Add BERTopic model

README.md

@@ -0,0 +1,80 @@
+
+---
+tags:
+- bertopic
+library_name: bertopic
+pipeline_tag: text-classification
+---
+
+# Emirates_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/Emirates_BERTopic")
+
+topic_model.get_topic_info()
+```
+
+## Topic overview
+
+* Number of topics: 11
+* Number of training documents: 375
+
+<details>
+  <summary>Click here for an overview of all topics.</summary>
+  
+  | Topic ID | Topic Keywords | Topic Frequency | Label | 
+|----------|----------------|-----------------|-------| 
+| -1 | emirates - airline - airlines - flights - refund | 9 | -1_emirates_airline_airlines_flights | 
+| 0 | emirates - airlines - airline - dubai - flights | 100 | 0_emirates_airlines_airline_dubai | 
+| 1 | airline - airlines - flights - aviation - planes | 68 | 1_airline_airlines_flights_aviation | 
+| 2 | emirates - meals - meal - attendant - airline | 35 | 2_emirates_meals_meal_attendant | 
+| 3 | emirates - refund - cancel - booking - ticket | 34 | 3_emirates_refund_cancel_booking | 
+| 4 | airline - refunded - refund - ticket - booking | 28 | 4_airline_refunded_refund_ticket | 
+| 5 | emirates - dubai - baggage - luggage - airline | 26 | 5_emirates_dubai_baggage_luggage | 
+| 6 | emirates - airline - refund - seats - flights | 26 | 6_emirates_airline_refund_seats | 
+| 7 | emirates - airlines - airline - booking - fees | 23 | 7_emirates_airlines_airline_booking | 
+| 8 | passengers - airline - emirates - stewardess - aisle | 14 | 8_passengers_airline_emirates_stewardess | 
+| 9 | emirates - delayed - dubai - delays - flights | 12 | 9_emirates_delayed_dubai_delays |
+  
+</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 sha256:3dd28c5de6541d68f6f45fae7a5e9e372b6887926960be3f49c7bf08f2925a8c
+size 147912

topic_embeddings.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0d1f32058410c53abdfc7bb83bc7b3cd4da2d915d7222e85d25c9b0a7ad8b7b
+size 16984

topics.json

@@ -0,0 +1,929 @@
+{
+  "topic_representations": {
+    "-1": [
+      [
+        "emirates",
+        0.4200151860713959
+      ],
+      [
+        "airline",
+        0.41257697343826294
+      ],
+      [
+        "airlines",
+        0.39219996333122253
+      ],
+      [
+        "flights",
+        0.37306544184684753
+      ],
+      [
+        "refund",
+        0.36261361837387085
+      ],
+      [
+        "flight",
+        0.3286304175853729
+      ],
+      [
+        "booking",
+        0.32838523387908936
+      ],
+      [
+        "dubai",
+        0.29855644702911377
+      ],
+      [
+        "customers",
+        0.28836768865585327
+      ],
+      [
+        "customer",
+        0.2847030758857727
+      ]
+    ],
+    "0": [
+      [
+        "emirates",
+        0.617570161819458
+      ],
+      [
+        "airlines",
+        0.4732361435890198
+      ],
+      [
+        "airline",
+        0.4587326645851135
+      ],
+      [
+        "dubai",
+        0.39003199338912964
+      ],
+      [
+        "flights",
+        0.37252041697502136
+      ],
+      [
+        "flight",
+        0.3089478611946106
+      ],
+      [
+        "flying",
+        0.27900591492652893
+      ],
+      [
+        "passengers",
+        0.27840614318847656
+      ],
+      [
+        "airport",
+        0.27814561128616333
+      ],
+      [
+        "etihad",
+        0.27481910586357117
+      ]
+    ],
+    "1": [
+      [
+        "airline",
+        0.7359843254089355
+      ],
+      [
+        "airlines",
