Add BERTopic model

README.md

@@ -0,0 +1,79 @@
+
+---
+tags:
+- bertopic
+library_name: bertopic
+pipeline_tag: text-classification
+---
+
+# Singapore_BERTopic
+
+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("sneakykilli/Singapore_BERTopic")
+
+topic_model.get_topic_info()
+```
+
+## Topic overview
+
+* Number of topics: 10
+* Number of training documents: 160
+
+<details>
+  <summary>Click here for an overview of all topics.</summary>
+  
+  | Topic ID | Topic Keywords | Topic Frequency | Label | 
+|----------|----------------|-----------------|-------| 
+| -1 | airline - airlines - flights - refund - flight | 6 | -1_airline_airlines_flights_refund | 
+| 0 | airline - airlines - flights - singapore - meals | 31 | 0_airline_airlines_flights_singapore | 
+| 1 | refund - airline - airlines - complaint - singapore | 43 | 1_refund_airline_airlines_complaint | 
+| 2 | baggage - luggage - airlines - airline - bags | 20 | 2_baggage_luggage_airlines_airline | 
+| 3 | airlines - passengers - seats - flight - cabin | 14 | 3_airlines_passengers_seats_flight | 
+| 4 | refund - repayment - sia - customer - complaints | 11 | 4_refund_repayment_sia_customer | 
+| 5 | airlines - airline - fees - singapore - flights | 10 | 5_airlines_airline_fees_singapore | 
+| 6 | refund - airline - cancellation - booking - cancel | 9 | 6_refund_airline_cancellation_booking | 
+| 7 | miles - airlines - airline - mileage - loyalty | 9 | 7_miles_airlines_airline_mileage | 
+| 8 | airline - flight - reviews - booking - customer | 7 | 8_airline_flight_reviews_booking |
+  
+</details>
+
+## Training hyperparameters
+
+* calculate_probabilities: False
+* language: None
+* low_memory: False
+* min_topic_size: 5
+* 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: 1.24.3
+* HDBSCAN: 0.8.33
+* UMAP: 0.5.5
+* Pandas: 2.0.3
+* Scikit-Learn: 1.2.2
+* Sentence-transformers: 2.3.1
+* Transformers: 4.36.2
+* Numba: 0.57.1
+* Plotly: 5.16.1
+* Python: 3.10.12

config.json

@@ -0,0 +1,17 @@
+{
+  "calculate_probabilities": false,
+  "language": null,
+  "low_memory": false,
+  "min_topic_size": 5,
+  "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,
+  "embedding_model": "all-MiniLM-L6-v2"
+}

ctfidf.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab6e192a6b8c4a5895c844acd2e5059ef123e06f8aee394e0c21aa10e9d79c0c
+size 77752

topic_embeddings.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dcc05adfdd3c56d5d8a07c2f46f5a79ee7e42f8a85d74317e06ab055080d3fa
+size 15448

