EIA191 rp8 data integration

dbt/models/eia191/core_eia191__monthly_gas_storage/schema.yml

@@ -0,0 +1,61 @@
+version: 2
+sources:
+  - name: pudl
+    tables:
+      - name: core_eia191__monthly_gas_storage
+
+        data_tests:
+          - expect_columns_not_all_null
+          - check_row_counts_per_partition:
+              arguments:
+                table_name: core_eia191__monthly_gas_storage
+                partition_expr: "report_date"
+          - expect_sum_close_to_total_column:
+              arguments:
+                sum_columns:
+                  - working_gas_capacity_mcf
+                  - base_gas_mcf
+                total_column: total_field_capacity_mcf
+                discrepancy_threshold: 0.01
+                max_discrepancy_rate: 0.25
+              description: >
+                total_field_capacity_mcf is reported as design capacity (base + working gas)
+                but is not reliably additive: approximately 23% of records have
+                total_field_capacity_mcf != working_gas_capacity_mcf + base_gas_mcf. This
+                reflects loose EIA definitions and operator self-reporting practices. The
+                threshold is set just above the observed ~23% failure rate so regressions
+                are flagged but existing failures do not hard-fail.
+
+        columns:
+          - name: storage_field_id_eia
+          - name: report_date
+          - name: state
+          - name: gas_field_id_eia
+          - name: reservoir_id_eia
+          - name: company_name
+          - name: field_name
+          - name: reservoir_name
+          - name: field_type
+          - name: county
+          - name: operational_status
+          - name: base_gas_mcf
+            data_tests:
+              - dbt_expectations.expect_column_min_to_be_between:
+                  arguments:
+                    min_value: 0
+          - name: working_gas_capacity_mcf
+            data_tests:
+              - dbt_expectations.expect_column_min_to_be_between:
+                  arguments:
+                    min_value: 0
+          - name: total_field_capacity_mcf
+            data_tests:
+              - dbt_expectations.expect_column_min_to_be_between:
+                  arguments:
+                    min_value: 0
+          - name: maximum_daily_delivery_mcf
+            data_tests:
+              - dbt_expectations.expect_column_min_to_be_between:
+                  arguments:
+                    min_value: 0
+          - name: region

migrations/versions/8ea3f44edf13_eia191_monthly_gas_storage.py

@@ -0,0 +1,46 @@
+"""eia191 monthly gas storage
+
+Revision ID: 8ea3f44edf13
+Revises: 649d707df89a
+Create Date: 2026-03-24 15:01:02.919488
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = '8ea3f44edf13'
+down_revision = '649d707df89a'
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.create_table('core_eia191__monthly_gas_storage',
+    sa.Column('storage_field_id_eia', sa.Text(), nullable=False, comment='EIA-assigned identifier for an underground natural gas storage reservoir. IDs are assigned per company and state, so the same physical reservoir may have different IDs if ownership changes.'),
+    sa.Column('report_date', sa.Date(), nullable=False, comment='Date reported.'),
+    sa.Column('state', sa.Text(), nullable=True, comment='Two letter US state abbreviation.'),
+    sa.Column('gas_field_id_eia', sa.Integer(), nullable=True, comment='EIA-assigned numeric identifier for a natural gas storage field.'),
+    sa.Column('reservoir_id_eia', sa.Integer(), nullable=True, comment='EIA-assigned numeric identifier for the individual storage reservoir within a natural gas storage field.'),
+    sa.Column('company_name', sa.Text(), nullable=True, comment='Name of the reporting company.'),
+    sa.Column('field_name', sa.Text(), nullable=True, comment='Name of the natural gas storage field.'),
+    sa.Column('reservoir_name', sa.Text(), nullable=True, comment='Name of the individual underground natural gas storage reservoir.'),
+    sa.Column('field_type', sa.Enum('aquifer', 'depleted field', 'salt dome'), nullable=True, comment='Type of underground natural gas storage facility. One of: depleted field (a reservoir previously used for natural gas production), aquifer (a porous rock structure used to store gas), or salt dome (a cavern created within a salt formation).'),
+    sa.Column('county', sa.Text(), nullable=True, comment='County name.'),
+    sa.Column('operational_status', sa.Enum('active', 'inactive'), nullable=True, comment='Operational status of the underground natural gas storage reservoir.'),
+    sa.Column('base_gas_mcf', sa.Float(), nullable=True, comment='Volume of base gas (cushion gas) in the underground storage reservoir. Base gas is the volume of gas intended as permanent inventory in a reservoir to maintain adequate pressure and deliverability rates.'),
+    sa.Column('working_gas_capacity_mcf', sa.Float(), nullable=True, comment='Volume of working gas (the portion of stored gas available for withdrawal) in the underground storage reservoir.'),
+    sa.Column('total_field_capacity_mcf', sa.Float(), nullable=True, comment='Total design capacity of the underground natural gas storage field (base gas plus working gas).'),
+    sa.Column('maximum_daily_delivery_mcf', sa.Float(), nullable=True, comment='Maximum daily quantity of gas that can be withdrawn from the underground storage reservoir under normal operating conditions.'),
+    sa.Column('region', sa.Enum('alaska', 'east region', 'midwest region', 'mountain region', 'pacific region', 'south central region'), nullable=True, comment='EIA storage region in which the underground natural gas storage field is located.'),
+    sa.PrimaryKeyConstraint('storage_field_id_eia', 'report_date', name=op.f('pk_core_eia191__monthly_gas_storage'))
+    )
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_table('core_eia191__monthly_gas_storage')
+    # ### end Alembic commands ###