Merge branch 'main' into olex/misc

xl2times/__main__.py

@@ -147,10 +147,10 @@ def convert_xl_to_times(
         transforms.process_units,
         transforms.complete_commodity_groups,
         transforms.process_wildcards,
+        transforms.convert_aliases,
         transforms.apply_transform_tables,
         transforms.explode_process_commodity_cols,
         transforms.apply_final_fixup,
-        transforms.convert_aliases,
         transforms.assign_model_attributes,
         transforms.fix_topology,
         transforms.resolve_remaining_cgs,

xl2times/datatypes.py

@@ -4,6 +4,7 @@
 from collections.abc import Iterable
 from dataclasses import dataclass, field
 from enum import Enum
+from functools import cached_property
 from importlib import resources
 from itertools import chain
 from pathlib import PurePath
@@ -266,6 +267,21 @@ def model_years(self) -> set[int]:
         """
         return self.past_years | set(self.time_periods["m"].values)
 
+    # TODO: Invalidate and recompute the below property when self.topology changes.
+    @cached_property
+    def veda_cgs(self) -> dict[tuple[str, str, str], str]:
+        """A dictionary mapping commodities to their Veda commodity groups."""
+        cols = ["region", "process", "commodity", "csets"]
+        # Exclude auxillary flows
+        index = self.topology["io"].isin({"IN", "OUT"})
+        veda_cgs = self.topology[cols + ["io"]][index].copy()
+        veda_cgs.drop_duplicates(subset=cols, keep="last", inplace=True)
+        veda_cgs["veda_cg"] = veda_cgs["csets"] + veda_cgs["io"].str[:1]
+        veda_cgs = veda_cgs.set_index(["region", "process", "commodity"])[
+            "veda_cg"
+        ].to_dict()
+        return veda_cgs
+
 
 class Config:
     """Encapsulates all configuration options for a run of the tool, including the