Lyapunov-Gate-Hadamard-Genetico-300-Copy2.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "c281fb25-0d6a-4709-8371-84fe30138a59",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Bibliotecas necessárias para o experimento\n",
    "\n",
    "import numpy as np, numpy.random\n",
    "import matplotlib.pyplot as plt\n",
    "from random import randint\n",
    "from mpl_toolkits.axes_grid1.inset_locator import inset_axes\n",
    "\n",
    "from random import randint, uniform, random\n",
    "from scipy.linalg import sqrtm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "831362ff-e7d3-432c-a57b-fa804626496e",
   "metadata": {},
   "outputs": [],
   "source": [
    "## CONSTANTES PARA O ALGORITMO GENÉTICO\n",
    "\n",
    "ELITISMO = True\n",
    "PORCENTAGEM_ELITISMO = 0.20\n",
    "\n",
    "TAMANHO_POP = 50\n",
    "TAXA_MUTACAO = 0.10\n",
    "TAXA_CRUZAMENTO = 0.70\n",
    "GERACOES = 100\n",
    "\n",
    "# Valores mínimos e máximos para gerar uma população\n",
    "MIN = 0\n",
    "MAX = 200\n",
    " # 115, 150"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "7bae10e9-e05a-4d8a-a271-5f11a724e9a2",
   "metadata": {},
   "outputs": [],
   "source": [
    "def S(Ut, Uf, X):\n",
    "    W = np.dot(np.transpose(Uf), Ut)\n",
    "    T = np.transpose(W)\n",
    "    A = np.dot(np.transpose(Ut), np.transpose(X))\n",
    "    C = np.dot(A, Uf)\n",
    "    L = W - np.identity(3) - 1/2*(W - np.identity(3))**2\n",
    "    S = 2*np.trace(np.dot((-np.dot(T, C) + 2*C),L))\n",
    "    #S = 2*np.trace(np.dot((-1/2*np.dot(C, T) - 1/2*np.dot(T, C) + 2*C),L))\n",
    "    return S"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "a74d139d-10c7-4292-91fc-fd488e6c47c9",
   "metadata": {},
   "outputs": [],
   "source": [
    "def field(Ut, Uf, a, h, A, B):\n",
    "    SA = S(Ut, Uf, A)\n",
    "    SB = S(Ut, Uf, B)\n",
    "    f = -a*SA-h*(SB/SA)\n",
    "    return f"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "36393204-3d86-4d66-848d-307116ef1180",
   "metadata": {},
   "outputs": [],
   "source": [
    "def lind(u, Ut, Uf, t, lbda):\n",
    "    n = 0.5005\n",
    "    Ax = [[0, 0, 0],[0, 0, -1], [0, 1, 0]]\n",
    "    Ay = [[0, 0, 1],[0, 0, 0], [-1, 0, 0]]\n",
    "    Az = [[0, -1, 0],[1, 0, 0], [0, 0, 0]]\n",
    "    B = [[(1-n*2)*lbda, 0, 0],[0, (1-n*2)*lbda, 0], [0, 0, (-n*2)*lbda]] # Amplitude Damping\n",
    "    #B = [[-1.01*lbda, 0, 0],[0, -1.01*lbda, 0], [0, 0, -0.01*lbda]] # Phase Damping\n",
    "    if t == 0:\n",
    "        fx = u[0]\n",
    "        fy = u[1]\n",
    "        fz = u[2]\n",
    "        F=np.dot(u[0],Ax)+np.dot(u[1],Ay)+np.dot(u[2],Az)+B\n",
    "    else:\n",
    "        fx=field(Ut, Uf, u[0], 0.35, Ax, B)\n",
    "        fy=field(Ut, Uf, u[1], 0.31, Ay, B)\n",
    "        fz=field(Ut, Uf, u[2], 0.34, Az, B)\n",
    "        P=400\n",
    "\n",
    "        if abs(fx) > P:\n",
    "            if fx < 0:\n",
    "                fx = -P\n",
    "            else:\n",
    "                fx = P\n",
    "        if abs(fy) > P:\n",
    "            if fy < 0:\n",
    "                fy = -P\n",
    "            else:\n",
    "                fy = P\n",
    "        if abs(fz) > P:\n",
