tritopic 0.1.0__py3-none-any.whl → 1.0.0__py3-none-any.whl

{tritopic-0.1.0.dist-info → tritopic-1.0.0.dist-info}/METADATA

@@ -1,14 +1,16 @@
 Metadata-Version: 2.4
 Name: tritopic
-Version: 0.1.0
-Summary: Tri-Modal Graph Topic Modeling with Iterative Refinement - A state-of-the-art topic modeling library
-Author-email: Roman Egger <roman@example.com>
+Version: 1.0.0
+Summary: Tri-Modal Graph Topic Modeling with Iterative Refinement
+Author-email: Roman Egger <roman.egger@example.com>
 License: MIT
 Project-URL: Homepage, https://github.com/roman-egger/tritopic
 Project-URL: Documentation, https://tritopic.readthedocs.io
 Project-URL: Repository, https://github.com/roman-egger/tritopic
-Keywords: topic-modeling,nlp,machine-learning,graph-clustering,leiden,embeddings,text-analysis,bertopic-alternative
+Project-URL: Issues, https://github.com/roman-egger/tritopic/issues
+Keywords: topic-modeling,nlp,machine-learning,bertopic,clustering,text-analysis,multilingual
 Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
 Classifier: License :: OSI Approved :: MIT License
 Classifier: Programming Language :: Python :: 3
@@ -20,35 +22,42 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Classifier: Topic :: Text Processing :: Linguistic
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
-License-File: LICENSE
 Requires-Dist: numpy>=1.21.0
-Requires-Dist: pandas>=1.3.0
 Requires-Dist: scipy>=1.7.0
 Requires-Dist: scikit-learn>=1.0.0
+Requires-Dist: pandas>=1.3.0
 Requires-Dist: sentence-transformers>=2.2.0
 Requires-Dist: leidenalg>=0.9.0
-Requires-Dist: igraph>=0.10.0
-Requires-Dist: umap-learn>=0.5.0
-Requires-Dist: hdbscan>=0.8.0
-Requires-Dist: plotly>=5.0.0
+Requires-Dist: python-igraph>=0.10.0
 Requires-Dist: tqdm>=4.60.0
-Requires-Dist: rank-bm25>=0.2.0
-Requires-Dist: keybert>=0.7.0
 Provides-Extra: llm
 Requires-Dist: anthropic>=0.18.0; extra == "llm"
 Requires-Dist: openai>=1.0.0; extra == "llm"
-Provides-Extra: full
-Requires-Dist: anthropic>=0.18.0; extra == "full"
-Requires-Dist: openai>=1.0.0; extra == "full"
-Requires-Dist: pacmap>=0.6.0; extra == "full"
-Requires-Dist: datamapplot>=0.1.0; extra == "full"
+Provides-Extra: multilingual
+Requires-Dist: langdetect>=1.0.9; extra == "multilingual"
+Requires-Dist: jieba>=0.42.1; extra == "multilingual"
+Provides-Extra: japanese
+Requires-Dist: fugashi>=1.2.0; extra == "japanese"
+Requires-Dist: unidic-lite>=1.0.8; extra == "japanese"
+Provides-Extra: korean
+Requires-Dist: konlpy>=0.6.0; extra == "korean"
+Provides-Extra: thai
+Requires-Dist: pythainlp>=4.0.0; extra == "thai"
+Provides-Extra: visualization
+Requires-Dist: plotly>=5.0.0; extra == "visualization"
+Requires-Dist: matplotlib>=3.4.0; extra == "visualization"
+Requires-Dist: umap-learn>=0.5.0; extra == "visualization"
+Provides-Extra: evaluation
+Requires-Dist: gensim>=4.0.0; extra == "evaluation"
+Provides-Extra: all
+Requires-Dist: tritopic[evaluation,llm,multilingual,visualization]; extra == "all"
 Provides-Extra: dev
 Requires-Dist: pytest>=7.0.0; extra == "dev"
 Requires-Dist: pytest-cov>=4.0.0; extra == "dev"
 Requires-Dist: black>=23.0.0; extra == "dev"
 Requires-Dist: ruff>=0.1.0; extra == "dev"
 Requires-Dist: mypy>=1.0.0; extra == "dev"
-Dynamic: license-file
+Requires-Dist: sphinx>=6.0.0; extra == "dev"
 
 # 🔺 TriTopic
 
@@ -68,6 +77,8 @@ A state-of-the-art topic modeling library that consistently outperforms BERTopic
 | **Mutual kNN + SNN** | Eliminates noise bridges between unrelated documents |
 | **Leiden + Consensus** | Dramatically more stable than single-run clustering |
 | **Iterative Refinement** | Topics improve embeddings, embeddings improve topics |
+| **Multilingual Support** | 60+ languages with auto language detection |
+| **Archetype Representatives** | Rich document selection beyond simple centroids |
 | **LLM-Powered Labels** | Human-readable topic names via Claude or GPT-4 |
 
