{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Symbolic Regression with Genetic Programming"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Import algorithms and selectors from modules in `core`; import representation-related operators from the appropriate  module in `evolvables` (in this case, `evolvables.gp` for tree-based genetic programming).\n",
    "\n",
    "The following modules are imported:\n",
    "\n",
    "- `SimpleLinearAlgorithm` for a simple algorithm that applies the variator, the evaluator, and the selector in this exact order.\n",
    "\n",
    "- `Population` contains individuals used in the learning process.\n",
    "\n",
    "- `Elitist` and `TournamentSelector` together construct an elitist tournament selector.\n",
    "\n",
    "- `Program` represents a tree-based genetic program, `ProgramFactory` constructs instances of `Program`.\n",
    "\n",
    "- `SymbolicEvaluator` evaluates instances of `Program`.\n",
    "\n",
    "- `CrossoverSubtree` creates new `Program`s from existing ones."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "from evokit.core.algorithm import SimpleLinearAlgorithm\n",
    "from evokit.core.population import Population\n",
    "from evokit.core.selector import Elitist, SimpleSelector, TournamentSelector\n",
    "\n",
    "from evokit.evolvables.funcs import *\n",
    "from evokit.evolvables.gp import CrossoverSubtree, ProgramFactory, Program, SymbolicEvaluator\n",
    "\n",
    "from typing import Tuple"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "To begin, initialise the following hyperparameters:\n",
    "\n",
    "- `POP_SIZE` is the size of the population. It affects the size of the initial population, and affects how many individuals are selected by the selector.\n",
    "\n",
    "- `STEP_COUNT` decides the number of generation before termination.\n",
    "\n",
    "- `TREE_DEPTH` and `NODE_BUDGET` affect how the `ProgramFactory` builds programs. By default, the factory builds with a modified full method, where it can only draw terminal nodes when depth exceeds `TREE_DEPTH` and the total number of nodes exceeds `NODE_BUDGET`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "POP_SIZE = 50\n",
    "STEP_COUNT = 50\n",
    "\n",
    "TREE_DEPTH = 4\n",
    "NODE_BUDGET = 20"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Define a program factory with a set of primitives and the arity of programs produced. Here, arity=1 means produced programs are unary."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "progf: ProgramFactory[float] =\\\n",
    "        ProgramFactory((add, sub, mul, div, sin, cos, mul, div, 2, 1, 0.5),\n",
    "        arity = 1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Define, then populate a population. The optional parameter `nullary_ratio` forces the factory to select terminal nodes with that probability; therefore, a higher value encourages wider trees. This setting does not bypass `TREE_DEPTH` and `NODE_BUDGET`."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "pops: Population[Program[float]] = Population()\n",
    "\n",
    "for i in range(0, POP_SIZE):\n",
    "    new_individual: Program[float] = progf.build(NODE_BUDGET, TREE_DEPTH, nullary_ratio=0.25)\n",
    "    pops.append(new_individual)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Define an objective function, then initialise an symbolic evaluator using that objective function. The parameter `support` decides the domain on which each program is compared against the objective function.\n",
    "\n",
    "Note that `SymbolicEvaluator` is genetic. Whereas the type of `new_individual` is Program[float], the type `SymbolicEvaluator` needs no subscript. This is because this evaluator is defined only for programs of floating-point numbers."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "def weird_function(x):\n",
