[ { "database": "gharchive_dev", "table": "github_events", "col_names": [ "id", "type", "created_at", "repo_id", "repo_name", "actor_id", "actor_login", "actor_location", "language", "additions", "deletions", "action", "number", "commit_id", "comment_id", "org_login", "org_id", "state", "closed_at", "comments", "pr_merged_at", "pr_merged", "pr_changed_files", "pr_review_comments", "pr_or_issue_id", "event_day", "event_month", "author_association", "event_year", "push_size", "push_distinct_size" ], "questions": [ "1. What is the most popular event type?", "2. What is the average number of additions and deletions per event?", "3. What is the most popular language used in events?", "4. What is the most active actor in terms of events?", "5. What is the most active repository in terms of events?", "6. What is the most active location in terms of events?", "7. What is the average number of comments per event?", "8. What is the average number of changed files per event?", "9. What is the average number of review comments per event?", "10. What is the average number of pushes per event?", "11. What is the average number of distinct pushes per event?", "12. What is the most popular action taken in events?", "13. What is the most popular author association in events?", "14. What is the average number of events per day?", "15. What is the average number of events per month?", "16. What is the average number of events per year?", "17. What is the average number of events per actor?", "18. What is the average number of events per repository?", "19. What is the average number of events per location?", "20. What is the average number of events per language?", "21. What is the average number of events per action?", "22. What is the average number of events per author association?", "23. What is the average number of events per push size?", "24. What is the average number of events per distinct push size?", "25. What is the average number of events per comment?", "26. What is the average number of events per changed file?", "27. What is the average number of events per review comment?", "28. What is the average number of events per pull request or issue?", "29. What is the average number of events per closed date?", "30. What is the average number of events per merged date?", "31. What is the average number of events per merged pull request?", "32. What is the average number of events per organization?", "33. What is the average number of events per organization ID?", "34. What is the average number of events per state?", "35. What is the average number of events per commit ID?", "36. What is the average number of events per comment ID?", "37. What is the average number of events per number?", "38. What is the average number of events per type?", "39. What is the average number of events per created date?", "40. What is the average number of events per actor ID?", "41. What is the average number of events per actor login?", "42. What is the average number of events per repository ID?", "43. What is the average number of events per repository name?", "44. What is the average number of events per event day?", "45. What is the average number of events per event month?", "46. What is the average number of events per event year?", "47. What is the average number of events per author association?", "48. What is the average number of events per push size?", "49. What is the average number of events per distinct push size?", "50. What is the average number of events per pull request or issue ID?" ], "answers": [ "\nSELECT type, COUNT(*) AS count \nFROM github_events \nGROUP BY type \nORDER BY count DESC \nLIMIT 1;", "\nSELECT AVG(additions) AS avg_additions, AVG(deletions) AS avg_deletions\nFROM github_events;", "\nSELECT language, COUNT(*) AS language_count\nFROM github_events\nGROUP BY language\nORDER BY language_count DESC\nLIMIT 1;", "\nSELECT actor_login, COUNT(*) AS event_count\nFROM