Add File Level Annotations (#111)

* adding recording annotation model

* Add recording annnotation and migrations

* client-side updates

* adding recording annotation interface

* basic adding/editing user based file level annotations

* adding file annotation to main recording view

* linting client

* change apt-fast to apt-get

* revert apt-fast

* convert to sudo apt-get

* pin to ubuntu 22.04

.github/workflows/ci.yaml

@@ -15,7 +15,7 @@ env:
 jobs:
   lint-python:
     name: Lint Python
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-22.04
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4
@@ -55,7 +55,7 @@ jobs:
         working-directory: client
   test-django:
     name: Test Django [${{ matrix.tox-env }}]
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-22.04
     strategy:
       fail-fast: false
       matrix:
@@ -92,7 +92,7 @@ jobs:
       - name: Update Package References
         run: sudo apt-get update
       - name: Install system dependencies
-        run: apt-fast install --no-install-recommends --yes
+        run: sudo apt-get install --no-install-recommends --yes
           libgdal30
           libproj22
           python3-cachecontrol
@@ -110,7 +110,7 @@ jobs:
         working-directory: bats_ai
   test-vue:
     name: Test [vue]
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-22.04
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4

bats_ai/api.py

@@ -3,7 +3,13 @@
 from ninja import NinjaAPI
 from oauth2_provider.models import AccessToken
 
-from bats_ai.core.views import GRTSCellsRouter, GuanoMetadataRouter, RecordingRouter, SpeciesRouter
+from bats_ai.core.views import (
+    GRTSCellsRouter,
+    GuanoMetadataRouter,
+    RecordingAnnotationRouter,
+    RecordingRouter,
+    SpeciesRouter,
+)
 
 logger = logging.getLogger(__name__)
 
@@ -28,3 +34,4 @@ def global_auth(request):
 api.add_router('/species/', SpeciesRouter)
 api.add_router('/grts/', GRTSCellsRouter)
 api.add_router('/guano/', GuanoMetadataRouter)
+api.add_router('/recording-annotation/', RecordingAnnotationRouter)

bats_ai/core/migrations/0011_alter_annotations_options_annotations_confidence_and_more.py

@@ -0,0 +1,107 @@
+# Generated by Django 4.1.13 on 2024-12-09 15:26
+
+from django.conf import settings
+import django.core.validators
+from django.db import migrations, models
+import django.db.models.deletion
+import django.utils.timezone
+import django_extensions.db.fields
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        migrations.swappable_dependency(settings.AUTH_USER_MODEL),
+        ('core', '0010_compressedspectrogram'),
+    ]
+
+    operations = [
+        migrations.AlterModelOptions(
+            name='annotations',
+            options={'get_latest_by': 'modified'},
+        ),
+        migrations.AddField(
+            model_name='annotations',
+            name='confidence',
+            field=models.FloatField(
+                default=1.0,
+                help_text='A confidence value between 0 and 1.0, default is 1.0.',
+                validators=[
+                    django.core.validators.MinValueValidator(0.0),
+                    django.core.validators.MaxValueValidator(1.0),
+                ],
+            ),
+        ),
+        migrations.AddField(
+            model_name='annotations',
+            name='created',
+            field=django_extensions.db.fields.CreationDateTimeField(
+                auto_now_add=True, default=django.utils.timezone.now, verbose_name='created'
+            ),
+            preserve_default=False,
+        ),
+        migrations.AddField(
+            model_name='annotations',
+            name='model',
+            field=models.TextField(blank=True, null=True),
+        ),
+        migrations.AddField(
+            model_name='annotations',
+            name='modified',
+            field=django_extensions.db.fields.ModificationDateTimeField(
+                auto_now=True, verbose_name='modified'
+            ),
+        ),
+        migrations.CreateModel(
+            name='RecordingAnnotation',
+            fields=[
+                (
+                    'id',
+                    models.BigAutoField(
+                        auto_created=True, primary_key=True, serialize=False, verbose_name='ID'
+                    ),
+                ),
+                (
+                    'created',
+                    django_extensions.db.fields.CreationDateTimeField(
+                        auto_now_add=True, verbose_name='created'
+                    ),
+                ),
+                (
+                    'modified',
+                    django_extensions.db.fields.ModificationDateTimeField(
+                        auto_now=True, verbose_name='modified'
+                    ),
+                ),
+                ('comments', models.TextField(blank=True, null=True)),
+                ('model', models.TextField(blank=True, null=True)),
+                (
+                    'confidence',
+                    models.FloatField(
+                        default=1.0,
+                        help_text='A confidence value between 0 and 1.0, default is 1.0.',
+                        validators=[
+                            django.core.validators.MinValueValidator(0.0),
+                            django.core.validators.MaxValueValidator(1.0),
+                        ],
+                    ),
+                ),
+                (
+                    'owner',
+                    models.ForeignKey(
+                        on_delete=django.db.models.deletion.CASCADE, to=settings.AUTH_USER_MODEL
+                    ),
+                ),
+                (
+                    'recording',
+                    models.ForeignKey(
+                        on_delete=django.db.models.deletion.CASCADE, to='core.recording'
+                    ),
+                ),
+                ('species', models.ManyToManyField(to='core.species')),
+            ],
+            options={
+                'get_latest_by': 'modified',
+                'abstract': False,
+            },
+        ),
+    ]