topics.json

@@ -0,0 +1,665 @@
+{
+  "topic_representations": {
+    "-1": [
+      [
+        "airline",
+        0.41720014810562134
+      ],
+      [
+        "airlines",
+        0.41072994470596313
+      ],
+      [
+        "flights",
+        0.3909800052642822
+      ],
+      [
+        "refund",
+        0.3571051359176636
+      ],
+      [
+        "flight",
+        0.3357126712799072
+      ],
+      [
+        "fare",
+        0.3030855059623718
+      ],
+      [
+        "singapore",
+        0.29068851470947266
+      ],
+      [
+        "complaint",
+        0.274583637714386
+      ],
+      [
+        "flying",
+        0.26368528604507446
+      ],
+      [
+        "voucher",
+        0.2579178214073181
+      ]
+    ],
+    "0": [
+      [
+        "airline",
+        0.47997474670410156
+      ],
+      [
+        "airlines",
+        0.4713612198829651
+      ],
+      [
+        "flights",
+        0.4244295060634613
+      ],
+      [
+        "singapore",
+        0.36062896251678467
+      ],
+      [
+        "meals",
+        0.3596476912498474
+      ],
+      [
+        "flight",
+        0.35365304350852966
+      ],
+      [
+        "food",
+        0.29792851209640503
+      ],
+      [
+        "eating",
+        0.2671264708042145
+      ],
+      [
+        "bread",
+        0.2548995316028595
+      ],
+      [
+        "fly",
+        0.2533579170703888
+      ]
+    ],
+    "1": [
+      [
+        "refund",
+        0.4560515880584717
+      ],
+      [
+        "airline",
+        0.3744000792503357
+      ],
+      [
+        "airlines",
+        0.3643943667411804
+      ],
+      [
+        "complaint",
+        0.3607919216156006
+      ],
+      [
+        "singapore",
+        0.35467201471328735
+      ],
+      [
+        "flights",
+        0.32735028862953186
+      ],
+      [
+        "cancel",
+        0.3221847414970398
+      ],
+      [
+        "compensation",
+        0.2879146933555603
+      ],
+      [
+        "flight",
+        0.2787000834941864
+      ],
+      [
+        "ticket",
+        0.27175629138946533
+      ]
+    ],
+    "2": [
+      [
+        "baggage",
+        0.47602730989456177
+      ],
+      [
+        "luggage",
+        0.45390939712524414
+      ],
+      [
+        "airlines",
+        0.43988215923309326
+      ],
+      [
+        "airline",
+        0.42567938566207886
+      ],
+      [
+        "bags",
+        0.3698173463344574
+      ],
+      [
+        "bag",
+        0.3604351878166199
+      ],
+      [
+        "handbag",
+        0.33640238642692566
+      ],
+      [
+        "haul",
+        0.31882810592651367
+      ],
+      [
+        "suitcase",
+        0.31776320934295654
+      ],
+      [
+        "singapore",
+        0.30839091539382935
+      ]
+    ],
+    "3": [
+      [
+        "airlines",
+        0.44553548097610474
+      ],
+      [
+        "passengers",
+        0.408767968416214
+      ],
+      [
+        "seats",
+        0.33244749903678894
+      ],
+      [
+        "flight",
+        0.3313222825527191
+      ],
+      [
+        "cabin",
+        0.31762823462486267
+      ],
+      [
+        "attendants",
+        0.3064364790916443
+      ],
+      [
+        "seat",
+        0.28947174549102783
+      ],
+      [
+        "plane",
+        0.2577582001686096
+      ],
+      [
+        "singapore",
+        0.25600093603134155
+      ],
+      [
+        "class",
+        0.24720510840415955
+      ]
+    ],
+    "4": [
+      [
+        "refund",
+        0.4529116153717041
+      ],
+      [
+        "repayment",
+        0.37985289096832275
+      ],
+      [
+        "sia",
+        0.36999768018722534
+      ],
+      [
+        "customer",
+        0.3524300456047058
+      ],
+      [
+        "complaints",
+        0.33408963680267334
+      ],
+      [
+        "customers",
+        0.3327406048774719
+      ],
+      [
+        "bank",
+        0.32434985041618347
+      ],
+      [
+        "service",
+        0.30804628133773804
+      ],
+      [
+        "charges",
+        0.30167824029922485
+      ],
+      [
+        "contact",
+        0.29032042622566223
+      ]
+    ],
+    "5": [
+      [
+        "airlines",
+        0.425093412399292
+      ],
+      [
+        "airline",
+        0.4162958860397339
+      ],
+      [
+        "fees",
+        0.39408397674560547
+      ],
+      [
+        "singapore",
+        0.39009320735931396
+      ],
+      [
+        "flights",
+        0.3763861060142517
+      ],
+      [
+        "booking",
+        0.3662506937980652
+      ],
+      [
+        "fare",
+        0.36056625843048096
+      ],
+      [
+        "ticket",
+        0.33361199498176575
+      ],
+      [
