85 lines
5.0 KiB
Python
85 lines
5.0 KiB
Python
# Generated by Django 4.2.30 on 2026-07-13 14:36
|
|
|
|
from django.db import migrations, models
|
|
import django.db.models.deletion
|
|
|
|
|
|
class Migration(migrations.Migration):
|
|
|
|
initial = True
|
|
|
|
dependencies = [
|
|
]
|
|
|
|
operations = [
|
|
migrations.CreateModel(
|
|
name='AnalysisRun',
|
|
fields=[
|
|
('id', models.BigAutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
|
|
('csv_glob', models.CharField(help_text='Glob pattern for CSV files', max_length=1024)),
|
|
('config', models.JSONField(blank=True, default=dict, help_text='YAML config snapshot')),
|
|
('status', models.CharField(choices=[('pending', 'Pending'), ('loading', 'Loading Data'), ('profiling', 'Profiling'), ('aggregating', 'Building Entity Profiles'), ('clustering', 'Clustering'), ('extracting', 'Extracting Features'), ('completed', 'Completed'), ('failed', 'Failed')], default='pending', max_length=32)),
|
|
('created_at', models.DateTimeField(auto_now_add=True)),
|
|
('updated_at', models.DateTimeField(auto_now=True)),
|
|
('error_message', models.TextField(blank=True, default='')),
|
|
('total_flows', models.IntegerField(blank=True, null=True)),
|
|
('entity_count', models.IntegerField(blank=True, null=True)),
|
|
('cluster_count', models.IntegerField(blank=True, null=True)),
|
|
('entity_column', models.CharField(blank=True, default='', help_text='Auto-detected entity column name', max_length=256)),
|
|
],
|
|
options={
|
|
'ordering': ['-created_at'],
|
|
},
|
|
),
|
|
migrations.CreateModel(
|
|
name='ClusterResult',
|
|
fields=[
|
|
('id', models.BigAutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
|
|
('cluster_label', models.IntegerField(help_text='Cluster label (-1 for noise)')),
|
|
('size', models.IntegerField(help_text='Number of entities in this cluster')),
|
|
('proportion', models.FloatField(blank=True, help_text='Proportion of total entities', null=True)),
|
|
('noise_ratio', models.FloatField(blank=True, help_text='Noise ratio of the clustering', null=True)),
|
|
('silhouette_score', models.FloatField(blank=True, help_text='Silhouette score (sampled if large)', null=True)),
|
|
('run', models.ForeignKey(on_delete=django.db.models.deletion.CASCADE, related_name='clusters', to='tianxuan_analysis.analysisrun')),
|
|
],
|
|
options={
|
|
'unique_together': {('run', 'cluster_label')},
|
|
},
|
|
),
|
|
migrations.CreateModel(
|
|
name='EntityProfile',
|
|
fields=[
|
|
('id', models.BigAutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
|
|
('entity_value', models.CharField(help_text='Entity identifier (IP, domain, etc.)', max_length=512)),
|
|
('cluster_label', models.IntegerField(blank=True, help_text='Assigned cluster (-1=noise)', null=True)),
|
|
('feature_json', models.JSONField(blank=True, default=dict, help_text='Aggregated entity features as dict')),
|
|
('embedding_x', models.FloatField(blank=True, help_text='PCA-2D X coordinate', null=True)),
|
|
('embedding_y', models.FloatField(blank=True, help_text='PCA-2D Y coordinate', null=True)),
|
|
('cluster', models.ForeignKey(blank=True, null=True, on_delete=django.db.models.deletion.SET_NULL, related_name='entities', to='tianxuan_analysis.clusterresult')),
|
|
('run', models.ForeignKey(on_delete=django.db.models.deletion.CASCADE, related_name='entities', to='tianxuan_analysis.analysisrun')),
|
|
],
|
|
options={
|
|
'unique_together': {('run', 'entity_value')},
|
|
},
|
|
),
|
|
migrations.CreateModel(
|
|
name='ClusterFeature',
|
|
fields=[
|
|
('id', models.BigAutoField(auto_created=True, primary_key=True, serialize=False, verbose_name='ID')),
|
|
('feature_name', models.CharField(max_length=256)),
|
|
('mean', models.FloatField(blank=True, null=True)),
|
|
('std', models.FloatField(blank=True, null=True)),
|
|
('median', models.FloatField(blank=True, null=True)),
|
|
('p25', models.FloatField(blank=True, null=True)),
|
|
('p75', models.FloatField(blank=True, null=True)),
|
|
('missing_rate', models.FloatField(blank=True, null=True)),
|
|
('distinguishing_score', models.FloatField(blank=True, help_text='Z-score or ANOVA F-score', null=True)),
|
|
('distinguishing_method', models.CharField(default='zscore', max_length=16)),
|
|
('cluster', models.ForeignKey(on_delete=django.db.models.deletion.CASCADE, related_name='features', to='tianxuan_analysis.clusterresult')),
|
|
],
|
|
options={
|
|
'unique_together': {('cluster', 'feature_name')},
|
|
},
|
|
),
|
|
]
|