Add BERTopic model

README.md

@@ -0,0 +1,68 @@
+
+---
+tags:
+- bertopic
+library_name: bertopic
+pipeline_tag: text-classification
+---
+
+# saxa3-capstone
+
+This is a [BERTopic](https://github.com/MaartenGr/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:
+
+```
+pip install -U bertopic
+```
+
+You can use the model as follows:
+
+```python
+from bertopic import BERTopic
+topic_model = BERTopic.load("magica1/saxa3-capstone")
+
+topic_model.get_topic_info()
+```
+
+## Topic overview
+
+* Number of topics: 1
+* Number of training documents: 196
+
+<details>
+  <summary>Click here for an overview of all topics.</summary>
+  
+  | Topic ID | Topic Keywords | Topic Frequency | Label | 
+|----------|----------------|-----------------|-------| 
+| -1 | medical - advisory - outreach - health - employment | 196 | -1_medical_advisory_outreach_health |
+  
+</details>
+
+## Training hyperparameters
+
+* calculate_probabilities: False
+* language: None
+* low_memory: False
+* min_topic_size: 10
+* n_gram_range: (1, 1)
+* nr_topics: None
+* seed_topic_list: None
+* top_n_words: 10
+* verbose: False
+
+## Framework versions
+
+* Numpy: 1.23.5
+* HDBSCAN: 0.8.33
+* UMAP: 0.5.4
+* Pandas: 2.1.2
+* Scikit-Learn: 1.2.2
+* Sentence-transformers: 2.2.2
+* Transformers: 4.35.0
+* Numba: 0.56.4
+* Plotly: 5.15.0
+* Python: 3.10.12

config.json

@@ -0,0 +1,14 @@
+{
+  "calculate_probabilities": false,
+  "language": null,
+  "low_memory": false,
+  "min_topic_size": 10,
+  "n_gram_range": [
+    1,
+    1
+  ],
+  "nr_topics": null,
+  "seed_topic_list": null,
+  "top_n_words": 10,
+  "verbose": false
+}

topic_embeddings.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8d97a65d10a07eda38703db03edb0bf5fde5781b525a745c9eb914046c356d9
+size 3160

topics.json

@@ -0,0 +1,260 @@
+{
+  "topic_representations": {
+    "-1": [
+      [
+        "medical",
+        0.3849537968635559
+      ],
+      [
+        "advisory",
+        0.33897143602371216
+      ],
+      [
+        "outreach",
+        0.3324600160121918
+      ],
+      [
+        "health",
+        0.32809799909591675
+      ],
+      [
+        "employment",
+        0.32660070061683655
+      ],
+      [
+        "military",
+        0.32183846831321716
+      ],
+      [
+        "trauma",
+        0.3200075030326843
+      ],
+      [
+        "assessment",
+        0.31925612688064575
+      ],
+      [
+        "effectiveness",
+        0.31517350673675537
+      ],
+      [
+        "support",
+        0.30763348937034607
+      ]
+    ]
+  },
+  "topics": [
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1
+  ],
+  "topic_sizes": {
+    "-1": 196
+  },
+  "topic_mapper": [
+    [
+      -1,
+      -1,
+      -1
+    ]
+  ],
+  "topic_labels": {
+    "-1": "-1_medical_advisory_outreach_health"
+  },
+  "custom_labels": null,
+  "_outliers": 1,
+  "topic_aspects": {}
+}