bats_ai/core/models/__init__.py

@@ -3,6 +3,7 @@
 from .grts_cells import GRTSCells
 from .image import Image
 from .recording import Recording, colormap
+from .recording_annotation import RecordingAnnotation
 from .recording_annotation_status import RecordingAnnotationStatus
 from .species import Species
 from .spectrogram import Spectrogram
@@ -19,4 +20,5 @@
     'GRTSCells',
     'colormap',
     'CompressedSpectrogram',
+    'RecordingAnnotation',
 ]

bats_ai/core/models/annotations.py

@@ -1,11 +1,13 @@
 from django.contrib.auth.models import User
+from django.core.validators import MaxValueValidator, MinValueValidator
 from django.db import models
+from django_extensions.db.models import TimeStampedModel
 
 from .recording import Recording
 from .species import Species
 
 
-class Annotations(models.Model):
+class Annotations(TimeStampedModel, models.Model):
     recording = models.ForeignKey(Recording, on_delete=models.CASCADE)
     owner = models.ForeignKey(User, on_delete=models.CASCADE)
     start_time = models.IntegerField(blank=True, null=True)
@@ -15,3 +17,12 @@ class Annotations(models.Model):
     type = models.TextField(blank=True, null=True)
     species = models.ManyToManyField(Species)
     comments = models.TextField(blank=True, null=True)
+    model = models.TextField(blank=True, null=True)  # AI Model information if inference used
+    confidence = models.FloatField(
+        default=1.0,
+        validators=[
+            MinValueValidator(0.0),
+            MaxValueValidator(1.0),
+        ],
+        help_text='A confidence value between 0 and 1.0, default is 1.0.',
+    )

bats_ai/core/models/recording_annotation.py

@@ -0,0 +1,23 @@
+from django.contrib.auth.models import User
+from django.core.validators import MaxValueValidator, MinValueValidator
+from django.db import models
+from django_extensions.db.models import TimeStampedModel
+
+from .recording import Recording
+from .species import Species
+
+
+class RecordingAnnotation(TimeStampedModel, models.Model):
+    recording = models.ForeignKey(Recording, on_delete=models.CASCADE)
+    owner = models.ForeignKey(User, on_delete=models.CASCADE)
+    species = models.ManyToManyField(Species)
+    comments = models.TextField(blank=True, null=True)
+    model = models.TextField(blank=True, null=True)  # AI Model information if inference used
+    confidence = models.FloatField(
+        default=1.0,
+        validators=[
+            MinValueValidator(0.0),
+            MaxValueValidator(1.0),
+        ],
+        help_text='A confidence value between 0 and 1.0, default is 1.0.',
+    )

bats_ai/core/views/__init__.py

@@ -2,6 +2,7 @@
 from .grts_cells import router as GRTSCellsRouter
 from .guanometadata import router as GuanoMetadataRouter
 from .recording import router as RecordingRouter
+from .recording_annotation import router as RecordingAnnotationRouter
 from .species import router as SpeciesRouter
 from .temporal_annotations import router as TemporalAnnotationRouter
 
@@ -12,4 +13,5 @@
     'TemporalAnnotationRouter',
     'GRTSCellsRouter',
     'GuanoMetadataRouter',
+    'RecordingAnnotationRouter',
 ]

bats_ai/core/views/recording.py

@@ -15,6 +15,7 @@
     Annotations,
     CompressedSpectrogram,
     Recording,
+    RecordingAnnotation,
     Species,
     TemporalAnnotations,
     colormap,
@@ -61,6 +62,26 @@ class RecordingUploadSchema(Schema):
     unusual_occurrences: str = None
 
