bertopic_tces_v2

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("lgdias/bertopic_tces_v2")

topic_model.get_topic_info()

Topic overview

• Number of topics: 10
• Number of training documents: 3765

Click here for an overview of all topics.

Topic ID	Topic Keywords	Topic Frequency	Label
-1	cerrado - pro - 2024 - despacho - fundacao	117	-1_cerrado_pro_2024_despacho
0	art - estado - administracao - social - lei	6	0_art_estado_administracao_social
1	notificacao - prestacao - ses - contas - 928	1001	1_notificacao_prestacao_ses_contas
2	go - preco - precos - empresa - licitacao	525	2_go_preco_precos_empresa
3	estado - contas - art - comissao - portaria	473	3_estado_contas_art_comissao
4	execucao - gestor - contrato - contratado - policia	741	4_execucao_gestor_contrato_contratado
5	ses - cptce - go - contas - saude	241	5_ses_cptce_go_contas
6	debito - contas - tomada - especial - atualizado	256	6_debito_contas_tomada_especial
7	contas - estado - saude - despacho - portaria	210	7_contas_estado_saude_despacho
8	estado - goias - contas - art - trabalhos	195	8_estado_goias_contas_art

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
• zeroshot_min_similarity: 0.7
• zeroshot_topic_list: None

Framework versions

• Numpy: 2.2.6
• HDBSCAN: 0.8.39
• UMAP: 0.5.9.post2
• Pandas: 2.3.3
• Scikit-Learn: 1.7.2
• Sentence-transformers: 5.1.1
• Transformers: 4.57.0
• Numba: 0.61.2
• Plotly: 6.3.1
• Python: 3.10.18