Merge remote-tracking branch 'refs/remotes/origin/main' into cabo-verde

docs/source/api/unfccc_ghg_data.unfccc_reader.United_Kingdom.config_uk_inv2024.rst

@@ -0,0 +1,6 @@
+unfccc\_ghg\_data.unfccc\_reader.United\_Kingdom.config\_uk\_inv2024
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. automodule:: unfccc_ghg_data.unfccc_reader.United_Kingdom.config_uk_inv2024
+
+.. currentmodule:: unfccc_ghg_data.unfccc_reader.United_Kingdom.config_uk_inv2024

docs/source/api/unfccc_ghg_data.unfccc_reader.United_Kingdom.read_GBR_2024_Inventory_from_xlsx.rst

@@ -0,0 +1,6 @@
+unfccc\_ghg\_data.unfccc\_reader.United\_Kingdom.read\_GBR\_2024\_Inventory\_from\_xlsx
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. automodule:: unfccc_ghg_data.unfccc_reader.United_Kingdom.read_GBR_2024_Inventory_from_xlsx
+
+.. currentmodule:: unfccc_ghg_data.unfccc_reader.United_Kingdom.read_GBR_2024_Inventory_from_xlsx

docs/source/api/unfccc_ghg_data.unfccc_reader.United_Kingdom.rst

@@ -0,0 +1,13 @@
+unfccc\_ghg\_data.unfccc\_reader.United\_Kingdom
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. automodule:: unfccc_ghg_data.unfccc_reader.United_Kingdom
+
+.. currentmodule:: unfccc_ghg_data.unfccc_reader.United_Kingdom
+
+
+.. autosummary::
+  :toctree: ./
+
+  unfccc_ghg_data.unfccc_reader.United_Kingdom.config_uk_inv2024
+  unfccc_ghg_data.unfccc_reader.United_Kingdom.read_GBR_2024_Inventory_from_xlsx

docs/source/api/unfccc_ghg_data.unfccc_reader.United_States_of_America.config_usa_inv2024.rst

@@ -0,0 +1,6 @@
+unfccc\_ghg\_data.unfccc\_reader.United\_States\_of\_America.config\_usa\_inv2024
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. automodule:: unfccc_ghg_data.unfccc_reader.United_States_of_America.config_usa_inv2024
+
+.. currentmodule:: unfccc_ghg_data.unfccc_reader.United_States_of_America.config_usa_inv2024

docs/source/api/unfccc_ghg_data.unfccc_reader.United_States_of_America.read_USA_2024_Inventory_from_xlsx.rst

@@ -0,0 +1,6 @@
+unfccc\_ghg\_data.unfccc\_reader.United\_States\_of\_America.read\_USA\_2024\_Inventory\_from\_xlsx
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. automodule:: unfccc_ghg_data.unfccc_reader.United_States_of_America.read_USA_2024_Inventory_from_xlsx
+
+.. currentmodule:: unfccc_ghg_data.unfccc_reader.United_States_of_America.read_USA_2024_Inventory_from_xlsx

docs/source/api/unfccc_ghg_data.unfccc_reader.United_States_of_America.rst

@@ -0,0 +1,13 @@
+unfccc\_ghg\_data.unfccc\_reader.United\_States\_of\_America
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. automodule:: unfccc_ghg_data.unfccc_reader.United_States_of_America
+
+.. currentmodule:: unfccc_ghg_data.unfccc_reader.United_States_of_America
+
+
+.. autosummary::
+  :toctree: ./
+
+  unfccc_ghg_data.unfccc_reader.United_States_of_America.config_usa_inv2024
+  unfccc_ghg_data.unfccc_reader.United_States_of_America.read_USA_2024_Inventory_from_xlsx

docs/source/api/unfccc_ghg_data.unfccc_reader.rst

@@ -32,5 +32,7 @@ unfccc\_ghg\_data.unfccc\_reader
   unfccc_ghg_data.unfccc_reader.Taiwan
   unfccc_ghg_data.unfccc_reader.Thailand
   unfccc_ghg_data.unfccc_reader.United_Arab_Emirates
+  unfccc_ghg_data.unfccc_reader.United_Kingdom
+  unfccc_ghg_data.unfccc_reader.United_States_of_America
   unfccc_ghg_data.unfccc_reader.get_submissions_info
   unfccc_ghg_data.unfccc_reader.read_UNFCCC_submission

downloaded_data/non-UNFCCC/United_Kingdom_of_Great_Britain_and_Northern_Ireland/2024-Inventory/2406181003_DA_GHGI_1990-2022_v2.1.xlsx

@@ -0,0 +1 @@
+../../../../.git/annex/objects/3x/2J/MD5E-s44506505--0b2541b974ecc11fcbdad969c244ec26.1.xlsx/MD5E-s44506505--0b2541b974ecc11fcbdad969c244ec26.1.xlsx

downloaded_data/non-UNFCCC/United_States_of_America/2024-Inventory/2024-annex-tables.zip

@@ -0,0 +1 @@
+../../../../.git/annex/objects/Qv/v6/MD5E-s362800--e26b798635b7cbdcd9d70f1101ac6a48.zip/MD5E-s362800--e26b798635b7cbdcd9d70f1101ac6a48.zip

downloaded_data/non-UNFCCC/United_States_of_America/2024-Inventory/main-text-tables/Chapter 1 - Introduction.zip

@@ -0,0 +1 @@
+../../../../../.git/annex/objects/gj/Jk/MD5E-s10117--bc89feacfd18a29a17cbcd01bcff667e.zip/MD5E-s10117--bc89feacfd18a29a17cbcd01bcff667e.zip

downloaded_data/non-UNFCCC/United_States_of_America/2024-Inventory/main-text-tables/Chapter 2 - Trends in Greenhouse Gas Emissions and Removals.zip

@@ -0,0 +1 @@
+../../../../../.git/annex/objects/Zz/27/MD5E-s53063--c3296af589f4db928509210f89c9f2d8.zip/MD5E-s53063--c3296af589f4db928509210f89c9f2d8.zip

downloaded_data/non-UNFCCC/United_States_of_America/2024-Inventory/main-text-tables/Chapter 3 - Energy.zip

@@ -0,0 +1 @@
+../../../../../.git/annex/objects/Qw/Pw/MD5E-s115491--466c2fa965ca2b567af87fa3842711da.zip/MD5E-s115491--466c2fa965ca2b567af87fa3842711da.zip

downloaded_data/non-UNFCCC/United_States_of_America/2024-Inventory/main-text-tables/Chapter 4 - Industrial Processes and Product Use.zip

@@ -0,0 +1 @@
+../../../../../.git/annex/objects/FZ/kJ/MD5E-s76570--9cefea5c58ab7c883013e45e2b6d9791.zip/MD5E-s76570--9cefea5c58ab7c883013e45e2b6d9791.zip

downloaded_data/non-UNFCCC/United_States_of_America/2024-Inventory/main-text-tables/Chapter 5 - Agriculture.zip

@@ -0,0 +1 @@
+../../../../../.git/annex/objects/j1/Wp/MD5E-s28831--a650a603d27a0d8c693bb4de360fcf4b.zip/MD5E-s28831--a650a603d27a0d8c693bb4de360fcf4b.zip

downloaded_data/non-UNFCCC/United_States_of_America/2024-Inventory/main-text-tables/Chapter 6 - LULUCF.zip

@@ -0,0 +1 @@
+../../../../../.git/annex/objects/p7/91/MD5E-s106058--e2d0bd408d6a807a3c96dd729b3b656a.zip/MD5E-s106058--e2d0bd408d6a807a3c96dd729b3b656a.zip

downloaded_data/non-UNFCCC/United_States_of_America/2024-Inventory/main-text-tables/Chapter 7 - Waste.zip

@@ -0,0 +1 @@
+../../../../../.git/annex/objects/Zv/zz/MD5E-s31128--22ae859d5bbe3756951ccbc5a27acfaa.zip/MD5E-s31128--22ae859d5bbe3756951ccbc5a27acfaa.zip

downloaded_data/non-UNFCCC/United_States_of_America/2024-Inventory/main-text-tables/Chapter 9 - Recalculations and Improvements.zip

@@ -0,0 +1 @@
+../../../../../.git/annex/objects/wM/0P/MD5E-s10668--2a63c5a0b3a4052043ae9132f1e1d954.zip/MD5E-s10668--2a63c5a0b3a4052043ae9132f1e1d954.zip

downloaded_data/non-UNFCCC/United_States_of_America/2024-Inventory/main-text-tables/Executive Summary.zip

@@ -0,0 +1 @@
+../../../../../.git/annex/objects/01/pM/MD5E-s9940--614068aa46245ceb2d6c9f5ac2be7a47.zip/MD5E-s9940--614068aa46245ceb2d6c9f5ac2be7a47.zip

downloaded_data/non-UNFCCC/United_States_of_America/2024-Inventory/main-text-tables/trends/Table 2-1.csv

@@ -0,0 +1 @@
+../../../../../../.git/annex/objects/9v/vG/MD5E-s19760--eaa733646ee6a7899a57152b4f09deda.csv/MD5E-s19760--eaa733646ee6a7899a57152b4f09deda.csv

downloaded_data/non-UNFCCC/United_States_of_America/2024-Inventory/main-text-tables/trends/Table 2-10.csv

@@ -0,0 +1 @@
+../../../../../../.git/annex/objects/KX/KW/MD5E-s16161--bd3909d3e9b58a7817e45b7df4325d52.csv/MD5E-s16161--bd3909d3e9b58a7817e45b7df4325d52.csv

downloaded_data/non-UNFCCC/United_States_of_America/2024-Inventory/main-text-tables/trends/Table 2-11.csv

@@ -0,0 +1 @@
+../../../../../../.git/annex/objects/m2/vj/MD5E-s3704--503a94bf49b6c66ae520d55ba77407a4.csv/MD5E-s3704--503a94bf49b6c66ae520d55ba77407a4.csv

downloaded_data/non-UNFCCC/United_States_of_America/2024-Inventory/main-text-tables/trends/Table 2-12.csv

@@ -0,0 +1 @@
+../../../../../../.git/annex/objects/qk/kZ/MD5E-s11635--768916ff244d5f0b88803b03c626fc3f.csv/MD5E-s11635--768916ff244d5f0b88803b03c626fc3f.csv

downloaded_data/non-UNFCCC/United_States_of_America/2024-Inventory/main-text-tables/trends/Table 2-13.csv

@@ -0,0 +1 @@
+../../../../../../.git/annex/objects/9w/8M/MD5E-s10626--3b6ad27b2b370ae9f181d22b41fc12c5.csv/MD5E-s10626--3b6ad27b2b370ae9f181d22b41fc12c5.csv

downloaded_data/non-UNFCCC/United_States_of_America/2024-Inventory/main-text-tables/trends/Table 2-14.csv

@@ -0,0 +1 @@
+../../../../../../.git/annex/objects/Q5/F0/MD5E-s1327--e44ccceeb12036dbf27091468767f2ef.csv/MD5E-s1327--e44ccceeb12036dbf27091468767f2ef.csv

downloaded_data/non-UNFCCC/United_States_of_America/2024-Inventory/main-text-tables/trends/Table 2-15.csv

@@ -0,0 +1 @@
+../../../../../../.git/annex/objects/pZ/wP/MD5E-s4487--439665237299b74dd228f0f259aee755.csv/MD5E-s4487--439665237299b74dd228f0f259aee755.csv

downloaded_data/non-UNFCCC/United_States_of_America/2024-Inventory/main-text-tables/trends/Table 2-2.csv

@@ -0,0 +1 @@
+../../../../../../.git/annex/objects/j3/KJ/MD5E-s20259--bd47b4a36758ffd7b52e706de19a8951.csv/MD5E-s20259--bd47b4a36758ffd7b52e706de19a8951.csv

downloaded_data/non-UNFCCC/United_States_of_America/2024-Inventory/main-text-tables/trends/Table 2-3.csv

@@ -0,0 +1 @@
+../../../../../../.git/annex/objects/vV/kX/MD5E-s13514--ab6a703ed68f725b6afa9589b5fe1446.csv/MD5E-s13514--ab6a703ed68f725b6afa9589b5fe1446.csv

downloaded_data/non-UNFCCC/United_States_of_America/2024-Inventory/main-text-tables/trends/Table 2-4.csv

@@ -0,0 +1 @@
+../../../../../../.git/annex/objects/2f/4k/MD5E-s8077--6f644323dd2acb9cdcece007976f8727.csv/MD5E-s8077--6f644323dd2acb9cdcece007976f8727.csv

downloaded_data/non-UNFCCC/United_States_of_America/2024-Inventory/main-text-tables/trends/Table 2-5.csv

@@ -0,0 +1 @@
+../../../../../../.git/annex/objects/5f/56/MD5E-s3997--24b3a63d2ba96ab079b50db67f8a7beb.csv/MD5E-s3997--24b3a63d2ba96ab079b50db67f8a7beb.csv

downloaded_data/non-UNFCCC/United_States_of_America/2024-Inventory/main-text-tables/trends/Table 2-6.csv

@@ -0,0 +1 @@
+../../../../../../.git/annex/objects/8q/9v/MD5E-s10218--40f53b3bb939c9391b98ffa14bcbae50.csv/MD5E-s10218--40f53b3bb939c9391b98ffa14bcbae50.csv

downloaded_data/non-UNFCCC/United_States_of_America/2024-Inventory/main-text-tables/trends/Table 2-7.csv

@@ -0,0 +1 @@
+../../../../../../.git/annex/objects/XM/Mj/MD5E-s2853--fd48704d0f26ecca3086da51a58c29bc.csv/MD5E-s2853--fd48704d0f26ecca3086da51a58c29bc.csv

downloaded_data/non-UNFCCC/United_States_of_America/2024-Inventory/main-text-tables/trends/Table 2-8.csv

@@ -0,0 +1 @@
+../../../../../../.git/annex/objects/0m/FJ/MD5E-s11789--4a6b47a12343b40c9d2f42af15f56c8d.csv/MD5E-s11789--4a6b47a12343b40c9d2f42af15f56c8d.csv

downloaded_data/non-UNFCCC/United_States_of_America/2024-Inventory/main-text-tables/trends/Table 2-9.csv

