clinical_text_classification

clinical_text_classification

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: <img src="data:image/png;base64,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"> I am revising a Google Colab Notebook to work with this model and will release it here when finished.

pip install -U bertopic

You can use the model as follows:

from bertopic import BERTopic
topic_model = BERTopic.load("janduplessis886/clinical_text_classification")

topic_model.get_topic_info()

Topic overview

• Number of topics: 300
• Number of training documents: 14442

<details> <summary>Click here for an overview of all topics.</summary> </details>

Training hyperparameters

• calculate_probabilities: False
• language: english
• low_memory: False
• min_topic_size: 10
• n_gram_range: (1, 1)
• nr_topics: 300
• seed_topic_list: None
• top_n_words: 10
• verbose: True
• zeroshot_min_similarity: 0.7
• zeroshot_topic_list: None

Framework versions

• Numpy: 1.23.5
• HDBSCAN: 0.8.33
• UMAP: 0.5.5
• Pandas: 1.5.3
• Scikit-Learn: 1.2.2
• Sentence-transformers: 2.2.2
• Transformers: 4.35.2
• Numba: 0.58.1
• Plotly: 5.15.0
• Python: 3.10.12