Add BERTopic model

README.md

@@ -0,0 +1,78 @@
+
+---
+tags:
+- bertopic
+library_name: bertopic
+pipeline_tag: text-classification
+---
+
+# BERTopic_TheWellnessCompany
+
+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("sdantonio/BERTopic_TheWellnessCompany")
+
+topic_model.get_topic_info()
+```
+
+## Topic overview
+
+* Number of topics: 9
+* Number of training documents: 481
+
+<details>
+  <summary>Click here for an overview of all topics.</summary>
+  
+  | Topic ID | Topic Keywords | Topic Frequency | Label | 
+|----------|----------------|-----------------|-------| 
+| -1 | thewellnesscompany - shots - reprisal - serves - coulson | 12 | -1_thewellnesscompany_shots_reprisal_serves | 
+| 0 | thewellnesscompany - gessling - compelling - prolonged - daily_clout | 41 | 0_thewellnesscompany_gessling_compelling_prolonged | 
+| 1 | cardiologists - thewellnesscompany - myocarditis - epidemiologist - publications | 138 | 1_cardiologists_thewellnesscompany_myocarditis_epidemiologist | 
+| 2 | myocarditis - thewellnesscompany - prolonged - shots - reprisal | 96 | 2_myocarditis_thewellnesscompany_prolonged_shots | 
+| 3 | thewellnesscompany - packed - prolonged - dissolved - pomegranate | 80 | 3_thewellnesscompany_packed_prolonged_dissolved | 
+| 4 | thewellnesscompany - tedros - insights - marik - toxicity | 52 | 4_thewellnesscompany_tedros_insights_marik | 
+| 5 | ivermectin - thewellnesscompany - epidemiologist - hydroxychloroquine - misbehavior | 21 | 5_ivermectin_thewellnesscompany_epidemiologist_hydroxychloroquine | 
+| 6 | thewellnesscompany - hearts - concerns - reprisal - shots | 21 | 6_thewellnesscompany_hearts_concerns_reprisal | 
+| 7 | backtobasicsconference - unprepared - pregnancytalk - twcadventures - may9th | 20 | 7_backtobasicsconference_unprepared_pregnancytalk_twcadventures |
+  
+</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
+* zeroshot_min_similarity: 0.7
+* zeroshot_topic_list: None
+
+## Framework versions
+
+* Numpy: 1.23.5
+* HDBSCAN: 0.8.38.post1
+* UMAP: 0.5.6
+* Pandas: 2.2.2
+* Scikit-Learn: 1.5.1
+* Sentence-transformers: 3.0.1
+* Transformers: 4.44.2
+* Numba: 0.60.0
+* Plotly: 5.24.0
+* 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": 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 sha256:291df0ab8abc304e689eced46d23bb296392d14b775f6ccbb0a9c7e6a0a049ac
+size 142844

topic_embeddings.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ed95d84dafd9f1fb4688cbaa428c25e8a9b904a8115a611f1e1a6115ab06e01
+size 36952

topics.json

@@ -0,0 +1,937 @@
+{
+  "topic_representations": {
+    "-1": [
+      [
+        "thewellnesscompany",
+        0.9924483895301819
+      ],
+      [
+        "shots",
+        0.991315484046936
+      ],
+      [
+        "reprisal",
+        0.991204023361206
+      ],
+      [
+        "serves",
+        0.9910897016525269
+      ],
+      [
+        "coulson",
+        0.991033136844635
+      ],
+      [
+        "cardiologist",
+        0.9902971386909485
+      ],
+      [
+        "harm",
+        0.990088939666748
+      ],
+      [
+        "md",
+        0.9898195266723633
+      ],
+      [
+        "pregnancy",
+        0.9897884130477905
+      ],
+      [
+        "mortality",
+        0.9897313117980957
+      ]
+    ],
+    "0": [
+      [
+        "thewellnesscompany",
+        0.9938153624534607
+      ],
+      [
+        "gessling",
+        0.9936378002166748
+      ],
+      [
+        "compelling",
+        0.9933173656463623
+      ],
+      [
+        "prolonged",