@@ -0,0 +1 @@
+../../../../../../.git/annex/objects/2F/9k/MD5E-s2109--efe9b45580fad2113b12cd33d24e995b.csv/MD5E-s2109--efe9b45580fad2113b12cd33d24e995b.csv

downloaded_data/non-UNFCCC/United_States_of_America/2024-Inventory/main-text.zip

@@ -0,0 +1 @@
+../../../../.git/annex/objects/j5/VQ/MD5E-s443178--f16e77072b6805100bd2659a98f6adfa.zip/MD5E-s443178--f16e77072b6805100bd2659a98f6adfa.zip

downloaded_data/non-UNFCCC/United_States_of_America/2024-Inventory/us-ghg-inventory-2024-annexes.pdf

@@ -0,0 +1 @@
+../../../../.git/annex/objects/g6/G8/MD5E-s10644515--302ad3030d9241f2db460fe930e0ee15.pdf/MD5E-s10644515--302ad3030d9241f2db460fe930e0ee15.pdf

downloaded_data/non-UNFCCC/United_States_of_America/2024-Inventory/us-ghg-inventory-2024-main-text_04-18-2024.pdf

@@ -0,0 +1 @@
+../../../../.git/annex/objects/zX/vg/MD5E-s16621762--342181fe9559ef7cdc46ba9b58c285bb.pdf/MD5E-s16621762--342181fe9559ef7cdc46ba9b58c285bb.pdf

extracted_data/non-UNFCCC/Japan/JPN_2024-Inventory_IPCC1996_2006_Japan_INV.nc

@@ -1 +1 @@
-../../../.git/annex/objects/76/Qp/MD5E-s101627--f2cae4c452bc87dcbfa99a1f86ffa8df.nc/MD5E-s101627--f2cae4c452bc87dcbfa99a1f86ffa8df.nc
+../../../.git/annex/objects/q8/Wj/MD5E-s101627--e23fe4b02aa1c64c0c945403bf8abce4.nc/MD5E-s101627--e23fe4b02aa1c64c0c945403bf8abce4.nc

extracted_data/non-UNFCCC/Japan/JPN_2024-Inventory_IPCC1996_2006_Japan_INV.yaml

@@ -12,11 +12,11 @@ time_format: '%Y'
 dimensions:
   '*':
   - time
-  - scenario (PRIMAP)
   - category (IPCC1996_2006_Japan_INV)
-  - source
   - provenance
   - area (ISO3)
+  - scenario (PRIMAP)
+  - source
   - entity
   - unit
 data_file: JPN_2024-Inventory_IPCC1996_2006_Japan_INV.csv

extracted_data/non-UNFCCC/Japan/JPN_2024-Inventory_IPCC2006_PRIMAP.csv

@@ -1 +1 @@
-../../../.git/annex/objects/FP/3p/MD5E-s555063--c1bdbdbd7f2f12bff9f797009a885910.csv/MD5E-s555063--c1bdbdbd7f2f12bff9f797009a885910.csv
+../../../.git/annex/objects/jj/19/MD5E-s559252--81ae16f3c3adbec33e197c8863bad253.csv/MD5E-s559252--81ae16f3c3adbec33e197c8863bad253.csv

extracted_data/non-UNFCCC/Japan/JPN_2024-Inventory_IPCC2006_PRIMAP.nc

@@ -1 +1 @@
-../../../.git/annex/objects/f0/XZ/MD5E-s339908--de3448e119d10b9fdd6a44f9cb2b3203.nc/MD5E-s339908--de3448e119d10b9fdd6a44f9cb2b3203.nc
+../../../.git/annex/objects/Pm/QF/MD5E-s340752--a0b3f0db541bf289e7984ee0aca2986b.nc/MD5E-s340752--a0b3f0db541bf289e7984ee0aca2986b.nc

extracted_data/non-UNFCCC/Japan/JPN_2024-Inventory_IPCC2006_PRIMAP.yaml

@@ -2,8 +2,8 @@ attrs:
   references: https://www.nies.go.jp/gio/en/aboutghg/index.html
   rights: ''
   contact: mail@johannes-guetschow.de
-  title: National GHG Inventory of Japan, 2024 Processed on 2024-07-29
-  comment: Read fom xlsx file by Johannes Gütschow Processed on 2024-07-29
+  title: National GHG Inventory of Japan, 2024 Processed on 2024-08-06
+  comment: Read fom xlsx file by Johannes Gütschow Processed on 2024-08-06
   institution: National Institute for Environmental Studies Japan
   cat: category (IPCC2006_PRIMAP)
   area: area (ISO3)
@@ -14,11 +14,11 @@ time_format: '%Y'
 dimensions:
   '*':
   - time
-  - scenario (PRIMAP)
   - category (IPCC2006_PRIMAP)
-  - source
   - provenance
   - area (ISO3)
+  - scenario (PRIMAP)
+  - source
   - entity
   - unit
 data_file: JPN_2024-Inventory_IPCC2006_PRIMAP.csv

extracted_data/non-UNFCCC/United_Kingdom/GBR_2024-Inventory_CRF2013_2023.csv

@@ -0,0 +1 @@
+../../../.git/annex/objects/0z/Z5/MD5E-s172823--eb90aa666d356ee042cb6fd5a0cbdc83.csv/MD5E-s172823--eb90aa666d356ee042cb6fd5a0cbdc83.csv

extracted_data/non-UNFCCC/United_Kingdom/GBR_2024-Inventory_CRF2013_2023.nc

@@ -0,0 +1 @@
+../../../.git/annex/objects/KQ/WV/MD5E-s124043--373eee21639db07acfaf2e7dc5c4c256.nc/MD5E-s124043--373eee21639db07acfaf2e7dc5c4c256.nc

extracted_data/non-UNFCCC/United_Kingdom/GBR_2024-Inventory_CRF2013_2023.yaml

@@ -0,0 +1,22 @@
+attrs:
+  references: https://naei.beis.gov.uk/reports/reports?report_id=1140
+  rights: ''
+  contact: mail@johannes-guetschow.de
+  title: Devolved Administration GHG Inventory 1990-2022
+  comment: Read fom xlsx file by Johannes Gütschow
+  institution: National Atmospheric Emissions Inventory (United Kingdom)
+  cat: category (CRF2013_2023)
+  area: area (ISO3)
+  scen: scenario (PRIMAP)
+time_format: '%Y'
+dimensions:
+  '*':
+  - time
+  - source
+  - area (ISO3)
+  - provenance
+  - category (CRF2013_2023)
+  - scenario (PRIMAP)
+  - entity
+  - unit
+data_file: GBR_2024-Inventory_CRF2013_2023.csv

extracted_data/non-UNFCCC/United_Kingdom/GBR_2024-Inventory_IPCC2006_PRIMAP.csv

@@ -0,0 +1 @@
+../../../.git/annex/objects/kJ/xW/MD5E-s1019513--a0065c926c456f319e1562ea49a0fd90.csv/MD5E-s1019513--a0065c926c456f319e1562ea49a0fd90.csv

extracted_data/non-UNFCCC/United_Kingdom/GBR_2024-Inventory_IPCC2006_PRIMAP.nc

@@ -0,0 +1 @@
+../../../.git/annex/objects/2z/ff/MD5E-s492947--0ab97e850f31fa6bf031f241dc59e836.nc/MD5E-s492947--0ab97e850f31fa6bf031f241dc59e836.nc

extracted_data/non-UNFCCC/United_Kingdom/GBR_2024-Inventory_IPCC2006_PRIMAP.yaml

@@ -0,0 +1,24 @@
+attrs:
+  references: https://naei.beis.gov.uk/reports/reports?report_id=1140
+  rights: ''
+  contact: mail@johannes-guetschow.de
+  title: Devolved Administration GHG Inventory 1990-2022 Processed on 2024-07-31
+  comment: Read fom xlsx file by Johannes Gütschow Processed on 2024-07-31
+  institution: National Atmospheric Emissions Inventory (United Kingdom)
+  cat: category (IPCC2006_PRIMAP)
+  area: area (ISO3)
+  scen: scenario (PRIMAP)
+  entity: PFCS
+  gwp_context: AR6GWP100
+time_format: '%Y'
+dimensions:
+  '*':
+  - time
+  - source
+  - area (ISO3)
+  - provenance
+  - category (IPCC2006_PRIMAP)
+  - scenario (PRIMAP)
+  - entity
+  - unit
+data_file: GBR_2024-Inventory_IPCC2006_PRIMAP.csv

extracted_data/non-UNFCCC/United_States_of_America/USA_2024-Inventory_CRF2013_2023.csv

@@ -0,0 +1 @@
+../../../.git/annex/objects/WG/QQ/MD5E-s36036--4efe0e848709275b585f7b54e59620b9.csv/MD5E-s36036--4efe0e848709275b585f7b54e59620b9.csv

extracted_data/non-UNFCCC/United_States_of_America/USA_2024-Inventory_CRF2013_2023.nc

@@ -0,0 +1 @@
+../../../.git/annex/objects/Fz/5K/MD5E-s83273--591a6e661f9cc1db3f57180e296eba86.nc/MD5E-s83273--591a6e661f9cc1db3f57180e296eba86.nc

extracted_data/non-UNFCCC/United_States_of_America/USA_2024-Inventory_CRF2013_2023.yaml

@@ -0,0 +1,23 @@
+attrs:
+  references: 
+    https://www.epa.gov/ghgemissions/inventory-us-greenhouse-gas-emissions-and-sinks-1990-2022
+  rights: ''
+  contact: johannes.guetschow@climate-resource.com
+  title: 'Inventory of U.S. Greenhouse Gas Emissions and Sinks: 1990-2022'
+  comment: Read fom csv files by Johannes Gütschow
+  institution: United States Environmental Protection Agency
+  cat: category (CRF2013_2023)
+  area: area (ISO3)
+  scen: scenario (PRIMAP)
+time_format: '%Y'
+dimensions:
+  '*':
+  - time
+  - scenario (PRIMAP)
+  - area (ISO3)
+  - provenance
+  - source
+  - category (CRF2013_2023)
+  - entity
+  - unit
+data_file: USA_2024-Inventory_CRF2013_2023.csv

extracted_data/non-UNFCCC/United_States_of_America/USA_2024-Inventory_IPCC2006_PRIMAP.csv

@@ -0,0 +1 @@
+../../../.git/annex/objects/mK/WM/MD5E-s331636--3388d98406c5db9dcf6d6a31ec4f1e8b.csv/MD5E-s331636--3388d98406c5db9dcf6d6a31ec4f1e8b.csv

extracted_data/non-UNFCCC/United_States_of_America/USA_2024-Inventory_IPCC2006_PRIMAP.nc

@@ -0,0 +1 @@
+../../../.git/annex/objects/qj/Q7/MD5E-s230309--a47abff0125233c321323a9ceb41319e.nc/MD5E-s230309--a47abff0125233c321323a9ceb41319e.nc

extracted_data/non-UNFCCC/United_States_of_America/USA_2024-Inventory_IPCC2006_PRIMAP.yaml

@@ -0,0 +1,26 @@
+attrs:
+  references: 
+    https://www.epa.gov/ghgemissions/inventory-us-greenhouse-gas-emissions-and-sinks-1990-2022
+  rights: ''
+  contact: johannes.guetschow@climate-resource.com
+  title: 'Inventory of U.S. Greenhouse Gas Emissions and Sinks: 1990-2022 Processed
+    on 2024-08-06'
+  comment: Read fom csv files by Johannes Gütschow Processed on 2024-08-06
+  institution: United States Environmental Protection Agency
+  cat: category (IPCC2006_PRIMAP)
+  area: area (ISO3)
+  scen: scenario (PRIMAP)
+  entity: PFCS
+  gwp_context: AR6GWP100
+time_format: '%Y'
+dimensions:
+  '*':
+  - time
+  - scenario (PRIMAP)
+  - area (ISO3)
+  - provenance
+  - source
+  - category (IPCC2006_PRIMAP)
+  - entity
+  - unit
+data_file: USA_2024-Inventory_IPCC2006_PRIMAP.csv

extracted_data/non-UNFCCC/folder_mapping.json

@@ -1,4 +1,5 @@
 {
+    "JPN": "Japan",
     "KOR": "Republic_of_Korea",
     "TWN": "Taiwan"
-}
+}

poetry.lock

@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 1.8.3 and should not be changed by hand.
+# This file is automatically @generated by Poetry 1.7.1 and should not be changed by hand.
 
