Change measurements and association DB indices to UUIDs

CHANGELOG.md

@@ -20,6 +20,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 
 #### Changed
 
+- V2: Change measurement and association DB indices to UUIDs [#844](https://github.com/askap-vast/vast-pipeline/pull/844)
 - V2: Limit associations upload to using num_io_workers [#833](https://github.com/askap-vast/vast-pipeline/pull/833)
 - V2: Allow user specification of dask dashboard paramters and add some further logging to dask setup [#829](https://github.com/askap-vast/vast-pipeline/pull/829)
 - V2: Replace all source, measurement, run etc. IDs with UUID indices. [#803](https://github.com/askap-vast/vast-pipeline/pull/803)
@@ -58,6 +59,7 @@ The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 
 #### List of PRs
 
+- [#844](https://github.com/askap-vast/vast-pipeline/pull/844): fix: V2: Change measurements and association DB indices to UUIDs
 - [#843](https://github.com/askap-vast/vast-pipeline/pull/843): feat: V2: Enable specification of Dask worker memory limits
 - [#833](https://github.com/askap-vast/vast-pipeline/pull/833): feat: V2: Limit associations upload to using num_io_workers
 - [#829](https://github.com/askap-vast/vast-pipeline/pull/829): feat: V2: Allow user specification of dask dashboard paramters and add some further logging to dask setup

vast_pipeline/image/main.py

@@ -6,6 +6,7 @@
 import logging
 import numpy as np
 import pandas as pd
+import uuid
 
 from django.conf import settings
 from astropy.io import fits
@@ -18,9 +19,7 @@
 
 from vast_pipeline import models
 from vast_pipeline.survey.translators import tr_selavy
-from vast_pipeline.utils.utils import (
-    generate_shortuuid, UUID_LEN_MEAS,
-)
+
 from vast_pipeline.image.utils import get_fits_header
 
 
@@ -341,7 +340,7 @@ def read_selavy(self, dj_image: models.Image) -> pd.DataFrame:
                 df[key["name"]] = df[key["name"]].astype(key["dtype"])
 
         # Add id column
-        df["id"] = df.apply(lambda _: generate_shortuuid(UUID_LEN_MEAS), axis=1)
+        df["id"] = df.apply(lambda _: str(uuid.uuid4()), axis=1)
 
         # do checks and fill in missing field for uploading sources
         # in DB (see fields in models.py -> Source model)

vast_pipeline/migrations/0003_alter_association_id_alter_measurement_id.py

@@ -0,0 +1,24 @@
+# Generated by Django 5.1.6 on 2025-03-30 23:19
+
+import uuid
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('vast_pipeline', '0002_q3c'),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name='association',
+            name='id',
+            field=models.UUIDField(default=uuid.uuid4, editable=False, primary_key=True, serialize=False),
+        ),
+        migrations.AlterField(
+            model_name='measurement',
+            name='id',
+            field=models.UUIDField(default=uuid.uuid4, editable=False, primary_key=True, serialize=False),
+        ),
+    ]

vast_pipeline/models.py

@@ -1,4 +1,5 @@
 import numpy as np
+import uuid
 
 from dataclasses import dataclass
 from itertools import combinations
@@ -417,7 +418,7 @@ class Measurement(CommentableModel):
     Essentially a source single measurement in time.
     """
 
-    id = ShortUUIDField(primary_key=True, editable=False, length=UUID_LEN_MEAS, alphabet=UUID_ALPHABET)
+    id = models.UUIDField(primary_key=True, default=uuid.uuid4, editable=False)
     image = models.ForeignKey(
         Image, null=True, on_delete=models.CASCADE, to_field="id"
     )  # first image seen in
@@ -713,7 +714,7 @@ class Association(models.Model):
     some parameters
     """
 
