semiotic/sql_templates

--- dataset_info: features: - name: datasource_id dtype: string - name: datasource_type dtype: string - name: query_template_id dtype: int64 - name: database_ids struct: - name: aan_1 dtype: int64 - name: activity_1 dtype: int64 - name: address_1 dtype: int64 - name: advertising_agencies dtype: int64 - name: aircraft dtype: int64 - name: allergy_1 dtype: int64 - name: apartment_rentals dtype: int64 - name: architecture dtype: int64 - name: art_1 dtype: int64 - name: assets_maintenance dtype: int64 - name: bakery_1 dtype: int64 - name: baseball_1 dtype: int64 - name: battle_death dtype: int64 - name: bbc_channels dtype: int64 - name: behavior_monitoring dtype: int64 - name: bike_1 dtype: int64 - name: bike_racing dtype: int64 - name: boat_1 dtype: int64 - name: body_builder dtype: int64 - name: book_1 dtype: int64 - name: book_2 dtype: int64 - name: book_press dtype: int64 - name: book_review dtype: int64 - name: browser_web dtype: int64 - name: candidate_poll dtype: int64 - name: car_1 dtype: int64 - name: car_racing dtype: int64 - name: car_road_race dtype: int64 - name: chinook_1 dtype: int64 - name: cinema dtype: int64 - name: city_record dtype: int64 - name: climbing dtype: int64 - name: club_1 dtype: int64 - name: club_leader dtype: int64 - name: coffee_shop dtype: int64 - name: college_1 dtype: int64 - name: college_2 dtype: int64 - name: college_3 dtype: int64 - name: company_1 dtype: int64 - name: company_employee dtype: int64 - name: company_office dtype: int64 - name: concert_singer dtype: int64 - name: conference dtype: int64 - name: country_language dtype: int64 - name: county_public_safety dtype: int64 - name: course_teach dtype: int64 - name: cre_Doc_Control_Systems dtype: int64 - name: cre_Doc_Template_Mgt dtype: int64 - name: cre_Doc_Tracking_DB dtype: int64 - name: cre_Doc_Workflow dtype: int64 - name: cre_Doc_and_collections dtype: int64 - name: cre_Docs_and_Epenses dtype: int64 - name: cre_Drama_Workshop_Groups dtype: int64 - name: cre_Students_Information_Systems dtype: int64 - name: cre_Theme_park dtype: int64 - name: csu_1 dtype: int64 - name: culture_company dtype: int64 - name: customer_complaints dtype: int64 - name: customer_deliveries dtype: int64 - name: customers_and_addresses dtype: int64 - name: customers_and_invoices dtype: int64 - name: customers_and_orders dtype: int64 - name: customers_and_products_contacts dtype: int64 - name: customers_campaigns_ecommerce dtype: int64 - name: customers_card_transactions dtype: int64 - name: debate dtype: int64 - name: decoration_competition dtype: int64 - name: department_management dtype: int64 - name: department_store dtype: int64 - name: device dtype: int64 - name: district_spokesman dtype: int64 - name: document_management dtype: int64 - name: dog_kennels dtype: int64 - name: dorm_1 dtype: int64 - name: driving_school dtype: int64 - name: e_commerce dtype: int64 - name: e_government dtype: int64 - name: e_learning dtype: int64 - name: election dtype: int64 - name: election_representative dtype: int64 - name: employee_hire_evaluation dtype: int64 - name: entertainment_awards dtype: int64 - name: entrepreneur dtype: int64 - name: epinions_1 dtype: int64 - name: farm dtype: int64 - name: film_rank dtype: int64 - name: flight_1 dtype: int64 - name: flight_2 dtype: int64 - name: flight_4 dtype: int64 - name: flight_company dtype: int64 - name: formula_1 dtype: int64 - name: game_1 dtype: int64 - name: game_injury dtype: int64 - name: gas_company dtype: int64 - name: government_shift dtype: int64 - name: gymnast dtype: int64 - name: headphone_store dtype: int64 - name: hospital_1 dtype: int64 - name: hr_1 dtype: int64 - name: icfp_1 dtype: int64 - name: inn_1 dtype: int64 - name: institution_sports dtype: int64 - name: insurance_and_eClaims dtype: int64 - name: insurance_fnol dtype: int64 - name: insurance_policies dtype: int64 - name: journal_committee dtype: int64 - name: loan_1 dtype: int64 - name: local_govt_and_lot dtype: int64 - name: local_govt_in_alabama dtype: int64 - name: local_govt_mdm dtype: int64 - name: machine_repair dtype: int64 - name: manufactory_1 dtype: int64 - name: manufacturer dtype: int64 - name: match_season dtype: int64 - name: medicine_enzyme_interaction dtype: int64 - name: mountain_photos dtype: int64 - name: movie_1 dtype: int64 - name: movie_2 dtype: int64 - name: museum_visit dtype: int64 - name: music_1 dtype: int64 - name: music_2 dtype: int64 - name: music_4 dtype: int64 - name: musical dtype: int64 - name: network_1 dtype: int64 - name: network_2 dtype: int64 - name: news_report dtype: int64 - name: online_exams dtype: int64 - name: orchestra dtype: int64 - name: party_host dtype: int64 - name: party_people dtype: int64 - name: performance_attendance dtype: int64 - name: perpetrator dtype: int64 - name: pets_1 dtype: int64 - name: phone_1 dtype: int64 - name: phone_market dtype: int64 - name: pilot_1 dtype: int64 - name: pilot_record dtype: int64 - name: planet_1 dtype: int64 - name: poker_player dtype: int64 - name: product_catalog dtype: int64 - name: products_for_hire dtype: int64 - name: products_gen_characteristics dtype: int64 - name: program_share dtype: int64 - name: protein_institute dtype: int64 - name: race_track dtype: int64 - name: railway dtype: int64 - name: real_estate_properties dtype: int64 - name: real_estate_rentals dtype: int64 - name: region_building dtype: int64 - name: restaurant_1 dtype: int64 - name: restaurant_bills dtype: int64 - name: riding_club dtype: int64 - name: roller_coaster dtype: int64 - name: sakila_1 dtype: int64 - name: school_bus dtype: int64 - name: school_finance dtype: int64 - name: school_player dtype: int64 - name: scientist_1 dtype: int64 - name: ship_1 dtype: int64 - name: ship_mission dtype: int64 - name: shop_membership dtype: int64 - name: sing_contest dtype: int64 - name: singer dtype: int64 - name: small_bank_1 dtype: int64 - name: soccer_1 dtype: int64 - name: soccer_2 dtype: int64 - name: soccer_3 dtype: int64 - name: solvency_ii dtype: int64 - name: sports_competition dtype: int64 - name: station_weather dtype: int64 - name: store_1 dtype: int64 - name: store_product dtype: int64 - name: storm_record dtype: int64 - name: student_1 dtype: int64 - name: student_assessment dtype: int64 - name: student_transcripts_tracking dtype: int64 - name: swimming dtype: int64 - name: theme_gallery dtype: int64 - name: tracking_grants_for_research dtype: int64 - name: tracking_orders dtype: int64 - name: tracking_share_transactions dtype: int64 - name: tracking_software_problems dtype: int64 - name: train_station dtype: int64 - name: tv_shows dtype: int64 - name: tvshow dtype: int64 - name: twitter_1 dtype: int64 - name: university_basketball dtype: int64 - name: university_rank dtype: int64 - name: vehicle_driver dtype: int64 - name: vehicle_rent dtype: int64 - name: video_game dtype: int64 - name: voter_1 dtype: int64 - name: voter_2 dtype: int64 - name: warehouse_1 dtype: int64 - name: wedding dtype: int64 - name: wine_1 dtype: int64 - name: workshop_paper dtype: int64 - name: world_1 dtype: int64 - name: wrestler dtype: int64 - name: wta_1 dtype: int64 - name: query_template dtype: string splits: - name: train num_bytes: 2793662 num_examples: 1610 download_size: 203205 dataset_size: 2793662 configs: - config_name: default data_files: - split: train path: data/train-* --- - **datasource_id**: The Huggingface Dataset where the template originated from. - **query_template_id**: A unique id tied to the datasource_id. - **database_ids**: A struct that maps dataset names to the count of occurrences of the template for that dataset. - **query_template**: The query template value.