    "            if fz < 0:\n",
    "                fz = -P\n",
    "            else:\n",
    "                fz = P\n",
    "\n",
    "        F=np.dot(fx,Ax)+np.dot(fy,Ay)+np.dot(fz,Az)+B\n",
    "        \t\n",
    "    return fx,fy,fz,F"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "ea216581-4d46-45e5-9de9-33fe47444a23",
   "metadata": {},
   "outputs": [],
   "source": [
    "def rungeKutta(u, Ut, Uf, h, t, lbda):\n",
    "\n",
    "    if t == 0:\n",
    "        \n",
    "        fx,fy,fz,k1 = lind(u, Ut, Uf, t, lbda)\n",
    "        k1 = np.dot(k1,Ut)\n",
    "        fx,fy,fz,k2 = lind(u, (Ut+h/2*k1), Uf, t, lbda)\n",
    "        k2 = np.dot(k2,(Ut+h/2*k1))\n",
    "        fx,fy,fz,k3 = lind(u, (Ut+h/2*k2), Uf, t, lbda)\n",
    "        k3 = np.dot(k3,(Ut+h/2*k2))\n",
    "        fx,fy,fz,k4 = lind(u, (Ut+h*k3), Uf, t, lbda)\n",
    "        k4 = np.dot(k4,(Ut+h*k3))\n",
    "        a = fx;\n",
    "        b = fy;\n",
    "        c = fz;\n",
    "\n",
    "    else:\n",
    "\n",
    "        fx,fy,fz,k1 = lind(u, Ut, Uf, t, lbda)\n",
    "        k1 = np.dot(k1,Ut)\n",
    "        fx,fy,fz,k2 = lind(u, (Ut+h/2*k1), Uf, t+h/2, lbda)\n",
    "        k2 = np.dot(k2,(Ut+h/2*k1))\n",
    "        fx,fy,fz,k3 = lind(u, (Ut+h/2*k2), Uf, t+h/2, lbda)\n",
    "        k3 = np.dot(k3,(Ut+h/2*k2))\n",
    "        fx,fy,fz,k4 = lind(u, (Ut+h*k3), Uf, t+h, lbda)\n",
    "        k4 = np.dot(k4,(Ut+h*k3))\n",
    "        a = fx;\n",
    "        b = fy;\n",
    "        c = fz;\n",
    "\n",
    "    \n",
    "    result = Ut+(h/6)*(k1+2*k2+2*k3+k4);\n",
    "    return a,b,c,result"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "aaef928c-c1b8-4841-a1d9-2626a9d13933",
   "metadata": {},
   "outputs": [],
   "source": [
    "def func_objetivo(u, Ut, Uf, h, tempo, lbda):\n",
    "    a, b, c, Ut1 = rungeKutta(u, Ut, Uf, h, tempo, lbda)\n",
    "    return (np.linalg.norm(Ut1-Uf))**2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "14d34807-6f7a-49b9-b471-0a0f315d9bd5",
   "metadata": {},
   "outputs": [],
   "source": [
    "def gerar_populacao():\n",
    "    populacao = np.zeros((TAMANHO_POP,3))\n",
    "    for individuo in range(TAMANHO_POP):\n",
    "        for genes in range(3):\n",
    "            populacao[individuo,genes] = uniform(MIN, MAX)\n",
    "    return populacao"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "1e415da2-51bb-45ab-9c26-cb7c73698aea",
   "metadata": {},
   "outputs": [],
   "source": [
    "def calcular_func(populacao, Ut, Uf, h, tempo, TAMANHO_POP, lbda):\n",
    "    valor_func = np.zeros(TAMANHO_POP)\n",
    "    for individuo in range(TAMANHO_POP):\n",
    "        valor_func[individuo] = func_objetivo(populacao[individuo,:], Ut, Uf, h, tempo, lbda)\n",
    "    return valor_func"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "4fa7e339-64bf-4566-acdd-74b195efb7f5",
   "metadata": {},
   "outputs": [],
   "source": [
    "def selecao(valor_fitness):\n",
    "    pos = np.random.choice(range(TAMANHO_POP), 2, replace=False)\n",
    "    valor = valor_fitness[pos[0]] < valor_fitness[pos[1]]\n",
    "    if valor == True:\n",
    "        return pos[0]\n",
    "    else:\n",
