Merge pull request #94 from AnFreTh/nstm

Nstm

Author: AnFreTh

README.md

@@ -1,5 +1,8 @@
 <div align="center">
-  <img src="./docs/images/logos/STREAM_2.jpg" width="400"/>
+  <a href="#get-started">
+    <img src="./assets/stream-topic-gif.gif" width="800"/>
+  </a>
+
 
 
 [![PyPI](https://img.shields.io/pypi/v/stream_topic)](https://pypi.org/project/stream_topic)
@@ -24,14 +27,6 @@
 <p>We present STREAM, a Simplified Topic Retrieval, Exploration, and Analysis Module for User-Friendly and Interactive Topic Modeling and Visualization. Our paper can be found <a href="https://aclanthology.org/2024.acl-short.41.pdf">here</a>.</p>
 
 
-
-<table>
-  <tr>
-    <td><img src="./docs/images/gif1.gif" alt="First GIF" width="400"/></td>
-    <td><img src="./docs/images/gif2.gif" alt="Second GIF" width="400"/></td>
-  </tr>
-</table>
-
 <h2> Table of Contents </h2>
 
 
@@ -164,6 +159,10 @@ STREAM offers a variety of neural as well as non-neural topic models and we are
         <td><a href="https://arxiv.org/abs/1703.01488">NeuralLDA</a></td>
         <td>Autoencoding Variational Inference For Topic Models</td>
       </tr>
+      <tr>
+        <td><a href="https://arxiv.org/abs/2008.13537">NSTM</a></td>
+        <td>Neural Topic Model via Optimal Transport</td>
+      </tr>
     </tbody>
   </table>
 </div>

assets/stream-topic-gif.gif

@@ -44,3 +44,6 @@ Models
 
 .. autoclass:: stream_topic.models.CBC
     :members:
+
+.. autoclass:: stream_topic.models.NSTM
+    :members:

docs/api/models/models.rst

@@ -62,7 +62,6 @@
     "plotly",
     "matplotlib",
     "gensim",
-    "octis",
     "nltk",
     "langdetect",
     "loguru",

docs/conf.py

@@ -273,9 +273,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "db",
+   "display_name": "Python (stream_topic_venv)",
    "language": "python",
-   "name": "python3"
+   "name": "stream_topic_venv"
   },
   "language_info": {
    "codemirror_mode": {

docs/images/logos/gif1.gif

@@ -269,9 +269,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "db",
+   "display_name": "Python (stream_topic_venv)",
    "language": "python",
-   "name": "python3"
+   "name": "stream_topic_venv"
   },
   "language_info": {
    "codemirror_mode": {

docs/images/logos/gif2.gif

@@ -13,7 +13,6 @@ torch==2.4.0
 transformers==4.40.2
 setfit==1.0.3
 gensim==4.2.0
-octis==1.13.1
 umap-learn==0.5.6
 wordcloud==1.9.3
 

docs/notebooks/examples.ipynb

@@ -323,6 +323,9 @@ def __init__(
             columns=["text", "tokens"], errors="ignore"
         )
 
+        if "predictions" in self.structured_data.columns:
+            self.structured_data = self.structured_data.drop(columns=["predictions"])
+
         self.target_column = target_column
 
         # Combine topic probabilities with structured data
@@ -520,7 +523,6 @@ def forward(self, x):
 
     def training_step(self, batch, batch_idx):
         x, y = batch
-        print(y)
         y_hat = self(x)
         loss = self.loss_fn(y_hat, y)