Add BERTopic model

README.md

@@ -0,0 +1,74 @@
+
+---
+tags:
+- bertopic
+library_name: bertopic
+pipeline_tag: text-classification
+---
+
+# MARTINI_enrich_BERTopic_AwakenedOutlaw
+
+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("AIDA-UPM/MARTINI_enrich_BERTopic_AwakenedOutlaw")
+
+topic_model.get_topic_info()
+```
+
+## Topic overview
+
+* Number of topics: 5
+* Number of training documents: 475
+
+<details>
+  <summary>Click here for an overview of all topics.</summary>
+  
+  | Topic ID | Topic Keywords | Topic Frequency | Label | 
+|----------|----------------|-----------------|-------| 
+| -1 | obama - democrats - michelle - pedophile - everyone | 27 | -1_obama_democrats_michelle_pedophile | 
+| 0 | leftists - globalist - freedom - everything - damn | 239 | 0_leftists_globalist_freedom_everything | 
+| 1 | doj - pelosi - testifying - presidency - corrupt | 152 | 1_doj_pelosi_testifying_presidency | 
+| 2 | zelensky - globalist - boris - tucker - gonzalo | 29 | 2_zelensky_globalist_boris_tucker | 
+| 3 | desantis - vote - republican - dumb - opponents | 28 | 3_desantis_vote_republican_dumb |
+  
+</details>
+
+## Training hyperparameters
+
+* calculate_probabilities: True
+* 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
+* zeroshot_min_similarity: 0.7
+* zeroshot_topic_list: None
+
+## Framework versions
+
+* Numpy: 1.26.4
+* HDBSCAN: 0.8.40
+* UMAP: 0.5.7
+* Pandas: 2.2.3
+* Scikit-Learn: 1.5.2
+* Sentence-transformers: 3.3.1
+* Transformers: 4.46.3
+* Numba: 0.60.0
+* Plotly: 5.24.1
+* Python: 3.10.12

config.json

@@ -0,0 +1,16 @@
+{
+  "calculate_probabilities": true,
+  "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,
+  "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:c7a48a6f2f6d6eefa558dfef1f0c56091e3fb4899eefdaa7b5e42184894861a2
+size 131356

topic_embeddings.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbb49aafe02ec0de3d6e178e4c4c0b3df390d6faa6abf43abe07621e03bfdc25
+size 20568