    "    return sin(x)+2*cos(x)\n",
    "\n",
    "support: Tuple[Tuple[float], ...] = tuple((x/4,) for x in range(-80, 80))\n",
    "\n",
    "symbolic_fitness: SymbolicEvaluator = SymbolicEvaluator(objective=weird_function, support = support)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Pick the selectors and the variator, then initialise the algorithm using the operators defined so far.\n",
    "\n",
    "The interceptor `Elitist` forces its argument, which must be a selector, to adopt elitism.\n",
    "\n",
    "The `CrossoverSubtree` uses two parents. It randomly selects one internal node from each parent, selects one child node for each internal node, then exchanges the selected child nodes."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "tournament_selector = Elitist(TournamentSelector(POP_SIZE))\n",
    "\n",
    "crossover_subtree = CrossoverSubtree()\n",
    "\n",
    "ctrl = SimpleLinearAlgorithm(evaluator=symbolic_fitness,\n",
    "                              selector=tournament_selector,\n",
    "                              population=pops,\n",
    "                              variator=crossover_subtree)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Generation: 1\n",
      "Best individual is: Program:sin(add(mul(1, div(1, 1)), x0)), with fitnss -127.65582808704299\n",
      "Generation: 2\n",
      "Best individual is: Program:sin(add(mul(1, div(1, 1)), x0)), with fitnss -127.65582808704299\n",
      "Generation: 3\n",
      "Best individual is: Program:sin(add(mul(1, div(1, 1)), x0)), with fitnss -127.65582808704299\n",
      "Generation: 4\n",
      "Best individual is: Program:sin(add(mul(1, div(1, 1)), x0)), with fitnss -127.65582808704299\n",
      "Generation: 5\n",
      "Best individual is: Program:sin(add(mul(1, div(1, 1)), x0)), with fitnss -127.65582808704299\n",
      "Generation: 6\n",
      "Best individual is: Program:sin(add(mul(1, div(1, 1)), x0)), with fitnss -127.65582808704299\n",
      "Generation: 7\n",
      "Best individual is: Program:sin(add(mul(1, div(1, 1)), x0)), with fitnss -127.65582808704299\n",
      "Generation: 8\n",
      "Best individual is: Program:sin(add(mul(1, div(1, 1)), x0)), with fitnss -127.65582808704299\n",
      "Generation: 9\n",
      "Best individual is: Program:mul(1, cos(sub(0.5, x0))), with fitnss -126.51070812473542\n",
      "Generation: 10\n",
      "Best individual is: Program:mul(1, cos(sub(0.5, x0))), with fitnss -126.51070812473542\n",
      "Generation: 11\n",
      "Best individual is: Program:mul(1, cos(sub(0.5, x0))), with fitnss -126.51070812473542\n",
      "Generation: 12\n",
      "Best individual is: Program:mul(1, cos(sub(0.5, x0))), with fitnss -126.51070812473542\n",
      "Generation: 13\n",
      "Best individual is: Program:add(add(sin(x0), mul(cos(x0), 1)), div(sub(cos(add(mul(x0, x0), 0.5)), mul(0.5, 1)), 2)), with fitnss -106.95855663138987\n",
      "Generation: 14\n",
      "Best individual is: Program:add(add(sin(x0), mul(cos(x0), 1)), div(sub(cos(add(mul(x0, x0), 0.5)), mul(0.5, 1)), 2)), with fitnss -106.95855663138987\n",
      "Generation: 15\n",
      "Best individual is: Program:add(add(sin(x0), mul(cos(x0), 1)), div(sub(cos(add(mul(x0, x0), 0.5)), mul(0.5, 1)), 2)), with fitnss -106.95855663138987\n",
      "Generation: 16\n",
      "Best individual is: Program:add(add(sin(x0), mul(cos(x0), 1)), div(sub(cos(add(mul(x0, x0), 0.5)), mul(0.5, 1)), 2)), with fitnss -106.95855663138987\n",
      "Generation: 17\n",
      "Best individual is: Program:add(add(sin(x0), cos(x0)), cos(x0)), with fitnss -4.496403249731884e-15\n",
      "Generation: 18\n",
      "Best individual is: Program:add(add(sin(x0), cos(x0)), cos(x0)), with fitnss -4.496403249731884e-15\n",
      "Generation: 19\n",
      "Best individual is: Program:add(add(sin(x0), cos(x0)), cos(x0)), with fitnss -4.496403249731884e-15\n",
