Move veda_cgs calculation to model property

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
 
@@ -205,6 +206,20 @@ def model_years(self) -> set[int]:
         """
         return self.past_years | set(self.time_periods["m"].values)
 
+    @cached_property
+    def veda_cgs(self) -> dict[tuple[str, str, str], str]:
+        """veda_cgs is 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

xl2times/transforms.py

@@ -1255,18 +1255,6 @@ def apply_fixups(
     tables: list[EmbeddedXlTable],
     model: TimesModel,
 ) -> list[EmbeddedXlTable]:
-
-    # Generate Veda CG info
-    cols = ["region", "process", "commodity", "csets"]
-    # Exclude auxillary flows
-    index = model.topology["io"].isin({"IN", "OUT"})
-    veda_cgs = model.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()
-
     def apply_fixups_table(table: EmbeddedXlTable):
         tag = Tag.fi_t
         if not table.tag == tag:
@@ -1286,7 +1274,9 @@ def apply_fixups_table(table: EmbeddedXlTable):
         if any(df["other_indexes"] == "veda_cg"):
             i = df["other_indexes"] == "veda_cg"
             df.loc[i, "other_indexes"] = df[i].apply(
-                lambda x: veda_cgs.get((x["region"], x["process"], x["commodity"])),
+                lambda x: model.veda_cgs.get(
+                    (x["region"], x["process"], x["commodity"])
+                ),
                 axis=1,
             )