|
|
|
|
|
--- |
|
|
tags: |
|
|
- bertopic |
|
|
library_name: bertopic |
|
|
pipeline_tag: text-classification |
|
|
--- |
|
|
|
|
|
# bertopic_first |
|
|
|
|
|
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("DobreMihai/bertopic_first") |
|
|
|
|
|
topic_model.get_topic_info() |
|
|
``` |
|
|
|
|
|
## Topic overview |
|
|
|
|
|
* Number of topics: 50 |
|
|
* Number of training documents: 24020 |
|
|
|
|
|
<details> |
|
|
<summary>Click here for an overview of all topics.</summary> |
|
|
|
|
|
| Topic ID | Topic Keywords | Topic Frequency | Label | |
|
|
|----------|----------------|-----------------|-------| |
|
|
| -1 | it - be - to - the - alarm | 10 | -1_it_be_to_the | |
|
|
| 0 | app - math - the - alarm - to | 9997 | 0_app_math_the_alarm | |
|
|
| 1 | alarm - snooze - not - be - it | 5678 | 1_alarm_snooze_not_be | |
|
|
| 2 | subscription - - - - | 1906 | 2_subscription___ | |
|
|
| 3 | picture - photo - take - the - emergency | 1326 | 3_picture_photo_take_the | |
|
|
| 4 | wake - up - it - annoying - love | 603 | 4_wake_up_it_annoying | |
|
|
| 5 | snooze - - - - | 293 | 5_snooze___ | |
|
|
| 6 | loud - - - - | 288 | 6_loud___ | |
|
|
| 7 | barcode - scan - code - scanner - qr | 285 | 7_barcode_scan_code_scanner | |
|
|
| 8 | mission - the - be - you - to | 282 | 8_mission_the_be_you | |
|
|
| 9 | easy - use - simple - very - and | 279 | 9_easy_use_simple_very | |
|
|
| 10 | loud - - - - | 256 | 10_loud___ | |
|
|
| 11 | help - up - early - wake - helpful | 246 | 11_help_up_early_wake | |
|
|
| 12 | ring - not - do - it - sometimes | 243 | 12_ring_not_do_it | |
|
|
| 13 | app - work - open - not - phone | 195 | 13_app_work_open_not | |
|
|
| 14 | ads - - - - | 179 | 14_ads___ | |
|
|
| 15 | volume - vibrate - mute - sound - vibration | 176 | 15_volume_vibrate_mute_sound | |
|
|
| 16 | work - use - great - easy - well | 170 | 16_work_use_great_easy | |
|
|
| 17 | star - give - it - because - five | 162 | 17_star_give_it_because | |
|
|
| 18 | prevent - phone - off - power - switch | 140 | 18_prevent_phone_off_power | |
|
|
| 19 | loud - - - - | 130 | 19_loud___ | |
|
|
| 20 | work - off - sometimes - not - go | 128 | 20_work_off_sometimes_not | |
|
|
| 21 | music - song - spotify - own - file | 127 | 21_music_song_spotify_own | |
|
|
| 22 | weather - - - - | 110 | 22_weather___ | |
|
|
| 23 | annoying - job - but - work - it | 88 | 23_annoying_job_but_work | |
|
|
| 24 | student - helpful - for - useful - very | 73 | 24_student_helpful_for_useful | |
|
|
| 25 | perfect - word - good - amazing - be | 66 | 25_perfect_word_good_amazing | |
|
|
| 26 | reliable - easy - dependable - use - and | 58 | 26_reliable_easy_dependable_use | |
|
|
| 27 | minute - 10 - set - scroll - add | 53 | 27_minute_10_set_scroll | |
|
|
| 28 | aap - very - this - student - good | 50 | 28_aap_very_this_student | |
|
|
| 29 | android - 10 - work - update - support | 45 | 29_android_10_work_update | |
|
|
| 30 | reliable - alarm - very - sometimes - not | 40 | 30_reliable_alarm_very_sometimes | |
|
|
| 31 | alarmy - thank - premium - wake - much | 37 | 31_alarmy_thank_premium_wake | |
|
|
| 32 | application - student - very - excellent - study | 31 | 32_application_student_very_excellent | |
|
|
| 33 | exit - message - quote - love - smile | 28 | 33_exit_message_quote_love | |
|
|
| 34 | paywall - behind - lock - feature - real | 25 | 34_paywall_behind_lock_feature | |
|
|
| 35 | mb - space - storage - size - take | 22 | 35_mb_space_storage_size | |
|
|
| 36 | easy - set - setup - up - to | 21 | 36_easy_set_setup_up | |
|
|
| 37 | squat - premium - the - mission - do | 21 | 37_squat_premium_the_mission | |
|
|
| 38 | overheat - hot - phone - heat - run | 19 | 38_overheat_hot_phone_heat | |
|
|
| 39 | star - give - deserve - it - scarey | 18 | 39_star_give_deserve_it | |
|
|
| 40 | add - instal - pretty - plaster - interfaceit | 16 | 40_add_instal_pretty_plaster | |
|
|
| 41 | uninstall - deactivate - logo - not - let | 14 | 41_uninstall_deactivate_logo_not | |
|
|
| 42 | develper - legend - describe - word - clear | 13 | 42_develper_legend_describe_word | |
|
|
| 43 | team - thank - alarmy - lot - help | 13 | 43_team_thank_alarmy_lot | |
|
|
| 44 | update - ui - the - version - new | 13 | 44_update_ui_the_version | |
|
|
| 45 | love - get - perfect - time - thay | 13 | 45_love_get_perfect_time | |
|
|
| 46 | scare - medication - it - weapon - secret | 12 | 46_scare_medication_it_weapon | |
|
|
| 47 | accurate - dependable - 8n - fashion - ti | 11 | 47_accurate_dependable_8n_fashion | |
|
|
| 48 | procrastinator - exms - help - anoye - hv | 11 | 48_procrastinator_exms_help_anoye | |
|
|
|
|
|
</details> |
|
|
|
|
|
## Training hyperparameters |
|
|
|
|
|
* calculate_probabilities: False |
|
|
* language: english |
|
|
* low_memory: False |
|
|
* min_topic_size: 10 |
|
|
* n_gram_range: (1, 1) |
|
|
* nr_topics: 50 |
|
|
* seed_topic_list: None |
|
|
* top_n_words: 10 |
|
|
* verbose: False |
|
|
* zeroshot_min_similarity: 0.85 |
|
|
* zeroshot_topic_list: ['android', 'premium*', 'ads', 'math', 'subscription', 'update', 'camera', 'shake', 'weather', 'snooze', 'loud', 'doesn', 'off'] |
|
|
|
|
|
## Framework versions |
|
|
|
|
|
* Numpy: 1.26.4 |
|
|
* HDBSCAN: 0.8.38.post1 |
|
|
* UMAP: 0.5.6 |
|
|
* Pandas: 2.2.1 |
|
|
* Scikit-Learn: 1.5.1 |
|
|
* Sentence-transformers: 3.0.1 |
|
|
* Transformers: 4.44.0 |
|
|
* Numba: 0.60.0 |
|
|
* Plotly: 5.23.0 |
|
|
* Python: 3.10.14 |
|
|
|
