReader; 11 | import java.io.FileWriter; 12 | import java.io.IOException; 13 | import java.lang.Math; 14 | 15 | import MTM.MultiTerm; 16 | 17 | public class MultiTermModel{ 18 | 19 | public ArrayList multiTerms; 20 | public ArrayList> multiTerms_list; 21 | public ArrayList> mit_id_text; 22 | public ArrayList>> text_multiTerms; 23 | public int topic_num; 24 | public int top_words_num; 25 | public int iter_times; 26 | public String input_dir; 27 | public String output_dir; 28 | public double alpha; 29 | public double beta; 30 | public int n_iter; 31 | public int text_size; 32 | public int voca_size; 33 | public int multiTerm_size; 34 | public int multiTerm_number; 35 | public int[] n_z; 36 | public int[][] nwz; 37 | public int[] n_sumw_z; 38 | public ArrayList> cache_count; 39 | public HashMap word_index; 40 | 41 | double[] p_z; 42 | double[][] pz_d; 43 | double[][] pz_m; 44 | double[][] pw_z; 45 | 46 | private Random random; 47 | 48 | public MultiTermModel( 49 | int topic_num, 50 | int top_words_num, 51 | String input_dir, 52 | String output_dir, 53 | double alpha, 54 | double beta, 55 | int iter_times 56 | ){ 57 | this.multiTerms = new ArrayList(); 58 | this.multiTerms_list = new ArrayList>(); 59 | this.mit_id_text = new ArrayList>(); 60 | this.text_multiTerms = new ArrayList>>(); 61 | this.topic_num = topic_num; 62 | this.iter_times = iter_times; 63 | this.input_dir = input_dir; 64 | this.output_dir = output_dir; 65 | this.alpha = alpha; 66 | this.beta = beta; 67 | this.n_iter = 1; 68 | this.top_words_num = top_words_num; 69 | word_index = new HashMap(); 70 | random = new Random(); 71 | } 72 | 73 | public static void main(String[] args){ 74 | 75 | int topic_num = Integer.parseInt(args[0]); 76 | String input_dir = args[1]; 77 | String output_dir = args[2]; 78 | double alpha = Double.parseDouble(args[3]); 79 | double beta = Double.parseDouble(args[4]); 80 | int iter_times = 500; 81 | if(args.length >= 6){ 82 | iter_times = Integer.parseInt(args[5]); 83 | } 84 | 85 | int top_words_num = 20; 86 | 87 | System.out.println("alpha: " + alpha); 88 | System.out.println("beta: " + beta); 89 | 90 | MultiTermModel model = new MultiTermModel(topic_num, top_words_num, input_dir, output_dir, alpha, beta, iter_times); 91 | try{ 92 | model.init_model(); 93 | }catch(IOException e){ 94 | e.printStackTrace(); 95 | } 96 | model.run_model(); 97 | model.save_pw_z(); 98 | model.save_pz_d(); 99 | } 100 | 101 | private static long getCurrTime() { 102 | return System.currentTimeMillis(); 103 | } 104 | 105 | public void run_model(){ 106 | System.out.println("\nBegin iteration..."); 107 | 108 | while(n_iter <= iter_times){ 109 | System.out.print("\r" + n_iter + "/" + iter_times); 110 | for(MultiTerm mit : multiTerms){ 111 | update_multiTerm(mit); 112 | } 113 | n_iter++; 114 | } 115 | System.out.println(); 116 | 117 | } 118 | 119 | public void update_multiTerm(MultiTerm mit){ 120 | reset_multiTerm(mit); 121 | double[] pz = new double[topic_num]; 122 | compute_pz(mit, pz); 123 | int topic_id = mult_sample(pz); 124 | assign_multiTerm_topic(mit, topic_id); 125 | } 126 | 127 | 128 | public void compute_pz(MultiTerm mit, double[] pz){ 129 | ArrayList words = mit.get_words(); 130 | int word_num = words.size(); 131 | double[] pwk = new double[word_num]; 132 | 133 | // nwz, n_z and n_sumw_z have already been updated in reset_multiterm(), so we don't need to exclude the mit in them. 134 | for(int k=0; k= u * pz[topic_num - 1]){ 154 | break; 155 | } 156 | } 157 | if(k == topic_num){ 158 | k--; 159 | } 160 | return k; 161 | } 162 | 163 | 164 | public void reset_multiTerm(MultiTerm mit){ 165 | int k = mit.get_topic(); 166 | ArrayList words = mit.get_words(); 167 | n_z[k]--; 168 | n_sumw_z[k] -= words.size(); 169 | for(int i=0; i words = mit.get_words(); 183 | mit.set_topic(topic_id); 184 | n_z[topic_id]++; 185 | n_sumw_z[topic_id] += words.size(); 186 | for(int i=0; i mit = new ArrayList(); 217 | for(int i=0; i> text_mit = new ArrayList>(); 234 | for(int i=0; i < mit_strings.length; i++){ 235 | String[] words = mit_strings[i].split("\\s+"); 236 | ArrayList mit = new ArrayList(); 237 | for(int j=0; j mit_ids = new ArrayList(); 269 | for(int i=0; i top_topics = new ArrayList(); 290 | ArrayList top_topics_words = new ArrayList(); 291 | 292 | for(int k=0; k word_dis = new ArrayList(); 296 | for(int i=0; i nw[w2] - nw[w1]); 302 | 303 | String[] top_topics_k = new String[top_words_num]; 304 | String[] top_topics_words_k = new String[top_words_num]; 305 | for(int i=0; i < top_words_num; i++){ 306 | top_topics_words_k[i] = word_index.get(word_dis.get(i)); 307 | top_topics_k[i] = word_dis.get(i).toString(); 308 | } 309 | 310 | top_topics.add(String.join(" ", top_topics_k) + "\n"); 311 | top_topics_words.add(String.join(" ", top_topics_words_k) + "\n"); 312 | } 313 | 314 | try { 315 | FileWriter writer = new FileWriter(output_dir + "top_topics"); 316 | writer.write(String.join("", top_topics)); 317 | writer.close(); 318 | } catch (IOException e) { 319 | e.printStackTrace(); 320 | } 321 | 322 | try { 323 | FileWriter writer = new FileWriter(output_dir + "top_topics_words"); 324 | writer.write(String.join("", top_topics_words)); 325 | writer.close(); 326 | } catch (IOException e) { 327 | e.printStackTrace(); 328 | } 329 | 330 | } 331 | 332 | public void save_pz_d(){ 333 | System.out.println("\nsave_pz_d"); 334 | 335 | pw_z = new double[topic_num][voca_size]; 336 | pz_d = new double[text_size][topic_num]; 337 | p_z = new double[topic_num]; 338 | pz_m = new double[multiTerm_number][topic_num]; 339 | 340 | for(int k=0; k word_ids = multiTerms_list.get(m); 373 | for(int k=0; k id_list = mit_id_text.get(t); 388 | for(int k=0; k 2 | 0 0.53831 [excel, vba, file, data, cell] 3 | 1 0.61347 [mac, os, application, qt, cocoa] 4 | 2 0.49934 [sharepoint, list, site, web, custom] 5 | 3 0.49917 [matlab, image, matrix, array, plot] 6 | 4 0.64424 [ajax, jquery, page, javascript, aspnet] 7 | 5 0.69347 [hibernate, linq, oracle, query, sql] 8 | 6 0.45341 [bash, script, file, command, line] 9 | 7 0.48547 [haskell, type, scala, function, error] 10 | 8 0.51815 [google, polygon, way, maps, api] 11 | 9 0.62048 [oracle, server, web, sql, use] 12 | 10 0.47750 [spring, hibernate, use, security, mvc] 13 | 11 0.47653 [apache, htaccess, server, rewrite, modrewrite] 14 | 12 0.54114 [magento, wordpress, page, product, custom] 15 | 13 0.58716 [ruby, rails, vs, leopard, snow] 16 | 14 0.53515 [drupal, form, view, node, views] 