    "        return pos[1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "dc674115-38e7-491f-8622-6dc456dbff3c",
   "metadata": {},
   "outputs": [],
   "source": [
    "def divisao_fitness(valor_funcao_objetivo):\n",
    "    divisao = 0\n",
    "    for i in range(len(valor_funcao_objetivo)):\n",
    "        divisao += valor_funcao_objetivo[i]\n",
    "    return divisao\n",
    "\n",
    "def fitness(valor_funca_objetivo):\n",
    "    return valor_funca_objetivo/divisao_fitness(valor_funca_objetivo)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "407419cf-49a3-4032-b401-8978fdf32118",
   "metadata": {},
   "outputs": [],
   "source": [
    "def cruzamento(pai1, pai2):\n",
    "    x = random()\n",
    "    filho1 = x*pai1+(1-x)*pai2\n",
    "    filho2 = (1-x)*pai1+x*pai2\n",
    "    return filho1, filho2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "edeb49da-4638-4cdf-b609-35302b0306cb",
   "metadata": {},
   "outputs": [],
   "source": [
    "def mutacao(individuo, horizonte):\n",
    "    \n",
    "    # Gaussian function\n",
    "    for i in range (0, horizonte):\n",
    "        if random() < TAXA_MUTACAO:\n",
    "            individuo[i] = (1/np.sqrt(2*np.pi))*np.exp((-1/2*(uniform(MIN, MAX)-2)**2))\n",
    "    \n",
    "    return individuo"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "37f841b8-c606-4378-8812-e5b8e5dffc74",
   "metadata": {},
   "outputs": [],
   "source": [
    "def genetico(Ut, Uf, h, tempo, TAMANHO_POP, lbda):\n",
    "    \n",
    "    horizonte = 3\n",
    "    pop = gerar_populacao()\n",
    "    fo = calcular_func(pop, Ut, Uf, h, tempo, TAMANHO_POP, lbda)\n",
    "    fit = fitness(fo)\n",
    "    fit_edit = fit\n",
    "    min_fit = min(fit)\n",
    "            \n",
    "    melhor_fo = np.zeros(GERACOES)\n",
    "    for geracao in range(GERACOES):\n",
    "        new_pop = np.empty((0, horizonte))\n",
    "        for i in range(round((TAMANHO_POP)/2)):\n",
    "            pai1 = 0\n",
    "            pai2 = 0\n",
    "            while pai1 == pai2:\n",
    "                pai1 = selecao(fit)\n",
    "                pai2 = selecao(fit)\n",
    "            if random() < TAXA_CRUZAMENTO:\n",
    "                filho1, filho2 = cruzamento(pop[pai1, :], pop[pai2, :])\n",
    "                filho1 = mutacao(filho1, horizonte)\n",
    "                filho2 = mutacao(filho2, horizonte)\n",
    "                new_pop = np.vstack([new_pop, filho1, filho2])\n",
    "            else:\n",
    "                pais = np.vstack([mutacao(pop[pai1, :], horizonte), mutacao(pop[pai2, :], horizonte)])\n",
    "                new_pop = np.vstack([new_pop, pais])\n",
    "                \n",
    "        fo = calcular_func(pop, Ut, Uf, h, tempo, TAMANHO_POP, lbda)\n",
    "        fit = fitness(fo)\n",
    "        min_fo = min(fo)\n",
    "        melhor_fo[geracao] = min_fo\n",
    "        pos_min_fo = np.where(fo == min_fo)\n",
    "                \n",
    "    return pop[pos_min_fo,:][0,0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "25912f07-5ea9-471e-83a5-2b92044ec127",
   "metadata": {},
   "outputs": [],
   "source": [
    "def leis_controle(fx, fy, fz, quant_pontos, lbda):\n",
    "    ts = np.linspace(0, 0.1, quant_pontos)\n",
