Improve the traffic fetching system

services/data/migrations/versions/001_create_traffic_data_table.py

@@ -0,0 +1,54 @@
+"""Create traffic_data table for storing traffic data for re-training
+
+Revision ID: 001_traffic_data
+Revises: 
+Create Date: 2025-01-08 12:00:00.000000
+
+"""
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects.postgresql import UUID
+
+# revision identifiers, used by Alembic.
+revision = '001_traffic_data'
+down_revision = None
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    """Create traffic_data table"""
+    op.create_table('traffic_data',
+        sa.Column('id', UUID(as_uuid=True), nullable=False, primary_key=True),
+        sa.Column('location_id', sa.String(100), nullable=False, index=True),
+        sa.Column('date', sa.DateTime(timezone=True), nullable=False, index=True),
+        sa.Column('traffic_volume', sa.Integer, nullable=True),
+        sa.Column('pedestrian_count', sa.Integer, nullable=True),
+        sa.Column('congestion_level', sa.String(20), nullable=True),
+        sa.Column('average_speed', sa.Float, nullable=True),
+        sa.Column('source', sa.String(50), nullable=False, server_default='madrid_opendata'),
+        sa.Column('raw_data', sa.Text, nullable=True),
+        sa.Column('created_at', sa.DateTime(timezone=True), nullable=False),
+        sa.Column('updated_at', sa.DateTime(timezone=True), nullable=False),
+    )
+    
+    # Create index for efficient querying by location and date
+    op.create_index(
+        'idx_traffic_location_date', 
+        'traffic_data', 
+        ['location_id', 'date']
+    )
+    
+    # Create index for date range queries  
+    op.create_index(
+        'idx_traffic_date_range',
+        'traffic_data',
+        ['date']
+    )
+
+
+def downgrade():
+    """Drop traffic_data table"""
+    op.drop_index('idx_traffic_date_range', table_name='traffic_data')
+    op.drop_index('idx_traffic_location_date', table_name='traffic_data')
+    op.drop_table('traffic_data')