f6.ipynb

{
 "metadata": {
  "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
  },
  "orig_nbformat": 2
 },
 "nbformat": 4,
 "nbformat_minor": 2,
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "class FeatureSolver(AbstractSolver):\n",
    "    def __init__(\n",
    "        self,\n",
    "        problem_type=float,\n",
    "        fitness_func= lambda a : fitness_func(a),\n",
    "        pop_cnt: int = 40,\n",
    "        gene_size: int = 50,\n",
    "        max_gen: int = 2,\n",
    "        mutation_ratio: float = 0.2,\n",
    "        selection_ratio: float = 0.2,\n",
    "        selection_type: str = \"roulette_wheel\",\n",
    "        mutation_type: str = \"insert\",\n",
    "        crossover_type: str = \"one_point\",\n",
    "        excluded_genes: Sequence = None,\n",
    "        variables_limits=(-10, 10),\n",
    "        verbose: bool = False,\n",
    "        cv=0,\n",
    "        **kwargs\n",
    "    ):\n",
    "        \"\"\"\n",
    "        :param fitness_function: can either be a fitness function or\n",
    "        a class implementing a fitness function + methods to override\n",
    "        the default ones: create_offspring, mutate_population, initialize_population\n",
    "        :param n_genes: number of genes (variables) to have in each chromosome\n",
    "        :param max_gen: maximum number of generations to perform the optimization\n",
    "        :param pop_size: population size\n",
    "        :param mutation_rate: rate at which random mutations occur\n",
    "        :param selection_rate: percentage of the population to be selected for crossover\n",
    "        :param selection_strategy: strategy to use for selection\n",
    "        :param verbose: whether to print iterations status\n",
    "        :param show_stats: whether to print stats at the end\n",
    "        :param plot_results: whether to plot results of the run at the end\n",
    "        :param variables_limits: limits for each variable [(x1_min, x1_max), (x2_min, x2_max), ...].\n",
    "        If only one tuple is provided, then it is assumed the same for every variable\n",
    "        :param problem_type: whether problem is of float or integer type\n",
    "        \"\"\"\n",
    "\n",
    "        AbstractSolver.__init__(\n",
    "            self,\n",
    "            problem_type=problem_type,\n",
    "            gene_size=gene_size,\n",
    "            fitness_func=fitness_func,\n",
    "            pop_cnt=pop_cnt,\n",
    "            max_gen=max_gen,\n",
    "            mutation_ratio=mutation_ratio,\n",
    "            selection_ratio=selection_ratio,\n",
    "            selection_type=selection_type,\n",
    "            mutation_type=mutation_type,\n",
    "            crossover_type=crossover_type,\n",
    "            excluded_genes=excluded_genes,\n",
    "            verbose=verbose,\n",
    "            cv=cv,\n",
    "            **kwargs\n",
    "        )\n",
    "        \n",
    "    def initialize_population(self):\n",
    "        \"\"\"\n",
    "        Initializes the population of the problem according to the\n",
    "        population size and number of genes and according to the problem\n",
    "        type (either integers or floats).\n",
    "\n",
    "        :return: a numpy array with a randomized initialized population\n",
    "        \"\"\"\n",
    "        population = np.empty(shape=(self.pop_cnt, self.gene_size))\n",
    "        for i in range(0,self.pop_cnt):\n",
    "            population[i] = random.sample(range(0,99) , self.gene_size)\n",
    "\n",
    "\n",
    "        return population\n",
    "\n",
    "random.seed(10)        \n",
    "solver = FeatureSolver(\n",
    "        gene_size=50,\n",
    "        cv=0 \n",
    "    )\n",
    "\n",
    "list(solver.solve())"
   ]
  }
 ]
}