summaryrefslogtreecommitdiffstats
path: root/test/GA.ipynb
diff options
context:
space:
mode:
Diffstat (limited to 'test/GA.ipynb')
-rw-r--r--test/GA.ipynb361
1 files changed, 361 insertions, 0 deletions
diff --git a/test/GA.ipynb b/test/GA.ipynb
new file mode 100644
index 0000000..9d73164
--- /dev/null
+++ b/test/GA.ipynb
@@ -0,0 +1,361 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "id": "2fd45b3a-9a24-4782-812c-08223edb750e",
+ "metadata": {},
+ "source": [
+ "# Prueba del algoritmo genetico"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 21,
+ "id": "45972b70-b2a6-48f2-aafa-9f660548079a",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import numpy as np\n",
+ "import random"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "34eab22f-a400-4a14-9ac4-047d87dff69f",
+ "metadata": {},
+ "source": [
+ "Data"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 97,
+ "id": "a5736dba-4c38-4b7f-9a1a-963bdb006236",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "class Ciudad:\n",
+ " regiones = {\n",
+ " 'costa': {\n",
+ " 'plazoentrega': 1\n",
+ " },\n",
+ " 'sierra': {\n",
+ " 'plazoentrega': 2\n",
+ " },\n",
+ " 'selva': {\n",
+ " 'plazoentrega': 3\n",
+ " }\n",
+ " }\n",
+ " def __init__(self, nombre, region, longitud, latitud):\n",
+ " self.nombre = nombre\n",
+ " self.region = region\n",
+ " self.x = longitud\n",
+ " self.y = latitud"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 101,
+ "id": "8ee9610f-d128-4d1b-9458-ca9048073f20",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "class Road_network:\n",
+ " def __init__(self, cities, distances):\n",
+ " \"\"\"Grafo completo del pais\n",
+ " \n",
+ " Params\n",
+ " ------\n",
+ " \n",
+ " cities: list\n",
+ " Lista de objetos Ciudad\n",
+ " \n",
+ " routes: dict\n",
+ " (Aun no se como implementar esto)\n",
+ " \"\"\"\n",
+ " \n",
+ " self.cities = cities\n",
+ " self.routes = {}"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 102,
+ "id": "7dd72c93-acba-46f9-ac99-8c3d1a8cfa67",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "class Vehiculo:\n",
+ " tipos = {\n",
+ " 1: {\n",
+ " 'cargamax': 50\n",
+ " },\n",
+ " 2: {\n",
+ " 'cargamax': 100\n",
+ " },\n",
+ " 3: {\n",
+ " 'cargamax': 200\n",
+ " }\n",
+ " }\n",
+ " \n",
+ " def __init__(self):\n",
+ " pass"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 96,
+ "id": "474a3596-f75d-411e-bf4c-20b8b8259434",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "class Pedido:\n",
+ " def __init__(self, cliente, cantidad):\n",
+ " self.cliente = cliente\n",
+ " self.cantidad = cantidad"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 98,
+ "id": "7602722f-9026-44dc-b922-e17a7d3af45b",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "class Cliente:\n",
+ " def __init__(self, nombre, ciudad):\n",
+ " self.nombre = nombre\n",
+ " self.ciudad = ciudad"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 100,
+ "id": "f6b4829a-9001-410c-b20c-01c65c777d8a",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "class VRP:\n",
+ " def __init__(self):\n",
+ " # Conjuntos\n",
+ " self.I = range(2)\n",
+ " self.J = range(3)\n",
+ " self.T = range(5) # en horas\n",
+ " self.V = range(3) # 3 tipos de vehiculos\n",
+ " \n",
+ " def init_data(self):\n",
+ " \"\"\"\n",
+ " Lista los parametros iniciales, definidos en \"Modelo Matematico\" en ISA v02\n",
+ " \n",
+ " i: almacen grande (depot)\n",
+ " j: almacen pequeño (customer)\n",
+ " v: tipo de vehiculo\n",
+ " t: tiempo\n",
+ " \"\"\"\n",
+ " # Parametros\n",
+ " # Nombres cortos confunden, pero matrices de varias dimensiones \n",
+ " # sin etiquetas confunden mas\n",
+ " \n",
+ " # Demanda\n",
+ " self.D_jt = [ [ random.choice([0,1,2,3]) for _ in self.I ] for _ in self.T ]\n",
+ " # Capacidades de vehiculos\n",
+ " self.VL_v = [ random.choice([10, 15, 20]) for _ in self.V ]\n",
+ " # distancia entre almacen i, j\n",
+ " self.d_ij = [ random.choice([25,50,100]) for _ in self.V ]\n",
+ " #self.r_ijvt = [ [ 0 for _ in self.V ] for "
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 82,
