Add initial input table validation schemas

src/ispypsa/validation/schemas/network_expansion_options.yaml

@@ -0,0 +1,32 @@
+table: network_expansion_options
+required: false
+unique:
+  - [expansion_id]
+description: >
+  Defines the selected expansion option and allowed capacity increase for
+  expandable network elements. Covers both physical transmission paths and
+  group constraints that can be relaxed through expansion.
+  expansion_id maps to either a path_id in network_transmission_paths or a
+  constraint_id in constraints_rhs.
+  If this table is absent, no network expansion is modelled.
+columns:
+  expansion_id:
+    type: string
+    required: true
+    allowed_values_from:
+      - table: network_transmission_paths
+        column: path_id
+      - table: constraints_rhs
+        column: constraint_id
+    description: >
+      Identifier for the expandable network element. Maps to path_id in
+      network_transmission_paths for physical paths, or to constraint_id
+      in constraints_rhs for group constraints.
+  allowed_expansion:
+    type: float
+    required: true
+    description: Capacity increase in MW provided by the selected expansion option.
+  expansion_option:
+    type: string
+    required: false
+    description: Name of the selected augmentation option, retained for traceability.

src/ispypsa/validation/schemas/network_nodes.yaml

@@ -0,0 +1,31 @@
+table: network_nodes
+required: true
+unique:
+  - [node_id]
+description: >
+  Unified node table representing all spatial entities in the network model:
+  NEM subregions, NEM regions, and renewable energy zones (REZs).
+  All table mappings use node_id as the primary key.
+  Subregion and region nodes are for spatial rollups and results formatting only.
+  Required — the model cannot run without nodes defined.
+columns:
+  node_id:
+    type: string
+    required: true
+    description: Unique identifier for the node.
+  node_type:
+    type: string
+    required: true
+    allowed_values: [subregion, region, rez]
+    description: Type of spatial entity.
+  region_id:
+    type: string
+    required: true
+    allowed_values: [QLD, NSW, VIC, SA, TAS]
+    description: NEM region the node belongs to.
+  subregion_id:
+    type: string
+    required: true
+    description: >
+      ISP sub-region the node belongs to.
+      For subregion nodes, equals node_id.

src/ispypsa/validation/schemas/network_transmission_path_expansion_costs.yaml

@@ -0,0 +1,26 @@
+table: network_transmission_path_expansion_costs
+required: false
+unique:
+  - [expansion_id, year]
+description: >
+  Time-varying annualised expansion costs for network elements, covering both
+  physical transmission paths and group constraints.
+  Merges flow path and REZ transmission expansion costs into a single long-format
+  table.
+  If this table is absent, network expansion is treated as free.
+columns:
+  expansion_id:
+    type: string
+    required: true
+    allowed_values_from:
+      table: network_expansion_options
+      column: expansion_id
+    description: Identifier for the expandable network element.
+  year:
+    type: integer
+    required: true
+    description: Financial year the cost applies to.
+  cost:
+    type: float
+    required: true
+    description: Annualised expansion cost in $/MW.

src/ispypsa/validation/schemas/network_transmission_path_limits.yaml

@@ -0,0 +1,46 @@
+table: network_transmission_path_limits
+required: false
+custom_validation:
+  - name: no_duplicate_path_direction_timeslice
+    description: >
+      No two rows may have the same path_id, direction, and timeslice value.
+      For NaN timeslice rows, at most one row is permitted per path_id and
+      direction combination.
+description: >
+  Static transmission capacity limits for each path by direction and timeslice.
+  Sourced from flow_path_transfer_capability and interconnector_transfer_capability
+  in the IASR workbook.
+  For REZ connections that are constraint-modelled rather than physically limited,
+  capacity is NaN — the translator assigns a sufficiently large default capacity
+  for these rows.
+  If timeslice is absent, capacity is treated as a static limit applying to all
+  conditions.
+  If this table is absent, no transmission capacity limits are enforced.
+columns:
+  path_id:
+    type: string
+    required: true
+    allowed_values_from:
+      table: network_transmission_paths
+      column: path_id
+    description: Transmission path identifier.
+  direction:
+    type: string
+    required: true
+    allowed_values: [forward, reverse]
+    description: Power flow direction relative to node_from and node_to.
+  timeslice:
+    type: string
+    required: false
+    allowed_values_from:
+      table: timeslices
+      column: timeslice_id
+    description: >
+      Demand condition the limit applies to.
+      If absent, capacity is treated as a static limit applying to all conditions.
+  capacity:
+    type: float
+    required: false
+    description: >
+      Transfer capability approximation in MW.
+      NaN indicates a constraint-modelled path with no explicit physical limit.

src/ispypsa/validation/schemas/network_transmission_paths.yaml

@@ -0,0 +1,33 @@
+table: network_transmission_paths
+required: false
+unique:
+  - [path_id]
+description: >
+  Transmission paths connecting nodes in the network model, including
+  inter-subregional flow paths, regional interconnectors, and REZ-to-subregion
+  connections. If absent, the model is constructed with no transmission paths.
+  Nodes with no connecting paths are electrically isolated.
+columns:
+  path_id:
+    type: string
+    required: true
+    description: Unique identifier for the path, formatted as node_from-node_to.
+  node_from:
+    type: string
+    required: true
+    allowed_values_from:
+      table: network_nodes
+      column: node_id
+    description: Origin node. Defines the forward flow direction.
+  node_to:
+    type: string
+    required: true
+    allowed_values_from:
+      table: network_nodes
+      column: node_id
+    description: Destination node. Defines the forward flow direction.
+  carrier:
+    type: string
+    required: true
+    allowed_values: [AC, DC]
+    description: Transmission technology.

src/ispypsa/validation/schemas/node_resource_limits.yaml

@@ -0,0 +1,47 @@
+table: node_resource_limits
+required: false
+unique:
+  - [node_id, resource_type, limit_type]
+description: >
+  Resource and land use limits for nodes in the network model.
+  Each row represents a limit on a specific resource type within a node.
+  Nodes with no rows in this table have no resource limits applied.
+  If resource_limit_penalty is NaN, no violation is allowed (hard cap).
+  If resource_limit_penalty is 0.0, there is effectively no limit — generation
+  can exceed the limit at zero cost.
+  If resource_limit_penalty is a positive value, the translator creates dummy
+  penalty generators to allow relaxation at that annualised cost in $/MW.
+  If this table is absent, the model is constructed without resource limits.
+columns:
+  node_id:
+    type: string
+    required: true
+    allowed_values_from:
+      table: network_nodes
+      column: node_id
+    description: Node identifier.
+  resource_type:
+    type: string
+    required: true
+    allowed_values: [wind_high, wind_medium, wind_offshore_fixed, wind_offshore_floating, solar, wind]
+    description: Resource type the limit applies to.
+  limit_type:
+    type: string
+    required: true
+    allowed_values: [generation, land_use]
+    description: >
+      Necessary to disambiguate resource_type values that appear in both
+      generation and land_use contexts (e.g. solar).
+  limit:
+    type: float
+    required: true
+    description: Limit value in MW.
+  resource_limit_penalty:
+    type: float
+    required: false
+    description: >
+      Annualised penalty in $/MW applied if a limit is exceeded.
+      NaN means no violation is allowed (hard cap).
+      0.0 means there is effectively no limit — generation can exceed the
+      limit at zero cost.
+      If this column is absent, all limits are treated as hard caps.