p1atdev/stackexchanges

--- license: cc-by-sa-3.0 dataset_info: - config_name: anime.stackexchange.com features: - name: question struct: - name: accepted_answer_id dtype: string - name: answer_count dtype: int64 - name: body dtype: string - name: comment_count dtype: int64 - name: content_license dtype: string - name: creation_date dtype: string - name: favorite_count dtype: int64 - name: id dtype: string - name: last_activity_date dtype: string - name: last_edit_date dtype: string - name: last_editor_user_id dtype: string - name: owner_user_id dtype: string - name: post_type dtype: string - name: score dtype: int64 - name: tags sequence: string - name: title dtype: string - name: view_count dtype: int64 - name: answers list: - name: body dtype: string - name: comment_count dtype: int64 - name: content_license dtype: string - name: creation_date dtype: string - name: id dtype: string - name: last_activity_date dtype: string - name: last_edit_date dtype: string - name: last_editor_user_id dtype: string - name: owner_user_id dtype: string - name: parent_id dtype: string - name: post_type dtype: string - name: score dtype: int64 - name: id dtype: string - name: accepted_answer_id dtype: string - name: popular_answer_id dtype: string splits: - name: train num_bytes: 32533359 num_examples: 12318 download_size: 19104522 dataset_size: 32533359 - config_name: anime.stackexchange.com_simple features: - name: id dtype: string - name: accepted_answer_id dtype: string - name: popular_answer_id dtype: string - name: title dtype: string - name: question_body dtype: string - name: question_score dtype: int64 - name: accepted_answer_body dtype: string - name: accepted_answer_score dtype: int64 - name: popular_answer_body dtype: string - name: popular_answer_score dtype: int64 - name: tags sequence: string splits: - name: train num_bytes: 29800087 num_examples: 12318 download_size: 18536497 dataset_size: 29800087 - config_name: default features: - name: id dtype: string - name: accepted_answer_id dtype: string - name: popular_answer_id dtype: string - name: title dtype: string - name: question_body dtype: string - name: question_score dtype: int64 - name: accepted_answer_body dtype: string - name: accepted_answer_score dtype: int64 - name: popular_answer_body dtype: string - name: popular_answer_score dtype: int64 - name: tags sequence: string splits: - name: anime.stackexchange.com_simple num_bytes: 29800087 num_examples: 12318 - name: japanese.stackexchange.com_simple num_bytes: 67358026 num_examples: 28850 - name: ja.stackoverflow.com_simple num_bytes: 115174959 num_examples: 30820 download_size: 117381584 dataset_size: 212333072 - config_name: ja.stackoverflow.com features: - name: question struct: - name: accepted_answer_id dtype: string - name: answer_count dtype: int64 - name: body dtype: string - name: comment_count dtype: int64 - name: content_license dtype: string - name: creation_date dtype: string - name: favorite_count dtype: int64 - name: id dtype: string - name: last_activity_date dtype: string - name: last_edit_date dtype: string - name: last_editor_user_id dtype: string - name: owner_user_id dtype: string - name: post_type dtype: string - name: score dtype: int64 - name: tags sequence: string - name: title dtype: string - name: view_count dtype: int64 - name: answers list: - name: body dtype: string - name: comment_count dtype: int64 - name: content_license dtype: string - name: creation_date dtype: string - name: id dtype: string - name: last_activity_date dtype: string - name: last_edit_date dtype: string - name: last_editor_user_id dtype: string - name: owner_user_id dtype: string - name: parent_id dtype: string - name: post_type dtype: string - name: score dtype: int64 - name: id dtype: string - name: accepted_answer_id dtype: string - name: popular_answer_id dtype: string splits: - name: train num_bytes: 114614992 num_examples: 30820 download_size: 55495217 dataset_size: 114614992 - config_name: ja.stackoverflow.com_simple features: - name: id dtype: string - name: accepted_answer_id dtype: string - name: popular_answer_id dtype: string - name: title dtype: string - name: question_body dtype: string - name: question_score dtype: int64 - name: accepted_answer_body dtype: string - name: accepted_answer_score dtype: int64 - name: popular_answer_body dtype: string - name: popular_answer_score dtype: int64 - name: tags sequence: string splits: - name: train num_bytes: 115174959 num_examples: 30820 download_size: 57385116 dataset_size: 115174959 - config_name: japanese.stackexchange.com features: - name: question struct: - name: accepted_answer_id dtype: string - name: answer_count dtype: int64 - name: body dtype: string - name: comment_count dtype: int64 - name: content_license dtype: string - name: creation_date dtype: string - name: favorite_count dtype: int64 - name: id dtype: string - name: last_activity_date dtype: string - name: last_edit_date dtype: string - name: last_editor_user_id dtype: string - name: owner_user_id dtype: string - name: post_type dtype: string - name: score dtype: int64 - name: tags sequence: string - name: title dtype: string - name: view_count dtype: int64 - name: answers list: - name: body dtype: string - name: comment_count dtype: int64 - name: content_license dtype: string - name: creation_date dtype: string - name: id dtype: string - name: last_activity_date dtype: string - name: last_edit_date dtype: string - name: last_editor_user_id dtype: string - name: owner_user_id dtype: string - name: parent_id dtype: string - name: post_type dtype: string - name: score dtype: int64 - name: id dtype: string - name: accepted_answer_id dtype: string - name: popular_answer_id dtype: string splits: - name: train num_bytes: 68978827 num_examples: 28850 download_size: 39676257 dataset_size: 68978827 - config_name: japanese.stackexchange.com_simple features: - name: id dtype: string - name: accepted_answer_id dtype: string - name: popular_answer_id dtype: string - name: title dtype: string - name: question_body dtype: string - name: question_score dtype: int64 - name: accepted_answer_body dtype: string - name: accepted_answer_score dtype: int64 - name: popular_answer_body dtype: string - name: popular_answer_score dtype: int64 - name: tags sequence: string splits: - name: train num_bytes: 67358026 num_examples: 28850 download_size: 41459971 dataset_size: 67358026 configs: - config_name: anime.stackexchange.com data_files: - split: train path: anime.stackexchange.com/train-* - config_name: anime.stackexchange.com_simple data_files: - split: train path: anime.stackexchange.com_simple/train-* - config_name: default data_files: - split: anime.stackexchange.com_simple path: data/anime.stackexchange.com_simple-* - split: japanese.stackexchange.com_simple path: data/japanese.stackexchange.com_simple-* - split: ja.stackoverflow.com_simple path: data/ja.stackoverflow.com_simple-* - config_name: ja.stackoverflow.com data_files: - split: train path: ja.stackoverflow.com/train-* - config_name: ja.stackoverflow.com_simple data_files: - split: train path: ja.stackoverflow.com_simple/train-* - config_name: japanese.stackexchange.com data_files: - split: train path: japanese.stackexchange.com/train-* - config_name: japanese.stackexchange.com_simple data_files: - split: train path: japanese.stackexchange.com_simple/train-* ---