原始信息汇总

数据集概述

数据集特征

• datasource_id: 数据源ID，数据类型为字符串。
• datasource_type: 数据源类型，数据类型为字符串。
• query_template_id: 查询模板ID，数据类型为整数（int64）。
• database_ids: 一个结构体，包含多个数据集名称及其对应的模板出现次数，数据类型均为整数（int64）。具体包括：
  • aan_1
  • activity_1
  • address_1
  • advertising_agencies
  • aircraft
  • allergy_1
  • apartment_rentals
  • architecture
  • art_1
  • assets_maintenance
  • bakery_1
  • baseball_1
  • battle_death
  • bbc_channels
  • behavior_monitoring
  • bike_1
  • bike_racing
  • boat_1
  • body_builder
  • book_1
  • book_2
  • book_press
  • book_review
  • browser_web
  • candidate_poll
  • car_1
  • car_racing
  • car_road_race
  • chinook_1
  • cinema
  • city_record
  • climbing
  • club_1
  • club_leader
  • coffee_shop
  • college_1
  • college_2
  • college_3
  • company_1
  • company_employee
  • company_office
  • concert_singer
  • conference
  • country_language
  • county_public_safety
  • course_teach
  • cre_Doc_Control_Systems
  • cre_Doc_Template_Mgt
  • cre_Doc_Tracking_DB
  • cre_Doc_Workflow
  • cre_Doc_and_collections
  • cre_Docs_and_Epenses
  • cre_Drama_Workshop_Groups
  • cre_Students_Information_Systems
  • cre_Theme_park
  • csu_1
  • culture_company
  • customer_complaints
  • customer_deliveries
  • customers_and_addresses
  • customers_and_invoices
  • customers_and_orders
  • customers_and_products_contacts
  • customers_campaigns_ecommerce
  • customers_card_transactions
  • debate
  • decoration_competition
  • department_management
  • department_store
  • device
  • district_spokesman
  • document_management
  • dog_kennels
  • dorm_1
  • driving_school
  • e_commerce
  • e_government
  • e_learning
  • election
  • election_representative
  • employee_hire_evaluation
  • entertainment_awards
  • entrepreneur
  • epinions_1
  • farm
  • film_rank
  • flight_1
  • flight_2
  • flight_4
  • flight_company
  • formula_1
  • game_1
  • game_injury
  • gas_company
  • government_shift
  • gymnast
  • headphone_store
  • hospital_1
  • hr_1
  • icfp_1
  • inn_1
  • institution_sports
  • insurance_and_eClaims
  • insurance_fnol
  • insurance_policies
  • journal_committee
  • loan_1
  • local_govt_and_lot
  • local_govt_in_alabama
  • local_govt_mdm
  • machine_repair
  • manufactory_1
  • manufacturer
  • match_season
  • medicine_enzyme_interaction
  • mountain_photos
  • movie_1
  • movie_2
  • museum_visit
  • music_1
  • music_2
  • music_4
  • musical
  • network_1
  • network_2
  • news_report
  • online_exams
  • orchestra
  • party_host
  • party_people
  • performance_attendance
  • perpetrator
  • pets_1
  • phone_1
  • phone_market
  • pilot_1
  • pilot_record
  • planet_1
  • poker_player
  • product_catalog
  • products_for_hire
  • products_gen_characteristics
  • program_share
  • protein_institute
  • race_track
  • railway
  • real_estate_properties
  • real_estate_rentals
  • region_building
  • restaurant_1
  • restaurant_bills
  • riding_club
  • roller_coaster
  • sakila_1
  • school_bus
  • school_finance
  • school_player
  • scientist_1
  • ship_1
  • ship_mission
  • shop_membership
  • sing_contest
  • singer
  • small_bank_1
  • soccer_1
  • soccer_2
  • soccer_3
  • solvency_ii
  • sports_competition
  • station_weather
  • store_1
  • store_product
  • storm_record
  • student_1
  • student_assessment
  • student_transcripts_tracking
  • swimming
  • theme_gallery
  • tracking_grants_for_research
  • tracking_orders
  • tracking_share_transactions
  • tracking_software_problems
  • train_station
  • tv_shows
  • tvshow
  • twitter_1
  • university_basketball
  • university_rank
  • vehicle_driver
  • vehicle_rent
  • video_game
  • voter_1
  • voter_2
  • warehouse_1
  • wedding
  • wine_1
  • workshop_paper
  • world_1
  • wrestler
  • wta_1
• query_template: 查询模板值，数据类型为字符串。

数据集分割

• train: 训练集，包含2793662字节的数据和1610个样本。

数据集大小

• 下载大小: 203205字节。
• 数据集大小: 2793662字节。

配置

• config_name: default
  • data_files:
    • split: train
    • path: data/train-*