 
+class RecordingAnnotationSchema(Schema):
+    species: list[SpeciesSchema] | None
+    comments: str | None = None
+    model: str | None = None
+    owner: str
+    confidence: float
+    id: int | None = None
+
+    @classmethod
+    def from_orm(cls, obj: RecordingAnnotation, **kwargs):
+        return cls(
+            species=[SpeciesSchema.from_orm(species) for species in obj.species.all()],
+            owner=obj.owner.username,
+            confidence=obj.confidence,
+            comments=obj.comments,
+            model=obj.model,
+            id=obj.pk,
+        )
+
+
 class AnnotationSchema(Schema):
     start_time: int
     end_time: int
@@ -73,7 +94,7 @@ class AnnotationSchema(Schema):
     owner_email: str = None
 
     @classmethod
-    def from_orm(cls, obj, owner_email=None, **kwargs):
+    def from_orm(cls, obj: Annotations, owner_email=None, **kwargs):
         return cls(
             start_time=obj.start_time,
             end_time=obj.end_time,
@@ -215,6 +236,11 @@ def get_recordings(request: HttpRequest, public: bool | None = None):
     # TODO with larger dataset it may be better to do this in a queryset instead of python
     for recording in recordings:
         user = User.objects.get(id=recording['owner_id'])
+        fileAnnotations = RecordingAnnotation.objects.filter(recording=recording['id'])
+        recording['fileAnnotations'] = [
+            RecordingAnnotationSchema.from_orm(fileAnnotation).dict()
+            for fileAnnotation in fileAnnotations
+        ]
         recording['owner_username'] = user.username
         recording['audio_file_presigned_url'] = default_storage.url(recording['audio_file'])
         recording['hasSpectrogram'] = Recording.objects.get(id=recording['id']).has_spectrogram
@@ -227,9 +253,12 @@ def get_recordings(request: HttpRequest, public: bool | None = None):
             .count()
         )
         recording['userAnnotations'] = unique_users_with_annotations
-        user_has_annotations = Annotations.objects.filter(
-            recording_id=recording['id'], owner=request.user
-        ).exists()
+        user_has_annotations = (
+            Annotations.objects.filter(recording_id=recording['id'], owner=request.user).exists()
+            or RecordingAnnotation.objects.filter(
+                recording_id=recording['id'], owner=request.user
+            ).exists()
+        )
         recording['userMadeAnnotations'] = user_has_annotations
 
     return list(recordings)
@@ -249,17 +278,38 @@ def get_recording(request: HttpRequest, id: int):
             recording['hasSpectrogram'] = Recording.objects.get(id=recording['id']).has_spectrogram
             if recording['recording_location']:
                 recording['recording_location'] = json.loads(recording['recording_location'].json)
-            unique_users_with_annotations = (
+            annotation_owners = (
                 Annotations.objects.filter(recording_id=recording['id'])
-                .values('owner')
+                .values_list('owner', flat=True)
                 .distinct()
-                .count()
+            )
+            recording_annotation_owners = (
+                RecordingAnnotation.objects.filter(recording_id=recording['id'])
+                .values_list('owner', flat=True)
+                .distinct()
+            )
+
+            # Combine the sets of owners and count unique entries
+            unique_users_with_annotations = len(
+                set(annotation_owners).union(set(recording_annotation_owners))
             )
             recording['userAnnotations'] = unique_users_with_annotations
-            user_has_annotations = Annotations.objects.filter(
-                recording_id=recording['id'], owner=request.user
-            ).exists()
+            user_has_annotations = (
+                Annotations.objects.filter(
+                    recording_id=recording['id'], owner=request.user
+                ).exists()
+                or RecordingAnnotation.objects.filter(
+                    recording_id=recording['id'], owner=request.user
+                ).exists()
+            )
             recording['userMadeAnnotations'] = user_has_annotations
+            fileAnnotations = RecordingAnnotation.objects.filter(recording=id).order_by(
+                'confidence'
+            )
+            recording['fileAnnotations'] = [
+                RecordingAnnotationSchema.from_orm(fileAnnotation).dict()
+                for fileAnnotation in fileAnnotations
+            ]
 
             return recording
         else:
@@ -268,6 +318,18 @@ def get_recording(request: HttpRequest, id: int):
         return {'error': 'Recording not found'}
 
 
+@router.get('/{recording_id}/recording-annotations')
+def get_recording_annotations(request: HttpRequest, recording_id: int):
+    fileAnnotations = RecordingAnnotation.objects.filter(recording=recording_id).order_by(
+        'confidence'
+    )
+    output = [
+        RecordingAnnotationSchema.from_orm(fileAnnotation).dict()
+        for fileAnnotation in fileAnnotations
+    ]
+    return output
+
+
 @router.get('/{id}/spectrogram')
 def get_spectrogram(request: HttpRequest, id: int):
     try: