Add BERTopic model

README.md

@@ -0,0 +1,87 @@
+
+---
+tags:
+- bertopic
+library_name: bertopic
+pipeline_tag: text-classification
+---
+
+# tweets_deforestation_withoutRT_pt
+
+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("thiagoquilice/tweets_deforestation_withoutRT_pt")
+
+topic_model.get_topic_info()
+```
+
+## Topic overview
+
+* Number of topics: 18
+* Number of training documents: 21239
+
+<details>
+  <summary>Click here for an overview of all topics.</summary>
+  
+  | Topic ID | Topic Keywords | Topic Frequency | Label | 
+|----------|----------------|-----------------|-------| 
+| -1 | brazil - the - amazon - soy - to | 152 | Deforestation in Brazil's Cerrado due to Soy Production | 
+| 0 | the - deforestation - to - in - amazon | 2949 | Deforestation in the Amazon | 
+| 1 | soy - the - to - cerrado - and | 5520 | Deforestation and Soy Imports | 
+| 2 | in - best - partners - hesitate - raze | 3354 | Deforestation of Indigenous Lands | 
+| 3 | destruction - billions - fires - funds - with | 2337 | Deforestation in Brazil | 
+| 4 | moratorium - soy - amazon - on - the | 1451 | Brazil's Soy Moratorium | 
+| 5 | scandal - bragging - disappearance - anti - while | 1443 | Environmental scandal: BNP and deforestation | 
+| 6 | hey - hypocrisy - talk - leader - you | 692 | Corporate hypocrisy in zero deforestation policies | 
+| 7 | disappearance - scandal - bragging - anti - while | 562 | Deforestation scandal involving BNP | 
+| 8 | fund - destruction - billions - fires - with | 512 | Deforestation in Brazil's Amazon and Cerrado regions | 
+| 9 | partner - bnpparibas - number - burning - world | 460 | Deforestation partnership with BNPP | 
+| 10 | palm - oil - sights - sets - danger | 380 | Threats to the Amazon rainforest: Palm oil expansion in Brazil | 
+| 11 | caso - yo - my - soy - me | 367 | Twitter memes using "yo soy" phrase | 
+| 12 | peasant - economy - amazonian - of - deforestation | 341 | Amazonian Peasant Economy and Deforestation | 
+| 13 | dramatically - reduced - moratorium - brazil - soy | 201 | Brazil's Soy Moratorium and Deforestation Reduction | 
+| 14 | faster - burns - destroyed - another - part | 179 | Deforestation in Brazil | 
+| 15 | partner - bofa - bankofamerica - number - burning | 172 | Deforestation partnerships with Bank of America | 
+| 16 | indigenouslivesmatter - indigenouspeoplematter - humanrights - amazoniasinextraccion - stopamazonextraction | 167 | Indigenous rights and environmental protection in the Amazon |
+  
+</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: True
+* zeroshot_min_similarity: 0.7
+* zeroshot_topic_list: None
+
+## Framework versions
+
+* Numpy: 1.25.2
+* HDBSCAN: 0.8.33
+* UMAP: 0.5.6
+* Pandas: 2.0.3
+* Scikit-Learn: 1.2.2
+* Sentence-transformers: 2.7.0
+* Transformers: 4.40.2
+* Numba: 0.58.1
+* Plotly: 5.15.0
+* Python: 3.10.12

config.json

@@ -0,0 +1,16 @@
+{
+  "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": true,
+  "zeroshot_min_similarity": 0.7,
+  "zeroshot_topic_list": null
+}

ctfidf.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e1e2b6d0e94992b63e0b0cda9c0d26c24e622b6dc612230bd8398e99d9cfb45
+size 403376

topic_embeddings.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:344c5e5093d863e9e4b9ef251e6b30769b8284570e97b7e6299b5bb98ab1d960
+size 55384