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

drop duplicates in prepare_hotmaps_database

Browse Source
This commit is contained in:
lisazeyen 2023-08-21 16:16:53 +02:00 committed by GitHub
parent 1fc83b793d
commit 8d09e38627
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 14 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
scripts/build_industrial_distribution_key.py
View File

@ -93,6 +93,20 @@ def prepare_hotmaps_database(regions):
gdf.rename(columns={"index_right": "bus"}, inplace=True) gdf.rename(columns={"index_right": "bus"}, inplace=True)
gdf["country"] = gdf.bus.str[:2] gdf["country"] = gdf.bus.str[:2]
# the .sjoin can lead to duplicates if a geom is in two 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]
# concat not duplicated and filtered gdf
gdf = pd.concat([gdf.drop(duplicated_i), gdf_filtered]).sort_index()
return gdf return gdf