Fine-tuned Topic Model for aspects_to_improve column

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+ctfidf_config.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,129 @@
+
+---
+tags:
+- bertopic
+library_name: bertopic
+pipeline_tag: text-classification
+---
+
+# after_covid_face_to_face_aspects_to_improve
+
+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("ShivamSrng/after_covid_face_to_face_aspects_to_improve")
+
+topic_model.get_topic_info()
+```
+
+## Topic overview
+
+* Number of topics: 60
+* Number of training documents: 76623
+
+<details>
+  <summary>Click here for an overview of all topics.</summary>
+  
+  | Topic ID | Topic Keywords | Topic Frequency | Label | 
+|----------|----------------|-----------------|-------| 
+| 0 | practice problems - grading - common exams - grades - improve | 53887 | 0_practice problems_grading_common exams_grades | 
+| 1 | lab reports - lab assignments - labs class - lab reports lab - class labs | 3550 | 1_lab reports_lab assignments_labs class_lab reports lab | 
+| 2 | ramblings cheers dallas - ramblings cheers dallas cowboys - cheers dallas cowboys year - lectures ramblings cheers dallas - cheers dallas cowboys | 522 | 2_ramblings cheers dallas_ramblings cheers dallas cowboys_cheers dallas cowboys year_lectures ramblings cheers dallas | 
+| 3 | class everything - class needs structure - helpful class way - purpose class - class needs | 508 | 3_class everything_class needs structure_helpful class way_purpose class | 
+| 4 | web development - softwares - technologies - implementation - data analytics | 503 | 4_web development_softwares_technologies_implementation | 
+| 5 | way misunderstands deliverable approach - misunderstands deliverable approach - way misunderstands deliverable - misunderstands deliverable - having entire role unfair | 486 | 5_way misunderstands deliverable approach_misunderstands deliverable approach_way misunderstands deliverable_misunderstands deliverable | 
+| 6 | research create highquality - case studies - economics ethics actual engineering - research - research create highquality scientificallyaccurate | 464 | 6_research create highquality_case studies_economics ethics actual engineering_research | 
+| 7 | calculators - calculator - calculations formulas - formula sheets - math formulas | 457 | 7_calculators_calculator_calculations formulas_formula sheets | 
+| 8 | teach matlab - teaching matlab - matlab taught class - students matlab - matlab taught | 445 | 8_teach matlab_teaching matlab_matlab taught class_students matlab | 
+| 9 | using creo - software - mylab mandatory installing - different software - vmware | 426 | 9_using creo_software_mylab mandatory installing_different software | 
+| 10 | material difficult - material challenging - materials better - approach materials - material needs | 393 | 10_material difficult_material challenging_materials better_approach materials | 
+| 11 | maybe movies - films - maybe mention oddities - maybe mention oddities life - film | 385 | 11_maybe movies_films_maybe mention oddities_maybe mention oddities life | 
+| 12 | class review exams - class review - review material exams - class review sessions - exam reviews | 383 | 12_class review exams_class review_review material exams_class review sessions | 
+| 13 | grade conclude keeps hostage - understand lab activity - understand lab activity approached - mentioned assigned lab activities - microscopes need repaired | 382 | 13_grade conclude keeps hostage_understand lab activity_understand lab activity approached_mentioned assigned lab activities | 
+| 14 | lab equipment outdated - better lab equipment - lab equipment better - equipment better lab - lab equipment old | 382 | 14_lab equipment outdated_better lab equipment_lab equipment better_equipment better lab | 
+| 15 | schedule felt disrespectful availability - schedule felt disrespectful - release schedule felt disrespectful - felt disrespectful availability advisor - disrespectful availability advisor | 381 | 15_schedule felt disrespectful availability_schedule felt disrespectful_release schedule felt disrespectful_felt disrespectful availability advisor | 
+| 16 | instructor studio critic - studio curriculum - studio classes - studio difficult - studio students | 379 | 16_instructor studio critic_studio curriculum_studio classes_studio difficult | 
+| 17 | prototyping - drawings projects - drawings class - model making - cad drawings | 378 | 17_prototyping_drawings projects_drawings class_model making | 
+| 18 | questions requires paying attention - understanding everything - understand asking based - understand asking based wording - homework problem word arbitrary | 373 | 18_questions requires paying attention_understanding everything_understand asking based_understand asking based wording | 
+| 19 | students software - students stay current remote - students access - provide students - available students | 371 | 19_students software_students stay current remote_students access_provide students | 