    "\n",
    "    plt.ylabel(\"Valores das leis de controle\") \n",
    "    plt.xlabel('Tempo (u. a.)') \n",
    "    plt.plot(ts, fx, color='g', marker='o', linewidth=1, markersize=1, label=\"$f_x(t)$\")\n",
    "    plt.plot(ts, fy, color='b', marker='_', linewidth=1, markersize=1, label=\"$f_y(t)$\")\n",
    "    plt.plot(ts, fz, color='r', marker='.', linewidth=1, markersize=1, label=\"$f_z(t)$\")\n",
    "    plt.legend(loc=\"upper right\")\n",
    "    plt.title(fr\"Leis de controle para $\\gamma = {lbda}$\")\n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "25a8f695-a131-41ef-b17c-88da84c48ade",
   "metadata": {},
   "outputs": [],
   "source": [
    "def fidelidade(fid, quant_pontos, lbda):\n",
    "    ts = np.linspace(0, 0.1, quant_pontos)\n",
    "\n",
    "    fig, ax = plt.subplots()\n",
    "\n",
    "    ax.set_ylabel(\"Valores de fidelidade\") \n",
    "    ax.set_xlabel('Tempo (u. a.)') \n",
    "    ax.plot(ts, np.abs(fid), color='g', marker='*', linewidth=1, markersize=1, label=fr\"$\\gamma = {lbda}$\")\n",
    "    ax.legend(loc=\"center right\")\n",
    "    ax.set_title(fr\"Fidelidade com $\\gamma = {lbda}$\")\n",
    "\n",
    "    x1, x2, y1, y2 = 2.5, 4, 0, max(np.abs(fid))\n",
    "    axins = inset_axes(ax, width=\"30%\", height=\"30%\", loc='upper center', borderpad=3)\n",
    "    axins.set_xlim(0.009, 0.020)\n",
    "    axins.set_ylim(0.98, 1)\n",
    "\n",
    "    axins.plot(ts, np.abs(fid), color='g', marker='*', linewidth=1, markersize=1, label=fr\"$\\gamma = {lbda}$\")\n",
    "    ax.indicate_inset_zoom(axins)\n",
    "    \n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "fb93a47b-e5ed-4861-9d8c-b571f12c0317",
   "metadata": {},
   "outputs": [],
   "source": [
    "def distance(fid, quant_pontos, lbda):\n",
    "    ts = np.linspace(0, 0.1, quant_pontos)\n",
    "\n",
    "    fig, ax = plt.subplots()\n",
    "\n",
    "    ax.set_ylabel(\"Valores de distância\") \n",
    "    ax.set_xlabel('Tempo (u. a.)') \n",
    "    ax.plot(ts, np.abs(fid), color='g', marker='*', linewidth=1, markersize=1, label=fr\"$\\gamma = {lbda}$\")\n",
    "    ax.legend(loc=\"center right\")\n",
    "    ax.set_title(fr\"Distância entre os operadores de evolução com $\\gamma = {lbda}$\")\n",
    "\n",
    "    #x1, x2, y1, y2 = 2.5, 4, 0, max(np.abs(fid))\n",
    "    #axins = inset_axes(ax, width=\"30%\", height=\"30%\", loc='upper center', borderpad=3)\n",
    "    #axins.set_xlim(0.009, 0.020)\n",
    "    #axins.set_ylim(0.98, 1)\n",
    "\n",
    "    #axins.plot(ts, np.abs(fid), color='g', marker='*', linewidth=1, markersize=1, label=fr\"$\\gamma = {lbda}$\")\n",
    "    #ax.indicate_inset_zoom(axins)\n",
    "    \n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "88260532-c848-4882-87e3-c2924a219ff0",
   "metadata": {},
   "outputs": [],
   "source": [
    "def densidade(rho, quant_pontos, lbda):\n",
    "    ts = np.linspace(0, 0.1, quant_pontos)\n",
    "\n",
    "    fig, ax = plt.subplots()\n",
    "\n",
    "    ax.set_ylabel('Valores da matriz de densidade') \n",
    "    ax.set_xlabel('Tempo (u. a.)') \n",
    "    ax.plot(ts, abs(rho[0]), color='g', marker='o', linewidth=1, markersize=1, label=r\"$\\rho_{00}$\")\n",
