Merge pull request #120 from AnFreTh/main

version 0.3.0

Author: AnFreTh

.gitignore

@@ -25,7 +25,8 @@ share/python-wheels/
 .installed.cfg
 *.egg
 MANIFEST
-
+lightning_logs/
+stream_topic_data/
 # PyInstaller
 #  Usually these files are written by a python script from a template
 #  before PyInstaller builds the exe, so as to inject date/other infos into it.
@@ -77,7 +78,7 @@ target/
 
 # Jupyter Notebook
 .ipynb_checkpoints
-
+.ipynb
 # IPython
 profile_default/
 ipython_config.py
@@ -166,7 +167,8 @@ docs/_build/*
 examples/lightning_logs/
 *.ckpt
 # *.yaml
-
+STREAM/lightning_logs/
+/STREAM/lightning_logs/
 # Additional files and directories to ignore
 __pycache__/
 *.pyc
@@ -190,4 +192,26 @@ docs/notebooks/data/*
 docs/notebooks/embeddings
 docs/notebooks/embeddings/*
 docs/notebooks/checkpoints
-docs/notebooks/checkpoints/*
+docs/notebooks/checkpoints/*
+embeddings
+embeddings/*
+.ipynb_checkpoints/
+.ipynb_checkpoints/*
+stream_topic.egg-info/
+stream_topic.egg-info/*
+stream_topic/stream_topic_data/*
+checkpoints/
+lightning_logs/
+test1.py
+exp_lda.py
+exp_nmf.py
+Chinese_test.ipynb
+get_metric.ipynb
+metrics.ipynb
+NPMI_PMI.ipynb
+run_parallel.ipynb
+Untitled.ipynb
+run_exp.ipynb
+Untitled1.ipynb
+run_exp2.ipynb
+result/

README.md

@@ -42,6 +42,7 @@
   - [🔍 Hyperparameter optimization](#-hyperparameter-optimization)
   - [🖼️ Visualization](#️-visualization)
   - [📈 Downstream Tasks](#-downstream-tasks)
+  - [🧪 Experimental 🧪](#-experimental-)
   - [🤝 Contributing and Testing New Models](#-contributing-and-testing-new-models)
 - [📜 Citation](#-citation)
 - [📝 License](#-license)
@@ -126,6 +127,11 @@ You can install STREAM directly from PyPI or from the GitHub repository:
     pip install stream-topic[dcte]
     ```
 
+    For the experimental features:
+    ```bash
+    pip install stream-topic[experimental]
+    ```
+
 # 📦 Available Models
 STREAM offers a variety of neural as well as non-neural topic models and we are always trying to incorporate more and new models. If you wish to incorporate your own model, or want another model incorporated please raise an issue with the required information. Currently, the following models are implemented:
 
@@ -482,7 +488,46 @@ from stream_topic.visuals import plot_downstream_model
 plot_downstream_model(downstream_model)
 ```
 
+# 🧪 Experimental 🧪
+stream-topic.experimental includes several experimental topic representations as well as new stuff we want to try out.
+
+This includes, e.g. topic summarization:
+
+```python
+from stream_topic.experimental import stopic_summaries
+
+summaries = topic_summaries(topics, openai_key)
+for summary in summaries:
+    print(f"{summary} \n")
+
+```
+
+But also the possibility to generate a story from the created topics:
+
+```python
+from stream_topic.experimental import story_topic
+
+story = story_topic(topics[1], openai_key)
+print(story)
+
+```
+
+Lastly, it offers the possibility to visualize your topic in a way, a movie poster could be designed:
+
+```python
+from stream_topic.experimental import movie_poster
+
+topic = ["tiger", "lion", "cougar", "cat", "hippo", "chair", "apple", "meat", "poachers", "hyeena"]
+
+movie_poster(topic, openai_key, return_style="plot")
+
+```
+This is just one of many possible visualization, but we found that to be rather coherent in terms of truly visualizing the created topics.
+Feel free to contribute or rais issues fo further experimental ideas.
 
+<p align="center">
+    <img src="assets/movie_poster_topic1.png" alt="Figure Description" width="600"/>
+</p>
 
 ## 🤝 Contributing and Testing New Models