PyEvolve: Genetic Algorithm Simulation

Quick Installation Guide

1. Clone the repository:

   git clone https://github.com/Papaya-Voldemort/Creature-Evolution-Sim.git
   cd Creature-Evolution-Sim

2. Install the required dependencies:

   pip install -r requirements.txt

3. Run the simulation:

   python main.py

Example Usage

Basic Simulation

The default configuration in main.py creates a population of 100 creatures and evolves them over 10 generations:

import random
from helpers import Creature
from helpers import calculate_offspring, produce_next_generation
import matplotlib.pyplot as plt
import os

population_count = 100
population = []
generation_goal = 10

# Create initial population
for i in range(population_count):
    speed = random.randint(1, 100)
    strength = random.randint(1, 100)
    vision = random.randint(1, 100)
    stamina = random.randint(1, 100)
    creature = Creature(speed, strength, vision, stamina)
    population.append(creature)

# Sort by fitness
population = sorted(population, key=lambda c: c.fitness, reverse=True)
generations = [population]

# Evolve for multiple generations
for gen in range(1, generation_goal + 1):
    survivors = generations[-1][:20]  # top 20 from previous generation
    next_generation = produce_next_generation(survivors, population_count)
    next_generation = sorted(next_generation, key=lambda c: c.fitness, reverse=True)
    generations.append(next_generation)

Customizing the Simulation

You can easily modify the simulation parameters:

• Change population_count to simulate larger or smaller populations
• Adjust generation_goal to run for more or fewer generations
• Modify the selection criteria (currently takes top 20 creatures)
• Edit the calculate_fitness method in the Creature class to change how fitness is determined
• Adjust mutation rates in the calculate_offspring function

Visualization Examples

Fitness trends over generations showing average, maximum, and minimum fitness values.

Evolution of average trait values (speed, strength, vision, stamina) across generations.

Distribution of trait values in the final generation.

Understanding the Code

Key Components

• Creature Class: Represents an individual with four attributes and a fitness calculation
• calculate_offspring: Creates new creatures by combining traits from parents with possible mutations
• produce_next_generation: Generates a new population from the selected survivors

Fitness Calculation

The default fitness function weights the attributes as follows:

def calculate_fitness(self):
    fitness = (0.3 * self.speed) + (0.3 * self.strength) + (0.2 * self.vision) + (0.2 * self.stamina)
    return fitness

Future Development

Check out the TODO.md file for planned improvements and features. Contributions are welcome!