    "    ax.plot(ts, abs(rho[1]), color='b', marker='8', linewidth=1, markersize=1, label=r\"$\\rho_{01}$\")\n",
    "    ax.plot(ts, abs(rho[2]), color='r', marker='.', linewidth=1, markersize=1, label=r\"$\\rho_{10}$\")\n",
    "    ax.plot(ts, abs(rho[3]), color='y', marker='*', linewidth=1, markersize=1, label=r\"$\\rho_{11}$\")\n",
    "    ax.legend(loc=\"center right\")\n",
    "    ax.set_title(fr\"Evolução da matriz de densidade $\\gamma = {lbda}$\")\n",
    "\n",
    "    x1, x2, y1, y2 = 2.5, 4, 0, max(max(abs(rho[0])), max(abs(rho[1])), max(abs(rho[2])), max(abs(rho[3])))\n",
    "    axins = inset_axes(ax, width=\"30%\", height=\"30%\", loc='upper center', borderpad=3)\n",
    "    axins.set_xlim(0.009, 0.020)\n",
    "    axins.set_ylim(0.98, 1)\n",
    "\n",
    "    axins.plot(ts, abs(rho[0]), color='g', marker='o', linewidth=1, markersize=1, label=r\"$\\rho_{00}$\")\n",
    "    axins.plot(ts, abs(rho[1]), color='b', marker='8', linewidth=1, markersize=1, label=r\"$\\rho_{01}$\")\n",
    "    axins.plot(ts, abs(rho[2]), color='r', marker='.', linewidth=1, markersize=1, label=r\"$\\rho_{10}$\")\n",
    "    axins.plot(ts, abs(rho[3]), color='y', marker='*', linewidth=1, markersize=1, label=r\"$\\rho_{11}$\")\n",
    "\n",
    "    ax.indicate_inset_zoom(axins)\n",
    "    \n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "29ff5391-7eea-4c95-936e-2a4220591a25",
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "def main():\n",
    "    u = [70, 106, 66, 0.35, 0.31, 0.34] # Hadamard\n",
    "    \n",
    "    Ut = [[1, 0, 0], [0, 1, 0], [0, 0, 1]]\n",
    "    Uf = [[0, 0, 1], [0, -1, 0], [1, 0, 0]] # Hadamard\n",
    "    \n",
    "    r0 = [[1], [0], [0]]\n",
    "    rf = np.dot(Uf, r0)\n",
    "    pf = [[1/2*(1+rf[2][0]), 1/2*(rf[0][0]-1j*rf[1][0])], [1/2*(rf[0][0]+1j*rf[1][0]), 1/2*(1-rf[2][0])]]\n",
    "    \n",
    "    h=0.001\n",
    "    t=0\n",
    "    i=0\n",
    "    lbda=0.01\n",
    "    # Proposta do algoritmo genético\n",
    "    resultado_algoritmo_genetico = genetico(Ut, Uf, h, t, TAMANHO_POP, lbda) \n",
    "    u[0] = resultado_algoritmo_genetico[0]\n",
    "    u[1] = resultado_algoritmo_genetico[1]\n",
    "    u[2] = resultado_algoritmo_genetico[2]\n",
    "    distance_vector = []\n",
    "    fx_vector = []\n",
    "    fy_vector = []\n",
    "    fz_vector = []\n",
    "    rho_vector = np.zeros((4,100),dtype=np.complex128)\n",
    "    fid_vector = []\n",
    "    fid_autores = []\n",
    "       \n",
    "    while t < 100:\n",
    "        a,b,c,Ut = rungeKutta(u, Ut, Uf, h, t, lbda)\n",
    "        D = np.linalg.norm(Ut-Uf)**2\n",
    "        distance_vector.append(D)\n",
    "        fx_vector.append(a)\n",
    "        fy_vector.append(b)\n",
    "        fz_vector.append(c)\n",
    "        rt = np.dot(Ut, r0)\n",
    "        pt = [[1/2*(1+rt[2][0]), 1/2*(rt[0][0]-1j*rt[1][0])], [1/2*(rt[0][0]+1j*rt[1][0]), 1/2*(1-rt[2][0])]]\n",
    "        rho_vector[0][t] = pt[0][0]\n",
    "        rho_vector[1][t] = pt[0][1]\n",
    "        rho_vector[2][t] = pt[1][0]\n",
    "        rho_vector[3][t] = pt[1][1]\n",
    "        fid_vector.append((np.trace(sqrtm(sqrtm(pt) @ pf @ sqrtm(pt))))**2)\n",
