CarlosMorales commited on
Commit
9b4a3d3
·
verified ·
1 Parent(s): a74933e

Add BERTopic model

Browse files
Files changed (4) hide show
  1. README.md +72 -0
  2. config.json +17 -0
  3. topic_embeddings.safetensors +3 -0
  4. topics.json +262 -0
README.md ADDED
@@ -0,0 +1,72 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ tags:
4
+ - bertopic
5
+ library_name: bertopic
6
+ pipeline_tag: text-classification
7
+ ---
8
+
9
+ # bbc_news_topics
10
+
11
+ This is a [BERTopic](https://github.com/MaartenGr/BERTopic) model.
12
+ BERTopic is a flexible and modular topic modeling framework that allows for the generation of easily interpretable topics from large datasets.
13
+
14
+ ## Usage
15
+
16
+ To use this model, please install BERTopic:
17
+
18
+ ```
19
+ pip install -U bertopic
20
+ ```
21
+
22
+ You can use the model as follows:
23
+
24
+ ```python
25
+ from bertopic import BERTopic
26
+ topic_model = BERTopic.load("CarlosMorales/bbc_news_topics")
27
+
28
+ topic_model.get_topic_info()
29
+ ```
30
+
31
+ ## Topic overview
32
+
33
+ * Number of topics: 3
34
+ * Number of training documents: 100
35
+
36
+ <details>
37
+ <summary>Click here for an overview of all topics.</summary>
38
+
39
+ | Topic ID | Topic Keywords | Topic Frequency | Label |
40
+ |----------|----------------|-----------------|-------|
41
+ | -1 | the - of - to - and - eu | 28 | -1_the_of_to_and |
42
+ | 0 | the - of - to - and - in | 6 | 0_the_of_to_and |
43
+ | 1 | the - to - of - and - in | 66 | 1_the_to_of_and |
44
+
45
+ </details>
46
+
47
+ ## Training hyperparameters
48
+
49
+ * calculate_probabilities: False
50
+ * language: english
51
+ * low_memory: False
52
+ * min_topic_size: 10
53
+ * n_gram_range: (1, 1)
54
+ * nr_topics: None
55
+ * seed_topic_list: None
56
+ * top_n_words: 10
57
+ * verbose: False
58
+ * zeroshot_min_similarity: 0.7
59
+ * zeroshot_topic_list: None
60
+
61
+ ## Framework versions
62
+
63
+ * Numpy: 1.26.4
64
+ * HDBSCAN: 0.8.33
65
+ * UMAP: 0.5.6
66
+ * Pandas: 2.2.1
67
+ * Scikit-Learn: 1.4.1.post1
68
+ * Sentence-transformers: 2.6.1
69
+ * Transformers: 4.39.3
70
+ * Numba: 0.59.1
71
+ * Plotly: 5.20.0
72
+ * Python: 3.11.6
config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "calculate_probabilities": false,
3
+ "language": "english",
4
+ "low_memory": false,
5
+ "min_topic_size": 10,
6
+ "n_gram_range": [
7
+ 1,
8
+ 1
9
+ ],
10
+ "nr_topics": null,
11
+ "seed_topic_list": null,
12
+ "top_n_words": 10,
13
+ "verbose": false,
14
+ "zeroshot_min_similarity": 0.7,
15
+ "zeroshot_topic_list": null,
16
+ "embedding_model": "sentence-transformers/all-MiniLM-L6-v2"
17
+ }
topic_embeddings.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab9bf8137b0dcf864c9b7043f3bc5aaa8128067943335e0417bf632b61ca4d0e
3
+ size 4696
topics.json ADDED
@@ -0,0 +1,262 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "topic_representations": {
3
+ "-1": [
4
+ [
5
+ "the",
6
+ 0.13804656283058866
7
+ ],
8
+ [
9