 [[package]]
 name = "accessible-pygments"
@@ -3850,7 +3850,6 @@ files = [
     {file = "PyYAML-6.0.1-cp311-cp311-win_amd64.whl", hash = "sha256:bf07ee2fef7014951eeb99f56f39c9bb4af143d8aa3c21b1677805985307da34"},
     {file = "PyYAML-6.0.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:855fb52b0dc35af121542a76b9a84f8d1cd886ea97c84703eaa6d88e37a2ad28"},
     {file = "PyYAML-6.0.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:40df9b996c2b73138957fe23a16a4f0ba614f4c0efce1e9406a184b6d07fa3a9"},
-    {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a08c6f0fe150303c1c6b71ebcd7213c2858041a7e01975da3a99aed1e7a378ef"},
     {file = "PyYAML-6.0.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6c22bec3fbe2524cde73d7ada88f6566758a8f7227bfbf93a408a9d86bcc12a0"},
     {file = "PyYAML-6.0.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8d4e9c88387b0f5c7d5f281e55304de64cf7f9c0021a3525bd3b1c542da3b0e4"},
     {file = "PyYAML-6.0.1-cp312-cp312-win32.whl", hash = "sha256:d483d2cdf104e7c9fa60c544d92981f12ad66a457afae824d146093b8c294c54"},

src/unfccc_ghg_data/unfccc_reader/Chile/__init__.py

@@ -1,6 +1,6 @@
 """Read Chile's BURs, NIRs, NCs
 
-Scripts and configurations to read Argentina's submissions to the UNFCCC.
+Scripts and configurations to read Chile's submissions to the UNFCCC.
 Currently, the following submissions and datasets are available (all datasets
 including DI (red using the DI-reader) and legacy BUR/NIR (no code)):
 

src/unfccc_ghg_data/unfccc_reader/Colombia/__init__.py

@@ -1,6 +1,6 @@
 """Read Colombia's BURs, NIRs, NCs
 
-Scripts and configurations to read Argentina's submissions to the UNFCCC.
+Scripts and configurations to read Colombia's submissions to the UNFCCC.
 Currently, the following submissions and datasets are available (all datasets
 including DI (red using the DI-reader) and legacy BUR/NIR (no code)):
 

src/unfccc_ghg_data/unfccc_reader/Indonesia/__init__.py

@@ -1,6 +1,6 @@
 """Read Indonesia's BURs, NIRs, NCs
 
-Scripts and configurations to read Argentina's submissions to the UNFCCC.
+Scripts and configurations to read Indonesia's submissions to the UNFCCC.
 Currently, the following submissions and datasets are available (all datasets
 including DI (red using the DI-reader) and legacy BUR/NIR (no code)):
 

src/unfccc_ghg_data/unfccc_reader/Israel/__init__.py

@@ -1,6 +1,6 @@
 """Read Israel's BURs, NIRs, NCs
 
-Scripts and configurations to read Argentina's submissions to the UNFCCC.
+Scripts and configurations to read Israel's submissions to the UNFCCC.
 Currently, the following submissions and datasets are available (all datasets
 including DI (red using the DI-reader) and legacy BUR/NIR (no code)):
 

src/unfccc_ghg_data/unfccc_reader/Japan/__init__.py

@@ -1,6 +1,6 @@
 """Read Japan's national inventories
 
-Scripts and configurations to read Argentina's submissions to the UNFCCC.
+Scripts and configurations to read Japans's submissions to the UNFCCC.
 Currently, the following submissions and datasets are available (all datasets
 including DI (red using the DI-reader) and legacy BUR/NIR (no code)):
 

src/unfccc_ghg_data/unfccc_reader/Japan/config_jpn_inv2024.py

@@ -348,12 +348,12 @@ cat_conversion = {
         },
         "3.A": {"sources": ["3.A.1", "3.A.2"]},
         "3.B": {"sources": ["3.B.1", "3.B.2", "3.B.3", "3.B.4", "3.B.5", "3.B.6"]},
-        "3.C.1": {"sources": ["3.C.1.AG"]},
+        "3.C.1": {"sources": ["M.3.C.1.AG"]},
         "M.3.C.AG": {"sources": ["3.C.1", "3.C.2", "3.C.3", "M.3.C.45.AG", "3.C.7"]},
         "3.C": {"sources": ["M.3.C.AG"]},
         "M.3.D.LU": {"sources": ["3.D.1", "M.3.D.2.LU"]},
         "3.D": {"sources": ["M.3.D.LU"]},
-        "M.AG.ELV": {"sources": ["3.C"]},
+        "M.AG.ELV": {"sources": ["M.3.C.AG"]},
         "3": {"sources": ["3.A", "3.B", "3.C", "3.D"]},
         "4": {"sources": ["4.A", "4.B", "4.C", "4.D", "4.E"]},
         # consistency check

src/unfccc_ghg_data/unfccc_reader/Japan/read_JPN_2024_Inventory_from_xlsx.py

@@ -5,9 +5,6 @@ Files available here: https://www.nies.go.jp/gio/en/aboutghg/index.html
 
 """
 
-import os
-import sys
-
 import pandas as pd
 import primap2 as pm2
 
@@ -55,17 +52,9 @@ if __name__ == "__main__":
     # ###
     # start data reading
     # ###
-
-    # change working directory to script directory for proper folder names
-    script_path = os.path.abspath(sys.argv[0])
-    script_dir_name = os.path.dirname(script_path)
-    os.chdir(script_dir_name)
-
     data_pm2 = None
 
     for sheet in sheets_to_read:
-        # read sheet for the year. Each sheet contains several tables,
-        # we only read the upper row as the other tables are summary tables
         current_sheet_config = sheets_to_read[sheet]
         df_current = pd.read_excel(
             input_folder / inventory_file,

src/unfccc_ghg_data/unfccc_reader/Malaysia/__init__.py

@@ -1,6 +1,6 @@
 """Read Malaysia's BURs, NIRs, NCs
 
-Scripts and configurations to read Argentina's submissions to the UNFCCC.
+Scripts and configurations to read Malaysia's submissions to the UNFCCC.
 Currently, the following submissions and datasets are available (all datasets
 including DI (red using the DI-reader) and legacy BUR/NIR (no code)):
 

src/unfccc_ghg_data/unfccc_reader/Mexico/__init__.py

@@ -1,6 +1,6 @@
 """Read Mexico's BURs, NIRs, NCs
 
-Scripts and configurations to read Argentina's submissions to the UNFCCC.
+Scripts and configurations to read Mexico's submissions to the UNFCCC.
 Currently, the following submissions and datasets are available (all datasets
 including DI (red using the DI-reader) and legacy BUR/NIR (no code)):
 

src/unfccc_ghg_data/unfccc_reader/Montenegro/__init__.py

@@ -1,6 +1,6 @@
 """Read Montenegro's BURs, NIRs, NCs
 
-Scripts and configurations to read Argentina's submissions to the UNFCCC.
+Scripts and configurations to read Montenegro's submissions to the UNFCCC.
 Currently, the following submissions and datasets are available (all datasets
 including DI (red using the DI-reader) and legacy BUR/NIR (no code)):
 

src/unfccc_ghg_data/unfccc_reader/Morocco/__init__.py

@@ -1,6 +1,6 @@
 """Read Morocco's BURs, NIRs, NCs
 
-Scripts and configurations to read Argentina's submissions to the UNFCCC.
+Scripts and configurations to read Morocco's submissions to the UNFCCC.
 Currently, the following submissions and datasets are available (all datasets
 including DI (red using the DI-reader) and legacy BUR/NIR (no code)):
 

src/unfccc_ghg_data/unfccc_reader/Nigeria/__init__.py

@@ -1,6 +1,6 @@
 """Read Nigeria's BURs, NIRs, NCs
 
-Scripts and configurations to read Argentina's submissions to the UNFCCC.
+Scripts and configurations to read Nigeria's submissions to the UNFCCC.
 Currently, the following submissions and datasets are available (all datasets
 including DI (red using the DI-reader) and legacy BUR/NIR (no code)):
 

src/unfccc_ghg_data/unfccc_reader/Peru/__init__.py

@@ -1,6 +1,6 @@
 """Read Peru's BURs, NIRs, NCs
 
-Scripts and configurations to read Argentina's submissions to the UNFCCC.
+Scripts and configurations to read Peru's submissions to the UNFCCC.
 Currently, the following submissions and datasets are available (all datasets
 including DI (red using the DI-reader) and legacy BUR/NIR (no code)):
 

src/unfccc_ghg_data/unfccc_reader/Republic_of_Korea/__init__.py

@@ -1,6 +1,6 @@
 """Read South Korea's BURs, NIRs, NCs
 
-Scripts and configurations to read Argentina's submissions to the UNFCCC.
+Scripts and configurations to read South Korea's submissions to the UNFCCC.
 Currently, the following submissions and datasets are available (all datasets
 including DI (red using the DI-reader) and legacy BUR/NIR (no code)):
 

src/unfccc_ghg_data/unfccc_reader/Singapore/__init__.py

@@ -1,6 +1,6 @@
 """Read Singapore's BURs, NIRs, NCs
 
-Scripts and configurations to read Argentina's submissions to the UNFCCC.
+Scripts and configurations to read Singapore's submissions to the UNFCCC.
 Currently, the following submissions and datasets are available (all datasets
 including DI (red using the DI-reader) and legacy BUR/NIR (no code)):
 

src/unfccc_ghg_data/unfccc_reader/Taiwan/__init__.py

@@ -1,6 +1,6 @@
 """Read Taiwan's inventories
 
-Scripts and configurations to read Argentina's submissions to the UNFCCC.
+Scripts and configurations to read Taiwan's submissions to the UNFCCC.
 Currently, the following submissions and datasets are available (all datasets
 including DI (red using the DI-reader) and legacy BUR/NIR (no code)):
 

src/unfccc_ghg_data/unfccc_reader/Thailand/__init__.py

@@ -1,6 +1,6 @@
 """Read Thailand's BURs, NIRs, NCs
 
-Scripts and configurations to read Argentina's submissions to the UNFCCC.
+Scripts and configurations to read Thailand's submissions to the UNFCCC.
 Currently, the following submissions and datasets are available (all datasets
 including DI (red using the DI-reader) and legacy BUR/NIR (no code)):
 

src/unfccc_ghg_data/unfccc_reader/United_Kingdom/__init__.py

@@ -0,0 +1,30 @@
+"""Read United Kingdom's national inventories
+
+Scripts and configurations to read United Kingdoms's submissions to the UNFCCC.
+Currently, the following submissions and datasets are available (all datasets
+including DI (red using the DI-reader) and legacy BUR/NIR (no code)):
+
+.. exec_code::
+    :hide_code:
+
+    from unfccc_ghg_data.helper.functions import (get_country_datasets,
+                                                  get_country_submissions)
+    country = 'GBR'
+    # print available submissions
+    print("="*15 + " Available submissions " + "="*15)
+    get_country_submissions(country, True)
+    print("")
+
+    #print available datasets
+    print("="*15 + " Available datasets " + "="*15)
+    get_country_datasets(country, True)
+
+You can also obtain this information running
+
+.. code-block:: bash
+
+    poetry run doit country_info country=GBR
+
+See below for a listing of scripts for BUR/NIR reading including links.
+
+"""