 ## 📦 Installation
@@ -79,8 +90,11 @@ pip install tritopic
 # With LLM labeling support
 pip install tritopic[llm]
 
+# With multilingual support
+pip install tritopic[multilingual]
+
 # Full installation (all features)
-pip install tritopic[full]
+pip install tritopic[all]
 ```
 
 ### From source (development)
@@ -171,6 +185,23 @@ model.generate_labels(labeler)
 print(model.get_topic_info())
 ```
 
+### Multilingual Support
+
+```python
+from tritopic import TriTopic
+
+# Auto-detect language and select appropriate model
+model = TriTopic(
+    language="auto",          # Auto-detect language
+    multilingual=False,       # Use language-specific model
+    verbose=True
+)
+
+# Works with Chinese, German, Japanese, etc.
+chinese_docs = ["机器学习正在改变医疗诊断", "深度神经网络取得超人类表现", ...]
+topics = model.fit_transform(chinese_docs)
+```
+
 ### With Metadata
 
 ```python
@@ -202,13 +233,18 @@ from tritopic import TriTopic, TriTopicConfig
 
 config = TriTopicConfig(
     # Embedding settings
-    embedding_model="all-MiniLM-L6-v2",  # or "BAAI/bge-base-en-v1.5"
+    embedding_model="all-MiniLM-L6-v2",  # or "auto", "BAAI/bge-base-en-v1.5"
     embedding_batch_size=32,
     
+    # Language settings
+    language="auto",           # or "en", "de", "zh", etc.
+    multilingual=False,        # Force multilingual model
+    language_detection_sample=100,
+    
     # Graph construction
     n_neighbors=15,
     metric="cosine",
-    graph_type="hybrid",  # "knn", "mutual_knn", "snn", "hybrid"
+    graph_type="hybrid",       # "knn", "mutual_knn", "snn", "hybrid"
     snn_weight=0.5,
     
     # Multi-view fusion weights
@@ -227,11 +263,17 @@ config = TriTopicConfig(
     use_iterative_refinement=True,
     max_iterations=5,
     convergence_threshold=0.95,
+    refinement_strength=0.15,
     
     # Keywords
     n_keywords=10,
+    keyword_method="ctfidf",   # "ctfidf", "bm25", "keybert"
+    
+    # Representatives (with archetype support)
     n_representative_docs=5,
-    keyword_method="ctfidf",  # "ctfidf", "bm25", "keybert"
+    representative_method="hybrid",  # "centroid", "medoid", "archetype", "diverse", "hybrid"
+    n_archetypes=4,
+    archetype_method="furthest_sum",
     
     # Misc
     outlier_threshold=0.1,
@@ -242,16 +284,25 @@ config = TriTopicConfig(
 model = TriTopic(config=config)
 ```
 
-### Quick Parameter Override
+### Pre-defined Configurations
 
 ```python
-# Override just what you need
-model = TriTopic(
-    embedding_model="BAAI/bge-base-en-v1.5",
-    n_neighbors=20,
-    use_iterative_refinement=True,
-    verbose=True,
-)
+from tritopic import TriTopic, get_config
+
+# Fast processing (less accurate)
+model = TriTopic(config=get_config("fast"))
+
+# High quality (slower)
+model = TriTopic(config=get_config("quality"))
+
+# Multilingual corpus
+model = TriTopic(config=get_config("multilingual"))
+
+# Chinese text
+model = TriTopic(config=get_config("chinese"))
+
+# German text
+model = TriTopic(config=get_config("german"))
 ```
 
 ## 📊 Evaluation
@@ -285,20 +336,6 @@ model = TriTopic()
 topics = model.fit_transform(documents, embeddings=embeddings)
 ```
 
-### Find Optimal Resolution
-
-```python
-from tritopic.core.clustering import ConsensusLeiden
-
-clusterer = ConsensusLeiden()
-optimal_res = clusterer.find_optimal_resolution(
-    graph=model.graph_,
-    resolution_range=(0.5, 2.0),
-    target_n_topics=15,  # Optional: target number
-)
-print(f"Optimal resolution: {optimal_res}")
-```
-
 ### Transform New Documents
 
