refactor: improve get pop issues (#5135)

# Pull Request Template
<!-- Please include a summary of the changes and the related issue.
Please also include relevant motivation and context. List any
dependencies that are required for this change. -->

Closes #5116

CONSIDERATIONS:
- I fixed the planned issues, BUT to order them in descending order, I
had to filter by v2. and the open ones (there were old milestones, and
if the closed ones are shown, only those will be shown). FOR DISTILABEL
UPDATE, the v2 filter should be removed.
I removed an API call as I found a key to determine if a member of the
org/repo opened the issue (pre-commit should not be additionally added
as previously because it only creates PRs, not issues). Locally, with a
token with the permissions defined, it correctly removed the members.
- I realized that the API call to list the issues also retrieves the
pull requests, so I added an if statement to filter them.
- I removed unneeded keys.

<img width="1402" alt="Screenshot 2024-06-30 at 02 42 51"
src="https://github.com/argilla-io/argilla/assets/127759186/5d32ebd9-da3b-4fca-a109-f0c251fe1aa1">

<img width="1402" alt="Screenshot 2024-06-30 at 02 42 38"
src="https://github.com/argilla-io/argilla/assets/127759186/57818ef5-933f-4337-8613-9091e5292fa4">

<img width="1402" alt="Screenshot 2024-06-30 at 02 42 44"
src="https://github.com/argilla-io/argilla/assets/127759186/4dfaee57-bc6c-4d22-b5cb-d51ceeb1827a">

**Type of change**
<!-- Please delete options that are not relevant. Remember to title the
PR according to the type of change -->

- Refactor (change restructuring the codebase without changing
functionality)
- Improvement (change adding some improvement to an existing
functionality)
- Documentation update

**How Has This Been Tested**
<!-- Please add some reference about how your feature has been tested.
-->

**Checklist**
<!-- Please go over the list and make sure you've taken everything into
account -->

- I made corresponding changes to the documentation
- I confirm My changes generate no new warnings

---------

Co-authored-by: David Berenstein <[email protected]>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

Author: 3 people

argilla/docs/scripts/gen_popular_issues.py

@@ -32,15 +32,12 @@ def fetch_data_from_github(repository, auth_token):
                 "Issue": [],
                 "State": [],
                 "Created at": [],
-                "Closed at": [],
-                "Last update": [],
-                "Labels": [],
                 "Milestone": [],
                 "Reactions": [],
                 "Comments": [],
                 "URL": [],
-                "Repository": [],
                 "Author": [],
+                "Author association": [],
             }
         )
     headers = {"Authorization": f"token {auth_token}", "Accept": "application/vnd.github.v3+json"}
@@ -58,20 +55,19 @@ def fetch_data_from_github(repository, auth_token):
             issues = response.json()
 
             for issue in issues:
+                if "pull_request" in issue:
+                    continue
                 issues_data.append(
                     {
                         "Issue": f"{issue['number']} - {issue['title']}",
                         "State": issue["state"],
                         "Created at": issue["created_at"],
-                        "Closed at": issue.get("closed_at", None),
-                        "Last update": issue["updated_at"],
-                        "Labels": [label["name"] for label in issue["labels"]],
                         "Milestone": (issue.get("milestone") or {}).get("title"),
                         "Reactions": issue["reactions"]["total_count"],
                         "Comments": issue["comments"],
                         "URL": issue["html_url"],
-                        "Repository": repo_name,
                         "Author": issue["user"]["login"],
+                        "Author association": issue["author_association"],
                     }
                 )
 
@@ -80,53 +76,32 @@ def fetch_data_from_github(repository, auth_token):
     return pd.DataFrame(issues_data)
 
 
-def get_org_members(auth_token):
-    headers = {"Authorization": f"token {auth_token}", "Accept": "application/vnd.github.v3+json"}
-    members_list = []
-
-    members_url = "https://api.github.com/orgs/argilla-io/members"
-
-    if auth_token is None:
-        return []
-
-    while members_url:
-        response = requests.get(members_url, headers=headers)
-        members = response.json()
-
-        for member in members:
-            members_list.append(member["login"])
-
-        members_list.extend(["pre-commit-ci[bot]"])
-
-        members_url = response.links.get("next", {}).get("url", None)
-
-    return members_list
-
-
 with mkdocs_gen_files.open(DATA_PATH, "w") as f:
     df = fetch_data_from_github(REPOSITORY, GITHUB_ACCESS_TOKEN)
 
     open_issues = df.loc[df["State"] == "open"]
     engagement_df = (
-        open_issues[["URL", "Issue", "Repository", "Reactions", "Comments"]]
+        open_issues[["URL", "Issue", "Reactions", "Comments"]]
         .sort_values(by=["Reactions", "Comments"], ascending=False)
         .head(10)
         .reset_index()
     )
 
-    members = get_org_members(GITHUB_ACCESS_TOKEN)
-    community_issues = df.loc[~df["Author"].isin(members)]
+    community_issues = df[df["Author association"] != "MEMBER"]
     community_issues_df = (
-        community_issues[["URL", "Issue", "Repository", "Created at", "Author", "State"]]
+        community_issues[["URL", "Issue", "Created at", "Author", "State"]]
         .sort_values(by=["Created at"], ascending=False)
         .head(10)
         .reset_index()
     )
 
-    planned_issues = df.loc[df["Milestone"].notna()]
+    planned_issues = df[
+        ((df["Milestone"].str.startswith("v2")) & (df["State"] == "open"))
+        | ((df["Milestone"].str.startswith("2")) & (df["State"] == "open"))
+    ]
     planned_issues_df = (
-        planned_issues[["URL", "Issue", "Repository", "Created at", "Milestone", "State"]]
-        .sort_values(by=["Milestone"], ascending=False)
+        planned_issues[["URL", "Issue", "Created at", "Milestone", "State"]]
+        .sort_values(by=["Milestone"], ascending=True)
         .head(10)
         .reset_index()
     )