+        0.7049427032470703
+      ],
+      [
+        "flights",
+        0.6178334951400757
+      ],
+      [
+        "aviation",
+        0.5455489158630371
+      ],
+      [
+        "planes",
+        0.49172019958496094
+      ],
+      [
+        "boarding",
+        0.3885127007961273
+      ],
+      [
+        "fly",
+        0.36450082063674927
+      ],
+      [
+        "reviews",
+        0.3518097996711731
+      ],
+      [
+        "quality",
+        0.30676043033599854
+      ],
+      [
+        "onboard",
+        0.30036407709121704
+      ]
+    ],
+    "2": [
+      [
+        "emirates",
+        0.4158428907394409
+      ],
+      [
+        "meals",
+        0.3790268898010254
+      ],
+      [
+        "meal",
+        0.3692361116409302
+      ],
+      [
+        "attendant",
+        0.33274564146995544
+      ],
+      [
+        "airline",
+        0.3177309036254883
+      ],
+      [
+        "eating",
+        0.30844801664352417
+      ],
+      [
+        "snack",
+        0.2912340462207794
+      ],
+      [
+        "flights",
+        0.2911188006401062
+      ],
+      [
+        "food",
+        0.2875499725341797
+      ],
+      [
+        "serve",
+        0.2780338525772095
+      ]
+    ],
+    "3": [
+      [
+        "emirates",
+        0.5533087253570557
+      ],
+      [
+        "refund",
+        0.5102535486221313
+      ],
+      [
+        "cancel",
+        0.33245331048965454
+      ],
+      [
+        "booking",
+        0.31715965270996094
+      ],
+      [
+        "ticket",
+        0.31508100032806396
+      ],
+      [
+        "airline",
+        0.30292195081710815
+      ],
+      [
+        "booked",
+        0.29438072443008423
+      ],
+      [
+        "cancelled",
+        0.2937238812446594
+      ],
+      [
+        "airlines",
+        0.2935619354248047
+      ],
+      [
+        "tickets",
+        0.28322264552116394
+      ]
+    ],
+    "4": [
+      [
+        "airline",
+        0.47385063767433167
+      ],
+      [
+        "refunded",
+        0.468755841255188
+      ],
+      [
+        "refund",
+        0.46341782808303833
+      ],
+      [
+        "ticket",
+        0.41224271059036255
+      ],
+      [
+        "booking",
+        0.3812403380870819
+      ],
+      [
+        "cancel",
+        0.3641064763069153
+      ],
+      [
+        "flight",
+        0.3594733476638794
+      ],
+      [
+        "tickets",
+        0.3518993854522705
+      ],
+      [
+        "complaints",
+        0.3250718116760254
+      ],
+      [
+        "booked",
+        0.3185856342315674
+      ]
+    ],
+    "5": [
+      [
+        "emirates",
+        0.5049640536308289
+      ],
+      [
+        "dubai",
+        0.40813714265823364
+      ],
+      [
+        "baggage",
+        0.37350815534591675
+      ],
+      [
+        "luggage",
+        0.3623806834220886
+      ],
+      [
+        "airline",
+        0.30339106917381287
+      ],
+      [
+        "suitcase",
+        0.2971385717391968
+      ],
+      [
+        "suitcases",
+        0.26742199063301086
+      ],
+      [
+        "bags",
+        0.2524309754371643
+      ],
+      [
+        "complaint",
+        0.2497742474079132
+      ],
+      [
+        "airport",
+        0.24321110546588898
+      ]
+    ],
+    "6": [
+      [
+        "emirates",
+        0.5479847192764282
+      ],
+      [
+        "airline",
+        0.3938390910625458
+      ],
+      [
+        "refund",
