bjoern/pypsa-eur
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

use country_converter instead of pycountry

Browse Source
This commit is contained in:
Fabian Neumann 2023-08-22 14:22:25 +02:00
parent dadc372ecd
commit f4d821ad2a
1 changed files with 5 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
scripts/build_industrial_distribution_key.py
View File

@ -93,22 +93,16 @@ def prepare_hotmaps_database(regions):
gdf.rename(columns={"index_right": "bus"}, inplace=True)
gdf["country"] = gdf.bus.str[:2]
# the .sjoin can lead to duplicates if a geom is in two regions
# the .sjoin can lead to duplicates if a geom is in two overlapping regions
if gdf.index.duplicated().any():
import pycountry
# get all duplicated entries
duplicated_i = gdf.index[gdf.index.duplicated()]
# convert from raw data country name to iso-2-code
s = df.loc[duplicated_i, "Country"].apply(
lambda x: pycountry.countries.lookup(x).alpha_2
)
# Get a boolean mask where gdf's country column matches s's values for the same index
mask = gdf["country"] == gdf.index.map(s)
# Filter gdf using the mask
gdf_filtered = gdf[mask]
code = cc.convert(gdf.loc[duplicated_i, "Country"], to="iso2")
# screen out malformed country allocation
gdf_filtered = gdf.loc[duplicated_i].query("country == @code")
# concat not duplicated and filtered gdf
gdf = pd.concat([gdf.drop(duplicated_i), gdf_filtered]).sort_index()
gdf = pd.concat([gdf.drop(duplicated_i), gdf_filtered])
return gdf