Merge branch 'features/#1095-mastr-status-quo' into continuous-integr…

…ation/run-everything-2022-11-10

CHANGELOG.rst

@@ -252,6 +252,8 @@ Added
   `PR #903 <https://github.com/openego/eGon-data/pull/903>`_
 * Add low flex scenario 'eGon2035_lowflex'
   `#822 <https://github.com/openego/eGon-data/issues/822>`_
+* Add MaStR geocoding and handling of conventional generators
+  `#1095 <https://github.com/openego/eGon-data/issues/1095>`_
 
 .. _PR #159: https://github.com/openego/eGon-data/pull/159
 .. _PR #703: https://github.com/openego/eGon-data/pull/703
@@ -496,9 +498,14 @@ Changed
   `#1073 <https://github.com/openego/eGon-data/issues/1073>`_
 * Rename eMob MIT carrier names (use underscores)
   `#1105 <https://github.com/openego/eGon-data/issues/1105>`_
+* Change desposit ID for data_bundle download from zenodo sandbox
+  `#1110 <https://github.com/openego/eGon-data/issues/1110>`_
+* Use MaStR geocoding results for pv rooftop to buildings mapping workflow
+  `#1095 <https://github.com/openego/eGon-data/issues/1095>`_
 
 .. _#799: https://github.com/openego/eGon-data/issues/799
 
+
 Bug Fixes
 ---------
 

docs/data.rst

@@ -7,3 +7,15 @@ Scenarios
 
 Published data
 ==============
+
+Data bundle
+-----------
+
+The data bundle is published on
+`zenodo <https://sandbox.zenodo.org/record/1167119>`_. It contains several data
+sets, which serve as a basis for egon-data. One such data set is the geocoding
+for the `MaStR data set <https://sandbox.zenodo.org/record/1132987>`_ which is
+used for eGon-data as well. Whenever the MaStR data set is updated it is
+necessary to redo the geocoding with the new data set and update the data
+bundle accordingly. The geocoding can be done based on the
+`mastr-geocoding repository <https://github.com/RLI-sandbox/mastr-geocoding>`_.

src/egon/data/datasets.yml

@@ -299,13 +299,20 @@ mastr:
 
 mastr_new:
   technologies:
-    - "wind"
+    - "biomass"
+    - "combustion"
+    - "gsgk"
     - "hydro"
+    - "nuclear"
     - "solar"
-    - "biomass"
+    - "storage"
+    - "wind"
   file_basename: "bnetza_mastr"
   deposit_id: 1132987
   egon2021_date_max: "2021-12-31 23:59:00"
+  geocoding_path:
+    - "data_bundle_egon_data"
+    - "mastr_geocoding"
 
 re_potential_areas:
   target:
@@ -356,14 +363,16 @@ hotmaps_current_policy_scenario_heat_demands_buildings:
 
 power_plants:
   sources:
-      mastr_pv: "bnetza_mastr_solar_cleaned.csv"
-      mastr_wind: "bnetza_mastr_wind_cleaned.csv"
       mastr_biomass: "bnetza_mastr_biomass_cleaned.csv"
+      mastr_combustion: "bnetza_mastr_combustion_cleaned.csv"
+      mastr_combustion_without_chp: "supply.egon_mastr_conventional_without_chp"
+      mastr_gsgk: "bnetza_mastr_gsgk_cleaned.csv"
       mastr_hydro: "bnetza_mastr_hydro_cleaned.csv"
       mastr_location: "location_elec_generation_raw.csv"
-      mastr_combustion_without_chp: "supply.egon_mastr_conventional_without_chp"
+      mastr_nuclear: "bnetza_mastr_nuclear_cleaned.csv"
+      mastr_pv: "bnetza_mastr_solar_cleaned.csv"
       mastr_storage: "bnetza_mastr_storage_cleaned.csv"
-      mastr_gsgk: "bnetza_mastr_gsgk_cleaned.csv"
+      mastr_wind: "bnetza_mastr_wind_cleaned.csv"
       capacities: "supply.egon_scenario_capacities"
       geom_germany: "boundaries.vg250_sta_union"
       geom_federal_states: "boundaries.vg250_lan"
@@ -531,7 +540,7 @@ solar_rooftop:
 data-bundle:
   sources:
     zenodo:
-      deposit_id: 1095882
+      deposit_id: 1167119
   targets:
     file:
       'data_bundle_egon_data.zip'

src/egon/data/datasets/data_bundle/__init__.py

@@ -2,13 +2,13 @@
 """
 
 
+from pathlib import Path
 from urllib.request import urlretrieve
+import shutil
 import zipfile
 
-import egon.data.config
+from egon.data import config
 from egon.data.datasets import Dataset
-from pathlib import Path
-import shutil
 
 
 def download():
@@ -23,9 +23,12 @@ def download():
     if data_bundle_path.exists() and data_bundle_path.is_dir():
         shutil.rmtree(data_bundle_path)
     # Get parameters from config and set download URL
-    sources = egon.data.config.datasets()["data-bundle"]["sources"]["zenodo"]
-    url = f"""https://sandbox.zenodo.org/record/{sources['deposit_id']}/files/data_bundle_egon_data.zip"""
-    target_file = egon.data.config.datasets()["data-bundle"]["targets"]["file"]
+    sources = config.datasets()["data-bundle"]["sources"]["zenodo"]
+    url = (
+        f"https://sandbox.zenodo.org/record/{sources['deposit_id']}/files/"
+        "data_bundle_egon_data.zip"
+    )
+    target_file = config.datasets()["data-bundle"]["targets"]["file"]
 
     # Retrieve files
     urlretrieve(url, target_file)
@@ -36,12 +39,12 @@ def download():
 
 class DataBundle(Dataset):
     def __init__(self, dependencies):
-        deposit_id = egon.data.config.datasets()["data-bundle"]["sources"][
-            "zenodo"
-        ]["deposit_id"]
+        deposit_id = config.datasets()["data-bundle"]["sources"]["zenodo"][
+            "deposit_id"
+        ]
         super().__init__(
             name="DataBundle",
-            version=str(deposit_id) + "-0.0.0",
+            version=f"{deposit_id}-0.0.1",
             dependencies=dependencies,
-            tasks=(download),
+            tasks=(download,),
         )

src/egon/data/datasets/power_plants/__init__.py

@@ -29,7 +29,6 @@
 )
 from egon.data.datasets.power_plants.pv_rooftop import pv_rooftop_per_mv_grid
 from egon.data.datasets.power_plants.pv_rooftop_buildings import (
-    geocode_mastr_data,
     pv_rooftop_to_buildings,
 )
 import egon.data.config
@@ -73,7 +72,6 @@ def __init__(self, dependencies):
                     pv_ground_mounted.insert,
                     (
                         pv_rooftop_per_mv_grid,
-                        geocode_mastr_data,
                         pv_rooftop_to_buildings,
                     ),
                 },
@@ -111,7 +109,10 @@ def create_tables():
     ]
     for t in tables:
         db.execute_sql(
-            f"DROP TABLE IF EXISTS {t.__table_args__['schema']}.{t.__tablename__} CASCADE;"
+            f"""
+            DROP TABLE IF EXISTS {t.__table_args__['schema']}.
+            {t.__tablename__} CASCADE;
+            """
         )
         t.__table__.create(bind=engine, checkfirst=True)