--- title: Create address only csv execute: eval: false echo: true format: html: code-fold: false --- ```{python} import osmnx as oximport pandas as pd``` ```{python} = "San Diego County, California, USA" ``` ```{python} = {'shop' : 'financial' , 'amenity' : 'bank' }``` ```{python} = ox.features_from_place(place, tags)``` ```{python} ``` ```{python} = gdf[['name' ,'addr:housenumber' , 'addr:street' , 'addr:city' , 'addr:postcode' ,'geometry' ]]``` ```{python} = gdf[['name' ,'addr:housenumber' , 'addr:street' , 'addr:city' , 'addr:postcode' ,'geometry' ]]``` ```{python} = addresses.dropna(subset= ['addr:street' ,'addr:postcode' , 'addr:housenumber' , 'name' ])``` ```{python} "financial.csv" , index= False )``` ```{python} = addresses_clean.copy()``` ```{python} 'address' ] = ao['addr:housenumber' ] + " " + ao['addr:street' ] + ", " + ao['addr:city' ] + " " + ao['addr:postcode' ]``` ```{python} ``` ```{python} = ao[['name' , 'address' ]]``` ```{python} 'financial_ao.csv' , index= False )``` ## Geocoding addresses ```{python} import pandas as pd``` ```{python} = pd.read_csv('financial_ao.csv' )``` ```{python} ``` ```{python} import geopandas``` ```{python} = geopandas.tools.geocode(df.address, provider= 'nominatim' , user_agent= 'geog385f24' )``` ```{python} ``` ```{python} ``` ```{python} ``` ### Create a geodataframe ```{python} = geopandas.GeoDataFrame(results, geometry= 'geometry' , crs= "EPSG:4326" )``` ```{python} ``` ### Drop the obvious error - use a point in polygon ```{python} import osmnx as ox= ox.geocode_to_gdf("San Diego County, California, USA" )``` ```{python} ``` ```{python} = geopandas.sjoin(gdf, county_boundary, how= "inner" , predicate= "within" )``` ```{python} ``` ```{python} = points_in_county``` ```{python} ``` ```{python} str .split("," ).str [- 2 ].str .strip()``` ```{python} 'zipcode' ] = gdf.address.str .split("," ).str [- 2 ].str .strip()``` ```{python} = 'zipcode' ).count()``` ```{python} from geosnap import DataStore``` ```{python} = DataStore("/srv/data/geosnap" )``` ```{python} dir (datasets)``` ```{python} from geosnap import io as gio``` ```{python} from geosnap.io import get_acs= get_acs(datasets, state_fips= ['06' ], level= 'tract' , years= [2016 ])``` ```{python} = ca[ca.geoid.str .startswith('06073' )]``` ```{python} ``` ```{python} ``` ```{python} ``` ```{python} = sd.to_crs(gdf.crs)``` ```{python} == gdf.crs``` ```{python} = sd= gdf[['geometry' , 'address' , 'name' ]]``` ```{python} ``` ```{python} = geopandas.sjoin(points, tracts, how= "inner" , predicate= "within" , lsuffix= "left" , rsuffix= "right" )``` ```{python} ``` ```{python} ``` ```{python} ``` ```{python} # Replace 'GEOID' with the appropriate identifier column in your tracts GeoDataFrame = points_with_tracts.groupby('geoid' ).size().reset_index(name= 'point_count' )``` ```{python} = tracts.merge(tract_counts, on= 'geoid' , how= 'left' )'point_count' ] = tracts['point_count' ].fillna(0 ).astype(int )``` ```{python} 'point_count' , legend= True )``` ```{python} 'geoid' , 'point_count' ]].sort_values(by= 'point_count' , ascending= False ).head(10 )``` ```{python} 'geoid' , 'point_count' ]].groupby(by= 'point_count' ).count()```