+| 20 | examples needs - examples help - examples help understand - examples helpful - need examples | 366 | 20_examples needs_examples help_examples help understand_examples helpful | 
+| 21 | class hard understand professor - everything class hard understand - everything professor - enjoyed class - great professor class | 362 | 21_class hard understand professor_everything class hard understand_everything professor_enjoyed class | 
+| 22 | vocareum terrible feedback wrong - vocareum terrible feedback - feedback wrong simply - having warning set instructor - simply having warning set | 358 | 22_vocareum terrible feedback wrong_vocareum terrible feedback_feedback wrong simply_having warning set instructor | 
+| 23 | industry projects - students looking internships jobs - career development - students looking internships - resumes | 356 | 23_industry projects_students looking internships jobs_career development_students looking internships | 
+| 24 | writing essays engineering - writing essays engineering topics - essays engineering topics - essays engineering - involved writing essays engineering | 354 | 24_writing essays engineering_writing essays engineering topics_essays engineering topics_essays engineering | 
+| 25 | architecture students - architecture taught - design courses - engineering design courses - design students | 353 | 25_architecture students_architecture taught_design courses_engineering design courses | 
+| 26 | office hours having time - office hours - office hours having - office hours nice independent - office hour | 353 | 26_office hours having time_office hours_office hours having_office hours nice independent | 
+| 27 | suggestions - suggestions think - suggestions right - suggestions right suggestions right - think suggestions | 347 | 27_suggestions_suggestions think_suggestions right_suggestions right suggestions right | 
+| 28 | physics classes - physics courses - mastering physics - students physics - physics class | 337 | 28_physics classes_physics courses_mastering physics_students physics | 
+| 29 | concepts realworld applications - examples realworld applications - real world application - practical examples - applications concepts | 335 | 29_concepts realworld applications_examples realworld applications_real world application_practical examples | 
+| 30 | class attendance policy - attendance policy - students attendance - way attendance taken - taking attendance | 331 | 30_class attendance policy_attendance policy_students attendance_way attendance taken | 
+| 31 | information felt waste time - information content - information felt waste - information harder - dense uninteresting | 331 | 31_information felt waste time_information content_information felt waste_information harder | 
+| 32 | chapter practice - learn chapters - learning chapters - learn chapter - homework chapters | 328 | 32_chapter practice_learn chapters_learning chapters_learn chapter | 
+| 33 | instruction manual needs clear - instructions manual - manual needs clear clearly - instruction manual - diagrams lab manual | 323 | 33_instruction manual needs clear_instructions manual_manual needs clear clearly_instruction manual | 
+| 34 | overwhelming workload - work workload - workload overwhelming - workload decrease - work load work | 319 | 34_overwhelming workload_work workload_workload overwhelming_workload decrease | 
+| 35 | respond classmates postings - forcing discussion - respond classmates postings following - think discussion - discussion posts | 318 | 35_respond classmates postings_forcing discussion_respond classmates postings following_think discussion | 
+| 36 | pearson online homework - pearson homework feel - pearson textbook - students pearson - homework assignments pearson | 317 | 36_pearson online homework_pearson homework feel_pearson textbook_students pearson | 
+| 37 | lecture hall difficult - lecture room - students room - class room - lecture hall class | 311 | 37_lecture hall difficult_lecture room_students room_class room | 
+| 38 | ebnf simply expanded years - simply expanded years pas - expanded years pas different - ebnf simply expanded - research ebnf simply expanded | 305 | 38_ebnf simply expanded years_simply expanded years pas_expanded years pas different_ebnf simply expanded | 
+| 39 | reading assignments week - multiple reading assignments week - reading assignments - readings boring - having multiple reading assignments | 304 | 39_reading assignments week_multiple reading assignments week_reading assignments_readings boring | 
+| 40 | opportunities active duty operations - active duty operations - opportunities active duty - duty operations person commissioning - operations person commissioning | 302 | 40_opportunities active duty operations_active duty operations_opportunities active duty_duty operations person commissioning | 
+| 41 | students notes - notes exams - class better notes - class notes - semester notes | 299 | 41_students notes_notes exams_class better notes_class notes | 