-    id = ShortUUIDField(primary_key=True, editable=False, length=UUID_LEN_MEAS, alphabet=UUID_ALPHABET)
+    id = models.UUIDField(primary_key=True, default=uuid.uuid4, editable=False)
     source = models.ForeignKey(Source, on_delete=models.CASCADE, to_field="id")
     meas = models.ForeignKey(Measurement, on_delete=models.CASCADE, to_field="id")
 

vast_pipeline/pipeline/forced_extraction.py

@@ -1,6 +1,8 @@
 import os
 import logging
 import datetime
+import uuid
+
 import numpy as np
 import pandas as pd
 import dask.dataframe as dd
@@ -20,11 +22,7 @@
 from vast_pipeline.pipeline.loading import copy_upload_measurements
 
 from forced_phot import ForcedPhot
-from ..utils.utils import (
-    StopWatch,
-    generate_shortuuid,
-    UUID_LEN_MEAS
-)
+from ..utils.utils import StopWatch
 from vast_pipeline.image.utils import open_fits
 
 # NOTE: We check here to see if we're in a testing environment.
@@ -486,7 +484,7 @@ def _update_forced_measurements(df: pd.DataFrame) -> pd.DataFrame:
             The forced extraction dataframe updated with defaults.
         """
         df["name"] = df["name"] + f"_f_{p_run_id}"
-        df["id"] = df.apply(lambda _: generate_shortuuid(UUID_LEN_MEAS), axis=1)
+        df["id"] = df.apply(lambda _: str(uuid.uuid4()), axis=1)
         default_pos_err = settings.POS_DEFAULT_MIN_ERROR / 3600.0
         df["ra_err"] = default_pos_err
         df["dec_err"] = default_pos_err

vast_pipeline/pipeline/loading.py

@@ -9,6 +9,7 @@
 from itertools import islice
 from django.db import transaction, connection, models
 from contextlib import closing
+from uuid import uuid4
 
 from vast_pipeline.image.main import SelavyImage
 from vast_pipeline.pipeline.model_generator import (
@@ -36,7 +37,6 @@
     deg2hms,
     deg2dms,
     generate_shortuuid,
-    UUID_LEN_MEAS,
     UUID_LEN_SOURCE
 )
 
@@ -432,7 +432,7 @@ def copy_upload_associations(
     }
 
     def upload(df, Association, mapping, batch_size):
-        df["db_id"] = df.apply(lambda _: generate_shortuuid(UUID_LEN_MEAS), axis=1)
+        df["db_id"] = df.apply(lambda _: str(uuid4()), axis=1)
         copy_upload_model(df, Association, mapping=mapping, batch_size=batch_size)
 
     associations_df = associations_df[columns_to_upload].map_partitions(upload,

vast_pipeline/plots.py

@@ -84,6 +84,7 @@ def plot_lightcurve(
 
     # lightcurve required cols: taustart_ts, flux, flux_err_upper, flux_err_lower, forced
     lightcurve = pd.DataFrame(measurements_qs)
+    lightcurve['id'] = lightcurve['id'].astype(str)
 
     # remap method values to labels to make a better legend
     lightcurve["method"] = lightcurve.forced.map({True: "Forced", False: "Selavy"})
@@ -167,6 +168,13 @@ def plot_lightcurve(
             )
             .reset_index()
         )
+
+        candidate_measurement_pairs_df = candidate_measurement_pairs_df.astype(
+            {'measurement_a_id': 'str',
+             'measurement_b_id': 'str',
+            }
+        )
+
         g = nx.Graph()
         for _row in candidate_measurement_pairs_df.itertuples(index=False):
             g.add_edge(_row.measurement_a_id, _row.measurement_b_id)

vast_pipeline/serializers.py

@@ -56,7 +56,7 @@ class Meta:
 
 
 class MeasurementSerializer(serializers.ModelSerializer):
-    id = serializers.CharField(read_only=True)
+    id = serializers.UUIDField(read_only=True)
     frequency = serializers.SerializerMethodField(read_only=True)
 
     def get_frequency(self, obj):

vast_pipeline/urls.py

@@ -38,6 +38,11 @@
         name="image_detail",
     ),
     path("measurements/", views.MeasurementIndex, name="measurement_index"),
+    path(
+        "measurements/<uuid:id>/",
+        views.MeasurementDetail,
+        name="measurement_detail"
+    ),
     re_path(
         fr"^measurements/(?P<id>[\w]{{{UUID_LEN_MEAS}}})(?:/(?P<action>[\w]+))?/$",
         views.MeasurementDetail,