+        0.3825901448726654
+      ],
+      [
+        "seats",
+        0.3225798010826111
+      ],
+      [
+        "flights",
+        0.30042117834091187
+      ],
+      [
+        "dubai",
+        0.292599081993103
+      ],
+      [
+        "complaints",
+        0.2923539876937866
+      ],
+      [
+        "booked",
+        0.28053128719329834
+      ],
+      [
+        "tickets",
+        0.26576465368270874
+      ],
+      [
+        "passengers",
+        0.2624097466468811
+      ]
+    ],
+    "7": [
+      [
+        "emirates",
+        0.5912024974822998
+      ],
+      [
+        "airlines",
+        0.38515931367874146
+      ],
+      [
+        "airline",
+        0.3650982975959778
+      ],
+      [
+        "booking",
+        0.3644976019859314
+      ],
+      [
+        "fees",
+        0.3528328537940979
+      ],
+      [
+        "dubai",
+        0.34011512994766235
+      ],
+      [
+        "flights",
+        0.31651344895362854
+      ],
+      [
+        "qantas",
+        0.29625287652015686
+      ],
+      [
+        "booked",
+        0.2681851387023926
+      ],
+      [
+        "tickets",
+        0.26173534989356995
+      ]
+    ],
+    "8": [
+      [
+        "passengers",
+        0.4284360408782959
+      ],
+      [
+        "airline",
+        0.3715548515319824
+      ],
+      [
+        "emirates",
+        0.3667936325073242
+      ],
+      [
+        "stewardess",
+        0.3552247881889343
+      ],
+      [
+        "aisle",
+        0.35331031680107117
+      ],
+      [
+        "seats",
+        0.348671019077301
+      ],
+      [
+        "passenger",
+        0.3409116864204407
+      ],
+      [
+        "seat",
+        0.32770836353302
+      ],
+      [
+        "sit",
+        0.3129791021347046
+      ],
+      [
+        "sitting",
+        0.2832213044166565
+      ]
+    ],
+    "9": [
+      [
+        "emirates",
+        0.5026525259017944
+      ],
+      [
+        "delayed",
+        0.42015165090560913
+      ],
+      [
+        "dubai",
+        0.41919344663619995
+      ],
+      [
+        "delays",
+        0.4042111337184906
+      ],
+      [
+        "flights",
+        0.3891065716743469
+      ],
+      [
+        "emirate",
+        0.3691459894180298
+      ],
+      [
+        "flight",
+        0.3519466519355774
+      ],
+      [
+        "bangkok",
+        0.34849923849105835
+      ],
+      [
+        "delay",
+        0.3425716161727905
+      ],
+      [
+        "karachi",
+        0.3171828091144562
+      ]
+    ]
+  },
+  "topics": [
+    -1,
+    4,
+    0,
+    2,
+    -1,
+    5,
+    2,
+    6,
+    4,
+    5,
+    5,
+    4,
+    0,
+    2,
+    -1,
+    -1,
+    4,
+    0,
+    1,
+    0,
+    0,
+    -1,
+    5,
+    9,
+    0,
+    6,
+    -1,
+    6,
+    1,
+    7,
+    5,
+    -1,
+    9,
+    6,
+    5,
+    5,
+    5,
+    6,
+    8,
+    1,
+    -1,
+    -1,
+    -1,
+    0,
+    5,
+    4,
+    3,
+    1,
+    0,
+    4,
+    -1,
+    2,
+    4,
+    6,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    1,
+    1,
+    0,
+    6,
+    6,
+    0,
+    5,
+    1,
+    6,
+    3,
+    6,
+    2,
+    0,
+    0,
+    3,
+    -1,
+    -1,
+    0,
+    -1,
+    -1,
+    4,
+    1,
+    1,
+    0,
+    0,
+    3,
+    0,
+    3,
+    -1,
+    0,
+    4,
+    -1,
+    7,
+    -1,
+    9,
+    0,
+    0,
+    7,
+    0,
+    2,
+    0,
+    0,
+    -1,
+    5,
+    1,
+    0,
+    -1,
+    1,
+    -1,
+    0,
+    -1,
