ShivamSrng commited on
Commit
ffab4e3
1 Parent(s): 46ff499

Fine-tuned Topic Model for best_features column

Browse files
README.md ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+
2
+ ---
3
+ tags:
4
+ - bertopic
5
+ library_name: bertopic
6
+ pipeline_tag: text-classification
7
+ ---
8
+
9
+ # before_covid_distance_learning_best_features
10
+
11
+ This is a [BERTopic](https://github.com/MaartenGr/BERTopic) model.
12
+ BERTopic is a flexible and modular topic modeling framework that allows for the generation of easily interpretable topics from large datasets.
13
+
14
+ ## Usage
15
+
16
+ To use this model, please install BERTopic:
17
+
18
+ ```
19
+ pip install -U bertopic
20
+ ```
21
+
22
+ You can use the model as follows:
23
+
24
+ ```python
25
+ from bertopic import BERTopic
26
+ topic_model = BERTopic.load("ShivamSrng/before_covid_distance_learning_best_features")
27
+
28
+ topic_model.get_topic_info()
29
+ ```
30
+
31
+ ## Topic overview
32
+
33
+ * Number of topics: 64
34
+ * Number of training documents: 13320
35
+
36
+ <details>
37
+ <summary>Click here for an overview of all topics.</summary>
38
+
39
+ | Topic ID | Topic Keywords | Topic Frequency | Label |
40
+ |----------|----------------|-----------------|-------|
41
+ | 0 | online class - lecture - lectures - class online - courses | 9409 | 0_online class_lecture_lectures_class online |
42
+ | 1 | project management learning project - management learning project management - project delivery according - project delivery - project management | 345 | 1_project management learning project_management learning project management_project delivery according_project delivery |
43
+ | 2 | waste money time - nope waste money time - waste money - recall future rewatching - nope waste money | 130 | 2_waste money time_nope waste money time_waste money_recall future rewatching |
44
+ | 3 | dbms - learn databases - learning database - useful learn sql - hands experience sql | 107 | 3_dbms_learn databases_learning database_useful learn sql |
45
+ | 4 | psychology internet aspects thought - psychology internet aspects - psychology related online media - cyberpsychology - psychology related online | 97 | 4_psychology internet aspects thought_psychology internet aspects_psychology related online media_cyberpsychology |
46
+ | 5 | construction learning - construction learn - learning construction - construction management - looked construction helps developing | 93 | 5_construction learning_construction learn_learning construction_construction management |
47
+ | 6 | professional writing future class - technical writing important - professional writing technical - technical writing - professional writing technical fields | 90 | 6_professional writing future class_technical writing important_professional writing technical_technical writing |
48
+ | 7 | learning linux - software learning - softwares learning - learning software - tools learning | 89 | 7_learning linux_software learning_softwares learning_learning software |
49
+ | 8 | applying ethical theories - practicing applying ethical theories - applying ethical theories scenarios - learning ethics - ethics learning | 87 | 8_applying ethical theories_practicing applying ethical theories_applying ethical theories scenarios_learning ethics |
50
+ | 9 | programming assignments learning computer - programming assignments learning - programming assignments good - learning code - programming assignments | 84 | 9_programming assignments learning computer_programming assignments learning_programming assignments good_learning code |
51
+ | 10 | pharmaceutical industry concepts things - pharmaceutical industry concepts - pharmaceutical facility design industry - industry material - product development | 77 | 10_pharmaceutical industry concepts things_pharmaceutical industry concepts_pharmaceutical facility design industry_industry material |
52
+ | 11 | mark helpful knowledgeable approachable - written work extremely - thoughtful responsive mark - thoughtful responsive - thinking skills listens cares | 74 | 11_mark helpful knowledgeable approachable_written work extremely_thoughtful responsive mark_thoughtful responsive |
53
+ | 12 | perspectives multiculturalism - perspectives multiculturalism means different - perspectives multiculturalism means - understanding race - perspectives complex ethical | 72 | 12_perspectives multiculturalism_perspectives multiculturalism means different_perspectives multiculturalism means_understanding race |
54
+ | 13 | moodle online class - moodle site - needed moodle homework assignments - lectures available moodle - moodle lectures | 70 | 13_moodle online class_moodle site_needed moodle homework assignments_lectures available moodle |
55
+ | 14 | case studies assignments - case studies interesting - helpful case studies - presentation case studies helps - past case studies | 70 | 14_case studies assignments_case studies interesting_helpful case studies_presentation case studies helps |
