From ArcPy to GeoPandas: A Technical Migration Guide

import arcpy
import os

# Setup
arcpy.env.workspace = "C:/data/flood_risk.gdb"
arcpy.env.overwriteOutput = True

# Read parcels and flood zones
parcels = "parcels"
flood_zones = "FEMA_flood_zones"

# Buffer flood zones by 50m for transition zone
print("Buffering flood zones...")
arcpy.Buffer_analysis(flood_zones, "flood_buffered", "50 METERS")

# Spatial join to find at-risk parcels
print("Identifying at-risk parcels...")
arcpy.SpatialJoin_analysis(
    parcels,
    "flood_buffered",
    "parcels_at_risk",
    "JOIN_ONE_TO_ONE",
    "KEEP_ALL",
    match_option="INTERSECT"
)

# Calculate risk score
print("Calculating risk scores...")
arcpy.AddField_management("parcels_at_risk", "RISK_SCORE", "DOUBLE")
arcpy.AddField_management("parcels_at_risk", "RISK_CATEGORY", "TEXT")

cursor = arcpy.da.UpdateCursor(
    "parcels_at_risk",
    ["SHAPE@AREA", "ASSESSED_VALUE", "FLOOD_ZONE", "RISK_SCORE", "RISK_CATEGORY"]
)

for row in cursor:
    area = row[0]
    value = row[1]
    zone = row[2]

    # Risk calculation
    if zone == "A":  # High risk
        risk = (value / area) * 1.5
        category = "HIGH"
    elif zone == "X":  # Moderate
        risk = (value / area) * 0.8
        category = "MODERATE"
    else:
        risk = 0
        category = "LOW"

    row[3] = risk
    row[4] = category
    cursor.updateRow(row)

del cursor

# Export to Excel for underwriting
print("Exporting results...")
arcpy.conversion.TableToExcel("parcels_at_risk", "C:/output/flood_risk_report.xlsx")

print("Complete!")

import geopandas as gpd
import pandas as pd

# Read data (compare format and access performance on the target run)
parcels = gpd.read_parquet("s3://bucket/parcels.parquet")
flood_zones = gpd.read_parquet("s3://bucket/flood_zones.parquet")

# Buffer flood zones (vectorised operation)
flood_buffered = flood_zones.copy()
flood_buffered['geometry'] = flood_zones.geometry.buffer(50)

# Spatial join (uses spatial index automatically)
at_risk = gpd.sjoin(
    parcels,
    flood_buffered[['geometry', 'FLOOD_ZONE']],
    how='inner',
    predicate='intersects'
)

# Calculate risk scores (fully vectorised - no cursor)
def calculate_risk(row):
    value_density = row['ASSESSED_VALUE'] / row.geometry.area

    if row['FLOOD_ZONE'] == 'A':
        return value_density * 1.5, 'HIGH'
    elif row['FLOOD_ZONE'] == 'X':
        return value_density * 0.8, 'MODERATE'
    else:
        return 0, 'LOW'

# Vectorised apply
at_risk[['RISK_SCORE', 'RISK_CATEGORY']] = at_risk.apply(
    calculate_risk,
    axis=1,
    result_type='expand'
)

# Export to Excel (Pandas integration)
at_risk.drop(columns='geometry').to_excel(
    "s3://bucket/output/flood_risk_report.xlsx",
    index=False,
    engine='openpyxl'
)

print("Complete!")