      "Generation: 20\n",
      "Best individual is: Program:add(add(sin(x0), cos(x0)), cos(x0)), with fitnss -4.496403249731884e-15\n",
      "Generation: 21\n",
      "Best individual is: Program:add(add(sin(x0), cos(x0)), cos(x0)), with fitnss -4.496403249731884e-15\n",
      "Generation: 22\n",
      "Best individual is: Program:add(add(sin(x0), cos(x0)), cos(x0)), with fitnss -4.496403249731884e-15\n",
      "Generation: 23\n",
      "Best individual is: Program:add(add(sin(x0), cos(x0)), cos(x0)), with fitnss -4.496403249731884e-15\n",
      "Generation: 24\n",
      "Best individual is: Program:add(add(sin(x0), cos(x0)), cos(x0)), with fitnss -4.496403249731884e-15\n",
      "Generation: 25\n",
      "Best individual is: Program:add(add(sin(x0), cos(x0)), cos(x0)), with fitnss -4.496403249731884e-15\n",
      "Generation: 26\n",
      "Best individual is: Program:add(add(sin(x0), cos(x0)), cos(x0)), with fitnss -4.496403249731884e-15\n",
      "Generation: 27\n",
      "Best individual is: Program:add(add(sin(x0), cos(x0)), cos(x0)), with fitnss -4.496403249731884e-15\n",
      "Generation: 28\n",
      "Best individual is: Program:add(add(sin(x0), cos(x0)), cos(x0)), with fitnss -4.496403249731884e-15\n",
      "Generation: 29\n",
      "Best individual is: Program:add(add(sin(x0), cos(x0)), cos(x0)), with fitnss -4.496403249731884e-15\n",
      "Generation: 30\n",
      "Best individual is: Program:add(add(sin(x0), mul(cos(x0), 1)), cos(x0)), with fitnss -4.496403249731884e-15\n",
      "Generation: 31\n",
      "Best individual is: Program:add(add(sin(x0), mul(cos(x0), 1)), cos(x0)), with fitnss -4.496403249731884e-15\n",
      "Generation: 32\n",
      "Best individual is: Program:add(add(sin(x0), mul(cos(x0), 1)), cos(x0)), with fitnss -4.496403249731884e-15\n",
      "Generation: 33\n",
      "Best individual is: Program:add(add(sin(x0), mul(cos(x0), 1)), cos(x0)), with fitnss -4.496403249731884e-15\n",
      "Generation: 34\n",
      "Best individual is: Program:add(add(sin(x0), mul(cos(x0), 1)), cos(x0)), with fitnss -4.496403249731884e-15\n",
      "Generation: 35\n",
      "Best individual is: Program:add(add(sin(x0), mul(cos(x0), 1)), cos(mul(x0, 1))), with fitnss -4.496403249731884e-15\n",
      "Generation: 36\n",
      "Best individual is: Program:add(add(sin(x0), mul(cos(mul(x0, 1)), 1)), cos(x0)), with fitnss -4.496403249731884e-15\n",
      "Generation: 37\n",
      "Best individual is: Program:add(add(sin(x0), mul(cos(mul(x0, 1)), 1)), cos(x0)), with fitnss -4.496403249731884e-15\n",
      "Generation: 38\n",
      "Best individual is: Program:add(add(sin(x0), mul(cos(mul(x0, 1)), 1)), cos(x0)), with fitnss -4.496403249731884e-15\n",
      "Generation: 39\n",
      "Best individual is: Program:add(add(sin(x0), mul(cos(mul(x0, 1)), 1)), cos(x0)), with fitnss -4.496403249731884e-15\n",
      "Generation: 40\n",
      "Best individual is: Program:add(add(sin(x0), mul(cos(mul(x0, 1)), 1)), cos(x0)), with fitnss -4.496403249731884e-15\n",
      "Generation: 41\n",
      "Best individual is: Program:add(add(sin(x0), mul(cos(mul(x0, 1)), 1)), cos(x0)), with fitnss -4.496403249731884e-15\n",
      "Generation: 42\n",
      "Best individual is: Program:add(add(sin(x0), mul(cos(x0), 1)), cos(div(x0, div(x0, x0)))), with fitnss -4.496403249731884e-15\n",
      "Generation: 43\n",
      "Best individual is: Program:add(add(sin(x0), mul(cos(x0), 1)), cos(mul(x0, 1))), with fitnss -4.496403249731884e-15\n",
      "Generation: 44\n",
      "Best individual is: Program:add(add(sin(x0), mul(cos(x0), 1)), cos(div(x0, div(mul(x0, 1), x0)))), with fitnss -4.496403249731884e-15\n",
      "Generation: 45\n",
      "Best individual is: Program:add(add(sin(x0), mul(cos(x0), 1)), cos(div(x0, div(mul(x0, 1), x0)))), with fitnss -4.496403249731884e-15\n",
      "Generation: 46\n",
