{ "cells": [ { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false }, "outputs": [], "source": [ "%matplotlib inline" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "\n# Example for evolutionary regression with genome reordering\n\nExample demonstrating the effect of genome reordering.\n\n## References\nGoldman B.W., Punch W.F. (2014): Analysis of Cartesian Genetic Programming\u2019s\nEvolutionary Mechanisms\nDOI: 10.1109/TEVC.2014.2324539\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false }, "outputs": [], "source": [ "# The docopt str is added explicitly to ensure compatibility with\n# sphinx-gallery.\ndocopt_str = \"\"\"\n Usage:\n example_reorder.py [--max-generations=]\n\n Options:\n -h --help\n --max-generations= Maximum number of generations [default: 300]\n\"\"\"\n\nimport matplotlib.pyplot as plt\nimport numpy as np\nimport scipy.constants\nfrom docopt import docopt\n\nimport cgp\n\nargs = docopt(docopt_str)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We first define a target function.\n\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false }, "outputs": [], "source": [ "def f_target(x):\n return x ** 2 + 1.0" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Then we define the objective function for the evolution. It uses\nthe mean-squared error between the output of the expression\nrepresented by a given individual and the target function evaluated\non a set of random points.\n\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false }, "outputs": [], "source": [ "def objective(individual):\n if not individual.fitness_is_None():\n return individual\n\n n_function_evaluations = 1000\n\n np.random.seed(1234)\n\n f = individual.to_func()\n loss = 0\n for x in np.random.uniform(-4, 4, n_function_evaluations):\n # the callable returned from `to_func` accepts and returns\n # lists; accordingly we need to pack the argument and unpack\n # the return value\n y = f(x)\n loss += (f_target(x) - y) ** 2\n\n individual.fitness = -loss / n_function_evaluations\n\n return individual" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Next, we set up the evolutionary search. We first define the\nparameters for the population, the genome of individuals, and two\nevolutionary algorithms without (default) and with genome reordering.\n\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false }, "outputs": [], "source": [ "population_params = {\"n_parents\": 1, \"seed\": 818821}\n\ngenome_params = {\n \"n_inputs\": 1,\n \"n_outputs\": 1,\n \"n_columns\": 12,\n \"n_rows\": 1,\n \"levels_back\": None,\n \"primitives\": (cgp.Add, cgp.Sub, cgp.Mul, cgp.ConstantFloat),\n}\n\nea_params = {\"n_offsprings\": 4, \"mutation_rate\": 0.03, \"n_processes\": 2}\nea_params_with_reorder = {\n \"n_offsprings\": 4,\n \"mutation_rate\": 0.03,\n \"n_processes\": 2,\n \"reorder_genome\": True,\n}\n\nevolve_params = {\"max_generations\": int(args[\"--max-generations\"]), \"termination_fitness\": 0.0}" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We create two populations that will be evolved\n\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false }, "outputs": [], "source": [ "pop = cgp.Population(**population_params, genome_params=genome_params)\npop_with_reorder = cgp.Population(**population_params, genome_params=genome_params)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "and two instances of the (mu + lambda) evolutionary algorithm\n\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false }, "outputs": [], "source": [ "ea = cgp.ea.MuPlusLambda(**ea_params)\nea_with_reorder = cgp.ea.MuPlusLambda(**ea_params_with_reorder)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "We define two callbacks for recording of fitness over generations\n\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false }, "outputs": [], "source": [ "history = {}\nhistory[\"fitness_champion\"] = []\n\n\ndef recording_callback(pop):\n history[\"fitness_champion\"].append(pop.champion.fitness)\n\n\nhistory_with_reorder = {}\nhistory_with_reorder[\"fitness_champion\"] = []\n\n\ndef recording_callback_with_reorder(pop):\n history_with_reorder[\"fitness_champion\"].append(pop.champion.fitness)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "and finally perform the evolution of the two populations\n\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false }, "outputs": [], "source": [ "cgp.evolve(\n pop, objective, ea, **evolve_params, print_progress=True, callback=recording_callback,\n)\n\ncgp.evolve(\n pop_with_reorder,\n objective,\n ea_with_reorder,\n **evolve_params,\n print_progress=True,\n callback=recording_callback_with_reorder,\n)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "After finishing the evolution, we plot the evolution of the fittest individual\nwith and without genome reordering\n\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "collapsed": false }, "outputs": [], "source": [ "width = 9.0\nfig = plt.figure(1, figsize=[width, width / scipy.constants.golden])\n\nplt.plot(history[\"fitness_champion\"], label=\"Champion\")\nplt.plot(history_with_reorder[\"fitness_champion\"], label=\"Champion with reorder\")\n\nplt.xlabel(\"Generation\")\nplt.ylabel(\"Fitness\")\nplt.legend([\"Champion\", \"Champion with reorder\"])\n\nplt.yscale(\"symlog\")\nplt.ylim(-1.0e2, 0.1)\nplt.axhline(0.0, color=\"0.7\")\n\nfig.savefig(\"example_reorder.pdf\", dpi=300)" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "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": "3.8.6" } }, "nbformat": 4, "nbformat_minor": 0 }