src/unfccc_ghg_data/unfccc_reader/United_Kingdom/config_uk_inv2024.py

@@ -0,0 +1,671 @@
+"""Config for UK 2024 Inventroy
+
+General configuration for reading the inventory files for UK's official 2024
+inventory from xlsx
+
+"""
+
+gwp_to_use = "AR5GWP100"
+cols_to_drop = ["Regioncode", "NCFormat", "SourceName", "TESS1"]  # , 'TESS2']
+
+entity_unit_filter = {
+    # 'CO2': {
+    #     'from': 'kilotonne',
+    #     'to': 'kt',
+    # },
+    # 'CH4': {
+    #     'from': 'kilotonne',
+    #     'to': 'kt',
+    # },
+    # 'N2O': {
+    #     'from': 'kilotonne',
+    #     'to': 'kt',
+    # },
+    # 'SF6': {
+    #     'from': 'kilotonne',
+    #     'to': 'kt',
+    # },
+    # 'NF3': {
+    #     'from': 'kilotonne',
+    #     'to': 'kt',
+    # },
+    "CO2": {
+        "from": "GWP CO2_AR5",
+        "to": "ktCO2eq",
+    },
+    "CH4": {
+        "from": "GWP CO2_AR5",
+        "to": "ktCO2eq",
+    },
+    "N2O": {
+        "from": "GWP CO2_AR5",
+        "to": "ktCO2eq",
+    },
+    "SF6": {
+        "from": "GWP CO2_AR5",
+        "to": "ktCO2eq",
+    },
+    "NF3": {
+        "from": "GWP CO2_AR5",
+        "to": "ktCO2eq",
+    },
+    "HFC": {
+        "from": "GWP CO2_AR5",
+        "to": "ktCO2eq",
+    },
+    "PFC": {
+        "from": "GWP CO2_AR5",
+        "to": "ktCO2eq",
+    },
+}
+
+time_format = "%Y"
+coords_cols = {
+    "category": "IPCC_code",
+    # "category_name": "IPCC_name",
+    # "subcategory": "Sourcename",
+    # "area": "RegionName",
+    "data": "Emission",
+    "time": "EmissionYear",
+    "entity": "Pollutant",
+    "unit": "ConvertTo",
+    # "type3": "TESS3",
+    # "type2": "TESS2",
+    # "type1": "TESS1",
+}
+
+coords_terminologies = {
+    "area": "ISO3",
+    "category": "CRF2013_2023",
+    "scenario": "PRIMAP",
+}
+
+coords_defaults = {
+    "source": "GBR-GHG-Inventory",
+    "provenance": "measured",
+    "area": "GBR",
+    "scenario": "2024INV",
+}
+
+coords_value_mapping = {
+    "entity": {
+        "HFC": f"HFCS ({gwp_to_use})",
+        "PFC": f"PFCS ({gwp_to_use})",
+        "CO2": "CO2",
+        "CH4": f"CH4 ({gwp_to_use})",
+        "N2O": f"N2O ({gwp_to_use})",
+        "SF6": f"SF6 ({gwp_to_use})",
+        "NF3": f"NF3 ({gwp_to_use})",
+    },
+    "unit": "PRIMAP1",
+    # for a correct mapping we need to use IPCC_name not IPCC_code as some codes are
+    # used twice so we have some aggregation (e.g. in animal species)
+    "category": {
+        "1A1ai": "1.A.1.a.i",  # 1A1ai_Public_Electricity&Heat_Production
+        "1A1aiii": "1.A.1.a.iii",  # 1A1aiii_Public_Heat_Production
+        "1A1b": "1.A.1.b",  # 1A1b_Petroleum_Refining
+        "1A1ci": "1.A.1.c.i",  # 1A1ci_Manufacture_of_solid_fuels
+        "1A1cii": "1.A.1.c.ii",  # 1A1cii_Oil_and_gas_extraction
+        "1A1ciii": "1.A.1.c.iii",  # 1A1ciii_Other_energy_industries
+        "1A2a": "1.A.2.a",  # 1A2a_Iron_and_steel
+        "1A2b": "1.A.2.b",  # 1A2b_Non-Ferrous_Metals
+        "1A2c": "1.A.2.c",  # 1A2c_Chemicals
+        "1A2d": "1.A.2.d",  # 1A2d_Pulp_Paper_Print
+        "1A2e": "1.A.2.e",  # 1A2e_food_processing_beverages_and_tobacco
+        "1A2f": "1.A.2.f",  # 1A2f_Non-metallic_minerals
+        "1A2giii": "1.A.2.g.iii",  # 1A2giii_Mining_and_quarrying
+        "1A2gv": "1.A.2.g.v",  # 1A2gv_Construction
+        "1A2gvii": "1.A.2.g.vii",  # 1A2gvii_Off-road_vehicles_and_other_machinery
+        "1A2gviii": "1.A.2.g.v.iii",  # 1A2gviii_Other_manufacturing_industries_and_construction
+        "1A3a": "1.A.3.a",  # 1A3a_Domestic_aviation
+        "1A3bi": "1.A.3.b.i",  # 1A3bi_Cars
+        "1A3bii": "1.A.3.b.ii",  # 1A3bii_Light_duty_trucks
+        "1A3biii": "1.A.3.b.iii",  # 1A3biii_Heavy_duty_trucks_and_buses
+        "1A3biv": "1.A.3.b.iv",  # 1A3biv_Motorcycles
+        "1A3bv": "1.A.3.b.v",  # 1A3bv_Other_road_transport
+        "1A3c": "1.A.3.c",  # 1A3c_Railways
+        "1A3d": "1.A.3.d",  # 1A3d_Domestic_navigation
+        "1A3eii": "1.A.3.e.ii",  # 1A3eii_Other_Transportation
+        "1A4ai": "1.A.4.a.i",  # 1A4ai_Commercial/Institutional
+        "1A4aii": "1.A.4.a.ii",  # 1A4aii_Commercial/Institutional_Mobile
+        "1A4bi": "1.A.4.b.i",  # 1A4bi_Residential_stationary
+        "1A4bii": "1.A.4.b.ii",  # 1A4bii_Residential:Off-road
+        "1A4ci": "1.A.4.c.i",  # 1A4ci_Agriculture/Forestry/Fishing:Stationary
+        "1A4cii": "1.A.4.c.ii",  # 1A4cii_Agriculture/Forestry/Fishing:Off-road
+        "1A4ciii": "1.A.4.c.iii",  # 1A4ciii_Fishing
+        "1A5b": "1.A.5.b",  # 1A5b_Other:Mobile
+        "1B1a1i": "1.B.1.a.i.1",  # 1B1ai_Underground_mines:Mining_activities
+        "1B1a1ii": "1.B.1.a.i.2",  # 1B1ai_Underground_mines:Post-mining_activities
+        "1B1a1iii": "1.B.1.a.i.3",  # 1B1ai_Underground_mines:Abandoned
+        "1B1a2i": "1.B.1.a.ii.1",  # 1B1aii_Surface_mines:Mining_activities
+        "1B1b": "1.B.1.b",  # 1B1b_Solid_Fuel_Transformation
+        "1B2a1": "1.B.2.a.1",  # 1B2a1_Oil_exploration
+        "1B2a2": "1.B.2.a.2",  # 1B2a2_Oil_Production
+        "1B2a3": "1.B.2.a.3",  # 1B2a3_Oil_transport
+        "1B2a4": "1.B.2.a.4",  # 1B2a4_Oil_refining/storage
+        "1B2a6": "1.B.2.a.6",  # 1B2a6_Oil_Production
+        "1B2b1": "1.B.2.b.1",  # 1B2b1_Gas_exploration
+        "1B2b2": "1.B.2.b.2",  # 1B2b2_Gas_production
+        "1B2b3": "1.B.2.b.3",  # 1B2b3_Gas_processing
+        "1B2b4": "1.B.2.b.4",  # 1B2b4_Gas_transmission_and_storage
+        "1B2b5": "1.B.2.b.5",  # 1B2b5_Gas_distribution
+        "1B2c1i": "1.B.2.c-ven.i",  # 1B2c_Venting_Oil
+        "1B2c1ii": "1.B.2.c-ven.ii",  # 1B2c_Venting_Gas
+        "1B2c2i": "1.B.2.c-fla.i",  # 1B2c_Flaring_Oil
+        "1B2c2ii": "1.B.2.c-fla.ii",  # 1B2c_Flaring_Gas
+        "1B2d": "1.B.2.d",  # 1B2d_Other_energy_industries
+        "2A1": "2.A.1",  # 2A1_Cement_Production
+        "2A2": "2.A.2",  # 2A2_Lime_Production
+        "2A3": "2.A.3",  # 2A3_Glass_production
+        "2A4a": "2.A.4.a",  # 2A4a_Other_process_uses_of_carbonates:ceramics
+        "2A4b": "2.A.4.b",  # 2A4b_Other_uses_of_Soda_Ash
+        "2A4d": "2.A.4.d",  # 2A4d_Other_process_uses_of_carbonates:other
+        "2B1": "2.B.1",  # 2B1_Chemical_Industry:Ammonia_production
+        "2B10": "2.B.10",  # 2B10_Chemical_Industry:Other
+        "2B2": "2.B.2",  # 2B2_Nitric_Acid_Production
+        "2B3": "2.B.3",  # 2B3_Adipic_Acid_Production
+        "2B6": "2.B.6",  # 2B6_Titanium_dioxide_production
+        "2B7": "2.B.7",  # 2B7_Soda_Ash_Production
+        "2B8a": "2.B.8.a",  # 2B8a_Methanol_production
+        "2B8b": "2.B.8.b",  # 2B8b_Ethylene_Production
+        "2B8c": "2.B.8.c",  # 2B8c_Ethylene_Dichloride_and_Vinyl_Chloride_Monomer
+        "2B8d": "2.B.8.d",  # 2B8d_Ethylene_Oxide
+        "2B8e": "2.B.8.e",  # 2B8e_Acrylonitrile
+        "2B8f": "2.B.8.f",  # 2B8f_Carbon_black_production
+        "2B8g": "2.B.8.g",  # 2B8g_Petrochemical_and_carbon_black_production:Other
+        "2B9a1": "2.B.9.a.i",  # 2B9a1_Fluorchemical_production:By-product_emissions
+        "2B9b3": "2.B.9.b.iii",  # 2B9b3_Fluorchemical_production:Fugitive_emissions
+        "2C1a": "2.C.1.a",  # 2C1a_Steel
+        "2C1b": "2.C.1.b",  # 2C1b_Pig_iron
+        "2C1d": "2.C.1.d",  # 2C1d_Sinter
+        "2C3a": "2.C.3.a",  # 2C3_Aluminium_Production
+        "2C3b": "2.C.3.b",  # 2C3_Aluminium_Production
+        "2C4": "2.C.4",  # 2C4_Magnesium_production
+        "2C6": "2.C.6",  # 2C6_Zinc_Production
+        "2D1": "2.D.1",  # 2D1_Lubricant_Use
+        "2D2": "2.D.2",  # 2D2 Non-energy_products_from_fuels_and_solvent_use:Paraffin_wax_use
+        "2D3": "2.D.3",  # 2D3_Other_NEU
+        "2E1": "2.E.1",  # 2E1_Integrated_circuit_or_semiconductor
+        "2F1a": "2.F.1.a",  # 2F1a_Commercial_refrigeration
+        "2F1b": "2.F.1.b",  # 2F1b_Domestic_refrigeration
+        "2F1c": "2.F.1.c",  # 2F1c_Industrial_refrigeration
+        "2F1d": "2.F.1.d",  # 2F1d_Transport_refrigeration
+        "2F1e": "2.F.1.e",  # 2F1e_Mobile_air_conditioning
+        "2F1f": "2.F.1.f",  # 2F1f_Stationary_air_conditioning
+        "2F2a": "2.F.2.a",  # 2F2a_Closed_foam_blowing_agents (not in CRF2023_2023)
+        "2F2b": "2.F.2.b",  # 2F2b_Open_foam_blowing_agents (not in CRF2023_2023)
+        "2F3": "2.F.3",  # 2F3_Fire_Protection
+        "2F4a": "2.F.4.a",  # 2F4a_Metered_dose_inhalers
+        "2F4b": "2.F.4.b",  # 2F4b_Aerosols:Other
+        "2F5": "2.F.5",  # 2F5_Solvents
+        "2F6b": "2.F.6.b",  # 2F6b_Other_Applications:Contained-Refrigerant_containers
+        "2G1": "2.G.1",  # 2G1_Electrical_equipment
+        "2G2a": "2.G.2.a",  # 2G2_Military_applications
+        "2G2b": "2.G.2.b",  # 2G2_Particle_accelerators
+        "2G2e": "2.G.2.e",  # 2G2e_Electronics_and_shoes
+        "2G3a": "2.G.3.a",  # 2G3a_Medical aplications
+        "2G3b": "2.G.3.b",  # 2G3b_N2O_from_product_uses:_Other
+        "2G4": "2.G.4",  # 2G4_Other_product_manufacture_and_use
+        "3A1a": "3.A.1.Aa",  # 3A1a_Enteric_Fermentation_dairy_cattle
+        "3A1b": "3.A.1.Ab",  # 3A1b_Enteric_Fermentation_non-dairy_cattle
+        "3A2": "3.A.2",  # 3A2_Enteric_Fermentation_sheep
+        "3A3": "3.A.3",  # 3A3_Enteric_Fermentation_swine
+        "3A4": "3.A.4",  # 3A4_Enteric_Fermentation_other:deer
+        "3B11a": "3.B.1.Aa",  # 3B11a_Manure_Management_Methane_dairy_cattle
+        "3B11b": "3.B.1.Ab",  # 3B11b_Manure_Management_Methane_non-dairy_cattle
+        "3B12": "3.B.2",  # 3B12_Manure_Management_Methane_sheep
+        "3B13": "3.B.3",  # 3B13_Manure_Management_Methane_swine
+        "3B14": "3.B.4",  # 3B14_Manure_Management_Methane_other:deer
+        "3B21a": "3.B.1.Aa",  # 3B21a_Manure_Management_Non-methane_dairy_cattle
+        "3B21b": "3.B.1.Ab",  # 3B21b_Manure_Management_Non-methane_non-dairy_cattle
+        "3B22": "3.B.2",  # 3B22_Manure_Management_Non-methane_sheep
+        "3B23": "3.B.3",  # 3B23_Manure_Management_Non-methane_swine
+        "3B24": "3.B.4",  # 3B24_Manure_Management_Non-methane_other:poultry
+        "3B25": "3.B.5",  # 3B25_Manure_Management_Indirect_Emissions_swine
+        "3D11": "3.D.a.1",  # 3D11_Agriculural_Soils_Inorganic_N_Fertilisers
+        "3D12a": "3.D.a.2.a",  # 3D12a_Agricultural_Soils_Manure_Applied_to_Soils
+        "3D12b": "3.D.a.2.b",  # 3D12b_Agricultural_Soils_Sewage_Sludge_Applied_to_Soils
+        "3D12c": "3.D.a.2.c",  # 3D12c_Agricultural_Soils_Other_Organic_Fertilisers_Applied_to_Soils
+        "3D13": "3.D.a.3",  # 3D13_Agricultural_Soils_Manure_Deposited_by_Grazing_Animals
+        "3D14": "3.D.a.4",  # 3D14_Agriculural_Soils_Residues
+        "3D15": "3.D.a.5",  # 3D15_Agricultural_soils_Mineralization/Immobilization
+        "3D16": "3.D.a.6",  # 3D16_Agricultural_soils_Cultivation_of_Organic_Soils
+        "3D21": "3.D.b.1",  # 3D21_Agriculural_Soils_Indirect_Deposition
+        "3D22": "3.D.b.2",  # 3D22_Agriculural_Soils_Indirect_Leaching_and_Run-off
