Edit model card

short-pubmed-bertopic

This is a BERTopic model. BERTopic is a flexible and modular topic modeling framework that allows for the generation of easily interpretable topics from large datasets.

Usage

To use this model, please install BERTopic:

pip install -U bertopic

You can use the model as follows:

from bertopic import BERTopic
topic_model = BERTopic.load("etanios/short-pubmed-bertopic")

topic_model.get_topic_info()

Topic overview

  • Number of topics: 32
  • Number of training documents: 9999
Click here for an overview of all topics.
Topic ID Topic Keywords Topic Frequency Label
-1 patients - activity - cells - acid - 10 53 Medical research studies
0 health - children - care - medical - patient 3897 Healthcare and Mental Health
1 renal - pressure - renin - blood - sodium 702 Renal physiology and hypertension
2 progesterone - pregnancy - lh - testosterone - fetal 516 Reproductive physiology and endocrinology
3 ventricular - coronary - left - patients - myocardial 404 Cardiac physiology and anatomy
4 method - gas - liquid - chromatography - urine 381 Analytical techniques for chemical analysis
5 morphine - mg kg - kg - brain - mg 296 Effects of drugs on rat behavior
6 cells - tumor - mice - cell - lymphocytes 281 Tumor immunology and lymphocyte activation
7 hip - patients - joint - rheumatoid - knee 278 Hip and Knee Fractures in Rheumatoid Arthritis Patients
8 cells - electron - cell - axons - synaptic 265 Neuroanatomy and Synaptic Structures
9 retinal - eyes - vitreous - eye - cases 237 Ocular Surgery
10 patients - ulcer - cases - disease - crohn 203 Gastrointestinal surgery and complications
11 strains - resistant - antibiotic - gentamicin - antibiotics 201 Antibiotic resistance in bacterial strains
12 enzyme - molecular - acid - activity - phosphate 201 Enzymology and Molecular Biology
13 iron - hemoglobin - hb - erythrocytes - deficiency 178 Iron Deficiency Anemia Research
14 infection - virus - infected - vaccinated - cattle 175 Virus infection and vaccination studies
15 platelet - platelets - aggregation - fibrinogen - coagulation 167 Platelet function and coagulation
16 cancer - carcinoma - patients - tumor - cases 158 Cancer treatment and survival rates
17 lung - volume - oxygen - flow - ventilation 152 Pulmonary Function and Exercise
18 calcium - thyroid - t3 - parathyroid - t4 151 Thyroid and Parathyroid Hormones
19 fatty - cholesterol - acid - liver - acids 144 Lipid metabolism in rats
20 diet - weight - egg - diets - fed 117 Poultry Nutrition and Physiology
21 stimulation - nerve - neurons - units - motor 111 Motor Neuron Discharge and Potentials
22 glucose - insulin - glucagon - levels - blood glucose 102 Insulin and glucose metabolism
23 hearing - ear - cochlear - auditory - noise 99 Hearing and Auditory Function
24 rna - dna - chromatin - proteins - polymerase 95
25 carotid - artery - intracranial - aneurysms - subdural 94 Carotid Artery Aneurysms and Intracranial Hemorrhage
26 bone - mineral - fluoride - enamel - mineralization 81 Bone and Mineral Metabolism
27 temperature - degrees - heat - temperatures - cold 75 Effects of Temperature on Human Physiology
28 bile - acid - biliary - cholesterol - bile acid 63 Biliary Lipid Metabolism
29 visual - light - receptive - sensitivity - dark 61 Visual processing and sensitivity
30 lung - pulmonary - chest - pleural - patients 61 Respiratory system diseases and disorders

Training hyperparameters

  • calculate_probabilities: False
  • language: None
  • low_memory: False
  • min_topic_size: 10
  • n_gram_range: (1, 1)
  • nr_topics: None
  • seed_topic_list: None
  • top_n_words: 10
  • verbose: True

Framework versions

  • Numpy: 1.23.5
  • HDBSCAN: 0.8.33
  • UMAP: 0.5.4
  • Pandas: 1.5.3
  • Scikit-Learn: 1.2.2
  • Sentence-transformers: 2.2.2
  • Transformers: 4.33.2
  • Numba: 0.56.4
  • Plotly: 5.15.0
  • Python: 3.10.12
Downloads last month
39
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.