Add BERTopic model

README.md

@@ -0,0 +1,75 @@
+
+---
+tags:
+- bertopic
+library_name: bertopic
+pipeline_tag: text-classification
+---
+
+# MARTINI_enrich_BERTopic_vakcmirt
+
+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_vakcmirt")
+
+topic_model.get_topic_info()
+```
+
+## Topic overview
+
+* Number of topics: 6
+* Number of training documents: 606
+
+<details>
+  <summary>Click here for an overview of all topics.</summary>
+  
+  | Topic ID | Topic Keywords | Topic Frequency | Label | 
+|----------|----------------|-----------------|-------| 
+| -1 | vakcinas - injekcija - gydytojai - eksperimento - mikrogramu | 56 | -1_vakcinas_injekcija_gydytojai_eksperimento | 
+| 0 | вакцинации - вакцину - сша - нет - во | 147 | 0_вакцинации_вакцину_сша_нет | 
+| 1 | niekada - pastoviai - sveiki - draugas - eurovizija | 121 | 1_niekada_pastoviai_sveiki_draugas | 
+| 2 | vaccinated - die - injection - never - suddenly | 109 | 2_vaccinated_die_injection_never | 
+| 3 | vakcinose - poliomielito - pandemija - imuniteto - injekciju | 101 | 3_vakcinose_poliomielito_pandemija_imuniteto | 
+| 4 | vakcinacijos - injekcijos - paskiepytieji - farmacijos - grafeno | 72 | 4_vakcinacijos_injekcijos_paskiepytieji_farmacijos |
+  
+</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:e50a6774a89ada16abaf3848e642a982781e7cd18b4704e444873eda029ef18c
+size 357848

topic_embeddings.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea4114ca0fa63b3c8626bee4dd213481c4138c15a3ebbfe7e2f6a083a78abd2a
+size 24664