topics.json

@@ -0,0 +1,635 @@
+{
+  "topic_representations": {
+    "-1": [
+      [
+        "obama",
+        0.5628839731216431
+      ],
+      [
+        "democrats",
+        0.508961021900177
+      ],
+      [
+        "michelle",
+        0.48871469497680664
+      ],
+      [
+        "pedophile",
+        0.4563555419445038
+      ],
+      [
+        "everyone",
+        0.4552122950553894
+      ]
+    ],
+    "0": [
+      [
+        "leftists",
+        0.5821783542633057
+      ],
+      [
+        "globalist",
+        0.5366305112838745
+      ],
+      [
+        "freedom",
+        0.5056643486022949
+      ],
+      [
+        "everything",
+        0.489115834236145
+      ],
+      [
+        "damn",
+        0.47751957178115845
+      ]
+    ],
+    "1": [
+      [
+        "doj",
+        0.5824503302574158
+      ],
+      [
+        "pelosi",
+        0.5214692950248718
+      ],
+      [
+        "testifying",
+        0.49994760751724243
+      ],
+      [
+        "presidency",
+        0.48891711235046387
+      ],
+      [
+        "corrupt",
+        0.4556235074996948
+      ]
+    ],
+    "2": [
+      [
+        "zelensky",
+        0.5839357376098633
+      ],
+      [
+        "globalist",
+        0.5244932174682617
+      ],
+      [
+        "boris",
+        0.5027751922607422
+      ],
+      [
+        "tucker",
+        0.48106610774993896
+      ],
+      [
+        "gonzalo",
+        0.4682276248931885
+      ]
+    ],
+    "3": [
+      [
+        "desantis",
+        0.5140770673751831
+      ],
+      [
+        "vote",
+        0.48935818672180176
+      ],
+      [
+        "republican",
+        0.48334789276123047
+      ],
+      [
+        "dumb",
+        0.4616287052631378
+      ],
+      [
+        "opponents",
+        0.4580000042915344
+      ]
+    ]
+  },
+  "topics": [
+    1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    0,
+    -1,
+    2,
+    3,
+    2,
+    -1,
+    2,
+    0,
+    0,
+    -1,
+    2,
+    -1,
+    0,
+    -1,
+    -1,
+    2,
+    0,
+    -1,
+    0,
+    0,
+    -1,
+    0,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    0,
+    0,
+    -1,
+    2,
+    2,
+    0,
+    2,
+    0,
+    -1,
+    0,
+    -1,
+    -1,
+    2,
+    -1,
+    -1,
+    -1,
+    3,
+    3,
+    3,
+    3,
+    -1,
+    3,
+    -1,
+    -1,
+    -1,
+    -1,
+    2,
+    1,
+    0,
+    0,
+    1,
+    2,
+    -1,
+    -1,
+    -1,
+    2,
+    0,
+    -1,
+    2,
+    -1,
+    1,
+    -1,
+    -1,
+    -1,
+    0,
+    -1,
+    -1,
+    -1,
+    2,
+    -1,
+    2,
+    -1,
+    0,
+    -1,
+    0,
+    0,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    3,
+    3,
+    0,
+    -1,
+    0,
+    0,
+    0,
+    -1,
+    -1,
+    0,
+    -1,
+    0,
+    -1,
+    2,
+    -1,
+    -1,
+    1,
+    3,
+    -1,
+    -1,
+    0,
+    -1,
+    -1,
+    -1,
+    0,
+    -1,
+    -1,
+    -1,
+    0,
+    0,
+    2,
+    0,
+    -1,
+    0,
+    2,
+    0,
+    1,
+    0,
+    -1,
+    -1,
+    0,
+    3,
+    -1,
+    -1,
+    3,
+    -1,
+    -1,
+    -1,
+    0,
+    1,
+    -1,
+    0,
+    -1,
+    0,
+    -1,
+    -1,
+    -1,
+    0,
+    -1,
+    -1,
+    0,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    3,
+    -1,
+    0,
+    0,
+    0,
+    3,
+    -1,
+    -1,
+    -1,
+    0,
+    -1,
+    -1,
+    -1,
+    3,
+    0,
+    0,
+    0,
+    0,
+    0,
+    -1,
+    -1,
+    0,
+    -1,
+    -1,
+    1,
+    -1,
+    0,
+    0,
+    -1,
+    -1,
+    -1,
+    2,
+    -1,
+    -1,
+    -1,
+    0,
+    -1,
+    0,
+    3,
+    0,
+    0,
+    0,
+    0,
+    0,
+    -1,
+    2,
+    2,
+    0,
+    -1,
+    -1,
+    3,
+    2,
+    0,
+    -1,
+    -1,
+    0,
+    1,
+    0,
+    -1,
+    2,
+    3,
+    3,
+    2,
+    -1,
+    -1,
+    0,
+    -1,
+    2,
+    -1,
+    -1,
+    -1,
+    0,
+    -1,
+    -1,
+    0,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    2,
+    -1,
+    1,
+    -1,
+    1,
+    0,
+    -1,
+    0,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    3,
+    -1,
+    0,
+    -1,
+    -1,
+    0,
+    -1,
+    0,
+    -1,
+    1,
+    -1,
+    0,
+    0,
+    0,
+    -1,
+    0,
+    -1,
+    -1,
+    -1,
+    0,
+    -1,
+    3,
+    0,
+    -1,
+    0,
+    -1,
+    0,
+    0,
+    -1,
+    0,
+    3,
+    -1,
+    0,
+    0,
+    3,
+    0,
+    0,
+    -1,
+    -1,
+    -1,
+    -1,
+    0,
+    -1,
+    0,
+    3,
+    -1,
+    -1,
+    0,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    0,
+    0,
+    -1,
+    -1,
+    -1,
+    -1,
+    0,
+    -1,
+    -1,
+    -1,
+    -1,
+    2,
+    1,
+    -1,
+    -1,
+    -1,
+    1,
+    -1,
+    -1,
+    0,
+    3,
+    -1,
+    0,
+    0,
+    0,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    1,
+    -1,
+    -1,
+    0,
+    0,
+    1,
+    -1,
+    0,
+    -1,
+    -1,
+    1,
+    0,
+    -1,
+    0,
+    0,
+    -1,
+    -1,
+    0,
+    1,
+    0,
+    0,
+    -1,
+    -1,
+    -1,
+    1,
+    1,
+    0,
+    0,
+    2,
+    -1,
+    3,
+    -1,
+    1,
+    -1,
+    -1,
+    0,
+    0,
+    0,
+    -1,
+    -1,
+    0,
+    -1,
+    -1,
+    -1,
+    0,
+    0,
+    0,
+    -1,
+    -1,
+    1,
+    1,
+    1,
+    -1,
+    0,
+    -1,
+    1,
+    -1,
+    -1,
+    -1,
+    0,
+    -1,
+    0,
+    -1,
+    -1,
+    0,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    0,
+    0,
+    -1,
+    0,
+    -1,
+    1,
+    -1,
+    -1,
+    0,
+    0,
+    0,
+    0,
+    -1,
+    0,
+    0,
+    0,
+    1,
+    0,
+    0,
+    3,
+    0,
+    0,
+    -1,
+    0,
+    -1,
+    -1,
+    -1,
+    0,
+    1,
+    0,
+    0,
+    0,
+    0,
+    0,
+    -1,
+    -1,
+    3,
+    0,
+    0,
+    0,
+    0,
+    1,
+    -1,
+    -1,
+    0,
+    0,
+    -1,
+    0,
+    0,
+    0,
+    -1,
+    0,
+    -1,
+    -1,
+    -1,
+    0,
+    0,
+    0,
+    -1,
+    -1,
+    -1,
+    -1,
+    0
+  ],
+  "topic_sizes": {
+    "1": 29,
+    "-1": 239,
+    "0": 152,
+    "2": 28,
+    "3": 27
+  },
+  "topic_mapper": [
+    [
+      -1,
+      -1,
+      -1
+    ],
+    [
+      0,
+      0,
+      2
+    ],
+    [
+      1,
+      1,
+      0
+    ],
+    [
+      2,
+      2,
+      1
+    ],
+    [
+      3,
+      3,
+      3
+    ]
+  ],
+  "topic_labels": {
+    "-1": "-1_obama_democrats_michelle_pedophile",
+    "0": "0_leftists_globalist_freedom_everything",
+    "1": "1_doj_pelosi_testifying_presidency",
+    "2": "2_zelensky_globalist_boris_tucker",
+    "3": "3_desantis_vote_republican_dumb"
+  },
+  "custom_labels": null,
+  "_outliers": 1,
+  "topic_aspects": {}
+}