    "        fid_autores.append((np.trace(np.dot(Ut, np.transpose(Ut)))+np.abs(np.trace(np.dot(np.transpose(Uf), Ut)))**2)/(3*(3+1)))\n",
    "        if t%5 == 0:\n",
    "            resultado_algoritmo_genetico = genetico(Ut, Uf, h, t, TAMANHO_POP, lbda) \n",
    "            u[0] = resultado_algoritmo_genetico[0]\n",
    "            u[1] = resultado_algoritmo_genetico[1]\n",
    "            u[2] = resultado_algoritmo_genetico[2]\n",
    "        t += 1\n",
    "    \n",
    "    rt = np.dot(Ut, r0)\n",
    "    pt = [[1/2*(1+rt[2][0]), 1/2*(rt[0][0]-1j*rt[1][0])], [1/2*(rt[0][0]+1j*rt[1][0]), 1/2*(1-rt[2][0])]]\n",
    "    \n",
    "    #leis_controle(fx_vector,fy_vector,fz_vector,t,lbda)\n",
    "    #densidade(rho_vector,t,lbda)\n",
    "    #fidelidade(fid_vector,t,lbda)\n",
    "    #fidelidade(fid_autores,t,lbda)\n",
    "    #distance(distance_vector,t,lbda)\n",
    "\n",
    "    return fid_vector, fid_autores, rho_vector, distance_vector, fx_vector, fy_vector, fz_vector"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "e1f25c52-1dd2-4e99-ba59-fda1c3a9c6dc",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Valores de média na iteração 1:\n",
      "Portas: 0.9949606854145856\n",
      "Estados: (0.9972122787946502+1.4907148124776498e-06j)\n",
      "Distância: 4.5240917922008894e-06\n",
      " \n"
     ]
    }
   ],
   "source": [
    "portas = []\n",
    "estados = []\n",
    "distancia = []\n",
    "\n",
    "i = 1\n",
    "\n",
    "fid_vector, fid_autores, rho_vector, distance_vector, fx_vector, fy_vector, fz_vector = main()\n",
    "portas.append(sum(fid_autores[30:])/(len(fid_autores)-30))\n",
    "estados.append(sum(fid_vector[30:])/(len(fid_vector)-30))\n",
    "distancia.append(sum(distance_vector[80:])/(len(distance_vector)-80))\n",
    "\n",
    "print(f\"Valores de média na iteração {i}:\")\n",
    "print(f\"Portas: {sum(portas)/i}\")\n",
    "print(f\"Estados: {sum(estados)/i}\")\n",
    "print(f\"Distância: {sum(distancia)/i}\")\n",
    "print(\" \")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "a2e4867e-f0db-4c5d-bc85-03807db5200d",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[np.clongdouble('0.4999997320317598591+0.00014517197448408618795j'),\n",
       " np.clongdouble('0.5001190999201595948-4.0260017742708211163e-07j'),\n",
       " np.clongdouble('0.5000857432056138124+8.763863654955455259e-05j'),\n",
       " np.clongdouble('0.50008383217180229737+8.4891670281728483904e-05j'),\n",
       " np.clongdouble('0.49999908674427321733+3.6894089185532437537e-05j'),\n",
       " np.clongdouble('0.49999865023420276538+1.39892158656764052185e-08j'),\n",
       " np.clongdouble('0.54332906018229900475+0.00020881772443966529035j'),\n",
       " np.clongdouble('0.579765554978241755+1.1606383452664245595e-12j'),\n",
       " np.clongdouble('0.5985772982903308194+0.00016705044034166073549j'),\n",
       " np.clongdouble('0.6057873817264713345-5.6737800528292128672e-13j'),\n",
       " np.clongdouble('0.6081971335731833549-0.0002504657266602158866j'),\n",
       " np.clongdouble('0.78930410622329586623+0.00020490610423526982087j'),\n",
       " np.clongdouble('0.90357102663114172527+0.00014031726687206055425j'),\n",