+        "3F11": "3.F.1.a",  # 3F11_Field_burning_wheat
+        "3F12": "3.F.1.b",  # 3F12_Field_burning_barley
+        "3F14": "3.F.1.d",  # 3F14_Field_burning_other_cereals
+        "3F5": "3.F.5",  # 3F5_Field_burning_other_residues
+        "3G1": "3.G.1",  # 3G1_Liming - limestone
+        "3G2": "3.G.2",  # 3G2_Liming - dolomite
+        "3H": "3.H",  # 3H_Urea application
+        "4": "4",  # 4_Indirect_N2O_Emissions
+        "4A": "4.A",  # 4A_Forest Land_Emissions_from_Drainage
+        "4A1": "4.A.1",  # 4A1_ Forest Land remaining Forest Land
+        "4A2": "4.A.2",  # 4A2_Cropland_converted_to_Forest_Land
+        "4B1": "4.B.1",  # 4B1_Cropland Remaining Cropland
+        "4B2": "4.B.2",  # 4B2_Forest_Land_converted_to_Cropland
+        "4C": "4.C",  # 4C_Grassland_Emissions_from_Drainage
+        "4C1": "4.C.1",  # 4C1_Grassland Remaining Grassland
+        "4C2": "4.C.2",  # 4C2_Forest_Land_converted_to_Grassland
+        "4D": "4.D",  # 4D_Wetlands_Emissions_from_Drainage
+        "4D1": "4.D.1",  # 4D1_Wetlands remaining wetlands
+        "4D2": "4.D.2",  # 4D2_Land_converted_to_Wetlands_Peat_Extraction
+        "4E": "4.E",  # 4E_Settlements_Emissions_from_Drainage
+        "4E1": "4.E.1",  # 4E1_Settlements remaining settlements
+        "4E2": "4.E.2",  # 4E2_Forest_Land_converted_to_Settlements
+        "4G": "4.G",  # 4G_Harvested Wood Products
+        "5A1a": "5.A.1.a",  # 5A1a_Managed_Waste_Disposal_sites_anaerobic
+        "5B1a": "5.B.1.a",  # 5B1a_composting_municipal_solid_waste
+        "5B2a": "5.B.2.a",  # 5B2a_Anaerobic_digestion_municipal_solid_waste
+        "5C1.1b": "5.C.1.a.ii.4",  # 5C1.1b_Biogenic:Sewage_sludge
+        "5C1.2a": "5.C.1.b.i",  # 5C1.2a_Non-biogenic:municipal_solid_waste
+        "5C1.2b": "5.C.1.b.ii.3",  # 5C1.2b_Non-biogenic:Clinical_waste
+        "5C2.1b": "5.C.2.a.ii.5",  # 5C2.1b_Biogenic:Other
+        "5C2.2b": "5.C.2.b.ii.5",  # 5C2.2b_Non-biogenic:Other
+        "5D1": "5.D.1",  # 5D1_Domestic_wastewater_treatment
+        "5D2": "5.D.2",  # 5D2_Industrial_wastewater_treatment
+        "Aviation_Bunkers": "M.Memo.Int.Avi",  # Aviation_Bunkers
+        "Marine_Bunkers": "M.Memo.Int.Mar",  # Marine_Bunkers
+    },
+}
+
+meta_data = {
+    "references": "https://naei.beis.gov.uk/reports/reports?report_id=1140",
+    "rights": "",
+    "contact": "mail@johannes-guetschow.de",
+    "title": "Devolved Administration GHG Inventory 1990-2022",
+    "comment": "Read fom xlsx file by Johannes Gütschow",
+    "institution": "National Atmospheric Emissions Inventory (United Kingdom)",
+}
+
+##################################3333333333
+
+
+filter_remove = {
+    "f1": {
+        "category": [
+            "Total (excluding LULUCF, including indirect CO2)",
+            "Total (including LULUCF, including indirect CO2)",
+        ]
+    }
+}
+
+# for processing
+terminology_proc = "IPCC2006_PRIMAP"
+
+cat_conversion = {
+    "mapping": {
+        "1.A.1.a.i": "1.A.1.a.i",  # 1A1ai_Public_Electricity&Heat_Production
+        "1.A.1.a.iii": "1.A.1.a.iii",  # 1A1aiii_Public_Heat_Production
+        "1.A.1.b": "1.A.1.b",  # 1A1b_Petroleum_Refining
+        "1.A.1.c.i": "1.A.1.c.i",  # 1A1ci_Manufacture_of_solid_fuels
+        "1.A.1.c.ii": "1.A.1.c.ii",  # 1A1cii_Oil_and_gas_extraction
+        "1.A.1.c.iii": "1.A.1.c.iii",  # 1A1ciii_Other_energy_industries
+        "1.A.2.a": "1.A.2.a",  # 1A2a_Iron_and_steel
+        "1.A.2.b": "1.A.2.b",  # 1A2b_Non-Ferrous_Metals
+        "1.A.2.c": "1.A.2.c",  # 1A2c_Chemicals
+        "1.A.2.d": "1.A.2.d",  # 1A2d_Pulp_Paper_Print
+        "1.A.2.e": "1.A.2.e",  # 1A2e_food_processing_beverages_and_tobacco
+        "1.A.2.f": "1.A.2.f",  # 1A2f_Non-metallic_minerals
+        "1.A.2.g.iii": "1.A.2.i",  # 1A2giii_Mining_and_quarrying
+        "1.A.2.g.v": "1.A.2.k",  # 1A2gv_Construction
+        "1.A.2.g.vii": "1.A.2.m.i",  # 1A2gvii_Off-road_vehicles_and_other_machinery
+        "1.A.2.g.v.iii": "1.A.2.m.ii",  # 1A2gviii_Other_manufacturing_industries_and_construction
+        "1.A.3.a": "1.A.3.a.ii",  # 1A3a_Domestic_aviation
+        "1.A.3.b.i": "1.A.3.b.i",  # 1A3bi_Cars
+        "1.A.3.b.ii": "1.A.3.b.ii",  # 1A3bii_Light_duty_trucks
+        "1.A.3.b.iii": "1.A.3.b.iii",  # 1A3biii_Heavy_duty_trucks_and_buses
+        "1.A.3.b.iv": "1.A.3.b.iv",  # 1A3biv_Motorcycles
+        "1.A.3.b.v": "M.1.A.3.b.v",  # 1A3bv_Other_road_transport (no direct match in IPCC2006)
+        "1.A.3.c": "1.A.3.c",  # 1A3c_Railways
+        "1.A.3.d": "1.A.3.d.ii",  # 1A3d_Domestic_navigation
+        "1.A.3.e.ii": "1.A.3.e.ii",  # 1A3eii_Other_Transportation (subsector consistent with CRF reporting)
+        "1.A.4.a.i": "1.A.4.a.i",  # 1A4ai_Commercial/Institutional (stationary)
+        "1.A.4.a.ii": "1.A.4.a.ii",  # 1A4aii_Commercial/Institutional_Mobile
+        "1.A.4.b.i": "1.A.4.b.i",  # 1A4bi_Residential_stationary
+        "1.A.4.b.ii": "1.A.4.b.ii",  # 1A4bii_Residential:Off-road
+        "1.A.4.c.i": "1.A.4.c.i",  # 1A4ci_Agriculture/Forestry/Fishing:Stationary
+        "1.A.4.c.ii": "1.A.4.c.ii",  # 1A4cii_Agriculture/Forestry/Fishing:Off-road
+        "1.A.4.c.iii": "1.A.4.c.iii",  # 1A4ciii_Fishing
+        "1.A.5.b": "1.A.5.b",  # 1A5b_Other:Mobile
+        "1.B.1.a.i.1": "1.B.1.a.i.1",  # 1B1ai_Underground_mines:Mining_activities
+        "1.B.1.a.i.2": "1.B.1.a.i.2",  # 1B1ai_Underground_mines:Post-mining_activities
+        "1.B.1.a.i.3": "1.B.1.a.i.3",  # 1B1ai_Underground_mines:Abandoned
+        "1.B.1.a.ii.1": "1.B.1.a.ii.1",  # 1B1aii_Surface_mines:Mining_activities
+        "1.B.1.b": "1.B.1.c",  # 1B1b_Solid_Fuel_Transformation
+        "1.B.2.a.1": "1.B.2.a.iii.1",  # 1B2a1_Oil_exploration
+        "1.B.2.a.2": "1.B.2.a.iii.2",  # 1B2a2_Oil_Production
+        "1.B.2.a.3": "1.B.2.a.iii.3",  # 1B2a3_Oil_transport
+        "1.B.2.a.4": "1.B.2.a.iii.4",  # 1B2a4_Oil_refining/storage
+        "1.B.2.a.6": "1.B.2.a.iii.6",  # 1B2a6_Oil_Production
+        "1.B.2.b.1": "1.B.2.b.iii.1",  # 1B2b1_Gas_exploration
+        "1.B.2.b.2": "1.B.2.b.iii.2",  # 1B2b2_Gas_production
+        "1.B.2.b.3": "1.B.2.b.iii.3",  # 1B2b3_Gas_processing
+        "1.B.2.b.4": "1.B.2.b.iii.4",  # 1B2b4_Gas_transmission_and_storage
+        "1.B.2.b.5": "1.B.2.b.iii.5",  # 1B2b5_Gas_distribution
+        "1.B.2.c-ven.i": "1.B.2.a.i",  # 1B2c_Venting_Oil
+        "1.B.2.c-ven.ii": "1.B.2.b.i",  # 1B2c_Venting_Gas
+        "1.B.2.c-fla.i": "1.B.2.a.ii",  # 1B2c_Flaring_Oil
+        "1.B.2.c-fla.ii": "1.B.2.b.ii",  # 1B2c_Flaring_Gas
+        "1.B.2.d": "1.B.3.b",  # 1B2d_Other_energy_industries
+        "2.A.1": "2.A.1",  # 2A1_Cement_Production
+        "2.A.2": "2.A.2",  # 2A2_Lime_Production
+        "2.A.3": "2.A.3",  # 2A3_Glass_production
+        "2.A.4.a": "2.A.4.a",  # 2A4a_Other_process_uses_of_carbonates:ceramics
+        "2.A.4.b": "2.A.4.b",  # 2A4b_Other_uses_of_Soda_Ash
+        "2.A.4.d": "2.A.4.d",  # 2A4d_Other_process_uses_of_carbonates:other
+        "2.B.1": "2.B.1",  # 2B1_Chemical_Industry:Ammonia_production
+        "2.B.10": "2.B.10",  # 2B10_Chemical_Industry:Other
+        "2.B.2": "2.B.2",  # 2B2_Nitric_Acid_Production
+        "2.B.3": "2.B.3",  # 2B3_Adipic_Acid_Production
+        "2.B.6": "2.B.6",  # 2B6_Titanium_dioxide_production
+        "2.B.7": "2.B.7",  # 2B7_Soda_Ash_Production
+        "2.B.8.a": "2.B.8.a",  # 2B8a_Methanol_production
+        "2.B.8.b": "2.B.8.b",  # 2B8b_Ethylene_Production
+        "2.B.8.c": "2.B.8.c",  # 2B8c_Ethylene_Dichloride_and_Vinyl_Chloride_Monomer
+        "2.B.8.d": "2.B.8.d",  # 2B8d_Ethylene_Oxide
+        "2.B.8.e": "2.B.8.e",  # 2B8e_Acrylonitrile
+        "2.B.8.f": "2.B.8.f",  # 2B8f_Carbon_black_production
+        "2.B.8.g": "2.B.8.g",  # 2B8g_Petrochemical_and_carbon_black_production:Other
+        "2.B.9.a.i": "2.B.9.a.i",  # 2B9a1_Fluorchemical_production:By-product_emissions
+        "2.B.9.b.iii": "2.B.9.b.iii",  # 2B9b3_Fluorchemical_production:Fugitive_emissions
+        "2.C.1.a": "2.C.1.a",  # 2C1a_Steel
+        "2.C.1.b": "2.C.1.b",  # 2C1b_Pig_iron
+        "2.C.1.d": "2.C.1.d",  # 2C1d_Sinter
+        "2.C.3.a": "2.C.3.a",  # 2C3_Aluminium_Production
+        "2.C.3.b": "2.C.3.b",  # 2C3_Aluminium_Production
+        "2.C.4": "2.C.4",  # 2C4_Magnesium_production
+        "2.C.6": "2.C.6",  # 2C6_Zinc_Production
+        "2.D.1": "2.D.1",  # 2D1_Lubricant_Use
+        "2.D.2": "2.D.2",  # 2D2 Non-energy_products_from_fuels_and_solvent_use:Paraffin_wax_use
+        "2.D.3": "2.D.3",  # 2D3_Other_NEU
+        "2.E.1": "2.E.1",  # 2E1_Integrated_circuit_or_semiconductor
+        "2.F.1.a": "M.2.F.1.a.i",  # 2F1a_Commercial_refrigeration
+        "2.F.1.b": "M.2.F.1.a.ii",  # 2F1b_Domestic_refrigeration
+        "2.F.1.c": "M.2.F.1.a.iii",  # 2F1c_Industrial_refrigeration
+        "2.F.1.d": "M.2.F.1.a.iv",  # 2F1d_Transport_refrigeration
+        "2.F.1.e": "2.F.1.b",  # 2F1e_Mobile_air_conditioning
+        "2.F.1.f": "M.2.F.1.a.v",  # 2F1f_Stationary_air_conditioning
+        "2.F.2.a": "M.2.F.2.a",  # 2F2a_Closed_foam_blowing_agents (not in CRF2023_2023)
+        "2.F.2.b": "M.2.F.2.b",  # 2F2b_Open_foam_blowing_agents (not in CRF2023_2023)
+        "2.F.3": "2.F.3",  # 2F3_Fire_Protection
+        "2.F.4.a": "M.2.F.4.a",  # 2F4a_Metered_dose_inhalers
+        "2.F.4.b": "M.2.F.4.b",  # 2F4b_Aerosols:Other
+        "2.F.5": "2.F.5",  # 2F5_Solvents
+        "2.F.6.b": "2.F.6.b",  # 2F6b_Other_Applications:Contained-Refrigerant_containers
+        "2.G.1": "2.G.1",  # 2G1_Electrical_equipment
+        "2.G.2.a": "2.G.2.a",  # 2G2_Military_applications
+        "2.G.2.b": "2.G.2.b",  # 2G2_Particle_accelerators
+        "2.G.2.e": "M.2.G.2.c.i",  # 2G2e_Electronics_and_shoes
+        "2.G.3.a": "2.G.3.a",  # 2G3a_Medical aplications
+        "2.G.3.b": "2.G.3.c",  # 2G3b_N2O_from_product_uses:_Other
+        "2.G.4": "2.G.4",  # 2G4_Other_product_manufacture_and_use
+        "3.A.1.Aa": "3.A.1.a.i",  # 3A1a_Enteric_Fermentation_dairy_cattle
+        "3.A.1.Ab": "3.A.1.a.ii",  # 3A1b_Enteric_Fermentation_non-dairy_cattle
+        "3.A.2": "3.A.1.c",  # 3A2_Enteric_Fermentation_sheep
+        "3.A.3": "3.A.1.h",  # 3A3_Enteric_Fermentation_swine
+        "3.A.4": "3.A.1.j",  # 3A4_Enteric_Fermentation_other:deer
+        "3.B.1.Aa": "3.A.2.a.i",  # 3B21a_Manure_Management_X_dairy_cattle
+        "3.B.1.Ab": "3.A.2.a.ii",  # 3B21b_Manure_Management_X_non-dairy_cattle
+        "3.B.2": "3.A.2.c",  # 3B22_Manure_Management_X_sheep
+        "3.B.3": "3.A.2.h",  # 3B23_Manure_Management_X_swine
+        "3.B.4": "3.A.2.i",  # 3B24_Manure_Management_X_other:poultry
+        "3.B.5": "3.C.6",  # 3B25_Manure_Management_Indirect_Emissions_swine
+        "3.D.a.1": "3.C.4.a",  # 3D11_Agriculural_Soils_Inorganic_N_Fertilisers
+        "3.D.a.2.a": "M.3.C.4.b.i",  # 3D12a_Agricultural_Soils_Manure_Applied_to_Soils
+        "3.D.a.2.b": "M.3.C.4.b.ii",  # 3D12b_Agricultural_Soils_Sewage_Sludge_Applied_to_Soils