+ "id": "ab559513-5c14-4dd2-a51d-7737114dfba1",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "array([10, 10, 15])"
+ ]
+ },
+ "execution_count": 82,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "p = VRP()\n",
+ "p.init_data()\n",
+ "np.array(p.VL_v)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 83,
+ "id": "2c3c85e0-a90c-4fda-86f7-778d7328c74d",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[25, 50, 50]"
+ ]
+ },
+ "execution_count": 83,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "p.d_ij"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "511ff788-0d1a-4ac7-9575-de182d236574",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "078280b5-70ef-4691-8798-a686d85d188c",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "611c9a0d-bb1a-48eb-af37-f033abe8ed66",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "64c68216-b9f1-45f9-a0fe-3862ab106c24",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "9cb6bb08-1547-4b64-993f-b2c453535264",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "b83d9e98-db8f-45cd-9eff-07d4194f7e07",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "b8c06031-9c55-4e13-a27b-91b0886902e6",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "e9483c22-243f-44e5-9a6d-09da92354554",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "12952643-4a10-40bf-8af3-41319c744732",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "b0306c4f-eb68-4009-9390-0f881c6a8cb4",
+ "metadata": {},
+ "outputs": [],
+ "source": []
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "id": "b3ad92de-b2ed-4f21-a696-1fa2981f89dc",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "def genetic_algorithm(population, fitness_fn, ngen=100, pmut=0.1):\n",
+ " \"Algoritmo Genetico \"\n",
+ " \n",
+ " popsize = len(population)\n",
+ " evaluate_population(population, fitness_fn) # evalua la poblacion inicial\n",
+ " ibest = sorted(range(len(population)), key=lambda i: population[i].fitness, reverse=True)[:1]\n",
+ " bestfitness = [population[ibest[0]].fitness]\n",
+ " print(\"Poblacion inicial, best_fitness = {}\".format(population[ibest[0]].fitness))\n",
+ " \n",
+ " for g in range(ngen): # Por cada generacion\n",
+ " \n",
+ " ## Selecciona las parejas de padres para cruzamiento \n",
+ " mating_pool = []\n",
+ " for i in range(int(popsize/2)): mating_pool.append(select_parents_roulette(population)) \n",
+ " \n",
+ " ## Crea la poblacion descendencia cruzando las parejas del mating pool con Recombinación de 1 punto\n",
+ " offspring_population = []\n",
+ " for i in range(len(mating_pool)): \n",
+ " #offspring_population.extend( mating_pool[i][0].crossover_onepoint(mating_pool[i][1]) )\n",
+ " offspring_population.extend( mating_pool[i][0].crossover_uniform(mating_pool[i][1]) )\n",
+ "\n",
+ " ## Aplica el operador de mutacion con probabilidad pmut en cada hijo generado\n",
+ " for i in range(len(offspring_population)):\n",
+ " if random.uniform(0, 1) < pmut: \n",
+ " offspring_population[i] = offspring_population[i].mutate_position()\n",
+ " \n",
+ " ## Evalua la poblacion descendencia\n",
+ " evaluate_population(offspring_population, fitness_fn) # evalua la poblacion inicial\n",
+ " \n",
+ " ## Selecciona popsize individuos para la sgte. generación de la union de la pob. actual y pob. descendencia\n",
+ " population = select_survivors(population, offspring_population, popsize)\n",
+ "\n",
+ " ## Almacena la historia del fitness del mejor individuo\n",
+ " ibest = sorted(range(len(population)), key=lambda i: population[i].fitness, reverse=True)[:1]\n",
+ " bestfitness.append(population[ibest[0]].fitness)\n",
+ " print(\"generacion {}, best_fitness = {}\".format(g, population[ibest[0]].fitness))\n",
+ " \n",
+ " return population[ibest[0]], bestfitness "
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3 (ipykernel)",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.9.2"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
generated by cgit v1.2.3 (git 2.25.1) at 2025-10-29 06:42:57 +0000