github_events\nGROUP BY actor_login\nORDER BY event_count DESC\nLIMIT 1;", "\nSELECT repo_name, COUNT(*) AS event_count\nFROM github_events\nGROUP BY repo_name\nORDER BY event_count DESC\nLIMIT 1;", "\nSELECT actor_location, COUNT(*) AS total_events\nFROM github_events\nGROUP BY actor_location\nORDER BY total_events DESC\nLIMIT 1;", "\nSELECT AVG(comments)\nFROM github_events;", "\nSELECT AVG(pr_changed_files)\nFROM github_events;", "\nSELECT AVG(pr_review_comments)\nFROM github_events;", "\nSELECT AVG(push_size)\nFROM github_events;", "\nSELECT AVG(push_distinct_size)\nFROM github_events;", "\nSELECT action, COUNT(*) AS action_count\nFROM github_events\nGROUP BY action\nORDER BY action_count DESC\nLIMIT 1;", "\nSELECT author_association, COUNT(*) AS count\nFROM github_events\nGROUP BY author_association\nORDER BY count DESC\nLIMIT 1;", "\nSELECT AVG(COUNT(id)) AS avg_events_per_day\nFROM github_events\nGROUP BY event_day;", "\nSELECT AVG(num_events)\nFROM (SELECT COUNT(*) AS num_events, MONTH(created_at) AS month\n FROM github_events\n GROUP BY MONTH(created_at)) AS monthly_events;", "\nSELECT AVG(COUNT(id)) AS avg_events_per_year\nFROM github_events\nGROUP BY event_year;", "\nSELECT AVG(COUNT(id))\nFROM github_events\nGROUP BY actor_id;", "\nSELECT AVG(COUNT(id))\nFROM github_events\nGROUP BY repo_id;", "\nSELECT AVG(COUNT(id)) AS avg_events_per_location\nFROM github_events\nGROUP BY actor_location;", "\nSELECT language, AVG(COUNT(*)) AS avg_events_per_language\nFROM github_events\nGROUP BY language;", "\nSELECT action, AVG(id) AS avg_events_per_action\nFROM github_events\nGROUP BY action;", "\nSELECT AVG(COUNT(id)) AS avg_events_per_author_association\nFROM github_events\nGROUP BY author_association;", "\nSELECT AVG(push_size)\nFROM github_events;", "\nSELECT AVG(push_size) / COUNT(DISTINCT push_size)\nFROM github_events;", "\nSELECT AVG(COUNT(id))\nFROM github_events\nGROUP BY comment_id;", "\nSELECT AVG(pr_changed_files)\nFROM github_events;", "\nSELECT AVG(pr_review_comments)\nFROM github_events;", "\nSELECT AVG(COUNT(id))\nFROM github_events\nWHERE pr_or_issue_id IS NOT NULL\nGROUP BY pr_or_issue_id;", "\nSELECT AVG(COUNT(id))\nFROM github_events\nWHERE state = 'closed'\nGROUP BY closed_at;", "\nSELECT AVG(COUNT(created_at))\nFROM github_events\nWHERE pr_merged = 'true'\nGROUP BY pr_merged_at;", "\nSELECT AVG(COUNT(*) / COUNT(pr_merged))\nFROM github_events\nWHERE pr_merged IS NOT NULL;", "\nSELECT AVG(num_events)\nFROM (SELECT COUNT(*) AS num_events, org_login\n FROM github_events\n GROUP BY org_login) AS org_events;", "\nSELECT AVG(COUNT(id))\nFROM github_events\nGROUP BY org_id;", "\nSELECT state, AVG(id) AS avg_events_per_state\nFROM github_events\nGROUP BY state;", "\nSELECT AVG(COUNT(id))\nFROM github_events\nGROUP BY commit_id;", "\nSELECT AVG(COUNT(id))\nFROM github_events\nGROUP BY comment_id;", "\nSELECT AVG(COUNT(id))\nFROM github_events\nGROUP BY number;", "\nSELECT type, AVG(id) AS avg_events_per_type\nFROM github_events\nGROUP BY type;", "\nSELECT AVG(COUNT(id))\nFROM github_events\nGROUP BY created_at;", "\nSELECT AVG(COUNT(id))\nFROM github_events\nGROUP BY actor_id;", "\nSELECT AVG(COUNT(id))\nFROM github_events\nGROUP BY actor_login;", "\nSELECT AVG(COUNT(id))\nFROM github_events\nGROUP BY repo_id;", "\nSELECT AVG(COUNT(repo_name))\nFROM github_events\nGROUP BY repo_name;", "\nSELECT AVG(COUNT(id))\nFROM github_events\nGROUP BY event_day;", "\nSELECT AVG(COUNT(id)) AS avg_events_per_month\nFROM github_events\nGROUP BY event_month;", "\nSELECT AVG(COUNT(id)) AS avg_events_per_year\nFROM github_events\nGROUP BY event_year;", "\nSELECT AVG(COUNT(*) / COUNT(DISTINCT actor_login))\nFROM github_events\nGROUP BY author_association;", "\nSELECT AVG(push_size)\nFROM github_events;", "\nSELECT AVG(push_size) / COUNT(DISTINCT push_size)\nFROM github_events;", "\nSELECT AVG(COUNT(pr_or_issue_id))\nFROM github_events\nGROUP BY pr_or_issue_id;" ] } ]