+        "3.D.a.2.c": "M.3.C.4.b.iii",  # 3D12c_Agricultural_Soils_Other_Organic_Fertilisers_Applied_to_Soils
+        "3.D.a.3": "3.C.4.c",  # 3D13_Agricultural_Soils_Manure_Deposited_by_Grazing_Animals
+        "3.D.a.4": "3.C.4.d",  # 3D14_Agriculural_Soils_Residues
+        "3.D.a.5": "M.3.C.4.e",  # 3D15_Agricultural_soils_Mineralization/Immobilization
+        "3.D.a.6": "M.3.C.4.f",  # 3D16_Agricultural_soils_Cultivation_of_Organic_Soils
+        "3.D.b.1": "M.3.C.5.AG.a",  # 3D21_Agriculural_Soils_Indirect_Deposition
+        "3.D.b.2": "M.3.C.5.AG.b",  # 3D22_Agriculural_Soils_Indirect_Leaching_and_Run-off
+        "3.F.1.a": "M.3.C.1.b.i",  # 3F11_Field_burning_wheat
+        "3.F.1.b": "M.3.C.1.b.ii",  # 3F12_Field_burning_barley
+        "3.F.1.d": "M.3.C.1.b.iii",  # 3F14_Field_burning_other_cereals
+        "3.F.5": "M.3.C.1.b.iv",  # 3F5_Field_burning_other_residues
+        "3.G.1": "M.3.C.2.a",  # 3G1_Liming - limestone
+        "3.G.2": "M.3.C.2.b",  # 3G2_Liming - dolomite
+        "3.H": "3.C.3",  # 3H_Urea application
+        "4": "M.3.C.5.LU",  # 4_Indirect_N2O_Emissions (LULUCF)
+        "4.A": "M.3.B.1.DR",  # 4A_Forest Land_Emissions_from_Drainage
+        "4.A.1": "3.B.1.a",  # 4A1_ Forest Land remaining Forest Land
+        "4.A.2": "3.B.1.b",  # 4A2_Cropland_converted_to_Forest_Land (and other land types)
+        "4.B.1": "3.B.2.a",  # 4B1_Cropland Remaining Cropland
+        "4.B.2": "3.B.2.b",  # 4B2_Forest_Land_converted_to_Cropland (and other land types)
+        "4.C": "M.3.B.3.DR",  # 4C_Grassland_Emissions_from_Drainage
+        "4.C.1": "3.B.3.a",  # 4C1_Grassland Remaining Grassland
+        "4.C.2": "3.B.3.b",  # 4C2_Forest_Land_converted_to_Grassland (and other land types)
+        "4.D": "M.3.B.4.DR",  # 4D_Wetlands_Emissions_from_Drainage
+        "4.D.1": "3.B.4.a",  # 4D1_Wetlands remaining wetlands
+        "4.D.2": "3.B.4.b",  # 4D2_Land_converted_to_Wetlands_Peat_Extraction
+        "4.E": "M.3.B.5.DR",  # 4E_Settlements_Emissions_from_Drainage
+        "4.E.1": "3.B.5.a",  # 4E1_Settlements remaining settlements
+        "4.E.2": "3.B.5.b",  # 4E2_Forest_Land_converted_to_Settlements (and other land types)
+        "4.G": "3.D.1",  # 4G_Harvested Wood Products
+        "5.A.1.a": "M.4.A.1.a",  # 5A1a_Managed_Waste_Disposal_sites_anaerobic
+        "5.B.1.a": "M.4.B.1.a",  # 5B1a_composting_municipal_solid_waste
+        "5.B.2.a": "M.4.B.2.a",  # 5B2a_Anaerobic_digestion_municipal_solid_waste
+        "5.C.1.a.ii.4": "M.4.C.1.a.ii.4",  # 5C1.1b_Biogenic:Sewage_sludge
+        "5.C.1.b.i": "M.4.C.1.b.i",  # 5C1.2a_Non-biogenic:municipal_solid_waste
+        "5.C.1.b.ii.3": "M.4.C.1.b.ii.3",  # 5C1.2b_Non-biogenic:Clinical_waste
+        "5.C.2.a.ii.5": "M.4.C.2.a.ii.5",  # 5C2.1b_Biogenic:Other
+        "5.C.2.b.ii.5": "M.4.C.2.b.ii.5",  # 5C2.2b_Non-biogenic:Other
+        "5.D.1": "4.D.1",  # 5D1_Domestic_wastewater_treatment
+        "5.D.2": "4.D.2",  # 5D2_Industrial_wastewater_treatment
+        "Aviation_Bunkers": "M.BK.A",  # Aviation_Bunkers
+        "Marine_Bunkers": "M.BK.B",  # Marine_Bunkers
+    },
+    "aggregate": {
+        # need to aggregate the whole tree as only leaves are given in the data
+        # 1
+        ## 1.A
+        "1.A.1.a": {"sources": ["1.A.1.a.i", "1.A.1.a.iii"]},
+        "1.A.1.c": {"sources": ["1.A.1.c.i", "1.A.1.c.ii", "1.A.1.c.iii"]},
+        "1.A.1": {"sources": ["1.A.1.a", "1.A.1.b", "1.A.1.c"]},
+        "1.A.2.m": {"sources": ["1.A.2.m.i", "1.A.2.m.ii"]},
+        "1.A.2": {
+            "sources": [
+                "1.A.2.a",
+                "1.A.2.b",
+                "1.A.2.c",
+                "1.A.2.d",
+                "1.A.2.e",
+                "1.A.2.f",
+                "1.A.2.i",
+                "1.A.2.k",
+                "1.A.2.m",
+            ]
+        },
+        "1.A.3.a": {"sources": ["1.A.3.a.ii"]},
+        "1.A.3.b": {
+            "sources": [
+                "1.A.3.b.i",
+                "1.A.3.b.ii",
+                "1.A.3.b.iii",
+                "1.A.3.b.iv",
+                "M.1.A.3.b.v",
+            ]
+        },
+        "1.A.3.d": {"sources": ["1.A.3.d.ii"]},
+        "1.A.3.e": {"sources": ["1.A.3.e.ii"]},
+        "1.A.3": {"sources": ["1.A.3.a", "1.A.3.b", "1.A.3.c", "1.A.3.d", "1.A.3.e"]},
+        "1.A.4.a": {"sources": ["1.A.4.a.i", "1.A.4.a.ii"]},
+        "1.A.4.b": {"sources": ["1.A.4.b.i", "1.A.4.b.ii"]},
+        "1.A.4.c": {"sources": ["1.A.4.c.i", "1.A.4.c.ii", "1.A.4.c.iii"]},
+        "1.A.4": {"sources": ["1.A.4.a", "1.A.4.b", "1.A.4.c"]},
+        "1.A.5": {"sources": ["1.A.5.b"]},
+        "1.A": {"sources": ["1.A.1", "1.A.2", "1.A.3", "1.A.4", "1.A.5"]},
+        ## 1.B
+        "1.B.1.a.i": {"sources": ["1.B.1.a.i.1", "1.B.1.a.i.2", "1.B.1.a.i.3"]},
+        "1.B.1.a.ii": {"sources": ["1.B.1.a.ii.1"]},
+        "1.B.1.a": {"sources": ["1.B.1.a.i", "1.B.1.a.ii"]},
+        "1.B.1": {"sources": ["1.B.1.a", "1.B.1.c"]},
+        "1.B.2.a.iii": {
+            "sources": [
+                "1.B.2.a.iii.1",
+                "1.B.2.a.iii.2",
+                "1.B.2.a.iii.3",
+                "1.B.2.a.iii.4",
+                "1.B.2.a.iii.6",
+            ]
+        },
+        "1.B.2.a": {"sources": ["1.B.2.a.i", "1.B.2.a.ii", "1.B.2.a.iii"]},
+        "1.B.2.b.iii": {
+            "sources": [
+                "1.B.2.b.iii.1",
+                "1.B.2.b.iii.2",
+                "1.B.2.b.iii.3",
+                "1.B.2.b.iii.4",
+                "1.B.2.b.iii.5",
+            ]
+        },
+        "1.B.2.b": {"sources": ["1.B.2.b.i", "1.B.2.b.ii", "1.B.2.b.iii"]},
+        "1.B.2": {"sources": ["1.B.2.a", "1.B.2.b"]},
+        "1.B.3": {"sources": ["1.B.3.b"]},
+        "1.B": {"sources": ["1.B.1", "1.B.2", "1.B.3"]},
+        ## 1
+        "1": {"sources": ["1.A", "1.B"]},
+        # 2
+        ## 2.A
+        "2.A.4": {"sources": ["2.A.4.a", "2.A.4.b", "2.A.4.d"]},
+        "2.A": {"sources": ["2.A.1", "2.A.2", "2.A.3", "2.A.4"]},
+        ## 2.B
+        "2.B.8": {
+            "sources": [
+                "2.B.8.a",
+                "2.B.8.b",
+                "2.B.8.c",
+                "2.B.8.d",
+                "2.B.8.e",
+                "2.B.8.f",
+                "2.B.8.g",
+            ]
+        },
+        "2.B.9.a": {"sources": ["2.B.9.a.i"]},
+        "2.B.9.b": {"sources": ["2.B.9.b.iii"]},
+        "2.B.9": {"sources": ["2.B.9.a", "2.B.9.b"]},
+        "2.B": {
+            "sources": [
+                "2.B.1",
+                "2.B.2",
+                "2.B.3",
+                "2.B.6",
+                "2.B.7",
+                "2.B.8",
+                "2.B.9",
+                "2.B.10",
+            ]
+        },
+        ## 2.C
+        "2.C.1": {"sources": ["2.C.1.a", "2.C.1.b", "2.C.1.d"]},
+        "2.C.3": {"sources": ["2.C.3.a", "2.C.3.b"]},
+        "2.C": {"sources": ["2.C.1", "2.C.3", "2.C.4", "2.C.6"]},
+        ## 2.D
+        "2.D": {"sources": ["2.D.1", "2.D.2", "2.D.3"]},
+        ## 2.E
+        "2.E": {"sources": ["2.E.1"]},
+        ## 2.F
+        "2.F.1.a": {
+            "sources": [
+                "M.2.F.1.a.i",
+                "M.2.F.1.a.ii",
+                "M.2.F.1.a.iii",
+                "M.2.F.1.a.iv",
+                "M.2.F.1.a.v",
+            ]
+        },
+        "2.F.1": {"sources": ["2.F.1.a", "2.F.1.b"]},
+        "2.F.2": {"sources": ["M.2.F.2.a", "M.2.F.2.b"]},
+        "2.F.4": {"sources": ["M.2.F.4.a", "M.2.F.4.b"]},
+        "2.F.6": {"sources": ["2.F.6.b"]},
+        "2.F": {"sources": ["2.F.1", "2.F.2", "2.F.3", "2.F.4", "2.F.5", "2.F.6"]},
+        ## 2.G
+        "2.G.2.c": {"sources": ["M.2.G.2.c.i"]},
+        "2.G.2": {"sources": ["2.G.2.a", "2.G.2.b", "2.G.2.c"]},
+        "2.G.3": {"sources": ["2.G.3.a", "2.G.3.c"]},
+        "2.G": {"sources": ["2.G.1", "2.G.2", "2.G.3", "2.G.4"]},
+        ## 2
+        "2": {"sources": ["2.A", "2.B", "2.C", "2.D", "2.E", "2.F", "2.G"]},
+        # 3
+        ## 3.A
+        "3.A.1.a": {"sources": ["3.A.1.a.i", "3.A.1.a.ii"]},
+        "3.A.1": {"sources": ["3.A.1.a", "3.A.1.c", "3.A.1.h", "3.A.1.j"]},
+        "3.A.2.a": {"sources": ["3.A.2.a.i", "3.A.2.a.ii"]},
+        "3.A.2": {"sources": ["3.A.2.a", "3.A.2.c", "3.A.2.h", "3.A.2.i"]},
+        "3.A": {"sources": ["3.A.1", "3.A.2"]},
+        ## 3.B
+        "3.B.1": {"sources": ["3.B.1.a", "3.B.1.b", "M.3.B.1.DR"]},
+        "3.B.2": {"sources": ["3.B.2.a", "3.B.2.b"]},
+        "3.B.3": {"sources": ["3.B.3.a", "3.B.3.b", "M.3.B.3.DR"]},
+        "3.B.4": {"sources": ["3.B.4.a", "3.B.4.b", "M.3.B.4.DR"]},
+        "3.B.5": {"sources": ["3.B.5.a", "3.B.5.b", "M.3.B.5.DR"]},
+        "3.B": {"sources": ["3.B.1", "3.B.2", "3.B.3", "3.B.4", "3.B.5"]},
+        ## 3.C
+        "3.C.1.b": {
+            "sources": ["M.3.C.1.b.i", "M.3.C.1.b.ii", "M.3.C.1.b.iii", "M.3.C.1.b.iv"]
+        },
+        "3.C.1": {"sources": ["3.C.1.b"]},
+        "M.3.C.1.AG": {"sources": ["3.C.1.b"]},
+        "3.C.2": {"sources": ["M.3.C.2.a", "M.3.C.2.b"]},
+        "3.C.4.b": {"sources": ["M.3.C.4.b.i", "M.3.C.4.b.ii", "M.3.C.4.b.iii"]},
+        "3.C.4": {
+            "sources": [
+                "3.C.4.a",
+                "3.C.4.b",
+                "3.C.4.c",
+                "3.C.4.d",
+                "M.3.C.4.e",
+                "M.3.C.4.f",
+            ]
+        },
+        "M.3.C.5.AG": {"sources": ["M.3.C.5.AG.a", "M.3.C.5.AG.b"]},
+        "3.C.5": {"sources": ["M.3.C.5.AG", "M.3.C.5.LU"]},
+        "3.C": {"sources": ["3.C.1", "3.C.2", "3.C.3", "3.C.4", "3.C.5", "3.C.6"]},
+        "M.3.C.AG": {
+            "sources": ["M.3.C.1.AG", "3.C.2", "3.C.3", "3.C.4", "M.3.C.5.AG", "3.C.6"]
+        },
+        "M.3.C.LU": {"sources": ["M.3.C.5.LU"]},
+        "M.3.D.LU": {"sources": ["3.D.1"]},
+        # 3.D
+        "3.D": {"sources": ["3.D.1"]},
+        "M.AG.ELV": {"sources": ["M.3.C.AG"]},
+        "3": {"sources": ["3.A", "3.B", "3.C", "3.D"]},
+        "M.AG": {"sources": ["3.A", "M.AG.ELV"]},
+        "M.LULUCF": {"sources": ["3.B", "M.3.C.LU", "M.3.D.LU"]},
+        # 4
+        "4.A.1": {"sources": ["M.4.A.1.a"]},
+        "4.A": {"sources": ["4.A.1"]},
+        "4.B.1": {"sources": ["M.4.B.1.a"]},
+        "4.B.2": {"sources": ["M.4.B.2.a"]},
+        "4.B": {"sources": ["4.B.1", "4.B.2"]},
+        "4.C.1": {"sources": ["M.4.C.1.a.ii.4", "M.4.C.1.b.i", "M.4.C.1.b.ii.3"]},
+        "4.C.2": {"sources": ["M.4.C.2.a.ii.5", "M.4.C.2.b.ii.5"]},
+        "4.C": {"sources": ["4.C.1", "4.C.2"]},
+        "4.D": {"sources": ["4.D.1", "4.D.2"]},
+        "4": {"sources": ["4.A", "4.B", "4.C", "4.D"]},
+        # top level and bunkers
+        "0": {"sources": ["1", "2", "3", "4"]},
+        "M.0.EL": {"sources": ["1", "2", "M.AG", "4"]},
+        "M.BK": {"sources": ["M.BK.A", "M.BK.B"]},
+    },
+}
+
+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)"],
+}