原始信息汇总

数据集概述

数据集配置

配置 anime.stackexchange.com

• 特征:
  • question:
    • accepted_answer_id: string
    • answer_count: int64
    • body: string
    • comment_count: int64
    • content_license: string
    • creation_date: string
    • favorite_count: int64
    • id: string
    • last_activity_date: string
    • last_edit_date: string
    • last_editor_user_id: string
    • owner_user_id: string
    • post_type: string
    • score: int64
    • tags: sequence
    • title: string
    • view_count: int64
  • answers:
    • body: string
    • comment_count: int64
    • content_license: string
    • creation_date: string
    • id: string
    • last_activity_date: string
    • last_edit_date: string
    • last_editor_user_id: string
    • owner_user_id: string
    • parent_id: string
    • post_type: string
    • score: int64
  • id: string
  • accepted_answer_id: string
  • popular_answer_id: string
• 分割:
  • train:
    • num_bytes: 32533359
    • num_examples: 12318
• 下载大小: 19104522
• 数据集大小: 32533359

配置 anime.stackexchange.com_simple

• 特征:
  • id: string
  • accepted_answer_id: string
  • popular_answer_id: string
  • title: string
  • question_body: string
  • question_score: int64
  • accepted_answer_body: string
  • accepted_answer_score: int64
  • popular_answer_body: string
  • popular_answer_score: int64
  • tags: sequence
• 分割:
  • train:
    • num_bytes: 29800087
    • num_examples: 12318
• 下载大小: 18536497
• 数据集大小: 29800087

配置 default

• 特征:
  • id: string
  • accepted_answer_id: string
  • popular_answer_id: string
  • title: string
  • question_body: string
  • question_score: int64
  • accepted_answer_body: string
  • accepted_answer_score: int64
  • popular_answer_body: string
  • popular_answer_score: int64
  • tags: sequence
• 分割:
  • anime.stackexchange.com_simple:
    • num_bytes: 29800087
    • num_examples: 12318
  • japanese.stackexchange.com_simple:
    • num_bytes: 67358026
    • num_examples: 28850
  • ja.stackoverflow.com_simple:
    • num_bytes: 115174959
    • num_examples: 30820
• 下载大小: 117381584
• 数据集大小: 212333072

配置 ja.stackoverflow.com

• 特征:
  • question:
    • accepted_answer_id: string
    • answer_count: int64
    • body: string
    • comment_count: int64
    • content_license: string
    • creation_date: string
    • favorite_count: int64
    • id: string
    • last_activity_date: string
    • last_edit_date: string
    • last_editor_user_id: string
    • owner_user_id: string
    • post_type: string
    • score: int64
    • tags: sequence
    • title: string
    • view_count: int64
  • answers:
    • body: string
    • comment_count: int64
    • content_license: string
    • creation_date: string
    • id: string
    • last_activity_date: string
    • last_edit_date: string
    • last_editor_user_id: string
    • owner_user_id: string
    • parent_id: string
    • post_type: string
    • score: int64
  • id: string
  • accepted_answer_id: string
  • popular_answer_id: string
• 分割:
  • train:
    • num_bytes: 114614992
    • num_examples: 30820
• 下载大小: 55495217
• 数据集大小: 114614992

配置 ja.stackoverflow.com_simple

• 特征:
  • id: string
  • accepted_answer_id: string
  • popular_answer_id: string
  • title: string
  • question_body: string
  • question_score: int64
  • accepted_answer_body: string
  • accepted_answer_score: int64
  • popular_answer_body: string
  • popular_answer_score: int64
  • tags: sequence
• 分割:
  • train:
    • num_bytes: 115174959
    • num_examples: 30820
• 下载大小: 57385116
• 数据集大小: 115174959

配置 japanese.stackexchange.com

• 特征:
  • question:
    • accepted_answer_id: string
    • answer_count: int64
    • body: string
    • comment_count: int64
    • content_license: string
    • creation_date: string
    • favorite_count: int64
    • id: string
    • last_activity_date: string
    • last_edit_date: string
    • last_editor_user_id: string
    • owner_user_id: string
    • post_type: string
    • score: int64
    • tags: sequence
    • title: string
    • view_count: int64
  • answers:
    • body: string
    • comment_count: int64
    • content_license: string
    • creation_date: string
    • id: string
    • last_activity_date: string
    • last_edit_date: string
    • last_editor_user_id: string
    • owner_user_id: string
    • parent_id: string
    • post_type: string
    • score: int64
  • id: string
  • accepted_answer_id: string
  • popular_answer_id: string
• 分割:
  • train:
    • num_bytes: 68978827
    • num_examples: 28850
• 下载大小: 39676257
• 数据集大小: 68978827

配置 japanese.stackexchange.com_simple

• 特征:
  • id: string
  • accepted_answer_id: string
  • popular_answer_id: string
  • title: string
  • question_body: string
  • question_score: int64
  • accepted_answer_body: string
  • accepted_answer_score: int64
  • popular_answer_body: string
  • popular_answer_score: int64
  • tags: sequence
• 分割:
  • train:
    • num_bytes: 67358026
    • num_examples: 28850
• 下载大小: 41459971
• 数据集大小: 67358026