Initial deploy setup

2026-07-21 14:00:00 +02:00
commit b8091e59bd
285 changed files with 27854 additions and 0 deletions
@@ -0,0 +1,125 @@
+#!/usr/bin/env python3
+from __future__ import annotations
+
+import argparse
+import os
+from collections import Counter
+from pathlib import Path
+
+import django
+
+os.environ.setdefault("DJANGO_SETTINGS_MODULE", "config.settings")
+django.setup()
+
+from apps.profiles.models import SearchProfile
+
+
+def _load_profile(profile_id: int | None, username: str | None) -> SearchProfile:
+    if profile_id:
+        return SearchProfile.objects.get(pk=profile_id)
+    if username:
+        profile = SearchProfile.objects.filter(user__username=username, is_active=True).first()
+        if profile is None:
+            raise ValueError(f"Geen actief profiel gevonden voor gebruiker {username}")
+        return profile
+    raise ValueError("Kies --profile-id of --user.")
+
+
+def _collect_feedback_churn(profile: SearchProfile) -> dict:
+    from apps.jobs.models import Feedback
+
+    all_feedback = Feedback.objects.filter(profile=profile).order_by("created_at")
+    status = Counter()
+    features = Counter()
+    sample_count = 0
+    false_negatives = []
+
+    for feedback in all_feedback:
+        learning = feedback.metadata.get("learning") if isinstance(feedback.metadata, dict) else None
+        if not isinstance(learning, dict):
+            continue
+        reason_code = learning.get("reason_code", "")
+        status[learning.get("status", "")] += 1
+        if feature := learning.get("feature"):
+            features[feature] += 1
+            sample_count += 1
+        if learning.get("status") == "queued" and reason_code.startswith("non_learning_"):
+            false_negatives.append(
+                {
+                    "job_id": str(feedback.job_id),
+                    "reason_code": reason_code,
+                }
+            )
+
+    return {
+        "samples": dict(status),
+        "features": dict(features),
+        "total_feedback": all_feedback.count(),
+        "sample_count": sample_count,
+        "queued_non_learning_signals": false_negatives[:25],
+    }
+
+
+def _collect_weight_churn(profile: SearchProfile) -> list[dict[str, float]]:
+    revisions = list(profile.revisions.order_by("version"))
+    if len(revisions) < 2:
+        return []
+
+    base = revisions[0].snapshot
+    latest = revisions[-1].snapshot
+    base_weights = base.get("weights", {})
+    latest_weights = latest.get("weights", {})
+    churn = []
+    for feature in sorted(set(base_weights) | set(latest_weights)):
+        before = float(base_weights.get(feature, 0.0))
+        after = float(latest_weights.get(feature, 0.0))
+        if before == after:
+            continue
+        churn.append({"feature": feature, "delta": round(after - before, 3)})
+    return sorted(churn, key=lambda item: abs(item["delta"]), reverse=True)
+
+
+def main(argv: list[str] | None = None) -> int:
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--profile-id", type=int, default=None)
+    parser.add_argument("--user", default=None)
+    parser.add_argument("--top", type=int, default=5)
+    args = parser.parse_args(argv)
+
+    if not args.profile_id and not args.user:
+        raise SystemExit("Gebruik --profile-id of --user.")
+
+    profile = _load_profile(args.profile_id, args.user)
+    feedback_report = _collect_feedback_churn(profile)
+    churn = _collect_weight_churn(profile)
+    report = {
+        "profile_id": profile.pk,
+        "profile_name": profile.name,
+        "learning_enabled": profile.learning_enabled,
+        "feedback": feedback_report,
+        "weight_churn": churn[: args.top],
+    }
+    output = Path("feedback_learning_report.txt")
+    output.write_text(
+        "\n".join(
+            [
+                f"Feedbacklearningrapport voor {profile.name} (id={profile.pk})",
+                f"Learning actief: {'ja' if profile.learning_enabled else 'nee'}",
+                f"Feedbacktotalen: {feedback_report['total_feedback']}",
+                f"Statuscounts: {feedback_report['samples']}",
+                f"Featurecounts: {feedback_report['features']}",
+                "Top-churn:",
+            ]
+            + [f" - {item['feature']}: {item['delta']:+.3f}" for item in report["weight_churn"]]
+            + [f"\nMogelijke non-learn false negatives (max {args.top}):"]
+            + [f" - {item['job_id']} ({item['reason_code']})" for item in feedback_report["queued_non_learning_signals"][: args.top]]
+        )
+        + "\n",
+        encoding="utf-8",
+    )
+    print(output.read_text(encoding="utf-8"))
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())