src/unfccc_ghg_data/unfccc_reader/United_Kingdom/read_GBR_2024_Inventory_from_xlsx.py

@@ -0,0 +1,167 @@
+"""
+Read UK's 2024 inventory from xlsx
+
+Files available here: https://naei.beis.gov.uk/reports/reports?report_id=1140
+
+Currently not all detail is read as the same IPCC code is used for subcategories
+in some cases. For animal species this leads to wrong attribution of emissions
+from several species to one.
+
+"""
+import pandas as pd
+import primap2 as pm2
+
+from unfccc_ghg_data.helper import (
+    downloaded_data_path,
+    extracted_data_path,
+    process_data_for_country,
+)
+from unfccc_ghg_data.unfccc_reader.United_Kingdom.config_uk_inv2024 import (
+    basket_copy,
+    cat_conversion,
+    cols_to_drop,
+    coords_cols,
+    coords_defaults,
+    coords_terminologies,
+    coords_value_mapping,
+    entity_unit_filter,
+    gas_baskets,
+    meta_data,
+    terminology_proc,
+    time_format,
+)
+
+if __name__ == "__main__":
+    pd.set_option("future.no_silent_downcasting", True)
+
+    # ###
+    # configuration
+    # ###
+
+    # folders and files
+    input_folder = (
+        downloaded_data_path
+        / "non-UNFCCC"
+        / "United_Kingdom_of_Great_Britain_and_Northern_Ireland"
+        / "2024-Inventory"
+    )
+    output_folder = extracted_data_path / "non-UNFCCC" / "United_Kingdom"
+    if not output_folder.exists():
+        output_folder.mkdir()
+
+    output_filename = "GBR_2024-Inventory_"
+
+    inventory_file = "2406181003_DA_GHGI_1990-2022_v2.1.xlsx"
+    sheet_to_read = "BySource_data"
+
+    name_for_cat_col = "category"
+    compression = dict(zlib=True, complevel=9)
+
+    # ###
+    # start data reading
+    # ###
+
+    data_pd = pd.read_excel(
+        input_folder / inventory_file,
+        sheet_name=sheet_to_read,
+        engine="openpyxl",
+        skiprows=6,
+        usecols="C:P",
+    )
+    data_pd = data_pd.drop(columns=cols_to_drop)
+
+    # filter for the right unit per gas
+    data_pd_unit = None
+    for entity in entity_unit_filter:
+        unit = entity_unit_filter[entity]["from"]
+        data_current = data_pd.query(
+            f"Pollutant == '{entity}' " f"& ConvertTo == '{unit}'"
+        ).copy()
+        data_current["ConvertTo"] = data_current["ConvertTo"].replace(
+            {unit: entity_unit_filter[entity]["to"]}
+        )
+
+        if data_pd_unit is None:
+            data_pd_unit = data_current
+        else:
+            data_pd_unit = pd.concat([data_pd_unit, data_current])
+
+    # remove base year data
+    data_pd = data_pd_unit.query("EmissionYear != 'BaseYear'")
+
+    # combine timeseries for given category, area, entity
+    coords_to_keep = ["EmissionYear", "IPCC_code", "ConvertTo", "Pollutant"]
+    more_cols_to_drop = ["RegionName", "Sourcecode", "IPCC_name", "TESS2", "TESS3"]
+    data_grouped = data_pd.groupby(coords_to_keep).sum().reset_index()
+
+    data_grouped = data_grouped.drop(columns=more_cols_to_drop)
+
+    data_if = pm2.pm2io.convert_long_dataframe_if(
+        data_grouped,
+        coords_cols=coords_cols,
+        coords_defaults=coords_defaults,
+        coords_terminologies=coords_terminologies,
+        coords_value_mapping=coords_value_mapping,
+        meta_data=meta_data,
+        time_format=time_format,
+    )
+
+    data_pm2 = pm2.pm2io.from_interchange_format(data_if)
+
+    # convert back to IF to have units in the fixed format
+    data_if = data_pm2.pr.to_interchange_format()
+
+    # ###
+    # save data to IF and native format
+    # ###
+    pm2.pm2io.write_interchange_format(
+        output_folder / (output_filename + coords_terminologies["category"]), data_if
+    )
+
+    encoding = {var: compression for var in data_pm2.data_vars}
+    data_pm2.pr.to_netcdf(
+        output_folder / (output_filename + coords_terminologies["category"] + ".nc"),
+        encoding=encoding,
+    )
+
+    # ###
+    # conversion to ipcc 2006 categories
+    # ###
+
+    data_pm2_2006 = data_pm2.copy()
+
+    # actual processing
+
+    country_processing = {
+        "basket_copy": basket_copy,
+    }
+
+    data_pm2_2006 = process_data_for_country(
+        data_pm2_2006,
+        entities_to_ignore=[],
+        gas_baskets=gas_baskets,
+        processing_info_country=country_processing,
+        cat_terminology_out=terminology_proc,
+        category_conversion=cat_conversion,
+        # sectors_out=sectors_to_save,
+    )
+
+    # adapt source and metadata
+    current_source = data_pm2_2006.coords["source"].to_numpy()[0]
+    data_temp = data_pm2_2006.pr.loc[{"source": current_source}]
+    data_pm2_2006 = data_pm2_2006.pr.set("source", "AI_INV", data_temp)
+    data_pm2_2006 = data_pm2_2006.pr.loc[{"source": ["AI_INV"]}]
+
+    # convert back to IF to have units in the fixed format
+    data_if_2006 = data_pm2_2006.pr.to_interchange_format()
+
+    pm2.pm2io.write_interchange_format(
+        output_folder / (output_filename + terminology_proc),
+        data_if_2006,
+    )
+
+    encoding = {var: compression for var in data_pm2_2006.data_vars}
+    data_pm2_2006.pr.to_netcdf(
+        output_folder / (output_filename + terminology_proc + ".nc"),
+        encoding=encoding,
+    )

src/unfccc_ghg_data/unfccc_reader/United_States_of_America/__init__.py

@@ -0,0 +1,30 @@
+"""Read United States of America's national inventories
+
+Scripts and configurations to read United States of America's submissions to the UNFCCC.
+Currently, the following submissions and datasets are available (all datasets
+including DI (red using the DI-reader) and legacy BUR/NIR (no code)):
+
+.. exec_code::
+    :hide_code:
+
+    from unfccc_ghg_data.helper.functions import (get_country_datasets,
+                                                  get_country_submissions)
+    country = 'USA'
+    # print available submissions
+    print("="*15 + " Available submissions " + "="*15)
+    get_country_submissions(country, True)
+    print("")
+
+    #print available datasets
+    print("="*15 + " Available datasets " + "="*15)
+    get_country_datasets(country, True)
+
+You can also obtain this information running
+
+.. code-block:: bash
+
+    poetry run doit country_info country=USA
+
+See below for a listing of scripts for BUR/NIR reading including links.
+
+"""

