Yangkt/github-issues-v2.0

---
configs:
- config_name: default
data_files:
- split: train
path: data/train-*
dataset_info:
features:
- name: url
dtype: string
- name: repository_url
dtype: string
- name: labels_url
dtype: string
- name: comments_url
dtype: string
- name: events_url
dtype: string
- name: html_url
dtype: string
- name: id
dtype: int64
- name: node_id
dtype: string
- name: number
dtype: int64
- name: title
dtype: string
- name: user
struct:
- name: login
dtype: string
- name: id
dtype: int64
- name: node_id
dtype: string
- name: avatar_url
dtype: string
- name: gravatar_id
dtype: string
- name: url
dtype: string
- name: html_url
dtype: string
- name: followers_url
dtype: string
- name: following_url
dtype: string
- name: gists_url
dtype: string
- name: starred_url
dtype: string
- name: subscriptions_url
dtype: string
- name: organizations_url
dtype: string
- name: repos_url
dtype: string
- name: events_url
dtype: string
- name: received_events_url
dtype: string
- name: type
dtype: string
- name: site_admin
dtype: bool
- name: labels
list:
- name: id
dtype: int64
- name: node_id
dtype: string
- name: url
dtype: string
- name: name
dtype: string
- name: color
dtype: string
- name: default
dtype: bool
- name: description
dtype: string
- name: state
dtype: string
- name: locked
dtype: bool
- name: assignee
struct:
- name: login
dtype: string
- name: id
dtype: int64
- name: node_id
dtype: string
- name: avatar_url
dtype: string
- name: gravatar_id
dtype: string
- name: url
dtype: string
- name: html_url
dtype: string
- name: followers_url
dtype: string
- name: following_url
dtype: string
- name: gists_url
dtype: string
- name: starred_url
dtype: string
- name: subscriptions_url
dtype: string
- name: organizations_url
dtype: string
- name: repos_url
dtype: string
- name: events_url
dtype: string
- name: received_events_url
dtype: string
- name: type
dtype: string
- name: site_admin
dtype: bool
- name: assignees
list:
- name: login
dtype: string
- name: id
dtype: int64
- name: node_id
dtype: string
- name: avatar_url
dtype: string
- name: gravatar_id
dtype: string
- name: url
dtype: string
- name: html_url
dtype: string
- name: followers_url
dtype: string
- name: following_url
dtype: string
- name: gists_url
dtype: string
- name: starred_url
dtype: string
- name: subscriptions_url
dtype: string
- name: organizations_url
dtype: string
- name: repos_url
dtype: string
- name: events_url
dtype: string
- name: received_events_url
dtype: string
- name: type
dtype: string
- name: site_admin
dtype: bool
- name: milestone
struct:
- name: url
dtype: string
- name: html_url
dtype: string
- name: labels_url
dtype: string
- name: id
dtype: int64
- name: node_id
dtype: string
- name: number
dtype: int64
- name: title
dtype: string
- name: description
dtype: string
- name: creator
struct:
- name: login
dtype: string
- name: id
dtype: int64
- name: node_id
dtype: string
- name: avatar_url
dtype: string
- name: gravatar_id
dtype: string
- name: url
dtype: string
- name: html_url
dtype: string
- name: followers_url
dtype: string
- name: following_url
dtype: string
- name: gists_url
dtype: string
- name: starred_url
dtype: string
- name: subscriptions_url
dtype: string
- name: organizations_url
dtype: string
- name: repos_url
dtype: string
- name: events_url
dtype: string
- name: received_events_url
dtype: string
- name: type
dtype: string
- name: site_admin
dtype: bool
- name: open_issues
dtype: int64
- name: closed_issues
dtype: int64
- name: state
dtype: string
- name: created_at
dtype: timestamp[s]
- name: updated_at
dtype: timestamp[s]
- name: due_on
dtype: 'null'
- name: closed_at
dtype: 'null'
- name: comments
sequence: string
- name: created_at
dtype: timestamp[s]
- name: updated_at
dtype: timestamp[s]
- name: closed_at
dtype: timestamp[s]
- name: author_association
dtype: string
- name: active_lock_reason
dtype: 'null'
- name: draft
dtype: bool
- name: pull_request
struct:
- name: url
dtype: string
- name: html_url
dtype: string
- name: diff_url
dtype: string
- name: patch_url
dtype: string
- name: merged_at
dtype: timestamp[s]
- name: body
dtype: string
- name: reactions
struct:
- name: url
dtype: string
- name: total_count
dtype: int64
- name: '+1'
dtype: int64
- name: '-1'
dtype: int64
- name: laugh
dtype: int64
- name: hooray
dtype: int64
- name: confused
dtype: int64
- name: heart
dtype: int64
- name: rocket
dtype: int64
- name: eyes
dtype: int64
- name: timeline_url
dtype: string
- name: performed_via_github_app
dtype: 'null'
- name: state_reason
dtype: string
- name: is_pull_request
dtype: bool
splits:
- name: train
num_bytes: 15393821
num_examples: 2000
download_size: 4215618
dataset_size: 15393821
---
# Dataset Card for "github-issues-v2.0"

