spa-l1-vienna-pip-count

Rerun

import geopandas as gpd

# Load datasets
districts = gpd.read_file('districts.geojson')
stations = gpd.read_file('stations.geojson')

# Inspect columns to find correct names
print("Districts columns:", districts.columns.tolist())
print("Stations columns:", stations.columns.tolist())
print("\nDistricts head:\n", districts.head())
print("\nStations head:\n", stations.head())

import geopandas as gpd

# Load datasets
districts = gpd.read_file('districts.geojson')
stations = gpd.read_file('stations.geojson')

# Inspect columns to find correct names
print("Districts columns:", districts.columns.tolist())
print("Stations columns:", stations.columns.tolist())
print("\nDistricts head:\n", districts.head())
print("\nStations head:\n", stations.head())

import geopandas as gpd
import pandas as pd

# Load datasets
districts = gpd.read_file('districts.geojson')
stations = gpd.read_file('stations.geojson')

# Ensure same CRS
if stations.crs != districts.crs:
    stations = stations.to_crs(districts.crs)

# Spatial join to find which district each station belongs to
# We want to count stations per district. 
# We'll join stations to districts.
joined = gpd.sjoin(stations, districts, how='left', predicate='within')

# Group by district to count stations
# Since a station might not be in any district (if 'left' join results in NaN), 
# we need to make sure we include all districts, even those with 0 stations.
# A better way:
# 1. Count stations per district from the joined dataframe
counts = joined.groupby('district_code').size().reset_index(name='station_count')

# 2. Merge this back with the original districts dataframe to ensure all districts are present
result = districts[['district_code', 'district_name']].merge(counts, on='district_code', how='left')

# Fill NaN with 0 for districts with no stations
result['station_count'] = result['station_count'].fillna(0).astype(int)

# Sort by district_code
result = result.sort_values('district_code')

# Select and order columns as requested
result = result[['district_code', 'district_name', 'station_count']]

# Save to CSV
result.to_csv('stations_per_district.csv', index=False)

print("Successfully created stations_per_district.csv")
print(result.head())

import geopandas as gpd
import pandas as pd

# Load datasets
districts = gpd.read_file('districts.geojson')
stations = gpd.read_file('stations.geojson')

# Ensure same CRS
if stations.crs != districts.crs:
    stations = stations.to_crs(districts.crs)

# Spatial join to find which district each station belongs to
# Note: 'within' or 'intersects' works for points in polygons.
joined = gpd.sjoin(stations, districts, how='left', predicate='intersects')

# The 'joined' dataframe contains the district information for each station.
# However, stations that don't fall in a district will have NaN for district columns.
# We want to count stations per district.
# Let's group the joined dataframe by the district's unique ID to get counts.
counts = joined.groupby('district_code').size().reset_index(name='station_count')

# We must ensure all districts from the original districts file are included, 
# even if they have zero stations.
result = districts[['district_code', 'district_name']].merge(counts, on='district_code', how='left')

# Fill NaN with 0 for districts with no stations and ensure integer type
result['station_count'] = result['station_count'].fillna(0).astype(int)

# Sort by district_code as requested
result = result.sort_values('district_code')

# Final selection of columns
result = result[['district_code', 'district_name', 'station_count']]

# Save to CSV without geometry
result.to_csv('stations_per_district.csv', index=False)