Geospatial Data Analysis and Mapping Guide

Analyze location-based datasets to uncover geographic patterns, build heat maps, optimize service areas, and make data-driven decisions about physical expansion or logistics.

Prompt Template

You are a geospatial data analyst. Help me analyze location-based data to uncover geographic patterns and make strategic decisions.

**Dataset description:** [e.g., 50,000 customer orders with lat/long coordinates, timestamps, and order values across 15 cities]
**Business context:** [e.g., food delivery startup deciding where to open 3 new dark kitchens]
**Available tools:** [e.g., Python with pandas, geopandas, folium; or SQL + Google BigQuery GIS]
**Key questions to answer:** [e.g., Where are demand hotspots? Which areas are underserved? What's the optimal radius for each kitchen?]
**Constraints:** [e.g., each kitchen covers max 5km radius, budget for 3 locations]

Provide:
1. **Data Preparation** — cleaning steps for geographic data (handling invalid coordinates, projections, geocoding)
2. **Exploratory Spatial Analysis** — code to generate:
   - Point density heat maps
   - Cluster analysis (DBSCAN or K-means on coordinates)
   - Spatial autocorrelation (Moran's I)
3. **Service Area Optimization** — algorithm to find optimal facility locations:
   - Weighted center-of-gravity method
   - Coverage maximization with radius constraints
   - Demand-weighted scoring per candidate location
4. **Visualization Code** — interactive maps with folium/plotly showing:
   - Customer density layers
   - Proposed locations with coverage circles
   - Revenue potential per zone
5. **Decision Framework** — ranked location recommendations with supporting metrics
6. **Monitoring Plan** — how to track location performance post-launch

Example Output

Geospatial Analysis: Dark Kitchen Location Optimization

1. Data Preparation

import geopandas as gpd

import pandas as pd

from shapely.geometry import Point

# Clean coordinates

df = df[(df['lat'].between(-90, 90)) & (df['lng'].between(-180, 180))]

df['geometry'] = df.apply(lambda r: Point(r['lng'], r['lat']), axis=1)

gdf = gpd.GeoDataFrame(df, crs='EPSG:4326')

# Project to local CRS for distance calculations (meters)

gdf_proj = gdf.to_crs('EPSG:3857')

3. Optimal Location Analysis

from sklearn.cluster import KMeans

import numpy as np

# Demand-weighted K-means (k=3 for 3 kitchens)

coords = gdf_proj[['geometry']].apply(

lambda g: [g.geometry.x, g.geometry.y], axis=1,

result_type='expand'

)

weights = gdf_proj['order_value'].values

kmeans = KMeans(n_clusters=3, random_state=42)

kmeans.fit(coords, sample_weight=weights)

5. Ranked Recommendations

|------|----------|---------------|-------------------|-------------|

| 1 | Downtown East (40.72, -73.99) | 12,400 | $890K/yr | Low |

| 2 | Midtown West (40.76, -73.98) | 9,800 | $720K/yr | Medium |

| 3 | Brooklyn Heights (40.69, -73.99) | 8,200 | $615K/yr | Low |

Tips for Best Results

💡Always validate coordinate data before analysis — even 1% invalid points can skew cluster centers significantly
💡Use projected coordinate systems (meters) for distance calculations, not raw lat/long degrees
💡Combine geospatial analysis with temporal patterns — demand at 6pm vs 6am may suggest very different optimal locations
💡Interactive maps are far more persuasive to stakeholders than static charts — use folium or Kepler.gl for presentations

Try it with

ChatGPT Claude Gemini

Related Prompts

Data Analysis

Dataset Summary and Insights

Paste or describe a dataset and get an instant summary of key statistics, patterns, anomalies, and actionable insights.

ChatGPTClaudeGemini

Data Analysis

SQL Query Writer for Business Reports

Generate SQL queries for common business reporting needs — revenue trends, cohort analysis, funnel metrics, and more.

ChatGPTClaude

Data Analysis

Dashboard KPI Definition Framework

Define the right KPIs for your business dashboard with clear formulas, targets, and data sources.

ChatGPTClaudeGemini