+        0.9929815530776978
+      ],
+      [
+        "daily_clout",
+        0.9928981065750122
+      ],
+      [
+        "packed",
+        0.9928769469261169
+      ],
+      [
+        "supported",
+        0.9927970767021179
+      ],
+      [
+        "featured",
+        0.9926791787147522
+      ],
+      [
+        "coulson",
+        0.9923766851425171
+      ],
+      [
+        "degradation",
+        0.9921965599060059
+      ]
+    ],
+    "1": [
+      [
+        "cardiologists",
+        0.9929624795913696
+      ],
+      [
+        "thewellnesscompany",
+        0.992820680141449
+      ],
+      [
+        "myocarditis",
+        0.9925523400306702
+      ],
+      [
+        "epidemiologist",
+        0.9924734830856323
+      ],
+      [
+        "publications",
+        0.99214106798172
+      ],
+      [
+        "shots",
+        0.9914146661758423
+      ],
+      [
+        "reprisal",
+        0.9913164377212524
+      ],
+      [
+        "deaths",
+        0.9912759065628052
+      ],
+      [
+        "respected",
+        0.9910982251167297
+      ],
+      [
+        "unvaccinated",
+        0.9909823536872864
+      ]
+    ],
+    "2": [
+      [
+        "myocarditis",
+        0.9924960136413574
+      ],
+      [
+        "thewellnesscompany",
+        0.9922083020210266
+      ],
+      [
+        "prolonged",
+        0.9913386106491089
+      ],
+      [
+        "shots",
+        0.991246223449707
+      ],
+      [
+        "reprisal",
+        0.9912334680557251
+      ],
+      [
+        "milligrams",
+        0.9911770820617676
+      ],
+      [
+        "deaths",
+        0.9911076426506042
+      ],
+      [
+        "pfizer",
+        0.990545928478241
+      ],
+      [
+        "cardiologist",
+        0.9903914928436279
+      ],
+      [
+        "cdc",
+        0.9901058077812195
+      ]
+    ],
+    "3": [
+      [
+        "thewellnesscompany",
+        0.992757260799408
+      ],
+      [
+        "packed",
+        0.9922465682029724
+      ],
+      [
+        "prolonged",
+        0.9922440052032471
+      ],
+      [
+        "dissolved",
+        0.9921209812164307
+      ],
+      [
+        "pomegranate",
+        0.9919652938842773
+      ],
+      [
+        "boosting",
+        0.9919150471687317
+      ],
+      [
+        "featured",
+        0.991796612739563
+      ],
+      [
+        "wreaths",
+        0.9917635917663574
+      ],
+      [
+        "degrades",
+        0.991762638092041
+      ],
+      [
+        "indicates",
+        0.9916923642158508
+      ]
+    ],
+    "4": [
+      [
+        "thewellnesscompany",
+        0.9919278621673584
+      ],
+      [
+        "tedros",
+        0.9904292225837708
+      ],
+      [
+        "insights",
+        0.9901975989341736
+      ],
+      [
+        "marik",
+        0.9900283217430115
+      ],
+      [
+        "toxicity",
+        0.9896097779273987
+      ],
+      [
+        "nattokinase",
+        0.9895783066749573
+      ],
+      [
+        "md",
+        0.9893758296966553
+      ],
+      [
+        "fda",
+        0.9893602728843689
+      ],
+      [
+        "mccullough",
+        0.9886065721511841
+      ],
+      [
+        "vigilantfox",
+        0.9885128736495972
+      ]
+    ],
+    "5": [
+      [
+        "ivermectin",
+        0.9925258159637451
+      ],
+      [
+        "thewellnesscompany",
+        0.992306649684906
+      ],
+      [
+        "epidemiologist",
+        0.9918921589851379