topics.json

@@ -0,0 +1,795 @@
+{
+  "topic_representations": {
+    "-1": [
+      [
+        "vakcinas",
+        0.5073167085647583
+      ],
+      [
+        "injekcija",
+        0.48654115200042725
+      ],
+      [
+        "gydytojai",
+        0.4563862979412079
+      ],
+      [
+        "eksperimento",
+        0.44255128502845764
+      ],
+      [
+        "mikrogramu",
+        0.4375452995300293
+      ]
+    ],
+    "0": [
+      [
+        "\u0432\u0430\u043a\u0446\u0438\u043d\u0430\u0446\u0438\u0438",
+        0.6868530511856079
+      ],
+      [
+        "\u0432\u0430\u043a\u0446\u0438\u043d\u0443",
+        0.6501733064651489
+      ],
+      [
+        "\u0441\u0448\u0430",
+        0.5741957426071167
+      ],
+      [
+        "\u043d\u0435\u0442",
+        0.573713481426239
+      ],
+      [
+        "\u0432\u043e",
+        0.5571335554122925
+      ]
+    ],
+    "1": [
+      [
+        "niekada",
+        0.49963563680648804
+      ],
+      [
+        "pastoviai",
+        0.4927947521209717
+      ],
+      [
+        "sveiki",
+        0.4836500287055969
+      ],
+      [
+        "draugas",
+        0.4823875427246094
+      ],
+      [
+        "eurovizija",
+        0.4484245777130127
+      ]
+    ],
+    "2": [
+      [
+        "vaccinated",
+        0.5962885022163391
+      ],
+      [
+        "die",
+        0.46118801832199097
+      ],
+      [
+        "injection",
+        0.46107447147369385
+      ],
+      [
+        "never",
+        0.4474841058254242
+      ],
+      [
+        "suddenly",
+        0.43549448251724243
+      ]
+    ],
+    "3": [
+      [
+        "vakcinose",
+        0.5637559294700623
+      ],
+      [
+        "poliomielito",
+        0.5397729873657227
+      ],
+      [
+        "pandemija",
+        0.5365506410598755
+      ],
+      [
+        "imuniteto",
+        0.5088011026382446
+      ],
+      [
+        "injekciju",
+        0.46290263533592224
+      ]
+    ],
+    "4": [
+      [
+        "vakcinacijos",
+        0.503873348236084
+      ],
+      [
+        "injekcijos",
+        0.47828713059425354
+      ],
+      [
+        "paskiepytieji",
+        0.4271463453769684
+      ],
+      [
+        "farmacijos",
+        0.4252373278141022
+      ],
+      [
+        "grafeno",
+        0.40179160237312317
+      ]
+    ]
+  },
+  "topics": [
+    4,
+    4,
+    -1,
+    0,
+    4,
+    0,
+    0,
+    -1,
+    0,
+    0,
+    -1,
+    1,
+    0,
+    -1,
+    3,
+    -1,
+    2,
+    -1,
+    -1,
+    2,
+    -1,
+    2,
+    -1,
+    -1,
+    2,
+    1,
+    -1,
+    2,
+    -1,
+    -1,
+    2,
+    -1,
+    2,
+    -1,
+    -1,
+    2,
+    0,
+    2,
+    -1,
+    2,
+    1,
+    1,
+    2,
+    1,
+    4,
+    2,
+    3,
+    3,
+    3,
+    1,
+    -1,
+    2,
+    -1,
+    4,
+    3,
+    0,
+    2,
+    3,
+    2,
+    -1,
+    2,
+    -1,
+    0,
+    1,
+    0,
+    2,
+    3,
+    0,
+    3,
+    3,
+    -1,
+    -1,
+    1,
+    2,
+    2,
+    3,
+    2,
+    3,
+    -1,
+    -1,
+    2,
+    -1,
+    2,
+    -1,
+    -1,
+    2,
+    1,
+    2,
+    0,
+    0,
+    -1,
+    4,
+    2,
+    3,
+    2,
+    1,
+    1,
+    0,
+    -1,
+    4,
+    4,
+    2,
+    1,
+    4,
+    2,
+    0,
+    1,
+    1,
+    -1,
+    4,
+    3,
+    0,
+    1,
+    0,
+    2,
+    3,
+    3,
+    0,
+    1,
+    4,
+    3,
+    1,
+    0,
+    2,
+    2,
+    -1,
+    4,
+    2,
+    -1,
+    3,
+    0,
+    2,
+    2,
+    -1,
+    2,
+    2,
+    0,
+    0,
+    2,
+    0,
+    2,
+    0,
+    4,
+    0,
+    2,
+    2,
+    3,
+    -1,
+    0,
+    2,
+    3,
+    4,
+    0,
+    2,
+    -1,
+    2,
+    1,
+    -1,
+    2,
+    -1,
+    1,
+    1,
+    -1,
+    -1,
+    -1,
+    -1,
+    3,
+    3,
+    0,
+    4,
+    -1,
+    3,
+    1,
+    4,
+    1,
+    2,
+    3,
+    4,
+    1,
+    -1,
+    0,
+    -1,
+    3,
+    1,
+    4,
+    -1,
+    1,
+    -1,
+    -1,
+    0,
+    3,
+    4,
+    -1,
+    4,
+    2,
+    3,
+    3,
+    1,
+    1,
+    -1,
+    0,
+    -1,
+    -1,
+    3,
+    1,
+    1,
+    -1,
+    3,
+    -1,
+    2,
+    4,
+    3,
+    -1,
+    4,
+    -1,
+    1,
