update broken urls and style issues

README.md

@@ -31,7 +31,7 @@ When using this template make sure to adapt it as needed:
 
 This repository provides an open MATSim transport model for Leipzig, provided by the [Transport Systems Planning and Transport Telematics group](https://www.vsp.tu-berlin.de) of [Technische Universität Berlin](http://www.tu-berlin.de).
 
-<a rel="TU Berlin" href="https://www.vsp.tu-berlin.de"><img src="https://svn.vsp.tu-berlin.de/repos/public-svn/ueber_uns/logo/TUB_Logo.png" width="15%" height="15%"/></a>
+<a rel="TU Berlin" href="https://www.vsp.tu-berlin.de"><img src="https://svn.vsp.tu-berlin.de/repos/public-svn/ueber_uns/logo/TU_BERLIN_Logo_Lang_RGB_SR_rot.svg" width="25%"/></a>
 
 This scenario contains a 25pct sample of Leipzig and its surrounding area; road capacities are accordingly reduced. The scenario is calibrated taking into consideration the traffic counts, modal split and mode-specific trip distance distributions.
 

src/main/python/create_ref.py

@@ -6,9 +6,11 @@
 from matsim.scenariogen.data import run_create_ref_data
 from matsim.scenariogen.data.preparation import calc_needed_short_distance_trips
 
+CRS = "EPSG:25832"
+
 
 def person_filter(df):
-    df = gpd.GeoDataFrame(df, geometry=gpd.GeoSeries.from_wkt(df.geom, crs="EPSG:4326").to_crs("EPSG:25832"))
+    df = gpd.GeoDataFrame(df, geometry=gpd.GeoSeries.from_wkt(df.geom, crs="EPSG:4326").to_crs(CRS))
     df = gpd.sjoin(df, region, how="inner", predicate="intersects")
 
     return df[df.present_on_day & (df.reporting_day <= 5)]
@@ -20,7 +22,7 @@ def trip_filter(df):
 
 
 if __name__ == "__main__":
-    region = gpd.read_file("../../../../shared-svn/projects/DiTriMo/data/shp/lausitz.shp").to_crs("EPSG:25832")
+    region = gpd.read_file("../../../../shared-svn/projects/DiTriMo/data/shp/lausitz.shp").to_crs(CRS)
 
     persons, trips, share = run_create_ref_data.create("/Volumes/Untitled/B3_Lokal-Datensatzpaket/CSV",
                                                        person_filter, trip_filter,
@@ -36,14 +38,14 @@ def trip_filter(df):
                               delimiter=";", dtype={"person": "str"})
     sim_persons = sim_persons[sim_persons.subpopulation == "person"]
     sim_persons = gpd.GeoDataFrame(sim_persons,
-                                   geometry=gpd.points_from_xy(sim_persons.home_x, sim_persons.home_y)).set_crs("EPSG:25832")
+                                   geometry=gpd.points_from_xy(sim_persons.home_x, sim_persons.home_y)).set_crs(CRS)
 
     sim_persons = gpd.sjoin(sim_persons, region, how="inner", predicate="intersects")
 
     sim = pd.read_csv("../../../output/output-lausitz-100pct/lausitz-100pct.output_trips.csv.gz",
                       delimiter=";", dtype={"person": "str"})
 
-    sim = pd.merge(sim, sim_persons, how="inner", left_on="person", right_on="person")
+    sim = pd.merge(sim, sim_persons, how="inner", left_on="person", right_on="person", validate="many_to_one")
 
     share, add_trips = calc_needed_short_distance_trips(trips, sim, max_dist=1500)
     print("Short distance trip missing: ", add_trips)