      "Best individual is: Program:add(add(sin(x0), mul(cos(x0), 1)), cos(x0)), with fitnss -4.496403249731884e-15\n",
      "Generation: 47\n",
      "Best individual is: Program:add(add(sin(x0), mul(cos(x0), 1)), cos(x0)), with fitnss -4.496403249731884e-15\n",
      "Generation: 48\n",
      "Best individual is: Program:add(add(sin(x0), mul(cos(x0), 1)), cos(x0)), with fitnss -4.496403249731884e-15\n",
      "Generation: 49\n",
      "Best individual is: Program:add(add(sin(x0), mul(cos(x0), 1)), cos(x0)), with fitnss -4.496403249731884e-15\n",
      "Generation: 50\n",
      "Best individual is: Program:add(add(sin(x0), mul(cos(x0), 1)), cos(x0)), with fitnss -4.496403249731884e-15\n"
     ]
    }
   ],
   "source": [
    "bests = []\n",
    "\n",
    "for _ in range(STEP_COUNT):\n",
    "    ctrl.step()\n",
    "    generational_best = ctrl.population.best()\n",
    "    bests.append(generational_best.copy())\n",
    "\n",
    "    print(f\"Generation: {ctrl.generation}\")\n",
    "    print(f\"Best individual is: {generational_best}, with fitnss {generational_best.fitness}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Note that the fitness of the best individual never declines - this is because the interceptor `Elitist` successfully turns the tournament selector elitist. This is expected behaviour."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Each `Program.genome` is a callable function - as an example, call the best individual of the last generation with argument 1."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.9092974268256817"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bests[0].genome(1)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The module `evokit.evolvables.gp_visualiser` contains an utility for visualising genetic programs. Use it to visualise the last best individual. Because the tournament selector is elitist, this individual is also the best in all generations."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/svg+xml": [
       "<?xml version=\"1.0\" encoding=\"UTF-8\" standalone=\"no\"?>\n",
       "<!DOCTYPE svg PUBLIC \"-//W3C//DTD SVG 1.1//EN\"\n",
       " \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n",
       "<!-- Generated by graphviz version 9.0.0 (20230911.1827)\n",
       " -->\n",
       "<!-- Title: square&#45;peg Pages: 1 -->\n",
       "<svg width=\"206pt\" height=\"332pt\"\n",
       " viewBox=\"0.00 0.00 206.00 332.00\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">\n",
       "<g id=\"graph0\" class=\"graph\" transform=\"scale(1 1) rotate(0) translate(4 328)\">\n",
       "<title>square&#45;peg</title>\n",
       "<polygon fill=\"white\" stroke=\"none\" points=\"-4,4 -4,-328 202,-328 202,4 -4,4\"/>\n",
       "<!-- a1 -->\n",
       "<g id=\"node1\" class=\"node\">\n",
       "<title>a1</title>\n",
       "<ellipse fill=\"none\" stroke=\"black\" cx=\"135\" cy=\"-306\" rx=\"27\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"135\" y=\"-300.57\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">add</text>\n",
       "</g>\n",
       "<!-- a2 -->\n",
       "<g id=\"node2\" class=\"node\">\n",
       "<title>a2</title>\n",
       "<ellipse fill=\"none\" stroke=\"black\" cx=\"99\" cy=\"-234\" rx=\"27\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"99\" y=\"-228.57\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">add</text>\n",
       "</g>\n",
       "<!-- a1&#45;&gt;a2 -->\n",
       "<g id=\"edge1\" class=\"edge\">\n",
       "<title>a1&#45;&gt;a2</title>\n",
       "<path fill=\"none\" stroke=\"black\" d=\"M126.65,-288.76C122.42,-280.55 117.19,-270.37 112.42,-261.09\"/>\n",
       "<polygon fill=\"black\" stroke=\"black\" points=\"115.68,-259.79 108,-252.49 109.46,-262.99 115.68,-259.79\"/>\n",
       "</g>\n",
       "<!-- a9 -->\n",
       "<g id=\"node9\" class=\"node\">\n",