17 | 15 0.46438 [studio, visual, project, code, file] 18 | 16 0.46862 [scala, class, java, method, way] 19 | 17 0.62170 [svn, subversion, files, repository, file] 20 | 18 0.40227 [using, best, without, get, one] 21 | 19 0.51038 [qt, cocoa, window, menu, item] 22 | 23 | Average score: 0.532517 24 | 25 | -------------------------------------------------------------------------------- /preprocess_multiTerm.py: -------------------------------------------------------------------------------- 1 | import os 2 | import codecs 3 | import argparse 4 | import regex 5 | import numpy as np 6 | import nltk 7 | from nltk.stem import WordNetLemmatizer 8 | from nltk.corpus import stopwords 9 | from collections import Counter 10 | import json 11 | 12 | 13 | parser = argparse.ArgumentParser() 14 | parser.add_argument('--data_path', default="data/Tweet") 15 | parser.add_argument('--output_dir', default="data") 16 | args = parser.parse_args() 17 | 18 | lemmatizer = WordNetLemmatizer() 19 | stopwords_list = list(set(stopwords.words('english'))) 20 | 21 | 22 | def load_data(data_path): 23 | texts = list() 24 | with open(data_path) as file: 25 | for line in file: 26 | texts.append(line) 27 | return texts 28 | 29 | 30 | NP_pattern = """ 31 | NP: {*+} 32 | """ 33 | 34 | 35 | NN_pattern = """ 36 | NN: {+} 37 | """ 38 | 39 | NP_parser = nltk.RegexpParser(NP_pattern) 40 | NN_parser = nltk.RegexpParser(NN_pattern) 41 | 42 | def get_text_multiTerm(text): 43 | words = text.split() 44 | tag_words = nltk.pos_tag(words) 45 | 46 | NP_result = NP_parser.parse(tag_words) 47 | NN_result = NN_parser.parse(tag_words) 48 | 49 | multiTerm_list = list() 50 | not_noun_phrase = list() 51 | not_noun_phrase_list = list() 52 | noun_phrase_list = list() 53 | only_noun_phrase_list = list() 54 | 55 | for subtree in NP_result: 56 | if type(subtree) == nltk.tree.Tree: 57 | if not_noun_phrase: 58 | not_noun_phrase_list.append(' '.join(not_noun_phrase)) 59 | not_noun_phrase = list() 60 | 61 | if subtree.label() == 'NP': 62 | term = ' '.join([w for w, pos in subtree.leaves()]) 63 | if term: 64 | noun_phrase_list.append(term) 65 | else: 66 | not_noun_phrase.append(subtree[0]) 67 | 68 | for subtree in NN_result.subtrees(): 69 | if subtree.label() == 'NN': 70 | term = ' '.join([w for w, pos in subtree.leaves()]) 71 | if term: 72 | only_noun_phrase_list.append(term) 73 | 74 | if not_noun_phrase: 75 | not_noun_phrase_list.append(' '.join(not_noun_phrase)) 76 | 77 | for mit in noun_phrase_list: 78 | multiTerm_list.append(mit) 79 | 80 | for mit in not_noun_phrase_list: 81 | multiTerm_list.append(mit) 82 | 83 | noun_phrase_size = len(noun_phrase_list) 84 | for i in range(noun_phrase_size - 2): 85 | multiTerm_list.append("{} {}".format(noun_phrase_list[i], noun_phrase_list[i+1])) 86 | 87 | only_noun_phrase_words = " ".join(only_noun_phrase_list).split() 88 | words_len = len(only_noun_phrase_words) 89 | for i in range(words_len): 90 | for j in range(i+1, words_len): 91 | multiTerm_list.append("{} {}".format(only_noun_phrase_words[i], only_noun_phrase_words[j])) 92 | 93 | return multiTerm_list 94 | 95 | 96 | def preprocess_data(): 97 | # load data 98 | texts = load_data(args.data_path) 99 | 100 | # counter for