+| 42 | videos beneficial - video lectures - lesson videos - videos lectures - tutorial videos | 297 | 42_videos beneficial_video lectures_lesson videos_videos lectures | 
+| 43 | ideas discussed agreed jury - design ideas discussed agreed - ideas discussed - ideas discussed agreed - enjoyed everything | 297 | 43_ideas discussed agreed jury_design ideas discussed agreed_ideas discussed_ideas discussed agreed | 
+| 44 | time management - time spent section - minutes instead - minutes - minutes questions | 289 | 44_time management_time spent section_minutes instead_minutes | 
+| 45 | difficult difficulty level - difficult difficulty - tedious time consuming - difficult time easier - difficult | 287 | 45_difficult difficulty level_difficult difficulty_tedious time consuming_difficult time easier | 
+| 46 | design process - final critiques interior designers - design development - design work - design project | 287 | 46_design process_final critiques interior designers_design development_design work | 
+| 47 | paper research - choose research paper - write research paper - research writing - research paper write | 276 | 47_paper research_choose research paper_write research paper_research writing | 
+| 48 | nj making students feel - requirements nj making students - covering naab requirements nj - nj making students - covering naab requirements | 268 | 48_nj making students feel_requirements nj making students_covering naab requirements nj_nj making students | 
+| 49 | underneath studio desk avoid - dirty dusty students - studio spaces - studio space - underneath studio desk | 258 | 49_underneath studio desk avoid_dirty dusty students_studio spaces_studio space | 
+| 50 | chem taught - learning chem - chemistry students - courses chem - taking chemistry | 253 | 50_chem taught_learning chem_chemistry students_courses chem | 
+| 51 | pacing felt little fast - think pacing better - pacing little bit slow - bit quick pacing - possible pacing | 244 | 51_pacing felt little fast_think pacing better_pacing little bit slow_bit quick pacing | 
+| 52 | everything great - think everything great - everything everything great - everything alright - everything alright everything | 235 | 52_everything great_think everything great_everything everything great_everything alright | 
+| 53 | midterm using practice exam - prepare midterm - midterm using practice - assessments midterm format learn - practice midterm | 225 | 53_midterm using practice exam_prepare midterm_midterm using practice_assessments midterm format learn | 
+| 54 | recitation assignments taught - recitation assignments relate lecture - recitation class recitation - recitation teaching - recitation class | 216 | 54_recitation assignments taught_recitation assignments relate lecture_recitation class recitation_recitation teaching | 
+| 55 | think way opinion think - think way great - think works way - great way think - way great way think | 206 | 55_think way opinion think_think way great_think works way_great way think | 
+| 56 | critiques - nice far material review - nitpicking experience great - opinion aspects milano beautiful - opinion review nice | 182 | 56_critiques_nice far material review_nitpicking experience great_opinion aspects milano beautiful | 
+| 57 | pearson homework terrible - using pearson - using pearson homework - pearson homeworks - pearson homework horrible | 178 | 57_pearson homework terrible_using pearson_using pearson homework_pearson homeworks | 
+| 58 | personally change - think change best personally - change personally - change everything - personally change change | 173 | 58_personally change_think change best personally_change personally_change everything | 
+| 59 | current state think great - right think opinion great - right think great - think opinion great - think coruse great | 88 | 59_current state think great_right think opinion great_right think great_think opinion great |
+  
+</details>
+
+## Training hyperparameters
+
+* calculate_probabilities: False
+* language: None
+* low_memory: False
+* min_topic_size: 10
+* n_gram_range: (1, 1)
+* nr_topics: auto
+* seed_topic_list: None
+* top_n_words: 7
+* verbose: True
+* zeroshot_min_similarity: 0.7
+* zeroshot_topic_list: None
+
+## Framework versions
+
+* Numpy: 1.26.4
+* HDBSCAN: 0.8.39
+* UMAP: 0.5.7
+* Pandas: 2.2.3
+* Scikit-Learn: 1.5.2
+* Sentence-transformers: 3.2.1
+* Transformers: 4.46.2
+* Numba: 0.60.0
+* Plotly: 5.24.1
+* Python: 3.10.11

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": "auto",
+  "seed_topic_list": null,
+  "top_n_words": 7,
+  "verbose": true,
+  "zeroshot_min_similarity": 0.7,
+  "zeroshot_topic_list": null
+}

ctfidf.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e5b220a78a344ddce307d187cf9b5aaea81fa4a75d1cdc5297aff5a5c1bdf86
+size 24191708

ctfidf_config.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e79605cb71093ea150df77e1805f36bcae52df3fe62cba91d2fbe5bb13560e0
+size 49368777

topic_embeddings.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:343dc508e86b0a77a0973d8b99fe6881e062a2f38da73202f682bd1e33195c0c
+size 184408