├── requirements.txt ├── README.md ├── darkbert.py └── LICENSE /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/shmishtopher/dark-bert/HEAD/requirements.txt -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # dark-bert 2 | 🧠 Using large language models to classify dark net documents in a zero-shot learning enviornments. 3 | 4 | Dark bert eneables you to cluster any corpus of markup documents in an entirely unsupervised way. 5 | 6 | ``` 7 | usage: darkbert.py [-h] -m {bert,albert,roberta} -i INPUT -o OUTPUT 8 | 9 | optional arguments: 10 | -h, --help show this help message and exit 11 | -m {bert,albert,roberta}, --model {bert,albert,roberta} 12 | -i INPUT, --input INPUT 13 | -o OUTPUT, --output OUTPUT 14 | ``` -------------------------------------------------------------------------------- /darkbert.py: -------------------------------------------------------------------------------- 1 | # Copyright 2022 Christopher K. Schmitt 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 | from sentence_transformers import SentenceTransformer 16 | from sklearn.manifold import TSNE 17 | from sklearn.cluster import DBSCAN 18 | from sklearn.metrics import silhouette_score, calinski_harabasz_score 19 | from pathlib import Path 20 | from bs4 import BeautifulSoup 21 | from argparse import ArgumentParser 22 | 23 | import matplotlib.pyplot as plt 24 | import numpy as np 25 | import nltk as nltk 26 | 27 | # The list of huggingface transformers with tensorflow 28 | # support and compatible tokenizers. 29 | available_models = { 30 | "bert": "sentence-transformers/multi-qa-distilbert-cos-v1", 31 | "albert": "sentence-transformers/paraphrase-albert-small-v2", 32 | "roberta": "sentence-transformers/all-distilroberta-v1", 33 | } 34 | 35 | display_titles = { 36 | "bert": "BERT", 37 | "albert": "ALBERT", 38 | "roberta": "RoBERTa", 39 | } 40 | 41 | # Define the CLI interface for modeling our data with 42 | # different transformer models. We want to control the 43 | # type of the tokenizer and the transformer we use, as well 44 | # as the input and output directories 45 | parser = ArgumentParser() 46 | parser.add_argument("-m", "--model", choices=available_models.keys(), required=True) 47 | parser.add_argument("-i", "--input", required=True) 48 | parser.add_argument("-o", "--output", required=True) 49 | 50 | args = parser.parse_args() 51 | input_dir = args.input 52 | output_dir = args.output 53 | model_name = available_models[args.model] 54 | display_name = display_titles[args.model] 55 | 56 | # To remove random glyphs and other noise, we 57 | # only extract words in the nltk corpus 58 | nltk.download("words") 59 | words = set(nltk.corpus.words.words()) 60 | 61 | def extract_words(document): 62 | cleaned = "" 63 | 64 | for word in nltk.wordpunct_tokenize(document): 65 | if word.lower() in words: 66 | cleaned += word.lower() + " " 67 | 68 | return cleaned 69 | 70 | # Iterate over all of the files in the provided data 71 | # directory. Parse each file with beautiful soup to parse 72 | # the relevant text out of the markup. 73 | data = Path(input_dir).iterdir() 74 | data = map(lambda doc: doc.read_bytes(), data) 75 | data = map(lambda doc: BeautifulSoup(doc, "html.parser"), data) 76 | data = map(lambda doc: doc.get_text(), data) 77 | data = filter(lambda doc: len(doc) > 0, data) 78 | data = map(extract_words, data) 79 | data = filter(lambda doc: len(doc) > 10, data) 80 | data = list(data) 81 | 82 | # Initilize transformer models and predict all of the 83 | # document embeddings as computed by bert and friends 84 | model = SentenceTransformer(model_name) 85 | embeddings = model.encode(data, show_progress_bar=True) 86 | 87 | # Fit TSNE model for embedding space. Sqush down to 2 88 | # dimentions for visualization purposes. 89 | tsne = TSNE(n_components=2, random_state=2, init="pca", learning_rate="auto", perplexity=40) 90 | tsne = tsne.fit_transform(embeddings) 91 | 92 | # Hyperparameter optimizations 93 | silhouettes = [] 94 | outliers = [] 95 | ch = [] 96 | 97 | for eps in np.arange(0.001, 1, 0.001): 98 | dbscan = DBSCAN(eps, metric="cosine", n_jobs=-1) 99 | dbscan = dbscan.fit_predict(embeddings) 100 | 101 | if len(np.unique(dbscan)) > 1: 102 | silhouettes.append(silhouette_score(embeddings, dbscan, metric="cosine")) 103 | ch.append(calinski_harabasz_score(embeddings, dbscan)) 104 | else: 105 | silhouettes.append(0) 106 | ch.append(0) 107 | 108 | outliers.append(len(dbscan[dbscan == -1])) 109 | 110 | for p in range(15, 51): 111 | best = np.argmax(silhouettes) 112 | 113 | dbscan = DBSCAN(0.001 + 0.001 * best, metric="cosine", n_jobs=-1) 114 | dbscan = dbscan.fit_predict(embeddings) 115 | 116 | tsne = TSNE(n_components=2, perplexity=p, learning_rate="auto", init="pca", metric="cosine") 117 | tsne = tsne.fit_transform(embeddings) 118 | 119 | plt.figure() 120 | plt.scatter(tsne[dbscan != -1][:, 0], tsne[dbscan != -1][:, 1], s=0.5, c=dbscan[dbscan != -1], cmap="hsv") 121 | plt.scatter(tsne[dbscan == -1][:, 0], tsne[dbscan == -1][:, 1], s=0.5, c="#abb8c3") 122 | plt.title(f"{display_name} Embeddings Visualized with T-SNE (p = {p})") 123 | plt.savefig(f"{output_dir}/tnse_{p:02}.png", format="png", dpi=600) 124 | plt.close() 125 | 126 | plt.figure() 127 | plt.plot(np.arange(0.001, 1, 0.001), silhouettes, lw=0.5, color="#dc322f") 128 | plt.legend() 129 | plt.xlabel("Epsilon") 130 | plt.ylabel("silhouette score") 131 | plt.title("Optimizing Epsilon by Silhouette Score") 132 | plt.savefig(f"silhouettes.png", format="png", dpi=600) 133 | plt.close() 134 | 135 | plt.figure() 136 | plt.plot(np.arange(0.001, 1, 0.001), outliers, lw=0.5, color="#dc322f") 137 | plt.legend() 138 | plt.xlabel("Epsilon") 139 | plt.ylabel("outliers") 140 | plt.title("Optimizing Epsilon by Number of Outliers") 141 | plt.savefig(f"outliers.png", format="png", dpi=600) 142 | plt.close() 143 | 144 | plt.figure() 145 | plt.plot(np.arange(0.001, 1, 0.001), ch, lw=0.5, color="#dc322f") 146 | plt.legend() 147 | plt.xlabel("Epsilon") 148 | plt.ylabel("Calinski-Harabasz score") 149 | plt.title("Optimizing Epsilon by Calinski-Harabasz Score") 150 | plt.savefig(f"calinski-harabasz.png", format="png", dpi=600) 151 | plt.close() -------------------------------------------------------------------------------- /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 | --------------------------------------------------------------------------------