geodatasim 0.6.0

Geospatial City Data & Machine Learning

GeoDataSim: Geospatial City Analysis (Phase 2)

GeoDataSim is a library for generating synthetic city data, simulating urban growth patterns, and performing geospatial analysis including clustering and feature engineering. Phase 2 focuses on advanced simulation patterns and World Bank data integration.

Installation

pip install geodatasim

Example Usage & Verification

Basic Usage

import geodatasim as gds
from geodatasim import City

# 1. Create City Objects
istanbul = City('Istanbul', population=15_840_900, lat=41.0082, lon=28.9784)
ankara = City('Ankara', population=5_663_322, lat=39.9334, lon=32.8597)

# 2. Calculate Distance
dist = istanbul.distance_to(ankara)
print(f"Distance {istanbul.name} -> {ankara.name}: {dist:.2f} km")

# 3. Simulate Growth (Year 2030)
future_pop = istanbul.simulate_population_growth(years=10, rate=0.015)
print(f"Est. Population 2030: {int(future_pop):,}")

Verified Output

Distance Istanbul -> Ankara: 351.48 km
Est. Population 2030: 18,383,968

Advanced Usage: Growth Simulation (Verified)

from geodatasim import City

cities_to_load = ['Berlin', 'Paris']

print(f"Simulating growth for {len(cities_to_load)} European cities:")
for name in cities_to_load:
    city = City(name)
    if city.population:
            # 1.2% annual growth for 5 years
            current = city.population
            future = int(current * (1.012 ** 5))
            print(f"  {city.name}: {current:,} -> {future:,} (5 Years Growth)")

Verified Output:

Simulating growth for 2 European cities:
  Berlin: 3,769,000 -> 4,000,632 (5 Years Growth)
  Paris: 11,020,000 -> 11,697,260 (5 Years Growth)

Features

• Synthetic Data: Generate realistic city datasets.
• Clustering: K-Means integration for city grouping.
• Simulation: Urban growth models.
• Visualization: Radar charts, heatmaps, and geospatial plots.

License

MIT