+    0,
+    2,
+    7,
+    0,
+    3,
+    -1,
+    6,
+    2,
+    4,
+    -1,
+    -1,
+    3,
+    0,
+    -1,
+    2,
+    2,
+    8,
+    -1,
+    9,
+    0,
+    1,
+    3,
+    2,
+    6,
+    7,
+    -1,
+    8,
+    3,
+    1,
+    4,
+    5,
+    7,
+    -1,
+    -1,
+    8,
+    -1,
+    -1,
+    3,
+    6,
+    -1,
+    -1,
+    5,
+    -1,
+    0,
+    5,
+    0,
+    5,
+    -1,
+    5,
+    1,
+    3,
+    0,
+    -1,
+    6,
+    -1,
+    7,
+    3,
+    1,
+    0,
+    4,
+    0,
+    8,
+    -1,
+    2,
+    5,
+    0,
+    2,
+    0,
+    4,
+    0,
+    2,
+    6,
+    -1,
+    0,
+    -1,
+    5,
+    -1,
+    0,
+    3,
+    -1,
+    8,
+    4,
+    8,
+    -1,
+    -1,
+    -1,
+    1,
+    1,
+    1,
+    3,
+    -1,
+    1,
+    -1,
+    0,
+    6,
+    0,
+    3,
+    1,
+    3,
+    4,
+    5,
+    1,
+    9,
+    -1,
+    0,
+    2,
+    2,
+    1,
+    -1,
+    0,
+    0,
+    -1,
+    2,
+    -1,
+    0,
+    7,
+    1,
+    -1,
+    0,
+    9,
+    -1,
+    6,
+    8,
+    8,
+    -1,
+    -1,
+    -1,
+    0,
+    0,
+    4,
+    4,
+    -1,
+    -1,
+    7,
+    0,
+    1,
+    -1,
+    -1,
+    0,
+    -1,
+    3,
+    1,
+    2,
+    0,
+    4,
+    3,
+    0,
+    -1,
+    1,
+    4,
+    -1,
+    -1,
+    0,
+    -1,
+    4,
+    1,
+    3,
+    2,
+    8,
+    -1,
+    1,
+    -1,
+    0,
+    2,
+    2,
+    0,
+    -1,
+    -1,
+    0,
+    8,
+    1,
+    5,
+    -1,
+    0,
+    -1,
+    0,
+    9,
+    5,
+    -1,
+    0,
+    2,
+    2,
+    0,
+    0,
+    2,
+    1,
+    3,
+    -1,
+    -1,
+    7,
+    3,
+    2,
+    2,
+    1,
+    2,
+    2,
+    5,
+    4,
+    -1,
+    3,
+    4,
+    -1,
+    6,
+    2,
+    3,
+    -1,
+    0,
+    -1,
+    2,
+    2,
+    3,
+    8,
+    -1,
+    -1,
+    -1,
+    -1,
+    -1,
+    6,
+    2,
+    3,
+    7,
+    -1,
+    6,
+    6,
+    0,
+    0,
+    2,
+    5,
+    -1,
+    3,
+    5,
+    -1,
+    0,
+    4,
+    1,
+    0,
+    0,
+    5,
+    -1,
+    0,
+    -1,
+    0,
+    6,
+    -1,
+    7,
+    1,
+    1,
+    3,
+    2,
+    4,
+    -1,
+    9,
+    7,
+    3,
+    4,
+    -1,
+    6,
+    4,
+    -1,
+    5,
+    -1,
+    -1,
+    9,
+    1,
+    7
+  ],
+  "topic_sizes": {
+    "-1": 100,
+    "4": 26,
+    "0": 68,
+    "2": 34,
+    "5": 26,
+    "6": 23,
+    "1": 35,
+    "9": 9,
+    "7": 14,
+    "8": 12,
+    "3": 28
+  },
+  "topic_mapper": [
+    [
+      -1,
+      -1,
+      -1
+    ],
+    [
+      0,
+      0,
+      8
+    ],
+    [
+      1,
+      1,
+      4
+    ],
+    [
+      2,
+      2,
+      1
+    ],
+    [
+      3,
+      3,
+      2
+    ],
+    [
+      4,
+      4,
+      5
+    ],
+    [
+      5,
+      5,
+      0
+    ],
+    [
+      6,
+      6,
+      7
+    ],
+    [
+      7,
+      7,
+      9
+    ],
+    [
+      8,
+      8,
+      3
+    ],
+    [
+      9,
+      9,
+      6
+    ]
+  ],
+  "topic_labels": {
+    "-1": "-1_emirates_airline_airlines_flights",
+    "0": "0_emirates_airlines_airline_dubai",
+    "1": "1_airline_airlines_flights_aviation",
+    "2": "2_emirates_meals_meal_attendant",
+    "3": "3_emirates_refund_cancel_booking",
+    "4": "4_airline_refunded_refund_ticket",
+    "5": "5_emirates_dubai_baggage_luggage",
+    "6": "6_emirates_airline_refund_seats",
+    "7": "7_emirates_airlines_airline_booking",
+    "8": "8_passengers_airline_emirates_stewardess",
+    "9": "9_emirates_delayed_dubai_delays"
+  },
+  "custom_labels": null,
+  "_outliers": 1,
+  "topic_aspects": {}
+}