--- tags: - bertopic library_name: bertopic pipeline_tag: text-classification --- # BERTopic-gemini-keywords 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("nataliecastro/BERTopic-gemini-keywords") topic_model.get_topic_info() ``` ## Topic overview * Number of topics: 90 * Number of training documents: 4040
Click here for an overview of all topics. | Topic ID | Topic Keywords | Topic Frequency | Label | |----------|----------------|-----------------|-------| | -1 | board - school - policy - covid19 - meeting | 10 | -1_board_school_policy_covid19 | | 0 | revenue - expenditures - budget - finance - funding | 1210 | 0_revenue_expenditures_budget_finance | | 1 | bond - projects - construction - issue - renovations | 196 | 1_bond_projects_construction_issue | | 2 | community - involvement - awards - appreciation - events | 155 | 2_community_involvement_awards_appreciation | | 3 | westminster - public - meeting - of - red | 111 | 3_westminster_public_meeting_of | | 4 | technology - internet - chromebooks - cell - devices | 78 | 4_technology_internet_chromebooks_cell | | 5 | growth - performance - data - scores - test | 76 | 5_growth_performance_data_scores | | 6 | construction - projects - building - costs - project | 75 | 6_construction_projects_building_costs | | 7 | diversity - racism - inclusion - equity - hiring | 74 | 7_diversity_racism_inclusion_equity | | 8 | mental - health - trauma - suicide - support | 68 | 8_mental_health_trauma_suicide | | 9 | sports - athletics - athletic - athletes - coach | 58 | 9_sports_athletics_athletic_athletes | | 10 | mask - mandates - mandate - parental - concerns | 57 | 10_mask_mandates_mandate_parental | | 11 | transportation - bus - drivers - routes - buses | 54 | 11_transportation_bus_drivers_routes | | 12 | family - parent - engagement - involvement - partnerships | 52 | 12_family_parent_engagement_involvement | | 13 | comment - comments - public - procedures - board | 51 | 13_comment_comments_public_procedures | | 14 | salary - negotiations - contract - compensation - teacher | 48 | 14_salary_negotiations_contract_compensation | | 15 | audit - financial - statements - pension - internal | 43 | 15_audit_financial_statements_pension | | 16 | greeley - evans - west - proclamation - scholarship | 39 | 16_greeley_evans_west_proclamation | | 17 | partnerships - community - engagement - collaboration - success | 38 | 17_partnerships_community_engagement_collaboration | | 18 | bullying - prevention - contest - poster - discipline | 37 | 18_bullying_prevention_contest_poster | | 19 | reopening - covid19 - safety - measures - guidelines | 37 | 19_reopening_covid19_safety_measures | | 20 | preschool - early - childhood - kindergarten - fullday | 37 | 20_preschool_early_childhood_kindergarten | | 21 | rate - dropout - graduation - rates - attendance | 36 | 21_rate_dropout_graduation_rates | | 22 | mill - levy - expenditures - charter - finance | 36 | 22_mill_levy_expenditures_charter | | 23 | thompson - staff - introductions - recognition - dr | 35 | 23_thompson_staff_introductions_recognition | | 24 | bilingual - language - translation - seal - bilingualism | 35 | 24_bilingual_language_translation_seal | | 25 | mask - masks - mandate - health - safety | 33 | 25_mask_masks_mandate_health | | 26 | charter - classical - complaint - values - policy | 32 | 26_charter_classical_complaint_values | | 27 | special - services - education - iep - staffing | 32 | 27_special_services_education_iep | | 28 | sro - sros - police - resource - discipline | 31 | 28_sro_sros_police_resource | | 29 | emotional - socialemotional - social - learning - sel | 31 | 29_emotional_socialemotional_social_learning | | 30 | lgbtq - transgender - identity - gender - rights | 30 | 30_lgbtq_transgender_identity_gender | | 31 | colorado - bills - amendment - funding - legislative | 30 | 31_colorado_bills_amendment_funding | | 32 | impact - covid19 - act - cares - budget | 29 | 32_impact_covid19_act_cares | | 33 | covid19 - response - recognition - challenges - covid | 29 | 33_covid19_response_recognition_challenges | | 34 | closure - closures - capacity - cuts - master | 28 | 34_closure_closures_capacity_cuts | | 35 | remote - learning - digital - schedules - online | 28 | 35_remote_learning_digital_schedules | | 36 | security - safety - measures - drills - communication | 28 | 36_security_safety_measures_drills | | 37 | cte - career - pathways - workbased - and | 27 | 37_cte_career_pathways_workbased | | 38 | adoption - curriculum - studies - resources - pilot | 27 | 38_adoption_curriculum_studies_resources | | 39 | literacy - math - reading - mathematics - assessments | 26 | 39_literacy_math_reading_mathematics | | 40 | valley - boulder - participation - superintendent - report | 26 | 40_valley_boulder_participation_superintendent | | 41 | agenda - consent - session - legislative - meeting | 26 | 41_agenda_consent_session_legislative | | 42 | leadership - transformation - outcomes - turnaround - leader | 25 | 42_leadership_transformation_outcomes_turnaround | | 43 | equity - visas - council - honor - national | 25 | 43_equity_visas_council_honor | | 44 | air - conditioning - cooling - heat - solutions | 24 | 44_air_conditioning_cooling_heat | | 45 | vaccination - case - masking - numbers - vaccines | 24 | 45_vaccination_case_masking_numbers | | 46 | contract - contracts - matters - superintendent - approval | 23 | 46_contract_contracts_matters_superintendent | | 47 | colorado - finance - budget - k12 - economy | 23 | 47_colorado_finance_budget_k12 | | 48 | strategic - plan - goals - planning - action | 23 | 48_strategic_plan_goals_planning | | 49 | nutrition - food - meals - pantry - meal | 22 | 49_nutrition_food_meals_pantry | | 50 | remote - learning - covid19 - attendance - inperson | 21 | 50_remote_learning_covid19_attendance | | 51 | quarantine - cases - tracing - quarantines - testing | 21 | 51_quarantine_cases_tracing_quarantines | | 52 | vaccine - mask - mandates - vaccines - mandate | 21 | 52_vaccine_mask_mandates_vaccines | | 53 | literacy - reading - curriculum - recommendations - parton | 21 | 53_literacy_reading_curriculum_recommendations | | 54 | online - enrollment - program - trends - advocacy | 20 | 54_online_enrollment_program_trends | | 55 | adjournment - motions - agenda - meeting - motion | 20 | 55_adjournment_motions_agenda_meeting | | 56 | teachers - students - academy - learning - teaching | 20 | 56_teachers_students_academy_learning | | 57 | fees - course - textbooks - athletic - athletics | 19 | 57_fees_course_textbooks_athletic | | 58 | donations - foundation - hires - day - picnic | 19 | 58_donations_foundation_hires_day | | 59 | professional - development - training - educator - evaluation | 18 | 59_professional_development_training_educator | | 60 | pandemic - safety - covid19 - cases - mou | 18 | 60_pandemic_safety_covid19_cases | | 61 | requirements - technical - fine - graduation - career | 17 | 61_requirements_technical_fine_graduation | | 62 | benefits - insurance - employee - healthcare - cost | 17 | 62_benefits_insurance_employee_healthcare | | 63 | dyslexia - reading - intervention - special - wilson | 17 | 63_dyslexia_reading_intervention_special | | 64 | vaccination - reopening - variants - vaccinations - vaccine | 17 | 64_vaccination_reopening_variants_vaccinations | | 65 | marijuana - medical - vaping - regulation - tax | 17 | 65_marijuana_medical_vaping_regulation | | 66 | cameras - security - privacy - surveillance - raptor | 16 | 66_cameras_security_privacy_surveillance | | 67 | property - mill - levy - assessed - taxes | 16 | 67_property_mill_levy_assessed | | 68 | the - engagement - facility - grace - priorities | 16 | 68_the_engagement_facility_grace | | 69 | sustainability - energy - environment - waste - efficiency | 16 | 69_sustainability_energy_environment_waste | | 70 | funding - opportunities - micro - private - philanthropy | 15 | 70_funding_opportunities_micro_private | | 71 | avid - ib - ap - program - college | 15 | 71_avid_ib_ap_program | | 72 | cultural - proficiency - inclusive - climate - culture | 14 | 72_cultural_proficiency_inclusive_climate | | 73 | gifted - english - language - identification - and | 14 | 73_gifted_english_language_identification | | 74 | geothermal - project - costs - pvc - timeline | 14 | 74_geothermal_project_costs_pvc | | 75 | items - agenda - housekeeping - member - meetings | 14 | 75_items_agenda_housekeeping_member | | 76 | ix - title - harassment - sexual - compliance | 14 | 76_ix_title_harassment_sexual | | 77 | wellness - schoolbased - healthcare - health - sunrise | 13 | 77_wellness_schoolbased_healthcare_health | | 78 | turnover - teacher - shortage - employee - retention | 13 | 78_turnover_teacher_shortage_employee | | 79 | mental - health - impact - covid19 - inperson | 13 | 79_mental_health_impact_covid19 | | 80 | reopening - phases - models - teachers - 91 | 13 | 80_reopening_phases_models_teachers | | 81 | land - property - purchase - easement - use | 13 | 81_land_property_purchase_easement | | 82 | head - start - childhood - early - assessment | 13 | 82_head_start_childhood_early | | 83 | safety - lead - snow - drinking - experiences | 12 | 83_safety_lead_snow_drinking | | 84 | scholarships - scholarship - teachers - dream - announcements | 12 | 84_scholarships_scholarship_teachers_dream | | 85 | religion - bible - curriculum - god - antiamericanism | 11 | 85_religion_bible_curriculum_god | | 86 | transparency - requests - information - cora - website | 11 | 86_transparency_requests_information_cora | | 87 | one - with - the - legislative - highlighting | 11 | 87_one_with_the_legislative | | 88 | holiday - calendar - greetings - holidays - calendars | 10 | 88_holiday_calendar_greetings_holidays |
## Training hyperparameters * calculate_probabilities: True * language: english * low_memory: False * min_topic_size: 10 * n_gram_range: (1, 1) * nr_topics: None * seed_topic_list: None * top_n_words: 10 * verbose: True * zeroshot_min_similarity: 0.7 * zeroshot_topic_list: None ## Framework versions * Numpy: 1.24.3 * HDBSCAN: 0.8.29 * UMAP: 0.5.6 * Pandas: 1.5.3 * Scikit-Learn: 1.2.2 * Sentence-transformers: 3.1.0 * Transformers: 4.44.2 * Numba: 0.57.0 * Plotly: 5.9.0 * Python: 3.10.12