       "<title>a9</title>\n",
       "<ellipse fill=\"none\" stroke=\"black\" cx=\"171\" cy=\"-234\" rx=\"27\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"171\" y=\"-228.57\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">cos</text>\n",
       "</g>\n",
       "<!-- a1&#45;&gt;a9 -->\n",
       "<g id=\"edge8\" class=\"edge\">\n",
       "<title>a1&#45;&gt;a9</title>\n",
       "<path fill=\"none\" stroke=\"black\" d=\"M143.35,-288.76C147.58,-280.55 152.81,-270.37 157.58,-261.09\"/>\n",
       "<polygon fill=\"black\" stroke=\"black\" points=\"160.54,-262.99 162,-252.49 154.32,-259.79 160.54,-262.99\"/>\n",
       "</g>\n",
       "<!-- a3 -->\n",
       "<g id=\"node3\" class=\"node\">\n",
       "<title>a3</title>\n",
       "<ellipse fill=\"none\" stroke=\"black\" cx=\"27\" cy=\"-162\" rx=\"27\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"27\" y=\"-156.57\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">sin</text>\n",
       "</g>\n",
       "<!-- a2&#45;&gt;a3 -->\n",
       "<g id=\"edge2\" class=\"edge\">\n",
       "<title>a2&#45;&gt;a3</title>\n",
       "<path fill=\"none\" stroke=\"black\" d=\"M84.08,-218.5C74.23,-208.92 61.14,-196.19 49.97,-185.34\"/>\n",
       "<polygon fill=\"black\" stroke=\"black\" points=\"52.59,-183 42.98,-178.54 47.71,-188.02 52.59,-183\"/>\n",
       "</g>\n",
       "<!-- a5 -->\n",
       "<g id=\"node5\" class=\"node\">\n",
       "<title>a5</title>\n",
       "<ellipse fill=\"none\" stroke=\"black\" cx=\"99\" cy=\"-162\" rx=\"27\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"99\" y=\"-156.57\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">mul</text>\n",
       "</g>\n",
       "<!-- a2&#45;&gt;a5 -->\n",
       "<g id=\"edge4\" class=\"edge\">\n",
       "<title>a2&#45;&gt;a5</title>\n",
       "<path fill=\"none\" stroke=\"black\" d=\"M99,-215.7C99,-208.41 99,-199.73 99,-191.54\"/>\n",
       "<polygon fill=\"black\" stroke=\"black\" points=\"102.5,-191.62 99,-181.62 95.5,-191.62 102.5,-191.62\"/>\n",
       "</g>\n",
       "<!-- a4 -->\n",
       "<g id=\"node4\" class=\"node\">\n",
       "<title>a4</title>\n",
       "<ellipse fill=\"none\" stroke=\"black\" cx=\"27\" cy=\"-90\" rx=\"27\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"27\" y=\"-84.58\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">x0</text>\n",
       "</g>\n",
       "<!-- a3&#45;&gt;a4 -->\n",
       "<g id=\"edge3\" class=\"edge\">\n",
       "<title>a3&#45;&gt;a4</title>\n",
       "<path fill=\"none\" stroke=\"black\" d=\"M27,-143.7C27,-136.41 27,-127.73 27,-119.54\"/>\n",
       "<polygon fill=\"black\" stroke=\"black\" points=\"30.5,-119.62 27,-109.62 23.5,-119.62 30.5,-119.62\"/>\n",
       "</g>\n",
       "<!-- a6 -->\n",
       "<g id=\"node6\" class=\"node\">\n",
       "<title>a6</title>\n",
       "<ellipse fill=\"none\" stroke=\"black\" cx=\"99\" cy=\"-90\" rx=\"27\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"99\" y=\"-84.58\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">cos</text>\n",
       "</g>\n",
       "<!-- a5&#45;&gt;a6 -->\n",
       "<g id=\"edge5\" class=\"edge\">\n",
       "<title>a5&#45;&gt;a6</title>\n",
       "<path fill=\"none\" stroke=\"black\" d=\"M99,-143.7C99,-136.41 99,-127.73 99,-119.54\"/>\n",
       "<polygon fill=\"black\" stroke=\"black\" points=\"102.5,-119.62 99,-109.62 95.5,-119.62 102.5,-119.62\"/>\n",
       "</g>\n",
       "<!-- a8 -->\n",
       "<g id=\"node8\" class=\"node\">\n",
       "<title>a8</title>\n",
       "<ellipse fill=\"none\" stroke=\"black\" cx=\"171\" cy=\"-90\" rx=\"27\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"171\" y=\"-84.58\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">1</text>\n",
       "</g>\n",
       "<!-- a5&#45;&gt;a8 -->\n",
       "<g id=\"edge7\" class=\"edge\">\n",
       "<title>a5&#45;&gt;a8</title>\n",