56
+ | 15 | reading wall street journal - wall street journal articles - wall street journal - daily wall street journal - read wall street journal | 70 | 15_reading wall street journal_wall street journal articles_wall street journal_daily wall street journal |
57
+ | 16 | provided helpful study aids - materials required text - semester answer provided - objectives assignments class hw - methods analysis attend | 69 | 16_provided helpful study aids_materials required text_semester answer provided_objectives assignments class hw |
58
+ | 17 | professor miserable loathed class - worst class taken - professor material challenging midterm - class taken professor - professor ta awful taught | 68 | 17_professor miserable loathed class_worst class taken_professor material challenging midterm_class taken professor |
59
+ | 18 | explain material - material explain - material explain material - material applicable - help understand material | 67 | 18_explain material_material explain_material explain material_material applicable |
60
+ | 19 | learn data mining - various data mining - concepts data mining - data mining concepts - different data mining | 65 | 19_learn data mining_various data mining_concepts data mining_data mining concepts |
61
+ | 20 | knowledgeable cares students - lectures great experience bring - knowledgeable cares students learning - teacher helps students cares - teacher helps students | 65 | 20_knowledgeable cares students_lectures great experience bring_knowledgeable cares students learning_teacher helps students cares |
62
+ | 21 | protocols wireless communication learn - wireless networks - protocols wireless communication - networking - projects practical application traffic | 65 | 21_protocols wireless communication learn_wireless networks_protocols wireless communication_networking |
63
+ | 22 | learnt topics corporate finance - learning economics applies - finance - corporate finance - learn finance | 62 | 22_learnt topics corporate finance_learning economics applies_finance_corporate finance |
64
+ | 23 | playing programs creative enjoyed - miniprojects great investment simulator - mode teaching great - projects learning - plus miniprojects | 62 | 23_playing programs creative enjoyed_miniprojects great investment simulator_mode teaching great_projects learning |
65
+ | 24 | enjoy learning experience - information enjoy learning experience - enjoy learning - information enjoy learning - learning things | 62 | 24_enjoy learning experience_information enjoy learning experience_enjoy learning_information enjoy learning |
66
+ | 25 | material learning fundermental html - learn web development - way learn web development - making website learning - learning html | 62 | 25_material learning fundermental html_learn web development_way learn web development_making website learning |
67
+ | 26 | online learning tools convenient - online learning tools - program helps learning - program helps learning process - online ebook connect mcgraw | 61 | 26_online learning tools convenient_online learning tools_program helps learning_program helps learning process |
68
+ | 27 | online aspect offered online - fact online offered online - online online aspect offered - online offered online fact - online ability online fact | 61 | 27_online aspect offered online_fact online offered online_online online aspect offered_online offered online fact |
69
+ | 28 | webex lectures - professor webex lessons class - professor webex meeting week - professor think webex sessions - professor webex lessons | 59 | 28_webex lectures_professor webex lessons class_professor webex meeting week_professor think webex sessions |
70
+ | 29 | weeks lecture test knowledge - weeks lecture test - problems good practice exams - exams assignments - exam questions | 59 | 29_weeks lecture test knowledge_weeks lecture test_problems good practice exams_exams assignments |
71
+ | 30 | group projects - group work - group project - members group projects - work group | 59 | 30_group projects_group work_group project_members group projects |
72
+ | 31 | perspective typical technical courses - prepares job industry classes - njitrutgers purchased material book - online class useful - njitrutgers purchased material | 59 | 31_perspective typical technical courses_prepares job industry classes_njitrutgers purchased material book_online class useful |
73
+ | 32 | quizes module helpful studying - quizzes frequent quizzes assessments - quizzes help learn topics - quizzes help learn - quiztests semester quizzes exams | 58 | 32_quizes module helpful studying_quizzes frequent quizzes assessments_quizzes help learn topics_quizzes help learn |
74
+ | 33 | matlab lessons intuitive - matlab exercises interesting practical - matlab lessons intuitive provide - matlab lessons - matlab implementation office | 56 | 33_matlab lessons intuitive_matlab exercises interesting practical_matlab lessons intuitive provide_matlab lessons |
75
