Skip to content

Add trend velocity detection #31

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

Merged
webstackdev merged 1 commit into from
Apr 30, 2026
Merged

Add trend velocity detection #31

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
10 changes: 10 additions & 0 deletions core/models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,18 +26,25 @@
from pipeline.models import SkillResult as _SkillResult
from pipeline.models import SkillStatus as _SkillStatus
from projects.models import Project as _Project
from trends.models import ContentClusterMembership as _ContentClusterMembership
from trends.models import TopicCentroidSnapshot as _TopicCentroidSnapshot
from trends.models import TopicCluster as _TopicCluster
from trends.models import TopicVelocitySnapshot as _TopicVelocitySnapshot

Project = _Project
ReviewQueue = _ReviewQueue
ReviewReason = _ReviewReason
ReviewResolution = _ReviewResolution
SkillResult = _SkillResult
SkillStatus = _SkillStatus
ContentClusterMembership = _ContentClusterMembership
TopicCluster = _TopicCluster
TopicCentroidSnapshot = _TopicCentroidSnapshot
TopicVelocitySnapshot = _TopicVelocitySnapshot

__all__ = [
"Content",
"ContentClusterMembership",
"Entity",
"EntityAuthoritySnapshot",
"EntityCandidate",
Expand All @@ -53,6 +60,9 @@
"NewsletterIntakeStatus",
"Project",
"RunStatus",
"TopicCluster",
"TopicCentroidSnapshot",
"TopicVelocitySnapshot",
"UserFeedback",
]

Expand Down
18 changes: 18 additions & 0 deletions core/tasks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -49,9 +49,13 @@
from newsletters.tasks import process_newsletter_intake
from trends.tasks import (
TOPIC_CENTROID_MIN_UPVOTES,
assign_content_to_topic_cluster,
queue_topic_centroid_recompute,
recompute_topic_centroid,
recompute_topic_clusters,
recompute_topic_velocity,
run_all_topic_centroid_recomputations,
run_all_topic_cluster_recomputations,
)

_COMPAT_TASK_EXPORTS = {
Expand All @@ -61,15 +65,25 @@
),
"run_all_ingestions": ("ingestion.tasks", "run_all_ingestions"),
"run_ingestion": ("ingestion.tasks", "run_ingestion"),
"assign_content_to_topic_cluster": (
"trends.tasks",
"assign_content_to_topic_cluster",
),
"TOPIC_CENTROID_MIN_UPVOTES": (
"trends.tasks",
"TOPIC_CENTROID_MIN_UPVOTES",
),
"recompute_topic_clusters": ("trends.tasks", "recompute_topic_clusters"),
"queue_topic_centroid_recompute": (
"trends.tasks",
"queue_topic_centroid_recompute",
),
"recompute_topic_centroid": ("trends.tasks", "recompute_topic_centroid"),
"recompute_topic_velocity": ("trends.tasks", "recompute_topic_velocity"),
"run_all_topic_cluster_recomputations": (
"trends.tasks",
"run_all_topic_cluster_recomputations",
),
"run_all_topic_centroid_recomputations": (
"trends.tasks",
"run_all_topic_centroid_recomputations",
Expand All @@ -79,12 +93,16 @@
__all__ = [
"process_newsletter_intake",
"run_all_ingestions",
"assign_content_to_topic_cluster",
"run_ingestion",
"TOPIC_CENTROID_MIN_UPVOTES",
"queue_topic_centroid_recompute",
"recompute_authority_scores",
"recompute_topic_clusters",
"recompute_topic_centroid",
"recompute_topic_velocity",
"run_all_authority_recomputations",
"run_all_topic_cluster_recomputations",
"run_all_topic_centroid_recomputations",
"run_relevance_scoring_skill",
"run_summarization_skill",
Expand Down
112 changes: 112 additions & 0 deletions core/tests/test_api.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,7 @@

from core.models import (
Content,
ContentClusterMembership,
Entity,
EntityAuthoritySnapshot,
EntityCandidate,
Expand All @@ -24,6 +25,8 @@
SkillResult,
SkillStatus,
TopicCentroidSnapshot,
TopicCluster,
TopicVelocitySnapshot,
UserFeedback,
)
from projects.model_support import SourcePluginName
Expand Down Expand Up @@ -540,6 +543,115 @@ def test_topic_centroid_summary_action_returns_latest_snapshot_and_averages(self
self.assertAlmostEqual(response.json()["avg_drift_from_previous"], 0.2)
self.assertAlmostEqual(response.json()["avg_drift_from_week_ago"], 0.3)

def test_topic_cluster_list_returns_current_velocity_annotation(self):
cluster = TopicCluster.objects.create(
project=self.owner_project,
first_seen_at="2026-04-22T00:00:00Z",
last_seen_at="2026-04-24T00:00:00Z",
is_active=True,
member_count=3,
dominant_entity=self.owner_entity,
)
TopicVelocitySnapshot.objects.create(
cluster=cluster,
project=self.owner_project,
window_count=4,
trailing_mean=1.5,
trailing_stddev=0.5,
z_score=3.0,
velocity_score=1.0,
)

response = self.client.get(
reverse(
"v1:project-topic-cluster-list",
kwargs={"project_id": self.owner_project.id},
),
{"ordering": "-velocity_score"},
)

self.assertEqual(response.status_code, status.HTTP_200_OK)
self.assertEqual(len(response.json()), 1)
self.assertEqual(response.json()[0]["id"], cluster.id)
self.assertEqual(response.json()[0]["member_count"], 3)
self.assertEqual(
response.json()[0]["dominant_entity"]["id"], self.owner_entity.id
)
self.assertAlmostEqual(response.json()[0]["velocity_score"], 1.0)
self.assertAlmostEqual(response.json()[0]["z_score"], 3.0)
self.assertEqual(response.json()[0]["window_count"], 4)

def test_topic_cluster_detail_and_velocity_history_action_return_memberships(self):
cluster = TopicCluster.objects.create(
project=self.owner_project,
first_seen_at="2026-04-22T00:00:00Z",
last_seen_at="2026-04-24T00:00:00Z",
is_active=True,
member_count=1,
dominant_entity=self.owner_entity,
)
ContentClusterMembership.objects.create(
content=self.owner_content,
cluster=cluster,
project=self.owner_project,
similarity=0.92,
)
first_snapshot = TopicVelocitySnapshot.objects.create(
cluster=cluster,
project=self.owner_project,
window_count=2,
trailing_mean=1.0,
trailing_stddev=0.2,
z_score=1.5,
velocity_score=0.75,
)
second_snapshot = TopicVelocitySnapshot.objects.create(
cluster=cluster,
project=self.owner_project,
window_count=3,
trailing_mean=1.0,
trailing_stddev=0.3,
z_score=3.0,
velocity_score=1.0,
)
TopicVelocitySnapshot.objects.filter(pk=first_snapshot.pk).update(
computed_at="2026-04-23T00:00:00Z"
)
TopicVelocitySnapshot.objects.filter(pk=second_snapshot.pk).update(
computed_at="2026-04-24T00:00:00Z"
)

detail_response = self.client.get(
reverse(
"v1:project-topic-cluster-detail",
kwargs={"project_id": self.owner_project.id, "pk": cluster.id},
)
)
history_response = self.client.get(
reverse(
"v1:project-topic-cluster-velocity-history",
kwargs={"project_id": self.owner_project.id, "pk": cluster.id},
),
{"limit": 1},
)

self.assertEqual(detail_response.status_code, status.HTTP_200_OK)
self.assertEqual(detail_response.json()["id"], cluster.id)
self.assertEqual(len(detail_response.json()["memberships"]), 1)
self.assertEqual(
detail_response.json()["memberships"][0]["content"]["id"],
self.owner_content.id,
)
self.assertEqual(len(detail_response.json()["velocity_history"]), 2)
self.assertEqual(
detail_response.json()["velocity_history"][0]["id"],
second_snapshot.id,
)

self.assertEqual(history_response.status_code, status.HTTP_200_OK)
self.assertEqual(len(history_response.json()), 1)
self.assertEqual(history_response.json()[0]["id"], second_snapshot.id)

def test_content_detail_includes_duplicate_state(self):
canonical = self.owner_content
canonical.canonical_url = "https://example.com/owner"
Expand Down
Loading
Loading