+      ],
+      [
+        "hydroxychloroquine",
+        0.9917668700218201
+      ],
+      [
+        "misbehavior",
+        0.9914377927780151
+      ],
+      [
+        "analyze",
+        0.9913100600242615
+      ],
+      [
+        "alarming",
+        0.9910611510276794
+      ],
+      [
+        "reprisal",
+        0.990990400314331
+      ],
+      [
+        "deaths",
+        0.9909043908119202
+      ],
+      [
+        "serves",
+        0.9907913208007812
+      ]
+    ],
+    "6": [
+      [
+        "thewellnesscompany",
+        0.9918699860572815
+      ],
+      [
+        "hearts",
+        0.9908273816108704
+      ],
+      [
+        "concerns",
+        0.99077969789505
+      ],
+      [
+        "reprisal",
+        0.9907045960426331
+      ],
+      [
+        "shots",
+        0.9906884431838989
+      ],
+      [
+        "deaths",
+        0.9906242489814758
+      ],
+      [
+        "clinical",
+        0.9906162023544312
+      ],
+      [
+        "unvaccinated",
+        0.9903703331947327
+      ],
+      [
+        "nattokinase",
+        0.9895355105400085
+      ],
+      [
+        "lancet",
+        0.9894989132881165
+      ]
+    ],
+    "7": [
+      [
+        "backtobasicsconference",
+        0.9944087862968445
+      ],
+      [
+        "unprepared",
+        0.9932331442832947
+      ],
+      [
+        "pregnancytalk",
+        0.9930314421653748
+      ],
+      [
+        "twcadventures",
+        0.9928005337715149
+      ],
+      [
+        "may9th",
+        0.9923923015594482
+      ],
+      [
+        "topics",
+        0.9922353029251099
+      ],
+      [
+        "spaces",
+        0.9921088218688965
+      ],
+      [
+        "anticipated",
+        0.9920806288719177
+      ],
+      [
+        "medicalexperts",
+        0.9919574856758118
+      ],
+      [
+        "personalgrowth",
+        0.9918033480644226
+      ]
+    ]
+  },
+  "topics": [
+    3,
+    0,
+    1,
+    1,
+    2,
+    -1,
+    6,
+    4,
+    -1,
+    5,
+    4,
+    1,
+    2,
+    6,
+    1,
+    2,
+    1,
+    6,
+    2,
+    1,
+    2,
+    2,
+    0,
+    4,
+    1,
+    3,
+    1,
+    0,
+    -1,
+    -1,
+    0,
+    2,
+    3,
+    3,
+    0,
+    4,
+    3,
+    0,
+    4,
+    3,
+    3,
+    3,
+    3,
+    2,
+    6,
+    2,
+    3,
+    0,
+    1,
+    3,
+    0,
+    3,
+    0,
+    0,
+    0,
+    -1,
+    3,
+    3,
+    2,
+    -1,
+    0,
+    3,
+    2,
+    4,
+    1,
+    -1,
+    3,
+    2,
+    2,
+    1,
+    2,
+    2,
+    0,
+    1,
+    3,
+    0,
+    2,
+    0,
+    0,
+    1,
+    2,
+    2,
+    0,
+    3,
+    3,
+    7,
+    7,
+    0,
+    2,
+    2,
+    2,
+    -1,
+    2,
+    7,
+    3,
+    2,
+    6,
+    3,
+    1,
+    1,
+    2,
+    0,
+    7,
+    4,
+    6,
+    -1,
+    7,
+    -1,
+    3,
+    -1,
+    7,
+    7,
+    4,
+    1,
+    7,
+    2,
+    1,
+    -1,
+    2,
+    6,
+    2,
+    0,
+    2,
+    2,
+    1,
+    0,
+    7,
+    1,
+    0,
+    4,
+    -1,
+    1,
+    2,
+    2,
+    3,
+    -1,
+    2,
+    4,
+    2,
+    2,
+    1,
+    0,
+    0,
+    7,
+    4,
+    0,
+    1,
+    0,
+    -1,
+    3,
+    2,
+    2,
+    2,
+    4,
+    2,
+    4,
+    2,
+    2,
+    6,
+    0,
+    0,
+    2,
+    2,
+    6,
+    6,
+    -1,
+    -1,
+    2,
+    6,
+    0,
+    0,
+    0,
+    2,
+    2,
+    0,
+    0,
+    0,
+    2,
+    4,
+    0,
+    6,
+    2,
+    0,
+    2,
+    1,
+    0,
+    2,
+    -1,
+    0,
+    2,
+    2,
+    2,
+    2,