+ | 34 | material useful information resources - practical information helpful life - plethora information topic - resources available - presented information resources refer | 54 | 34_material useful information resources_practical information helpful life_plethora information topic_resources available |
76
+ | 35 | plan involved learn business - business plan - learning business - learning businesses - opportunity develop business plan | 52 | 35_plan involved learn business_business plan_learning business_learning businesses |
77
+ | 36 | power engineer learning - materials power engineer learning - engineering - materials power engineer - power engineer | 51 | 36_power engineer learning_materials power engineer learning_engineering_materials power engineer |
78
+ | 37 | reasonable workload difficult - limited work load - workload manageable - load reasonable work - workloads helps understand | 49 | 37_reasonable workload difficult_limited work load_workload manageable_load reasonable work |
79
+ | 38 | pace learn material - learning pace - pace style learn - pace learning pace straightforward - pace freedom learn | 49 | 38_pace learn material_learning pace_pace style learn_pace learning pace straightforward |
80
+ | 39 | distance learning content - distance learning content available - online assignments online materials - resources distance learning - online learning ease access | 48 | 39_distance learning content_distance learning content available_online assignments online materials_resources distance learning |
81
+ | 40 | skills work online pace - tasks pace work time - time online complete work - tasks pace work - skills work online | 47 | 40_skills work online pace_tasks pace work time_time online complete work_tasks pace work |
82
+ | 41 | professor responsive email genuinely - reachable email professor amazing - quick response emails professor - professor responsive emails questions - professor responsive emails | 47 | 41_professor responsive email genuinely_reachable email professor amazing_quick response emails professor_professor responsive emails questions |
83
+ | 42 | information present easy useful - hectic schedules ease access - understand ease access - tasks information present easy - information present easy | 47 | 42_information present easy useful_hectic schedules ease access_understand ease access_tasks information present easy |
84
+ | 43 | office hours class meetings - meeting time class entire - lectures office hours hold - office hours form lecture - lectures office hours | 46 | 43_office hours class meetings_meeting time class entire_lectures office hours hold_office hours form lecture |
85
+ | 44 | material good useful enjoyed - material good useful - liked practicality material covered - materials covered great - material easy follow material | 45 | 44_material good useful enjoyed_material good useful_liked practicality material covered_materials covered great |
86
+ | 45 | good content interesting applicable - online content relevant interesting - great content easy access - interesting current online content - online content relevant | 45 | 45_good content interesting applicable_online content relevant interesting_great content easy access_interesting current online content |
87
+ | 46 | marketing research learning various - learning marketing - marketing research learning - marketing learning - marketing showing basic concepts | 45 | 46_marketing research learning various_learning marketing_marketing research learning_marketing learning |
88
+ | 47 | requirements engineering - learning concepts requirements engineering - methodologies describing - learning various cases designing - business process | 43 | 47_requirements engineering_learning concepts requirements engineering_methodologies describing_learning various cases designing |
89
+ | 48 | management skills best feature - feature online best feature - best feature - best feature getting - best feature online | 43 | 48_management skills best feature_feature online best feature_best feature_best feature getting |
90
+ | 49 | class useful - involved class great classes - feature class love - feature class useful - new platforms class beneficial | 43 | 49_class useful_involved class great classes_feature class love_feature class useful |
91
+ | 50 | environmental law - environmental laws - njspecific remediation topics - njspecific remediation topics lsrp - new jersey statelevel regulationstopics | 43 | 50_environmental law_environmental laws_njspecific remediation topics_njspecific remediation topics lsrp |
92
+ | 51 | quickly professor responds - professor responds quickly - quickly professor responded students - quickly professor responds emails - professors quick response time | 42 | 51_quickly professor responds_professor responds quickly_quickly professor responded students_quickly professor responds emails |
93