       "<path fill=\"none\" stroke=\"black\" d=\"M113.92,-146.5C123.77,-136.92 136.86,-124.19 148.03,-113.34\"/>\n",
       "<polygon fill=\"black\" stroke=\"black\" points=\"150.29,-116.02 155.02,-106.54 145.41,-111 150.29,-116.02\"/>\n",
       "</g>\n",
       "<!-- a7 -->\n",
       "<g id=\"node7\" class=\"node\">\n",
       "<title>a7</title>\n",
       "<ellipse fill=\"none\" stroke=\"black\" cx=\"99\" cy=\"-18\" rx=\"27\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"99\" y=\"-12.57\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">x0</text>\n",
       "</g>\n",
       "<!-- a6&#45;&gt;a7 -->\n",
       "<g id=\"edge6\" class=\"edge\">\n",
       "<title>a6&#45;&gt;a7</title>\n",
       "<path fill=\"none\" stroke=\"black\" d=\"M99,-71.7C99,-64.41 99,-55.73 99,-47.54\"/>\n",
       "<polygon fill=\"black\" stroke=\"black\" points=\"102.5,-47.62 99,-37.62 95.5,-47.62 102.5,-47.62\"/>\n",
       "</g>\n",
       "<!-- a10 -->\n",
       "<g id=\"node10\" class=\"node\">\n",
       "<title>a10</title>\n",
       "<ellipse fill=\"none\" stroke=\"black\" cx=\"171\" cy=\"-162\" rx=\"27\" ry=\"18\"/>\n",
       "<text text-anchor=\"middle\" x=\"171\" y=\"-156.57\" font-family=\"Times New Roman,serif\" font-size=\"14.00\">x0</text>\n",
       "</g>\n",
       "<!-- a9&#45;&gt;a10 -->\n",
       "<g id=\"edge9\" class=\"edge\">\n",
       "<title>a9&#45;&gt;a10</title>\n",
       "<path fill=\"none\" stroke=\"black\" d=\"M171,-215.7C171,-208.41 171,-199.73 171,-191.54\"/>\n",
       "<polygon fill=\"black\" stroke=\"black\" points=\"174.5,-191.62 171,-181.62 167.5,-191.62 174.5,-191.62\"/>\n",
       "</g>\n",
       "</g>\n",
       "</svg>\n"
      ],
      "text/plain": [
       "<graphviz.graphs.Digraph at 0x29aff4bfef0>"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from evokit.evolvables.gp_visualiser import p2dot\n",
    "p2dot(bests[-1])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "To visualise the learning process: note that earlier highest-fitness programs (whose plotted colours are lighter) do not approximate the objective function as closely as later ones."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "from typing import Sequence\n",
    "from typing import Tuple\n",
    "from typing import Callable\n",
    "\n",
    "from matplotlib import pyplot as plt\n",
    "from matplotlib.patches import Patch\n",
    "\n",
    "def plot_range(function: Callable[[float], float],\n",
    "               support:Sequence[Tuple[float,]],\n",
    "               color: str,\n",
    "               alpha: float,\n",
    "               linewidth: float):\n",
    "    xs = [t[0] for t in support]\n",
    "    ys = [function(x) for x in xs]\n",
    "    plt.plot(xs, ys, color=color, alpha=alpha, linewidth=linewidth)\n",
    "\n",
    "def alpha_from_index(bests, index):\n",
    "    return index / len(bests) / 2\n",
    "\n",
    "plot_range(weird_function, support, \"red\", 1, 4)\n",
    "\n",
    "for i in range(len(bests)):\n",
    "    plot_range(bests[i].genome, support, \"blue\", alpha_from_index(bests, i), 1)\n",
    "\n",
    "plt.title('Best Individuals over Generations')\n",
    "\n",
    "\n",
    "obj_color = Patch(color='red', label='Objective')\n",
    "bests_color = Patch(color='blue', label='Best Individuals')\n",
    "plt.legend(handles=[obj_color, bests_color])\n",
    "\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The following plot illustrates the learning curve."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot(list(range(len(bests))), [ind.fitness for ind in bests])\n",
    "plt.title('Training Curve of the Custom Algorithm')\n",
    "plt.xlabel('Generation')\n",
    "plt.ylabel('Fitness of Best Individual')\n",
    "plt.show()"
   ]
  }
 ],
 "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": "3.12.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}