 ```python
@@ -327,7 +364,8 @@ model = TriTopic.load("my_topic_model.pkl")
 | Views | Embeddings only | Semantic + Lexical + Metadata |
 | Refinement | None | Iterative embedding refinement |
 | Stability | Low (varies by run) | High (consensus clustering) |
-| Outlier Handling | HDBSCAN built-in | Configurable threshold |
+| Languages | Limited | 60+ with auto-detection |
+| Representatives | Centroid only | Archetypes, medoids, diverse |
 
 ### Benchmark Results
 
@@ -339,7 +377,7 @@ On 20 Newsgroups dataset (n=18,846):
 | Diversity | 0.834 | **0.891** | +7% |
 | Stability (ARI) | 0.721 | **0.934** | +30% |
 
-## 🏗️ Architecture
+## 🗂️ Architecture
 
 ```
 Documents
@@ -347,10 +385,10 @@ Documents
     ├─── Embedding Engine ──────────────┐
     │    (Sentence-BERT/BGE/Instructor) │
     │                                   │
-    ├─── Lexical Matrix ───────────────┼─── Multi-View
+    ├─── Lexical Matrix ────────────────┼─── Multi-View
     │    (TF-IDF/BM25)                  │    Graph Builder
     │                                   │         │
-    └─── Metadata Graph ───────────────┘         │
+    └─── Metadata Graph ────────────────┘         │
          (Optional)                              │
                                                  ▼
                                     ┌─────────────────────┐
@@ -369,6 +407,12 @@ Documents
                                     └──────────┬──────────┘
                                                │
                                     ┌──────────▼──────────┐
+                                    │  Representative      │
+                                    │  Selection           │
+                                    │  (Archetype/Hybrid)  │
+                                    └──────────┬──────────┘
+                                               │
+                                    ┌──────────▼──────────┐
                                     │   LLM Labeling       │
                                     │  (Claude/GPT-4)      │
                                     └─────────────────────┘

tritopic-1.0.0.dist-info/RECORD

@@ -0,0 +1,20 @@
+tritopic/__init__.py,sha256=BaHbardg5BW9zykYOtYG1ZM1nGwvfVt7DV7NJ7tp4l8,936
+tritopic/config.py,sha256=bsornL0etlRxQyMa6-Yx7tgXqVR1b8OZPpXM62cibhI,10120
+tritopic/labeling.py,sha256=SJsvOXRl-q8f3qtk1S66FGozTJsW8bwNnAKGkAklmVQ,8883
+tritopic/model.py,sha256=mzptfvqG_Q81OcS6kiYd7u2uU2AKjxpDYKo9u1EfpH4,25015
+tritopic/visualization.py,sha256=MCiIgIoTzFoQ7GG9WjfSZlV2j1BBGzZwxRddmvmh1OY,9841
+tritopic/core/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+tritopic/core/clustering.py,sha256=mZoU8SkfSLWjFbdJYcBfjIJ75uQJVH1guMPoVTZOmnM,9461
+tritopic/core/embeddings.py,sha256=ouqW9YQKSn8MtIt0DShhFB14QIhCnqryyz27Ilwg6sM,6707
+tritopic/core/graph.py,sha256=a949-6N9ZH8Jd7hFt6fDdB4K7r1A2qs16eZfYmJFKHM,13605
+tritopic/core/keywords.py,sha256=AnHY7QFGlGsSRfcsss6EpUIGD91ybo3MsWs5Ritb9cM,9667
+tritopic/core/refinement.py,sha256=7e6K-EuqZ4ttqNkhsvOeHlDC1ZjP9TA0_8mdyy5kTEw,7695
+tritopic/core/representatives.py,sha256=hqpnNMxhqyZxjM7CaGV5M1RxR3B358tMaGTKWn8jWOo,19154
+tritopic/multilingual/__init__.py,sha256=EagOqVqMDNKX7AfEAQfVgbR92f2vBy1KSM5O88AEt20,699
+tritopic/multilingual/detection.py,sha256=xeZqNp4l-fRII5s2S4EMzBdJPf3Xgt6e1a3Od2hc2q4,5700
+tritopic/multilingual/stopwords.py,sha256=viMM1pb4VpDEmDpGpx_8sDfumXfrVXKfUULyOZXFFYU,29942
+tritopic/multilingual/tokenizers.py,sha256=seTCzRiUOqO0UbAqA3nn8V8EoVYQ1wiwqcH8lafRCxM,9954
+tritopic-1.0.0.dist-info/METADATA,sha256=kwoHBkE7i3m59h5i5QA10IsfBpJ5_rqI1u_SKXHFjQU,14178
+tritopic-1.0.0.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
+tritopic-1.0.0.dist-info/top_level.txt,sha256=9PASbqQyi0-wa7E2Hl3Z0u1ae7MwLcfgFliFE1ioFBA,9
+tritopic-1.0.0.dist-info/RECORD,,