[More Information needed](https://github.com/huggingface/datasets/blob/main/CONTRIBUTING.md#how-to-contribute-to-the-dataset-cards)

原始信息汇总

数据集概述

数据集配置

• 配置名称: default
• 数据文件:
  • 分割: train
  • 路径: data/train-*

数据集信息

特征

• url: string
• repository_url: string
• labels_url: string
• comments_url: string
• events_url: string
• html_url: string
• id: int64
• node_id: string
• number: int64
• title: string
• user: struct
  • login: string
  • id: int64
  • node_id: string
  • avatar_url: string
  • gravatar_id: string
  • url: string
  • html_url: string
  • followers_url: string
  • following_url: string
  • gists_url: string
  • starred_url: string
  • subscriptions_url: string
  • organizations_url: string
  • repos_url: string
  • events_url: string
  • received_events_url: string
  • type: string
  • site_admin: bool
• labels: list
  • id: int64
  • node_id: string
  • url: string
  • name: string
  • color: string
  • default: bool
  • description: string
• state: string
• locked: bool
• assignee: struct
  • login: string
  • id: int64
  • node_id: string
  • avatar_url: string
  • gravatar_id: string
  • url: string
  • html_url: string
  • followers_url: string
  • following_url: string
  • gists_url: string
  • starred_url: string
  • subscriptions_url: string
  • organizations_url: string
  • repos_url: string
  • events_url: string
  • received_events_url: string
  • type: string
  • site_admin: bool
• assignees: list
  • login: string
  • id: int64
  • node_id: string
  • avatar_url: string
  • gravatar_id: string
  • url: string
  • html_url: string
  • followers_url: string
  • following_url: string
  • gists_url: string
  • starred_url: string
  • subscriptions_url: string
  • organizations_url: string
  • repos_url: string
  • events_url: string
  • received_events_url: string
  • type: string
  • site_admin: bool
• milestone: struct
  • url: string
  • html_url: string
  • labels_url: string
  • id: int64
  • node_id: string
  • number: int64
  • title: string
  • description: string
  • creator: struct
    • login: string
    • id: int64
    • node_id: string
    • avatar_url: string
    • gravatar_id: string
    • url: string
    • html_url: string
    • followers_url: string
    • following_url: string
    • gists_url: string
    • starred_url: string
    • subscriptions_url: string
    • organizations_url: string
    • repos_url: string
    • events_url: string
    • received_events_url: string
    • type: string
    • site_admin: bool
  • open_issues: int64
  • closed_issues: int64
  • state: string
  • created_at: timestamp[s]
  • updated_at: timestamp[s]
  • due_on: null
  • closed_at: null
• comments: sequence of string
• created_at: timestamp[s]
• updated_at: timestamp[s]
• closed_at: timestamp[s]
• author_association: string
• active_lock_reason: null
• draft: bool
• pull_request: struct
  • url: string
  • html_url: string
  • diff_url: string
  • patch_url: string
  • merged_at: timestamp[s]
• body: string
• reactions: struct
  • url: string
  • total_count: int64
  • +1: int64
  • -1: int64
  • laugh: int64
  • hooray: int64
  • confused: int64
  • heart: int64
  • rocket: int64
  • eyes: int64
• timeline_url: string
• performed_via_github_app: null
• state_reason: string
• is_pull_request: bool

分割

• 名称: train
• 字节数: 15393821
• 样本数: 2000

数据集大小

• 下载大小: 4215618
• 数据集大小: 15393821