process and save data

UNFCCC_GHG_data/UNFCCC_reader/Burundi/config_BDI_BUR1.py

@@ -144,8 +144,13 @@ coords_terminologies = {
     "scenario": "PRIMAP",
 }
 
-
-gwp_to_use = "AR4GWP100"
+# Page 64: The global warming potentials (GWPs) recommended by the IPCC Fifth Assessment Report (AR5)
+# and based on the annex to Decision 18/CMA.1 have been used to convert GHGs other than CO2
+# into their equivalent. These GWPs provide a consistent basis for comparing the relative effect
+# of emissions of all GHGs standardized over a 100-year period by converting emissions of other
+# GHGs into those of CO2. The values adopted for the three direct GHGs are 1 for CO2, 28 for CH4
+# and 265 for N2O.
+gwp_to_use = "AR5GWP100"
 coords_value_mapping = {
     "unit": "PRIMAP1",
     "category": "PRIMAP1",
@@ -178,3 +183,50 @@ meta_data = {
     "comment": "Read fom pdf by Daniel Busch",
     "institution": "UNFCCC",
 }
+
+country_processing_step1 = {
+    "aggregate_cats": {
+        "M.3.C.AG": {
+            "sources": [
+                "3.C.1",
+                "3.C.2",
+                "3.C.3",
+                "3.C.4",
+                "3.C.5",
+                "3.C.6",
+                "3.C.7",
+                "3.C.8",
+            ],
+            "name": "Aggregate sources and non-CO2 emissions sources on land "
+            "(Agriculture)",
+        },
+        "M.3.D.AG": {"sources": ["3.D.2"], "name": "Other (Agriculture)"},
+        "M.AG.ELV": {
+            "sources": ["M.3.C.AG", "M.3.D.AG"],
+            "name": "Agriculture excluding livestock",
+        },
+        "M.AG": {"sources": ["3.A", "M.AG.ELV"], "name": "Agriculture"},
+        "M.3.D.LU": {"sources": ["3.D.1"], "name": "Other (LULUCF)"},
+        "M.LULUCF": {"sources": ["3.B", "M.3.D.LU"], "name": "LULUCF"},
+        "M.0.EL": {
+            "sources": ["1", "2", "M.AG", "4"],
+            "name": "National total emissions excluding LULUCF",
+        },
+    },
+    "basket_copy": {
+        "GWPs_to_add": ["SARGWP100", "AR4GWP100", "AR6GWP100"],
+        "entities": ["HFCS", "PFCS"],
+        "source_GWP": gwp_to_use,
+    },
+}
+
+gas_baskets = {
+    "FGASES (SARGWP100)": ["HFCS (SARGWP100)", "PFCS (SARGWP100)", "SF6", "NF3"],
+    "FGASES (AR4GWP100)": ["HFCS (AR4GWP100)", "PFCS (AR4GWP100)", "SF6", "NF3"],
+    "FGASES (AR5GWP100)": ["HFCS (AR5GWP100)", "PFCS (AR5GWP100)", "SF6", "NF3"],
+    "FGASES (AR6GWP100)": ["HFCS (AR6GWP100)", "PFCS (AR6GWP100)", "SF6", "NF3"],
+    "KYOTOGHG (SARGWP100)": ["CO2", "CH4", "N2O", "FGASES (SARGWP100)"],
+    "KYOTOGHG (AR4GWP100)": ["CO2", "CH4", "N2O", "FGASES (AR4GWP100)"],
+    "KYOTOGHG (AR5GWP100)": ["CO2", "CH4", "N2O", "FGASES (AR5GWP100)"],
+    "KYOTOGHG (AR6GWP100)": ["CO2", "CH4", "N2O", "FGASES (AR6GWP100)"],
+}

UNFCCC_GHG_data/UNFCCC_reader/Burundi/read_BDI_BUR1_from_pdf.py

@@ -9,6 +9,7 @@ import primap2 as pm2
 import pandas as pd
 
 from UNFCCC_GHG_data.helper import downloaded_data_path, extracted_data_path
+from UNFCCC_GHG_data.helper.functions import process_data_for_country
 
 from config_BDI_BUR1 import (
     inv_conf,
@@ -19,6 +20,8 @@ from config_BDI_BUR1 import (
     coords_defaults,
     coords_cols,
     years_to_read,
+    gas_baskets,
+    country_processing_step1,
 )
 
 # ###
@@ -176,4 +179,60 @@ df_all_IF = pm2.pm2io.convert_long_dataframe_if(
 
 print("Converting to primap2 format.")
 ### convert to primap2 format ###
-data_pm2_all = pm2.pm2io.from_interchange_format(df_all_IF)
+data_pm2 = pm2.pm2io.from_interchange_format(df_all_IF)
+
+
+# ###
+# Save raw data to IF and native format.
+# ###
+
+data_if = data_pm2.pr.to_interchange_format()
+
+pm2.pm2io.write_interchange_format(
+    output_folder / (output_filename + coords_terminologies["category"] + "_raw"),
+    data_if,
+)
+
+encoding = {var: compression for var in data_pm2.data_vars}
+data_pm2.pr.to_netcdf(
+    output_folder / (output_filename + coords_terminologies["category"] + "_raw.nc"),
+    encoding=encoding,
+)
+
+
+# ###
+# Processing
+# ###
+
+data_proc_pm2 = process_data_for_country(
+    data_country=data_pm2,
+    entities_to_ignore=[],
+    gas_baskets=gas_baskets,
+    filter_dims=None,  # leaving this explicit for now
+    cat_terminology_out=None,
+    category_conversion=None,
+    sectors_out=None,
+    processing_info_country=country_processing_step1,
+)
+
+
+# ###
+# save processed data to IF and native format
+# ###
+
+terminology_proc = coords_terminologies["category"]
+
+data_proc_if = data_proc_pm2.pr.to_interchange_format()
+
+if not output_folder.exists():
+    output_folder.mkdir()
+pm2.pm2io.write_interchange_format(
+    output_folder / (output_filename + terminology_proc), data_proc_if
+)
+
+encoding = {var: compression for var in data_proc_pm2.data_vars}
+data_proc_pm2.pr.to_netcdf(
+    output_folder / (output_filename + terminology_proc + ".nc"), encoding=encoding
+)
+
+print("Saved processed data.")