+    1,
+    -1,
+    4,
+    -1,
+    4,
+    1,
+    -1,
+    3,
+    4,
+    -1,
+    4,
+    -1,
+    -1,
+    4,
+    -1,
+    3,
+    3,
+    1,
+    -1,
+    1,
+    -1,
+    1,
+    4,
+    4,
+    2,
+    0,
+    1,
+    1,
+    3,
+    1,
+    1,
+    4,
+    1,
+    -1,
+    -1,
+    4,
+    0,
+    -1,
+    1,
+    0,
+    -1,
+    4,
+    -1,
+    3,
+    3,
+    -1,
+    0,
+    0,
+    1,
+    -1,
+    4,
+    1,
+    -1,
+    3,
+    4,
+    1,
+    0,
+    2,
+    1,
+    0,
+    -1,
+    2,
+    0,
+    0,
+    3,
+    1,
+    -1,
+    0,
+    1,
+    0,
+    2,
+    -1,
+    3,
+    0,
+    1,
+    2,
+    0,
+    4,
+    4,
+    2,
+    1,
+    1,
+    -1,
+    0,
+    -1,
+    4,
+    2,
+    0,
+    -1,
+    1,
+    3,
+    3,
+    4,
+    -1,
+    3,
+    3,
+    3,
+    0,
+    -1,
+    3,
+    0,
+    1,
+    0,
+    3,
+    1,
+    2,
+    3,
+    -1,
+    1,
+    0,
+    3,
+    0,
+    -1,
+    0,
+    -1,
+    3,
+    1,
+    4,
+    0,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    1,
+    1,
+    3,
+    0,
+    -1,
+    1,
+    2,
+    2,
+    3,
+    -1,
+    1,
+    0,
+    -1,
+    -1,
+    3,
+    0,
+    0,
+    0,
+    0,
+    0,
+    0,
+    0,
+    4,
+    0,
+    2,
+    4,
+    2,
+    -1,
+    3,
+    1,
+    0,
+    3,
+    2,
+    0,
+    1,
+    1,
+    0,
+    -1,
+    1,
+    1,
+    1,
+    1,
+    0,
+    0,
+    0,
+    -1,
+    1,
+    -1,
+    0,
+    -1,
+    0,
+    1,
+    0,
+    0,
+    4,
+    4,
+    1,
+    -1,
+    4,
+    0,
+    2,
+    -1,
+    4,
+    1,
+    0,
+    0,
+    0,
+    1,
+    -1,
+    3,
+    -1,
+    -1,
+    3,
+    2,
+    2,
+    3,
+    0,
+    -1,
+    0,
+    0,
+    1,
+    2,
+    -1,
+    0,
+    2,
+    2,
+    3,
+    2,
+    2,
+    -1,
+    0,
+    2,
+    2,
+    2,
+    0,
+    -1,
+    -1,
+    2,
+    1,
+    0,
+    -1,
+    2,
+    -1,
+    0,
+    2,
+    0,
+    -1,
+    2,
+    1,
+    4,
+    2,
+    1,
+    2,
+    2,
+    2,
+    0,
+    1,
+    0,
+    -1,
+    1,
+    0,
+    2,
+    3,
+    -1,
+    1,
+    -1,
+    -1,
+    1,
+    -1,
+    -1,
+    3,
+    0,
+    2,
+    2,
+    2,
+    4,
+    2,
+    2,
+    1,
+    -1,
+    1,
+    0,
+    -1,
+    1,
+    1,
+    -1,
+    0,
+    -1,
+    0,
+    0,
+    0,
+    1,
+    3,
+    -1,
+    -1,
+    1,
+    0,
+    -1,
+    1,
+    2,
+    1,
+    1,
+    1,
+    -1,
+    1,
+    2,
+    1,
+    4,
+    0,
+    -1,
+    1,
+    3,
+    0,
+    2,
+    1,
+    2,
+    1,
+    1,
+    -1,
+    3,
+    -1,
+    0,
+    0,
+    -1,
+    2,
+    0,
+    1,
+    1,
+    0,
+    0,
+    0,
+    0,
+    0,
+    0,
+    1,
+    -1,
+    0,
+    0,
+    -1,
+    0,
+    0,
+    2,
+    3,
+    3,
+    4,
+    0,
+    -1,
+    2,
+    3,
+    2,
+    0,
+    0,
+    0,
+    1,
+    3,
+    4,
+    -1,
+    2,
+    4,
+    -1,
+    3,
+    -1,
+    1,
+    1,
+    -1,
+    2,
+    3,
+    1,
+    1,
+    1,
+    0,
+    0,
+    0,
+    1,
+    1,
+    -1,
+    4,
+    -1,
+    4,
+    -1,
+    2,
+    -1,
+    -1,
+    0,
+    2,
+    0,
+    2,
+    1,
+    4,
+    4,
+    -1,
+    4,
+    -1,
+    0,
+    2,
+    2,
+    3,
+    1,
+    1,
+    3,
+    -1,
+    -1,
+    3,
+    -1,
+    2,
+    -1
+  ],
+  "topic_sizes": {
+    "4": 56,
+    "-1": 147,
+    "0": 121,
+    "1": 109,
+    "3": 72,
+    "2": 101
+  },
+  "topic_mapper": [
+    [
+      -1,
+      -1,
+      -1
+    ],
+    [
+      0,
+      0,
+      2
+    ],
+    [
+      1,
+      1,
+      0
+    ],
+    [
+      2,
+      2,
+      1
+    ],
+    [
+      3,
+      3,
+      3
+    ],
+    [
+      4,
+      4,
+      4
+    ]
+  ],
+  "topic_labels": {
+    "-1": "-1_vakcinas_injekcija_gydytojai_eksperimento",
+    "0": "0_\u0432\u0430\u043a\u0446\u0438\u043d\u0430\u0446\u0438\u0438_\u0432\u0430\u043a\u0446\u0438\u043d\u0443_\u0441\u0448\u0430_\u043d\u0435\u0442",
+    "1": "1_niekada_pastoviai_sveiki_draugas",
+    "2": "2_vaccinated_die_injection_never",
+    "3": "3_vakcinose_poliomielito_pandemija_imuniteto",
+    "4": "4_vakcinacijos_injekcijos_paskiepytieji_farmacijos"
+  },
+  "custom_labels": null,
+  "_outliers": 1,
+  "topic_aspects": {}
+}