src/unfccc_ghg_data/unfccc_reader/United_States_of_America/config_usa_inv2024.py

@@ -0,0 +1,364 @@
+"""Config for USA 2024 Inventroy
+
+General configuration for reading the inventory files for USA's official 2024
+inventory from xlsx
+
+"""
+
+gwp_to_use = "AR5GWP100"
+category_mapping = {
+    "Abandoned Oil and Gas Wells": "M.1.B.2.ab.6",
+    "Abandoned Underground Coal Mines": "1.B.1.a.i.3",
+    "Adipic Acid Production": "2.B.3",
+    "Agricultural Soil Management": "3.D",
+    "Aluminum Production": "2.C.3",
+    "Ammonia Production": "2.B.1",
+    "Anaerobic Digestion at Biogas Facilities": "5.B.2",
+    "Biomass and Biodiesel Consumptiona": "M.Memo.Bio",
+    #'CH4': '4',
+    "CH4c": "M.0.EL",
+    "CO2": "M.0.EL",
+    "Caprolactam, Glyoxal, and Glyoxylic Acid Production": "2.B.4",
+    "Carbide Production and Consumption": "2.B.5",
+    "Carbon Dioxide Consumption": "M.2.B.10.b",
+    "Cement Production": "2.A.1",
+    "Coal Mining": "M.1.B.1.a",  # abandoned underground mines are missing
+    "Commercial": "1.A.4.a",
+    "Composting": "5.B.1",
+    "Electric Power Sector": "1.A.1",
+    "Electrical Equipment": "2.G.1",
+    "Electronics Industry": "2.E",
+    "Enteric Fermentation": "3.A",
+    "Ferroalloy Production": "2.C.2",
+    "Field Burning of Agricultural Residues": "3.F",
+    "Fluorochemical Production": "2.B.9",
+    "Fossil Fuel Combustion": "1.A",
+    "Glass Production": "2.A.3",
+    "HFCs": "2",
+    "Incineration of Waste": "1.A.5.a.iv",
+    "Industrial": "1.A.2",
+    "International Bunker Fuelsb": "M.Memo.Int",
+    "Iron and Steel Production & Metallurgical Coke Production": "2.C.1",
+    # 'LULUCF Carbon Stock Changee': '',
+    # 'LULUCF Emissionsc': '',
+    # 'LULUCF Sector Net Totalf': '',
+    "Landfills": "5.A.1",
+    "Lead Production": "2.C.5",
+    "Lime Production": "2.A.2",
+    "Liming": "3.G",
+    "Magnesium Production and Processing": "2.C.4",
+    "Manure Management": "3.B",
+    "Mobile Combustion": "M.1.A.MOB",
+    #'N2O': '4',
+    "N2O from Product Uses": "2.G.3",
+    "N2Oc": "M.0.EL",
+    "NF3": "2",
+    "Natural Gas Systems": "M.1.B.2.b",  # abandoned wells missing
+    "Net Emissions (Sources and Sinks)": "0",
+    "Nitric Acid Production": "2.B.2",
+    "Non-Energy Use of Fuels": "1.A.5.a.iii",
+    "Other Process Uses of Carbonates": "2.A.4",
+    "PFCs": "2",
+    "Petrochemical Production": "2.B.8",
+    "Petroleum Systems": "M.1.B.2.a",  # abandoned wells missing
+    "Phosphoric Acid Production": "M.2.B.10.c",
+    "Residential": "1.A.4.b",
+    "Rice Cultivation": "3.C",
+    "SF6": "2",
+    "SF6 and PFCs from Other Product Use": "2.G.2",
+    "Soda Ash Production": "2.B.7",
+    "Stationary Combustion": "M.1.A.STAT",
+    "Substitution of Ozone Depleting Substances": "2.F",
+    "Titanium Dioxide Production": "2.B.6",
+    "Total Gross Emissions (Sources)": "M.0.EL",
+    "Transportation": "1.A.3",
+    "U.S. Territories": "1.A.5.a.v",
+    "Urea Consumption for Non-Agricultural Purposes": "M.2.B.10.a",
+    "Urea Fertilization": "3.H",
+    "Wastewater Treatment": "5.D",
+    "Zinc Production": "2.C.6",
+}
+
+category_col = "Gas/Source"
+inventory_files = {
+    "Table 2-1.csv": {
+        "CO2": None,
+        "CH4c": None,
+        "N2Oc": None,
+        "HFCs": {
+            "coords_defaults": {
+                "entity": f"HFCS ({gwp_to_use})",
+                "unit": "Mt CO2 / year",
+            },
+            "coords_value_mapping": {
+                "category": category_mapping,
+            },
+        },
+        "PFCs": {
+            "coords_defaults": {
+                "entity": f"PFCS ({gwp_to_use})",
+                "unit": "Mt CO2 / year",
+            },
+            "coords_value_mapping": {
+                "category": category_mapping,
+            },
+        },
+        "SF6": {
+            "coords_defaults": {
+                "entity": f"SF6 ({gwp_to_use})",
+                "unit": "Mt CO2 / year",
+            },
+            "coords_value_mapping": {
+                "category": category_mapping,
+            },
+        },
+        "NF3": {
+            "coords_defaults": {
+                "entity": f"NF3 ({gwp_to_use})",
+                "unit": "Mt CO2 / year",
+            },
+            "coords_value_mapping": {
+                "category": category_mapping,
+            },
+        },
+        "Total Gross Emissions (Sources)": {
+            "coords_defaults": {
+                "entity": f"KYOTOGHG ({gwp_to_use})",
+                "unit": "Mt CO2 / year",
+            },
+            "coords_value_mapping": {
+                "category": category_mapping,
+            },
+        },
+        "LULUCF Emissionsc": {
+            "coords_defaults": {"unit": "Mt CO2 / year"},
+            "coords_value_mapping": {
+                "entity": {
+                    #'LULUCF Emissionsc': '',
+                    "CH4": f"CH4 ({gwp_to_use})",
+                    "N2O": f"N2O ({gwp_to_use})",
+                    "LULUCF Carbon Stock Changee": "CO2",
+                    "LULUCF Sector Net Totalf": f"KYOTGHG ({gwp_to_use})",
+                },
+                "category": {
+                    #'LULUCF Emissionsc': '',
+                    "CH4": "4",
+                    "N2O": "4",
+                    "LULUCF Carbon Stock Changee": "4",
+                    "LULUCF Sector Net Totalf": "4",
+                },
+            },
+        },
+        "Net Emissions (Sources and Sinks)": {
+            "coords_defaults": {
+                "entity": f"KYOTOGHG ({gwp_to_use})",
+                "unit": "Mt CO2 / year",
+            },
+            "coords_value_mapping": {
+                "category": category_mapping,
+            },
+        },
+        "+ Does not exceed 0.05 MMT CO2 Eq.": None,
+    },
+    "Table 2-2.csv": {
+        "CO2": {
+            "coords_defaults": {"entity": "CO2", "unit": "kt CO2 / year"},
+            "coords_value_mapping": {
+                "category": category_mapping,
+            },
+        },
+        "CH4c": {
+            "coords_defaults": {"entity": "CH4", "unit": "kt CH4 / year"},
+            "coords_value_mapping": {
+                "category": category_mapping,
+            },
+        },
+        "N2Oc": {
+            "coords_defaults": {"entity": "N2O", "unit": "kt N2O / year"},
+            "coords_value_mapping": {
+                "category": category_mapping,
+            },
+        },
+        "HFCs": None,
+        "PFCs": None,
+        "SF?": None,
+        "NF?": None,
+        "+ Does not exceed 0.5 kt.": None,
+    },
+}
+
+time_format = "%Y"
+
+coords_cols_template = {
+    "category": category_col,
+}
+
+coords_terminologies = {
+    "area": "ISO3",
+    "category": "CRF2013_2023",
+    "scenario": "PRIMAP",
+}
+
+coords_defaults_template = {
+    "source": "USA-GHG-Inventory",
+    "provenance": "measured",
+    "area": "USA",
+    "scenario": "2024INV",
+}
+
+meta_data = {
+    "references": "https://www.epa.gov/ghgemissions/"
+    "inventory-us-greenhouse-gas-emissions-and-sinks-1990-2022",
+    "rights": "",
+    "contact": "johannes.guetschow@climate-resource.com",
+    "title": "Inventory of U.S. Greenhouse Gas Emissions and Sinks: 1990-2022",
+    "comment": "Read fom csv files by Johannes Gütschow",
+    "institution": "United States Environmental Protection Agency",
+}
+
+filter_remove = {
+    "f1": {
+        category_col: [
+            "LULUCF Emissionsc",
+        ]
+    }
+}
+
+### processing
+
+cat_conversion = {
+    "mapping": {
+        "0": "0",
+        "1.A": "1.A",
+        "1.A.1": "1.A.1",
+        "1.A.2": "1.A.2",
+        "1.A.3": "1.A.3",
+        "1.A.4.a": "1.A.4.a",
+        "1.A.4.b": "1.A.4.b",
+        "1.A.5.a.iii": "2.D",  # non energy fuel use
+        "1.A.5.a.iv": "M.1.A.5.a.iv",  # waste incineration
+        "1.A.5.a.v": "1.A.5.a.v",  # US Territories
+        "1.B.1.a.i.3": "1.B.1.a.i.3",
+        "2": "2",
+        "2.A.1": "2.A.1",
+        "2.A.2": "2.A.2",
+        "2.A.3": "2.A.3",
+        "2.A.4": "2.A.4",
+        "2.B.1": "2.B.1",
+        "2.B.2": "2.B.2",
+        "2.B.3": "2.B.3",
+        "2.B.4": "2.B.4",
+        "2.B.5": "2.B.5",
+        "2.B.6": "2.B.6",
+        "2.B.7": "2.B.7",
+        "2.B.8": "2.B.8",
+        "2.B.9": "2.B.9",
+        "2.C.1": "2.C.1",
+        "2.C.2": "2.C.2",
+        "2.C.3": "2.C.3",
+        "2.C.4": "2.C.4",
+        "2.C.5": "2.C.5",
+        "2.C.6": "2.C.6",
+        "2.E": "2.E",
+        "2.F": "2.F",
+        "2.G.1": "2.G.1",
+        "2.G.2": "2.G.2",
+        "2.G.3": "2.G.3",
+        "3.A": "3.A.1",
+        "3.B": "3.A.2",
+        "3.C": "3.C.7",
+        "3.D": "M.3.C.45.AG",
+        "3.F": "M.3.C.1.AG",
+        "3.G": "3.C.2",
+        "3.H": "3.C.3",
+        "4": "M.LULUCF",
+        "5.A.1": "4.A.1",
+        "5.B.1": "4.B.1",
+        "5.B.2": "4.B.2",
+        "5.D": "4.D",
+        "M.0.EL": "M.0.EL",
+        "M.1.A.MOB": "M.1.A.MOB",
+        "M.1.A.STAT": "M.1.A.STAT",
+        "M.1.B.1.a": "M.1.B.1.a",
+        "M.1.B.2.a": "M.1.B.2.a",
+        "M.1.B.2.ab.6": "M.1.B.2.ab.6",
+        "M.1.B.2.b": "M.1.B.2.b",
+        "M.2.B.10.a": "M.2.B.10.a",
+        "M.2.B.10.b": "M.2.B.10.b",
+        "M.2.B.10.c": "M.2.B.10.c",
+        "M.Memo.Bio": "M.BIO",
+        "M.Memo.Int": "M.BK",
+    },
+    "aggregate": {
+        # 1
+        "1.A.4": {"sources": ["1.A.4.a", "1.A.4.b"]},
+        "1.A.5.a": {"sources": ["M.1.A.5.a.iv", "M.1.A.5.a.v"]},
+        "1.A.5": {"sources": ["1.A.5.a"]},
+        "1.A": {
+            "sources": ["M.1.A.MOB", "M.1.A.STAT", "1.A.5"],
+            "filter": {"entity": ["CH4", "N2O"]},
+        },
+        "1.B.1": {"sources": ["M.1.B.1.a", "1.B.1.a.i.3"]},
+        "1.B.2": {"sources": ["M.1.B.2.a", "M.1.B.2.b", "M.1.B.2.ab.6"]},
+        "1.B": {"sources": ["1.B.1", "1.B.2"]},
+        "1": {"sources": ["1.A", "1.B"]},
+        # 2
+        "2.A": {"sources": ["2.A.1", "2.A.2", "2.A.3", "2.A.4"]},
+        "2.B.10": {"sources": ["M.2.B.10.a", "M.2.B.10.b", "M.2.B.10.c"]},
+        "2.B": {
+            "sources": [
+                "2.B.1",
+                "2.B.2",
+                "2.B.3",
+                "2.B.4",
+                "2.B.5",
+                "2.B.6",
+                "2.B.7",
+                "2.B.8",
+                "2.B.9",
+                "2.B.10",
+            ]
+        },
+        "2.C": {"sources": ["2.C.1", "2.C.2", "2.C.3", "2.C.4", "2.C.5", "2.C.6"]},
+        "2.G": {"sources": ["2.G.1", "2.G.2", "2.G.3"]},
+        "2": {
+            "sources": ["2.A", "2.B", "2.C", "2.D", "2.E", "2.F", "2.G"],
+            "tolerance": 0.251,  # rounding inconsistencies in NF3 and PFCs after 2008
+        },
+        # M.AG
+        "3.A": {"sources": ["3.A.1", "3.A.2"]},
+        "3.C.1": {"sources": ["M.3.C.1.AG"]},
+        "M.3.C.AG": {"sources": ["3.C.1", "3.C.2", "3.C.3", "M.3.C.45.AG", "3.C.7"]},
+        "3.C": {"sources": ["M.3.C.AG"]},
+        "M.AG.ELV": {"sources": ["M.3.C.AG"]},
+        "M.AG": {"sources": ["M.AG.ELV", "3.A"]},
+        # 3
+        "3": {"sources": ["M.AG", "M.LULUCF"]},
+        # 4
+        "4.A": {"sources": ["4.A.1"]},
+        "4.B": {"sources": ["4.B.1", "4.B.2"]},
+        "4": {"sources": ["4.A", "4.B", "4.D"]},
+        # consistency check
+        "0": {"sources": ["1", "2", "3", "4"]},
+        "M.0.EL": {"sources": ["1", "2", "M.AG", "4"]},
+    },
+}
+
+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)"],
+}
+
+terminology_proc = "IPCC2006_PRIMAP"

src/unfccc_ghg_data/unfccc_reader/United_States_of_America/read_USA_2024_Inventory_from_xlsx.py

@@ -0,0 +1,182 @@
+"""
+Read USA's 2024 inventory from xlsx
+
+Files available here: https://www.epa.gov/ghgemissions/
+inventory-us-greenhouse-gas-emissions-and-sinks-1990-2022
+
+Only the overview tables are read as details are in several individual tables and
+overview is sufficient for PRIMAP-hist
+
+"""
+import pandas as pd
+import primap2 as pm2
+
+from unfccc_ghg_data.helper import (
+    downloaded_data_path,
+    extracted_data_path,
+    process_data_for_country,
+)
+from unfccc_ghg_data.unfccc_reader.United_States_of_America.config_usa_inv2024 import (
+    basket_copy,
+    cat_conversion,
+    category_col,
+    coords_cols_template,
+    coords_defaults_template,
+    coords_terminologies,
+    filter_remove,
+    gas_baskets,
+    inventory_files,
+    meta_data,
+    terminology_proc,
+    time_format,
+)
+
+if __name__ == "__main__":
+    pd.set_option("future.no_silent_downcasting", True)
+
+    # ###
+    # configuration
+    # ###
+
+    # folders and files
+    input_folder = (
+        downloaded_data_path
+        / "non-UNFCCC"
+        / "United_States_of_America"
+        / "2024-Inventory"
+        / "main-text-tables"
+        / "trends"
+    )
+    output_folder = extracted_data_path / "non-UNFCCC" / "United_States_of_America"
+    if not output_folder.exists():
+        output_folder.mkdir()
+
+    output_filename = "USA_2024-Inventory_"
+    compression = dict(zlib=True, complevel=9)
+
+    # ###
+    # start data reading
+    # ###
+
+    data_pm2 = None
+
+    for file in inventory_files.keys():
+        data_current_pd = pd.read_csv(input_folder / file, header=[1])
+        # remove the thousands separators (can't be done during reading as data is
+        # stored as string)
+        all_cols = data_current_pd.columns
+        data_cols = [col for col in all_cols if col != category_col]
+        for col in data_cols:
+            if data_current_pd.dtypes[col] == "object":
+                data_current_pd[col] = data_current_pd[col].str.replace(",", "")
+
+        section_keys = inventory_files[file].keys()
+        key_info = {}
+        last_key = None
+        for i, row in data_current_pd.iterrows():
+            if row[category_col] in section_keys:
+                key_info[row[category_col]] = {}
+                key_info[row[category_col]]["start"] = i
+                if last_key is not None:
+                    key_info[last_key]["end"] = i
+                last_key = row[category_col]
+
+        for section_key in section_keys:
+            current_config = inventory_files[file][section_key]
+            if current_config is not None:
+                # get the data
+                if "end" in key_info[section_key].keys():
+                    data_section = data_current_pd.iloc[
+                        key_info[section_key]["start"] : key_info[section_key]["end"]
+                    ].copy()
+                else:
+                    data_section = data_current_pd.iloc[
+                        key_info[section_key]["start"] :
+                    ].copy()
+
+                # convert to primap2 IF
+                coords_defaults = coords_defaults_template.copy()
+                coords_defaults.update(current_config["coords_defaults"])
+                coords_value_mapping = current_config["coords_value_mapping"]
+                coords_cols = coords_cols_template.copy()
+                if "entity" in coords_value_mapping:
+                    # make a copy of the category column as we also need if for entity
+                    data_section["entity"] = data_section[category_col]
+                    coords_cols["entity"] = "entity"
+
+                data_section_if = pm2.pm2io.convert_wide_dataframe_if(
+                    data_section,
+                    coords_cols=coords_cols,
+                    coords_terminologies=coords_terminologies,
+                    coords_defaults=coords_defaults,
+                    coords_value_mapping=coords_value_mapping,
+                    filter_remove=filter_remove,
+                    meta_data=meta_data,
+                    time_format=time_format,
+                )
+                # convert to primap2 native format
+                data_section_pm2 = pm2.pm2io.from_interchange_format(data_section_if)
+
+                # merge with other data
+                if data_pm2 is None:
+                    data_pm2 = data_section_pm2
+                else:
+                    data_pm2 = data_pm2.pr.merge(data_section_pm2)
+
+    # convert back to IF to have units in the fixed format
+    data_if = data_pm2.pr.to_interchange_format()
+
+    # ###
+    # save data to IF and native format
+    # ###
+    pm2.pm2io.write_interchange_format(
+        output_folder / (output_filename + coords_terminologies["category"]), data_if
+    )
+
+    encoding = {var: compression for var in data_pm2.data_vars}
+    data_pm2.pr.to_netcdf(
+        output_folder / (output_filename + coords_terminologies["category"] + ".nc"),
+        encoding=encoding,
+    )
+
+    # ###
+    # conversion to ipcc 2006 categories
+    # ###
+
+    data_pm2_2006 = data_pm2.copy()
+
+    # actual processing
+
+    country_processing = {
+        "basket_copy": basket_copy,
+    }
+
+    data_pm2_2006 = process_data_for_country(
+        data_pm2_2006,
+        entities_to_ignore=[],
+        gas_baskets=gas_baskets,
+        processing_info_country=country_processing,
+        cat_terminology_out=terminology_proc,
+        category_conversion=cat_conversion,
+        # sectors_out=sectors_to_save,
+    )
+
+    # adapt source and metadata
+    current_source = data_pm2_2006.coords["source"].to_numpy()[0]
+    data_temp = data_pm2_2006.pr.loc[{"source": current_source}]
+    data_pm2_2006 = data_pm2_2006.pr.set("source", "AI_INV", data_temp)
+    data_pm2_2006 = data_pm2_2006.pr.loc[{"source": ["AI_INV"]}]
+
+    # convert back to IF to have units in the fixed format
+    data_if_2006 = data_pm2_2006.pr.to_interchange_format()
+
+    pm2.pm2io.write_interchange_format(
+        output_folder / (output_filename + terminology_proc),
+        data_if_2006,
+    )
+
+    encoding = {var: compression for var in data_pm2_2006.data_vars}
+    data_pm2_2006.pr.to_netcdf(
+        output_folder / (output_filename + terminology_proc + ".nc"),
+        encoding=encoding,
+    )