Jerado's picture
Add BERTopic model
54efcc6 verified
metadata
tags:
  - bertopic
library_name: bertopic
pipeline_tag: text-classification

BERTopic-2024-05-02-165545

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("Jerado/BERTopic-2024-05-02-165545")

topic_model.get_topic_info()

Topic overview

  • Number of topics: 17
  • Number of training documents: 1000
Click here for an overview of all topics.
Topic ID Topic Keywords Topic Frequency Label
-1 theism - much - way - think - just 15 -1_theism_much_way_think
0 nhl - playoffs - rangers - hockey - league 304 0_nhl_playoffs_rangers_hockey
1 performance - ram - drivers - monitor - speed 92 1_performance_ram_drivers_monitor
2 x11r5 - hyperhelp - windows - pc - application 82 2_x11r5_hyperhelp_windows_pc
3 dos - windows - harddisk - disk - software 82 3_dos_windows_harddisk_disk
4 amp - amps - amplifier - ampere - current 75 4_amp_amps_amplifier_ampere
5 scripture - christians - sin - bible - commandment 44 5_scripture_christians_sin_bible
6 patients - biological - medicine - studies - doctors 41 6_patients_biological_medicine_studies
7 nasa - solar - space - shuttle - orbiting 39 7_nasa_solar_space_shuttle
8 armenians - armenian - armenia - turks - genocide 38 8_armenians_armenian_armenia_turks
9 guns - gun - amendment - constitution - laws 36 9_guns_gun_amendment_constitution
10 - - - - 33 10____
11 motorcycle - bikes - cobralinks - bike - riding 32 11_motorcycle_bikes_cobralinks_bike
12 encryption - security - encrypted - privacy - secure 24 12_encryption_security_encrypted_privacy
13 contacted - address - mail - contact - email 23 13_contacted_address_mail_contact
14 paganism - faith - christianity - christians - atheists 21 14_paganism_faith_christianity_christians
15 action - fbi - batf - war - president 19 15_action_fbi_batf_war

Training hyperparameters

  • calculate_probabilities: False
  • language: english
  • low_memory: False
  • min_topic_size: 10
  • n_gram_range: (1, 1)
  • nr_topics: None
  • seed_topic_list: [['drug', 'cancer', 'drugs', 'doctor'], ['windows', 'drive', 'dos', 'file'], ['space', 'launch', 'orbit', 'lunar']]
  • top_n_words: 10
  • verbose: False
  • zeroshot_min_similarity: 0.7
  • zeroshot_topic_list: None

Framework versions

  • Numpy: 1.23.5
  • HDBSCAN: 0.8.33
  • UMAP: 0.5.6
  • Pandas: 2.0.3
  • Scikit-Learn: 1.2.2
  • Sentence-transformers: 2.7.0
  • Transformers: 4.40.1
  • Numba: 0.58.1
  • Plotly: 5.15.0
  • Python: 3.10.12