Add BERTopic.

2025-08-12 19:01:20 +08:00
parent e2323d579c
commit c5c530775e
256 changed files with 28666 additions and 0 deletions
@@ -0,0 +1,129 @@
+site_name: BERTopic
+repo_url: https://github.com/MaartenGr/BERTopic
+site_url: https://maartengr.github.io/BERTopic/
+site_description: Leveraging BERT and a class-based TF-IDF to create easily interpretable topics.
+site_author: Maarten P. Grootendorst
+use_directory_urls: false
+extra_css:
+  - stylesheets/extra.css
+
+nav:
+  - Home: index.md
+  - The Algorithm: algorithm/algorithm.md
+  - Getting Started:
+      - Quick Start: getting_started/quickstart/quickstart.md
+      - Serialization: getting_started/serialization/serialization.md
+      - Search Topics: getting_started/search/search.md
+      - Best Practices: getting_started/best_practices/best_practices.md
+      - In-depth:
+        - Visualizations:
+          - Topics:  getting_started/visualization/visualize_topics.md
+          - Documents:  getting_started/visualization/visualize_documents.md
+          - Terms:  getting_started/visualization/visualize_terms.md
+          - Hierarchy:  getting_started/visualization/visualize_hierarchy.md
+        - Update Topics:
+          - Topic Reduction: getting_started/topicreduction/topicreduction.md
+          - Update Topic Representations: getting_started/topicrepresentation/topicrepresentation.md
+          - Outlier reduction: getting_started/outlier_reduction/outlier_reduction.md
+        - Parameter tuning: getting_started/parameter tuning/parametertuning.md
+        - Tips & Tricks: getting_started/tips_and_tricks/tips_and_tricks.md
+      - Sub-models:
+        - 1. Embeddings: getting_started/embeddings/embeddings.md
+        - 2. Dimensionality Reduction: getting_started/dim_reduction/dim_reduction.md
+        - 3. Clustering: getting_started/clustering/clustering.md
+        - 4. Vectorizers: getting_started/vectorizers/vectorizers.md
+        - 5. c-TF-IDF: getting_started/ctfidf/ctfidf.md
+        - 6. Fine-tune Topics:
+          - 6A. Representation Models: getting_started/representation/representation.md
+          - 6B. LLM & Generative AI: getting_started/representation/llm.md
+          - 6C. Multiple Representations: getting_started/multiaspect/multiaspect.md
+      - Variations:
+        - Dynamic Topic Modeling: getting_started/topicsovertime/topicsovertime.md
+        - Hierarchical Topic Modeling: getting_started/hierarchicaltopics/hierarchicaltopics.md
+        - Multimodal Topic Modeling: getting_started/multimodal/multimodal.md
+        - Online Topic Modeling: getting_started/online/online.md
+        - Merge Multiple Models: getting_started/merge/merge.md
+        - (semi)-supervised:
+          - Semi-supervised Topic Modeling: getting_started/semisupervised/semisupervised.md
+          - Supervised Topic Modeling: getting_started/supervised/supervised.md
+          - Manual Topic Modeling: getting_started/manual/manual.md
+          - Guided Topic Modeling: getting_started/guided/guided.md
+          - Zero-shot Topic Modeling: getting_started/zeroshot/zeroshot.md
+        - Topic Distributions: getting_started/distribution/distribution.md
+        - Topics per Class: getting_started/topicsperclass/topicsperclass.md
+        - Seed Words: getting_started/seed_words/seed_words.md
+  - FAQ: faq.md
+  - Use Cases: usecases.md
+  - API:
+      - BERTopic: api/bertopic.md
+      - Sub-models:
+        - 1. Backends: api/backends.md
+        - 2. Dimensionality Reduction: api/dimensionality.md
+        - 3. Clustering: api/cluster.md
+        - 4. Vectorizers: api/vectorizers.md
+        - 5. c-TF-IDF: api/ctfidf.md
+        - 6. Fine-Tune Topic Representation: api/representations.md
+      - Plotting:
+        - Barchart: api/plotting/barchart.md
+        - Documents: api/plotting/documents.md
+        - Documents with DataMapPlot: api/plotting/document_datamap.md
+        - DTM: api/plotting/dtm.md
+        - Hierarchical documents: api/plotting/hierarchical_documents.md
+        - Hierarchical topics: api/plotting/hierarchy.md
+        - Distribution: api/plotting/distribution.md
+        - Heatmap: api/plotting/heatmap.md
+        - Term Scores: api/plotting/term.md
+        - Topics: api/plotting/topics.md
+        - Topics per Class: api/plotting/topics_per_class.md
+  - Changelog: changelog.md
+
+plugins:
+  - mkdocstrings:
+      watch:
+        - bertopic
+  - search
+copyright: Copyright &copy; 2024 Maintained by <a href="https://github.com/MaartenGr">Maarten Grootendorst</a>.
+
+theme:
+  custom_dir: images/
+  name: material
+  icon:
+    logo: material/library
+  font:
+    text: Ubuntu
+    code: Ubuntu Mono
+  favicon: icon.png
+  logo: img/icon.png
+  feature:
+    tabs: true
+  features:
+    - navigation.tabs
+    - navigation.sections
+    - navigation.instant
+    - navigation.top
+    - navigation.tracking
+    - toc.follow
+    - content.code.copy
+  palette:
+  - media: "(prefers-color-scheme: light)"
+    primary: custom
+    scheme: black
+    toggle:
+      icon: material/weather-sunny
+      name: Switch to dark mode
+  - media: "(prefers-color-scheme: dark)"
+    scheme: slate
+    primary: black
+    toggle:
+      icon: material/weather-night
+      name: Switch to light mode
+
+markdown_extensions:
+  - admonition
+  - md_in_html
+  - pymdownx.details
+  - pymdownx.highlight
+  - pymdownx.superfences
+  - pymdownx.snippets
+  - toc:
+      permalink: true