Better handle zero values in efficiency variables

Fix scenario report generation
polca · Dec 13, 2023 · b43bb3a · b43bb3a
1 parent c1083b1
commit b43bb3a
Show file tree

Hide file tree

Showing 4 changed files with 29 additions and 3 deletions.
diff --git a/premise/data_collection.py b/premise/data_collection.py
@@ -571,6 +571,7 @@ def __init__(
                 if any(x in k for x in ["biogas", "methane", "natural gas"])
             },
         )
+
         self.hydrogen_efficiencies = self.get_iam_efficiencies(
             data=data,
             efficiency_labels={
@@ -866,6 +867,12 @@ def get_iam_efficiencies(
                 eff_data.coords["variables"] = [
                     rev_eff_labels[x] for x in eff_data.variables.values
                 ]
+                # convert zero values to nan
+                # and back-fill and forward-fill missing values with nearest available
+                eff_data = eff_data.where(eff_data != 0)
+                eff_data = eff_data.bfill(dim="year")
+                eff_data = eff_data.ffill(dim="year")
+
             else:
                 return None
 
@@ -883,6 +890,10 @@ def get_iam_efficiencies(
                         data.loc[:, energy_labels[k], :].sum(dim="variables")
                         / data.loc[:, v, :]
                     )
+                    # back-fill nans
+                    d = d.bfill(dim="year")
+                    # forward-fill nans
+                    d = d.ffill(dim="year")
 
                 else:
                     # fill d with ones
@@ -1016,6 +1027,7 @@ def __get_carbon_capture_rate(
                         .sum(dim=["variables", "region"])
                         .values
                     )
+
                 except ZeroDivisionError:
                     rate.loc[dict(region="World", variables="cement")] = 0
 
@@ -1033,6 +1045,7 @@ def __get_carbon_capture_rate(
                     ].sum(
                         dim=["variables", "region"]
                     )
+
                 except ZeroDivisionError:
                     rate.loc[dict(region="World", variables="steel")] = 0
 

diff --git a/premise/iam_variables_mapping/cement_variables.yaml b/premise/iam_variables_mapping/cement_variables.yaml
@@ -8,6 +8,7 @@ cement, dry feed rotary kiln:
     message: Production|Non-Metallic Minerals|Cement
     gcam: Production|Industry|Cement
     tiam: Production|Cement
+
   energy_use_aliases:
     remind: FE|Industry|+++|Cement
     image:

diff --git a/premise/iam_variables_mapping/iam_region_to_climate.yaml b/premise/iam_variables_mapping/iam_region_to_climate.yaml
@@ -64,9 +64,11 @@ gcam:
   Brazil: tropical
   Canada: temperate
   Central America and Caribbean: tropical
+  Central Asia: temperate
   China: temperate
   Colombia: tropical
   EU-15: temperate
+  EU-12: temperate
   India: tropical
   Indonesia: tropical
   Japan: temperate
@@ -80,6 +82,14 @@ gcam:
   Southeast Asia: tropical
   Taiwan: tropical
   USA: temperate
+  Africa_Eastern: tropical
+  Africa_Southern: tropical
+  Africa_Western: tropical
+  Europe_Eastern: temperate
+  European Free Trade Association: temperate
+  Europe_Non_EU: temperate
+  South America_Northern: tropical
+  South Asia: tropical
 
 tiam:
   AFR: tropical

diff --git a/premise/report.py b/premise/report.py
@@ -183,22 +183,24 @@ def generate_summary_report(scenarios: list, filename: Path) -> None:
         },
         "Fuel (gasoline) - generation": {
             "filepath": IAM_FUELS_VARS,
-            "filter": ["gasoline", "ethanol"],
+            "filter": ["gasoline", "ethanol", "bioethanol", "methanol"],
         },
         "Fuel (gasoline) - efficiency": {
             "filepath": IAM_FUELS_VARS,
-            "filter": ["gasoline", "ethanol"],
+            "filter": ["gasoline", "ethanol", "bioethanol", "methanol"],
         },
         "Fuel (diesel) - generation": {
             "filepath": IAM_FUELS_VARS,
             "filter": [
                 "diesel",
+                "biodiesel",
             ],
         },
         "Fuel (diesel) - efficiency": {
             "filepath": IAM_FUELS_VARS,
             "filter": [
                 "diesel",
+                "biodiesel",
             ],
         },
         "Fuel (gas) - generation": {
@@ -296,7 +298,7 @@ def generate_summary_report(scenarios: list, filename: Path) -> None:
             variables = get_variables(filepath["filepath"])
             if "filter" in filepath:
                 variables = [
-                    x for x in variables if any(y in x for y in filepath["filter"])
+                    x for x in variables if any(x.startswith(y) for y in filepath["filter"])
                 ]
 
         worksheet = workbook.create_sheet(sector)