Maitorokku commited on
Commit
67d94f4
1 Parent(s): 93df272

Add BERTopic model

Browse files
Files changed (4) hide show
  1. README.md +97 -0
  2. config.json +15 -0
  3. topic_embeddings.safetensors +3 -0
  4. topics.json +0 -0
README.md ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ tags:
4
+ - bertopic
5
+ library_name: bertopic
6
+ pipeline_tag: text-classification
7
+ ---
8
+
9
+ # transformers_issues_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("Maitorokku/transformers_issues_topics")
27
+
28
+ topic_model.get_topic_info()
29
+ ```
30
+
31
+ ## Topic overview
32
+
33
+ * Number of topics: 30
34
+ * Number of training documents: 9000
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 | climate - environmental - research - analysis - study | 11 | -1_climate_environmental_research_analysis |
42
+ | 0 | climate - climatic - ecological - environmental - precipitation | 2717 | 0_climate_climatic_ecological_environmental |
43
+ | 1 | resilience - practices - innovation - preparedness - management | 2162 | 1_resilience_practices_innovation_preparedness |
44
+ | 2 | ndvi - correlation - vegetation - pearson - formula | 642 | 2_ndvi_correlation_vegetation_pearson |
45
+ | 3 | study - questionnaire - criteria - respondents - conducted | 427 | 3_study_questionnaire_criteria_respondents |
46
+ | 4 | software - sustainable - research - researchers - development | 394 | 4_software_sustainable_research_researchers |
47
+ | 5 | malaria - prevalence - population - mosquitoes - mosquito | 309 | 5_malaria_prevalence_population_mosquitoes |
48
+ | 6 | pandemic - pandemics - covid19 - crisis - governments | 290 | 6_pandemic_pandemics_covid19_crisis |
49
+ | 7 | journals - journal - article - articles - bibliometric | 252 | 7_journals_journal_article_articles |
50
+ | 8 | propolis - antimicrobial - aloe - antibacterial - biofilm | 228 | 8_propolis_antimicrobial_aloe_antibacterial |
51
+ | 9 | health - millennials - healthy - healthcare - changehealth | 216 | 9_health_millennials_healthy_healthcare |
52
+ | 10 | deficiency - vitamin - diseases - supplementation - dietary | 184 | 10_deficiency_vitamin_diseases_supplementation |
53
+ | 11 | quails - quail - insulation - temperatures - heatstress | 153 | 11_quails_quail_insulation_temperatures |
54
+ | 12 | ethics - ethical - researchers - moral - research | 144 | 12_ethics_ethical_researchers_moral |
55
+ | 13 | obesity - metabolic - diabetes - circadian - health | 140 | 13_obesity_metabolic_diabetes_circadian |
56
+ | 14 | poultry - chickens - chicken - livestock - farms | 134 | 14_poultry_chickens_chicken_livestock |
57
+ | 15 | lightning - incidence - fatalities - bangladesh - deaths | 80 | 15_lightning_incidence_fatalities_bangladesh |
58
+ | 16 | harassment - gaming - behavior - games - narratives | 72 | 16_harassment_gaming_behavior_games |
59
+ | 17 | indigenous - knowledge - concept - ik - principles | 68 | 17_indigenous_knowledge_concept_ik |
60
+ | 18 | kinase - gene - signaling - phosphorylates - phosphorylation | 60 | 18_kinase_gene_signaling_phosphorylates |
61
+ | 19 | camel - camels - meat - meats - beef | 44 | 19_camel_camels_meat_meats |
62
+ | 20 | turkey - turkeyeu - turkeys - turkish - ankara | 43 | 20_turkey_turkeyeu_turkeys_turkish |
63
+ | 21 | wasserwiedernutzung - treibhausgaseffekt - wiedernutzung - beschreibt - khleffekt | 41 | 21_wasserwiedernutzung_treibhausgaseffekt_wiedernutzung_beschreibt |
64
+ | 22 | locusts - genome - locust - sequencing - genes | 41 | 22_locusts_genome_locust_sequencing |
65
+ | 23 | chainsaw - noisy - noise - nonchainsaw - earmuffs | 37 | 23_chainsaw_noisy_noise_nonchainsaw |
66
+ | 24 | evolution - evolved - brains - neuroplasticity - brain | 36 | 24_evolution_evolved_brains_neuroplasticity |
67
+ | 25 | sinusitis - sinus - sinuses - aplasia - paranasal | 31 | 25_sinusitis_sinus_sinuses_aplasia |
68
+ | 26 | mandarins - mandarin - citrus - fruits - fruit | 16 | 26_mandarins_mandarin_citrus_fruits |
69
+ | 27 | hikikomori - otaku - japanese - anime - otakus | 16 | 27_hikikomori_otaku_japanese_anime |
70
+ | 28 | travel - trips - businesses - business - corporate | 12 | 28_travel_trips_businesses_business |
71
+
72
+ </details>
73
+
74
+ ## Training hyperparameters
75
+
76
+ * calculate_probabilities: False
77
+ * language: english
78
+ * low_memory: False
79
+ * min_topic_size: 10
80
+ * n_gram_range: (1, 1)
81
+ * nr_topics: 30
82
+ * seed_topic_list: None
83
+ * top_n_words: 10
84
+ * verbose: True
85
+
86
+ ## Framework versions
87
+
88
+ * Numpy: 1.22.4
89
+ * HDBSCAN: 0.8.29
90
+ * UMAP: 0.5.3
91
+ * Pandas: 1.5.3
92
+ * Scikit-Learn: 1.2.2
93
+ * Sentence-transformers: 2.2.2
94
+ * Transformers: 4.30.2
95
+ * Numba: 0.56.4
96
+ * Plotly: 5.13.1
97
+ * Python: 3.10.12
config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 30,
11
+ "seed_topic_list": null,
12
+ "top_n_words": 10,
13
+ "verbose": true,
14
+ "embedding_model": "sentence-transformers/all-MiniLM-L6-v2"
15
+ }
topic_embeddings.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d819e10ed950076580183fa249b03a614aea223865a9cac1e4d5fd0cbd25843
3
+ size 46168
topics.json ADDED
The diff for this file is too large to render. See raw diff