domainiac 3.0.0__tar.gz → 5.0.0__tar.gz

{domainiac-3.0.0 → domainiac-5.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: domainiac
-Version: 3.0.0
+Version: 5.0.0
 Summary: Package for working with Energinet data, but with specialized functions used for Enigma.
 Author: Team Enigma
 Author-email: gridop-enigma@energinet.dk

{domainiac-3.0.0 → domainiac-5.0.0}/domainiac/managers/plant_manager.py

@@ -41,20 +41,20 @@ class PlantManager(MasterdataManager):
             "is_tso_connected",
             "valid_from_date_utc",
             "valid_to_date_utc",
-            "net_component_id",
+            "primary_net_component_id",
         ]
         if not columns:
             columns = default_columns
 
         # TODO: masterdata_plant table doesn't have net_component_id column
         # Find a better way to do this in future.
-        plant_columns = [col for col in columns if col != "net_component_id"]
+        plant_columns = [col for col in columns if col != "primary_net_component_id"]
         df_plant = self.get_data(
             "masterdataPlant", filters=filters, columns=plant_columns
         )
-        df_psrt = self._get_power_system_resource_type()
-        df = df_psrt.merge(
-            df_plant, on=["plant_id"], how="inner", validate="m:1"
+        df_psr = self._get_power_system_resource()
+        df = df_plant.merge(
+            df_psr, on=["plant_id"], how="left", validate="m:1"
         ).drop_duplicates()
 
         df = df[columns]
@@ -117,23 +117,44 @@ class PlantManager(MasterdataManager):
 
         return df
 
-    def _get_power_system_resource_type(self) -> pd.DataFrame:
+    def _get_power_system_resource(self) -> pd.DataFrame:
 
-        df_unit = self.unit_manager.get_units(columns=["masterdata_gsrn"])
+        df_unit = self.unit_manager.get_units(
+            columns=["masterdata_gsrn", "capacity_min_MW", "capacity_max_MW"]
+        )
 
-        df_power_system_resource_map = self.db.query("masterdataAggregatedUnit")[
+        df_psr_mapping = self.db.query("masterdataAggregatedUnit")[
             ["unit_gsrn", "net_component_id"]
         ]
 
-        df_unit = df_unit[["masterdata_gsrn", "plant_id"]]
-
         df = pd.merge(
-            df_power_system_resource_map,
+            df_psr_mapping,
             df_unit,
             left_on="unit_gsrn",
             right_on="masterdata_gsrn",
-            how="inner",
+            how="left",
             validate="1:m",
-        )[["net_component_id", "plant_id"]]
+        )
+
+        # for a small number of plants, the underlying unit can
+        # be associated with different net components. Too avoid
+        # this issue, we choose for each plant, the net component,
+        # for which the underlying units amounts to the largest
+        # capacity
+        df = pdz.group(df, by=["net_component_id", "plant_id"]).agg(
+            {"capacity_min_MW": "sum", "capacity_max_MW": "sum"}
+        )
+
+        df["capacity_range_MW"] = df["capacity_max_MW"] - df["capacity_min_MW"]
+
+        df = df.sort_values(
+            ["plant_id", "capacity_range_MW"], ascending=False
+        ).drop_duplicates(subset=["plant_id"], keep="first")
+
+        df = df.rename(
+            columns={
+                "net_component_id": "primary_net_component_id",
+            }
+        )
 
         return df

{domainiac-3.0.0 → domainiac-5.0.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "domainiac"
-version = "3.0.0"
+version = "5.0.0"
 description = "Package for working with Energinet data, but with specialized functions used for Enigma."
 authors = ["Team Enigma <gridop-enigma@energinet.dk>"]
 packages = [