+    4,
+    0,
+    2,
+    2,
+    2,
+    0,
+    2,
+    6,
+    0,
+    4,
+    4,
+    6,
+    0,
+    4,
+    3,
+    0,
+    3,
+    3,
+    0,
+    0,
+    2,
+    3,
+    0,
+    3,
+    2,
+    3,
+    3,
+    0,
+    3,
+    0,
+    2,
+    0,
+    0,
+    3,
+    1,
+    7,
+    0,
+    -1,
+    0,
+    0,
+    -1,
+    2,
+    0,
+    6,
+    0,
+    3,
+    0,
+    0,
+    0,
+    2,
+    7,
+    0,
+    3,
+    3,
+    0,
+    6,
+    2,
+    0,
+    3,
+    3,
+    2,
+    0,
+    3,
+    1,
+    2,
+    -1,
+    0,
+    0,
+    0,
+    -1,
+    2,
+    0,
+    2,
+    0,
+    0,
+    0,
+    0,
+    5,
+    0,
+    4,
+    0,
+    5,
+    0,
+    -1,
+    0,
+    0,
+    0,
+    0,
+    0,
+    0,
+    1,
+    2,
+    1,
+    0,
+    1,
+    1,
+    1,
+    4,
+    0,
+    0,
+    3,
+    0,
+    2,
+    0,
+    3,
+    1,
+    1,
+    0,
+    0,
+    6,
+    1,
+    0,
+    3,
+    0,
+    0,
+    5,
+    2,
+    1,
+    1,
+    -1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    -1,
+    3,
+    0,
+    3,
+    0,
+    3,
+    0,
+    1,
+    1,
+    0,
+    0,
+    1,
+    0,
+    1,
+    0,
+    1,
+    5,
+    3,
+    1,
+    1,
+    0,
+    0,
+    0,
+    1,
+    1,
+    -1,
+    1,
+    0,
+    3,
+    3,
+    0,
+    3,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    3,
+    1,
+    1,
+    1,
+    3,
+    1,
+    1,
+    2,
+    1,
+    1,
+    2,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    0,
+    1,
+    0,
+    0,
+    0,
+    0,
+    0,
+    1,
+    0,
+    1,
+    1,
+    0,
+    0,
+    2,
+    0,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    5,
+    1,
+    1,
+    1,
+    1,
+    1,
+    1,
+    0,
+    2,
+    1,
+    2,
+    0,
+    5,
+    -1,
+    0,
+    0,
+    2,
+    5,
+    0,
+    0,
+    -1,
+    -1,
+    2,
+    -1,
+    -1,
+    -1,
+    5,
+    1,
+    5,
+    5,
+    -1,
+    5,
+    5,
+    6,
+    -1,
+    0,
+    5,
+    6,
+    5,
+    6,
+    5,
+    -1,
+    2,
+    5,
+    -1,
+    5,
+    0,
+    2,
+    1,
+    0,
+    3,
+    0,
+    0,
+    5,
+    0,
+    0,
+    0,
+    -1,
+    0,
+    2,
+    5,
+    0,
+    1,
+    5,
+    -1,
+    0,
+    -1,
+    0,
+    -1,
+    1,
+    4,
+    0,
+    0,
+    -1,
+    0,
+    0
+  ],
+  "topic_sizes": {
+    "3": 52,
+    "0": 138,
+    "1": 96,
+    "2": 80,
+    "-1": 41,
+    "6": 20,
+    "4": 21,
+    "5": 21,
+    "7": 12
+  },
+  "topic_mapper": [
+    [
+      -1,
+      -1,
+      -1
+    ],
+    [
+      0,
+      0,
+      0
+    ],
+    [
+      1,
+      1,
+      7
+    ],
+    [
+      2,
+      2,
+      3
+    ],
+    [
+      3,
+      3,
+      1
+    ],
+    [
+      4,
+      4,
+      4
+    ],
+    [
+      5,
+      5,
+      2
+    ],
+    [
+      6,
+      6,
+      5
+    ],
+    [
+      7,
+      7,
+      6
+    ]
+  ],
+  "topic_labels": {
+    "-1": "-1_thewellnesscompany_shots_reprisal_serves",
+    "0": "0_thewellnesscompany_gessling_compelling_prolonged",
+    "1": "1_cardiologists_thewellnesscompany_myocarditis_epidemiologist",
+    "2": "2_myocarditis_thewellnesscompany_prolonged_shots",
+    "3": "3_thewellnesscompany_packed_prolonged_dissolved",
+    "4": "4_thewellnesscompany_tedros_insights_marik",
+    "5": "5_ivermectin_thewellnesscompany_epidemiologist_hydroxychloroquine",
+    "6": "6_thewellnesscompany_hearts_concerns_reprisal",
+    "7": "7_backtobasicsconference_unprepared_pregnancytalk_twcadventures"
+  },
+  "custom_labels": null,
+  "_outliers": 1,
+  "topic_aspects": {}
+}