Skip to content

Fix company contribution calculation discrepancies in governance data #120

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Arunodoy18 wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Fix company contribution calculation discrepancies in governance data #120

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
55 changes: 55 additions & 0 deletions metrics/kubernetes/project_developer_stats.sql
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1184,6 +1184,61 @@ where
)
)
-- limit amount of data

-- Add company-level aggregation using distinct event counting to match companies table logic
-- This prevents discrepancies between individual developer sums and direct company calculations
union select 'hdev_contributions_company,All_All' as metric,
coalesce(aa.company_name, 'Independent') as name,
count(distinct e.id) as value
from
gha_events e
left join
gha_actors_affiliations aa
on
aa.actor_id = e.actor_id
and aa.dt_from <= e.created_at
and aa.dt_to > e.created_at
where
e.type in (
'PushEvent', 'PullRequestEvent', 'IssuesEvent', 'PullRequestReviewEvent',
'CommitCommentEvent', 'IssueCommentEvent', 'PullRequestReviewCommentEvent'
)
and {{period:e.created_at}}
and (lower(e.dup_actor_login) {{exclude_bots}})
and coalesce(aa.company_name, '') != ''
group by
aa.company_name
having
count(distinct e.id) >= 30

union select 'hdev_contributions_company,' || r.repo_group || '_All' as metric,
coalesce(aa.company_name, 'Independent') as name,
count(distinct e.id) as value
from
gha_events e,
gha_repos r
left join
gha_actors_affiliations aa
on
aa.actor_id = e.actor_id
and aa.dt_from <= e.created_at
and aa.dt_to > e.created_at
where
e.repo_id = r.id
and e.type in (
'PushEvent', 'PullRequestEvent', 'IssuesEvent', 'PullRequestReviewEvent',
'CommitCommentEvent', 'IssueCommentEvent', 'PullRequestReviewCommentEvent'
)
and {{period:e.created_at}}
and (lower(e.dup_actor_login) {{exclude_bots}})
and r.repo_group in (select repo_group_name from trepo_groups)
and coalesce(aa.company_name, '') != ''
group by
r.repo_group,
aa.company_name
having
count(distinct e.id) >= 30

order by
metric asc,
value desc,
Expand Down
55 changes: 55 additions & 0 deletions metrics/shared/project_developer_stats.sql
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1135,6 +1135,61 @@ where
) and sub.value > 0.2 * {{project_scale}} * sqrt({{range}}/1450.0)
)
-- limit amount of data

-- Add company-level aggregation using distinct event counting to match companies table logic
-- This prevents discrepancies between individual developer sums and direct company calculations
union select 'hdev_contributions_company,All_All' as metric,
coalesce(aa.company_name, 'Independent') as name,
count(distinct e.id) as value
from
gha_events e
left join
gha_actors_affiliations aa
on
aa.actor_id = e.actor_id
and aa.dt_from <= e.created_at
and aa.dt_to > e.created_at
where
e.type in (
'PushEvent', 'PullRequestEvent', 'IssuesEvent', 'PullRequestReviewEvent',
'CommitCommentEvent', 'IssueCommentEvent', 'PullRequestReviewCommentEvent'
)
and {{period:e.created_at}}
and (lower(e.dup_actor_login) {{exclude_bots}})
and coalesce(aa.company_name, '') != ''
group by
aa.company_name
having
count(distinct e.id) >= 30

union select 'hdev_contributions_company,' || r.repo_group || '_All' as metric,
coalesce(aa.company_name, 'Independent') as name,
count(distinct e.id) as value
from
gha_events e,
gha_repo_groups r
left join
gha_actors_affiliations aa
on
aa.actor_id = e.actor_id
and aa.dt_from <= e.created_at
and aa.dt_to > e.created_at
where
e.repo_id = r.id
and e.type in (
'PushEvent', 'PullRequestEvent', 'IssuesEvent', 'PullRequestReviewEvent',
'CommitCommentEvent', 'IssueCommentEvent', 'PullRequestReviewCommentEvent'
)
and {{period:e.created_at}}
and (lower(e.dup_actor_login) {{exclude_bots}})
and r.repo_group in (select repo_group_name from trepo_groups)
and coalesce(aa.company_name, '') != ''
group by
r.repo_group,
aa.company_name
having
count(distinct e.id) >= 30

order by
metric asc,
value desc,
Expand Down