+        "extortion",
+        0.3151136040687561
+      ],
+      [
+        "flight",
+        0.3104732036590576
+      ]
+    ],
+    "6": [
+      [
+        "refund",
+        0.5809109210968018
+      ],
+      [
+        "airline",
+        0.4229697287082672
+      ],
+      [
+        "cancellation",
+        0.3839954733848572
+      ],
+      [
+        "booking",
+        0.36461541056632996
+      ],
+      [
+        "cancel",
+        0.36459028720855713
+      ],
+      [
+        "repurchase",
+        0.363625705242157
+      ],
+      [
+        "receipt",
+        0.32762402296066284
+      ],
+      [
+        "flight",
+        0.3106320798397064
+      ],
+      [
+        "return",
+        0.29938411712646484
+      ],
+      [
+        "overbooked",
+        0.2789418399333954
+      ]
+    ],
+    "7": [
+      [
+        "miles",
+        0.38810890913009644
+      ],
+      [
+        "airlines",
+        0.38180404901504517
+      ],
+      [
+        "airline",
+        0.35821104049682617
+      ],
+      [
+        "mileage",
+        0.3231382966041565
+      ],
+      [
+        "loyalty",
+        0.30341872572898865
+      ],
+      [
+        "booking",
+        0.2877732515335083
+      ],
+      [
+        "singapore",
+        0.28564366698265076
+      ],
+      [
+        "alliance",
+        0.27681979537010193
+      ],
+      [
+        "redeeming",
+        0.2671453356742859
+      ],
+      [
+        "service",
+        0.25483736395835876
+      ]
+    ],
+    "8": [
+      [
+        "airline",
+        0.582975447177887
+      ],
+      [
+        "flight",
+        0.4120853543281555
+      ],
+      [
+        "reviews",
+        0.37630897760391235
+      ],
+      [
+        "booking",
+        0.37470388412475586
+      ],
+      [
+        "customer",
+        0.341844379901886
+      ],
+      [
+        "review",
+        0.3333813548088074
+      ],
+      [
+        "flyer",
+        0.32562053203582764
+      ],
+      [
+        "agency",
+        0.29199445247650146
+      ],
+      [
+        "ticket",
+        0.2773098945617676
+      ],
+      [
+        "service",
+        0.25537988543510437
+      ]
+    ]
+  },
+  "topics": [
+    0,
+    8,
+    -1,
+    1,
+    5,
+    6,
+    0,
+    2,
+    4,
+    1,
+    7,
+    3,
+    -1,
+    -1,
+    3,
+    8,
+    0,
+    4,
+    2,
+    3,
+    -1,
+    7,
+    3,
+    1,
+    4,
+    1,
+    5,
+    -1,
+    2,
+    -1,
+    4,
+    6,
+    8,
+    0,
+    8,
+    3,
+    0,
+    7,
+    6,
+    0,
+    -1,
+    4,
+    -1,
+    0,
+    0,
+    -1,
+    0,
+    1,
+    0,
+    -1,
+    0,
+    0,
+    0,
+    0,
+    0,
+    -1,
+    0,
+    6,
+    5,
+    2,
+    0,
+    0,
+    2,
+    5,
+    1,
+    0,
+    -1,
+    -1,
+    4,
+    7,
+    2,
+    0,
+    -1,
+    5,
+    8,
+    1,
+    -1,
+    4,
+    0,
+    0,
+    -1,
+    1,
+    3,
+    -1,
+    6,
+    1,
+    0,
+    6,
+    2,
+    1,
+    6,
+    7,
+    1,
+    -1,
+    3,
+    -1,
+    0,
+    -1,
+    0,
+    0,
+    5,
+    0,
+    -1,
+    1,
+    3,
+    5,
+    -1,
+    -1,
+    3,
+    1,
+    8,
+    0,
+    -1,
+    -1,
+    0,
+    -1,
+    -1,
+    0,
+    6,
+    -1,
+    0,
+    0,
+    5,
+    3,
+    0,
+    2,
+    0,
+    1,
+    2,
+    0,
+    2,
+    6,
+    0,
+    2,
+    7,
+    4,
+    2,
+    0,
+    -1,
+    7,
+    0,
+    0,
+    2,
+    -1,
+    5,
+    0,
+    2,
+    -1,
+    1,
+    0,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0,
+    3,
+    4,
+    1,
+    4
+  ],
+  "topic_sizes": {
+    "0": 43,
+    "8": 6,
+    "-1": 31,
+    "1": 20,
+    "5": 9,
+    "6": 9,
+    "2": 14,
+    "4": 10,
+    "7": 7,
+    "3": 11
+  },
+  "topic_mapper": [
+    [
+      -1,
+      -1,
+      -1
+    ],
+    [
+      0,
+      0,
+      0
+    ],
+    [
+      1,
+      1,
+      4
+    ],
+    [
+      2,
+      2,
+      8
+    ],
+    [
+      3,
+      3,
+      6
+    ],
+    [
+      4,
+      4,
+      3
+    ],
+    [
+      5,
+      5,
+      7
+    ],
+    [
+      6,
+      6,
+      2
+    ],
+    [
+      7,
+      7,
+      1
+    ],
+    [
+      8,
+      8,
+      5
+    ]
+  ],
+  "topic_labels": {
+    "-1": "-1_airline_airlines_flights_refund",
+    "0": "0_airline_airlines_flights_singapore",
+    "1": "1_refund_airline_airlines_complaint",
+    "2": "2_baggage_luggage_airlines_airline",
+    "3": "3_airlines_passengers_seats_flight",
+    "4": "4_refund_repayment_sia_customer",
+    "5": "5_airlines_airline_fees_singapore",
+    "6": "6_refund_airline_cancellation_booking",
+    "7": "7_miles_airlines_airline_mileage",
+    "8": "8_airline_flight_reviews_booking"
+  },
+  "custom_labels": null,
+  "_outliers": 1,
+  "topic_aspects": {}
+}