+ "of",
10
+ 0.07825405363842275
11
+ ],
12
+ [
13
+ "to",
14
+ 0.0772985504098433
15
+ ],
16
+ [
17
+ "and",
18
+ 0.057608023675185964
19
+ ],
20
+ [
21
+ "eu",
22
+ 0.05441345274003265
23
+ ],
24
+ [
25
+ "in",
26
+ 0.054258494077856614
27
+ ],
28
+ [
29
+ "is",
30
+ 0.04620225771054437
31
+ ],
32
+ [
33
+ "brexit",
34
+ 0.04166188146807172
35
+ ],
36
+ [
37
+ "european",
38
+ 0.037377992114263486
39
+ ],
40
+ [
41
+ "uk",
42
+ 0.03479815498437571
43
+ ]
44
+ ],
45
+ "0": [
46
+ [
47
+ "the",
48
+ 0.10874855481558174
49
+ ],
50
+ [
51
+ "of",
52
+ 0.06634622479412591
53
+ ],
54
+ [
55
+ "to",
56
+ 0.06451676138637687
57
+ ],
58
+ [
59
+ "and",
60
+ 0.06281384435758307
61
+ ],
62
+ [
63
+ "in",
64
+ 0.06036585051618699
65
+ ],
66
+ [
67
+ "on",
68
+ 0.04067850804885957
69
+ ],
70
+ [
71
+ "was",
72
+ 0.0379906368007012
73
+ ],
74
+ [
75
+ "is",
76
+ 0.037654043139849894
77
+ ],
78
+ [
79
+ "for",
80
+ 0.03695174642522398
81
+ ],
82
+ [
83
+ "it",
84
+ 0.031825849733819044
85
+ ]
86
+ ],
87
+ "1": [
88
+ [
89
+ "the",
90
+ 0.12256853839401158
91
+ ],
92
+ [
93
+ "to",
94
+ 0.07758366134034063
95
+ ],
96
+ [
97
+ "of",
98
+ 0.06958004226056384
99
+ ],
100
+ [
101
+ "and",
102
+ 0.06074592235451145
103
+ ],
104
+ [
105
+ "in",
106
+ 0.055861273979050344
107
+ ],
108
+ [
109
+ "trump",
110
+ 0.04639481547390947
111
+ ],
112
+ [
113
+ "as",
114
+ 0.04060120868254382
115
+ ],
116
+ [
117
+ "that",
118
+ 0.04004072506992107
119
+ ],
120
+ [
121
+ "on",
122
+ 0.03557763021260862
123
+ ],
124
+ [
125
+ "for",
126
+ 0.03549585785428864
127
+ ]
128
+ ]
129
+ },
130
+ "topics": [
131
+ 0,
132
+ 0,
133
+ 0,
134
+ 0,
135
+ 0,
136
+ 0,
137
+ 0,
138
+ 0,
139
+ 0,
140
+ 0,
141
+ 0,
142
+ 1,
143
+ 0,
144
+ 1,
145
+ 1,
146
+ 0,
147
+ 0,
148
+ 0,
149
+ 0,
150
+ 1,
151
+ 0,
152
+ 1,
153
+ 0,
154
+ 0,
155
+ 1,
156
+ 1,
157
+ 1,
158
+ 0,
159
+ 1,
160
+ 0,
161
+ 1,
162
+ 0,
163
+ 1,
164
+ 0,
165
+ 1,
166
+ 1,
167
+ 0,
168
+ -1,
169
+ 1,
170
+ 1,
171
+ 0,
172
+ 0,
173
+ 0,
174
+ 0,
175
+ 0,
176
+ 1,
177
+ 1,
178
+ 1,
179
+ 0,
180
+ 1,
181
+ 1,
182
+ 0,
183
+ 1,
184
+ 0,
185
+ -1,
186
+ 0,
187
+ -1,
188
+ 0,
189
+ 1,
190
+ 1,
191
+ 0,
192
+ 0,
193
+ 1,
194
+ 0,
195
+ 0,
196
+ 0,
197
+ 1,
198
+ 0,
199
+ 0,
200
+ 0,
201
+ 0,
202
+ -1,
203
+ 0,
204
+ 0,
205
+ 0,
206
+ 0,
207
+ 1,
208
+ 1,
209
+ 0,
210
+ 0,
211
+ 0,
212
+ 0,
213
+ 0,
214
+ 0,
215
+ 0,
216
+ 0,
217
+ 0,
218
+ 1,
219
+ 0,
220
+ 0,
221
+ 0,
222
+ 0,
223
+ 0,
224
+ 0,
225
+ 0,
226
+ -1,
227
+ -1,
228
+ 0,
229
+ 0,
230
+ 0
231
+ ],
232
+ "topic_sizes": {
233
+ "0": 66,
234
+ "1": 28,
235
+ "-1": 6
236
+ },
237
+ "topic_mapper": [
238
+ [
239
+ -1,
240
+ -1,
241
+ -1
242
+ ],
243
+ [
244
+ 0,
245
+ 0,
246
+ 1
247
+ ],
248
+ [
249
+ 1,
250
+ 1,
251
+ 0
252
+ ]
253
+ ],
254
+ "topic_labels": {
255
+ "-1": "-1_the_of_to_and",
256
+ "0": "0_the_of_to_and",
257
+ "1": "1_the_to_of_and"
258
+ },
259
+ "custom_labels": null,
260
+ "_outliers": 1,
261
+ "topic_aspects": {}
262
+ }