+ | 52 | patient assistance received project - pharmaceutical industry phenomenal educator - patient assistance received - patient assistance - material longo great professor | 42 | 52_patient assistance received project_pharmaceutical industry phenomenal educator_patient assistance received_patient assistance |
94
+ | 53 | informative structured material organized - notes organized online - organized assignments communicated - organized informative structured material - online notes organized online | 41 | 53_informative structured material organized_notes organized online_organized assignments communicated_organized informative structured material |
95
+ | 54 | homework time finish assignments - time finish assignments - homeworks time usually online - lots time finish assignments - assignments time | 39 | 54_homework time finish assignments_time finish assignments_homeworks time usually online_lots time finish assignments |
96
+ | 55 | practical information security auditing - information security auditing - opportunity learn computer auditing - security auditing - network security helps analyse | 38 | 55_practical information security auditing_information security auditing_opportunity learn computer auditing_security auditing |
97
+ | 56 | pace important freedom work - instead having deadlines flexibility - complete work pace - manner allows work pace - instead having deadlines | 38 | 56_pace important freedom work_instead having deadlines flexibility_complete work pace_manner allows work pace |
98
+ | 57 | methods involved decision analysis - methodology decision analysis - operations research - managers decisionmakers helpful calculate - decision analysis | 36 | 57_methods involved decision analysis_methodology decision analysis_operations research_managers decisionmakers helpful calculate |
99
+ | 58 | requires critical thinking student - critical thinking - questions essays approach required - questions essays - questions essays approach | 36 | 58_requires critical thinking student_critical thinking_questions essays approach required_questions essays |
100
+ | 59 | taking learned totally worthless - learned totally worthless good - learned totally worthless - educational value learn value - taking learned totally | 36 | 59_taking learned totally worthless_learned totally worthless good_learned totally worthless_educational value learn value |
101
+ | 60 | subpar audio visual quality - quality subpar audio visual - audio visual quality subpar - subpar audio visual - visual quality subpar audio | 26 | 60_subpar audio visual quality_quality subpar audio visual_audio visual quality subpar_subpar audio visual |
102
+ | 61 | learn important data structure - improving data structure concepts - important data structure concepts - mainly data structures - data structures | 23 | 61_learn important data structure_improving data structure concepts_important data structure concepts_mainly data structures |
103
+ | 62 | professors reasons lose - professors reasons governor - professor expected evident supervised - professor obviously extremely knowledgeable - professors professors reasons lose | 22 | 62_professors reasons lose_professors reasons governor_professor expected evident supervised_professor obviously extremely knowledgeable |
104
+ | 63 | biomedical ethics - good articles ethics biomedical - field opened ethics pertaining - learned history issues medical - field opened ethics | 21 | 63_biomedical ethics_good articles ethics biomedical_field opened ethics pertaining_learned history issues medical |
105
+
106
+ </details>
107
+
108
+ ## Training hyperparameters
109
+
110
+ * calculate_probabilities: False
111
+ * language: None
112
+ * low_memory: False
113
+ * min_topic_size: 10
114
+ * n_gram_range: (1, 1)
115
+ * nr_topics: auto
116
+ * seed_topic_list: None
117
+ * top_n_words: 7
118
+ * verbose: True
119
+ * zeroshot_min_similarity: 0.7
120
+ * zeroshot_topic_list: None
121
+
122
+ ## Framework versions
123
+
124
+ * Numpy: 1.26.4
125
+ * HDBSCAN: 0.8.39
126
+ * UMAP: 0.5.7
127
+ * Pandas: 2.2.3
128
+ * Scikit-Learn: 1.5.2
129
+ * Sentence-transformers: 3.2.1
130
+ * Transformers: 4.46.2
131
+ * Numba: 0.60.0
132
+ * Plotly: 5.24.1
133
+ * Python: 3.10.11
config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "calculate_probabilities": false,
3
+ "language": null,
4
+ "low_memory": false,
5
+ "min_topic_size": 10,
6
+ "n_gram_range": [
7
+ 1,
8
+ 1
9
+ ],
10
+ "nr_topics": "auto",
11
+ "seed_topic_list": null,
12
+ "top_n_words": 7,
13
+ "verbose": true,
14
+ "zeroshot_min_similarity": 0.7,
15
+ "zeroshot_topic_list": null
16
+ }
ctfidf.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b02b53aab7e0e8a72df0c61e19bf09157e4e7f50806b0bbf6246985e2d3ff0e1
3
+ size 4145076
ctfidf_config.json ADDED
The diff for this file is too large to render. See raw diff
 
topic_embeddings.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b613de5da4e63e6c9cc7562d31ccc2f93d045f9e5ec788a94dee45d61029405
3
+ size 196696
topics.json ADDED
The diff for this file is too large to render. See raw diff