multiTerms 101 | counter = Counter() 102 | words = list() 103 | transformed_multiTerm_texts = list() 104 | all_multiTerm_list = list() 105 | all_length = len(texts) 106 | 107 | for i in range(all_length): 108 | 109 | print("{}/{}".format(i+1, all_length), end='\r') 110 | 111 | text_multiTerms = get_text_multiTerm(texts[i]) 112 | 113 | transformed_multiTerm_texts.append(','.join(text_multiTerms)) 114 | 115 | all_multiTerm_list.extend(text_multiTerms) 116 | 117 | counter.update(text_multiTerms) 118 | 119 | print("\nsaving files...") 120 | 121 | multiTerm_counter_dict = dict(counter) 122 | multiTerm_list = list(counter.keys()) 123 | multiTerm_size = len(multiTerm_list) 124 | multiTerm_index = dict(zip(multiTerm_list, range(multiTerm_size))) 125 | 126 | # sort multiTerm_list according to the id 127 | # multiTerm_list.sort(key=lambda mit: multiTerm_index[mit]) 128 | 129 | multiTerm_number = list() 130 | for mit in multiTerm_list: 131 | multiTerm_number.append(str(multiTerm_counter_dict[mit])) 132 | 133 | # get all words in muliTerms 134 | for mit in multiTerm_list: 135 | words += mit.split() 136 | 137 | words = list(set(words)) 138 | voca_size = len(words) 139 | word_dict = dict(zip(words, range(voca_size))) 140 | 141 | with open(os.path.join(args.output_dir, 'multiTerm_number'), 'w') as file: 142 | file.write('\n'.join(multiTerm_number)) 143 | 144 | with open(os.path.join(args.output_dir, "multiTerms_words"), 'w') as f: 145 | f.write('\n'.join(all_multiTerm_list)) 146 | 147 | all_multiTerm_list = list(map( 148 | lambda mit: ' '.join([str(word_dict[word]) for word in mit.split()]), 149 | all_multiTerm_list 150 | )) 151 | 152 | multiTerm_list = list(map( 153 | lambda mit: ' '.join([str(word_dict[word]) for word in mit.split()]), 154 | multiTerm_list 155 | )) 156 | 157 | mit_id_text = list(map( 158 | lambda text: ' '.join(str(multiTerm_index[mit]) for mit in text.split(',')), 159 | transformed_multiTerm_texts 160 | )) 161 | 162 | transformed_multiTerm_texts = list(map( 163 | lambda text: ','.join([' '.join([str(word_dict[word]) for word in mit.split()]) for mit in text.split(',')]), 164 | transformed_multiTerm_texts 165 | )) 166 | 167 | 168 | word_index = dict() 169 | for key in word_dict: 170 | word_index[word_dict[key]] = key 171 | 172 | with open(os.path.join(args.output_dir, "multiTerms"), 'w') as f: 173 | f.write('\n'.join(all_multiTerm_list)) 174 | 175 | with open(os.path.join(args.output_dir, "multiTerms_list"), 'w') as f: 176 | f.write('\n'.join(multiTerm_list)) 177 | 178 | with open(os.path.join(args.output_dir, "mit_id_text"), 'w') as f: 179 | f.write('\n'.join(mit_id_text)) 180 | 181 | with open(os.path.join(args.output_dir, "transformed_multiTerm_texts"), 'w') as f: 182 | f.write('\n'.join(transformed_multiTerm_texts)) 183 | 184 | word_index_string = list() 185 | for key in word_index: 186 | word_index_string.append('{} {}\n'.format(key, word_index[key])) 187 | 188 | with open(os.path.join(args.output_dir, 'word_index.txt'), 'w') as file: 189 | file.write(''.join(word_index_string)) 190 | 191 | print("done.") 192 | 193 | 194 | if __name__ == "__main__": 195 | preprocess_data() 196 | --------------------------------------------------------------------------------