       " np.clongdouble('0.95162024108094945326+1.9681670353215245494e-14j'),\n",
       " np.clongdouble('0.9741550588339557506+8.465923763656400537e-05j'),\n",
       " np.clongdouble('0.98574178722750277834-1.2074450695446035212e-06j'),\n",
       " np.clongdouble('0.9856541426618220632+8.540975776724810968e-05j'),\n",
       " np.clongdouble('0.98573771945453886827+1.9239548466232848995e-05j'),\n",
       " np.clongdouble('0.9857052796842209653+5.930931636928640634e-05j'),\n",
       " np.clongdouble('0.98568281280270934555-4.130832810387588604e-05j'),\n",
       " np.clongdouble('0.9857599109132689534-1.4131420627799862793e-05j'),\n",
       " np.clongdouble('0.9856340260227738164+8.41543959812010343e-05j'),\n",
       " np.clongdouble('0.9856695906491178882+4.5108998393737799273e-05j'),\n",
       " np.clongdouble('0.98562449164733862854+0.00010357383610842688927j'),\n",
       " np.clongdouble('0.985707836244142226-1.8313669340636929065e-05j'),\n",
       " np.clongdouble('0.9857243723513360797-3.213240631125633329e-05j'),\n",
       " np.clongdouble('0.98567760788964149427+2.6506956583648588036e-05j'),\n",
       " np.clongdouble('0.98563846079363159934+6.628027163065288763e-05j'),\n",
       " np.clongdouble('0.9857307099800636819-1.40130565955649424546e-05j'),\n",
       " np.clongdouble('0.98560724577689140237-0.00010562200585889141184j'),\n",
       " np.clongdouble('0.98564939610571592057+7.646914457487770901e-05j'),\n",
       " np.clongdouble('0.9866257707143422678+2.6457149731628573205e-06j'),\n",
       " np.clongdouble('0.9868388985447139056+2.99787719036662895e-06j'),\n",
       " np.clongdouble('0.98691577771459847016+1.8215976472137786178e-05j'),\n",
       " np.clongdouble('0.9868549125789234298-8.7937136141938721296e-05j'),\n",
       " np.clongdouble('0.986920255666384068-1.8620175902572482138e-05j'),\n",
       " np.clongdouble('0.98687606539194651+2.2804983279787240904e-15j'),\n",
       " np.clongdouble('0.9869490374584996656+7.279524165850477287e-16j'),\n",
       " np.clongdouble('0.98687944692872733144+1.9601130847300827556e-05j'),\n",
       " np.clongdouble('0.9869724506371480356+4.4361483733753244938e-05j'),\n",
       " np.clongdouble('0.98697410324777162257+5.3855883679864743915e-19j'),\n",
       " np.clongdouble('0.991262764013978169+4.2794021423519754893e-05j'),\n",
       " np.clongdouble('0.99408708701027202265+3.5575496097460879682e-16j'),\n",
       " np.clongdouble('0.995929331859474117+3.297983865716760229e-05j'),\n",
       " np.clongdouble('0.9971572948701703414-3.368354645948267031e-05j'),\n",
       " np.clongdouble('0.998008472052228239-9.351525630440139798e-06j'),\n",
       " np.clongdouble('0.9992695741809489635+1.0784644581763199509e-05j'),\n",
       " np.clongdouble('0.9995700568439946397+5.2077128389086702437e-19j'),\n",
       " np.clongdouble('0.99962785072249331114+2.4427792069491874898e-06j'),\n",
       " np.clongdouble('0.9996409137187888337-5.6660904774022992e-07j'),\n",
       " np.clongdouble('0.9996396827588337562-2.1168170409160828637e-07j'),\n",
       " np.clongdouble('0.9996340822648883884+5.7093720660243321433e-07j'),\n",
       " np.clongdouble('0.9996280567913216782-1.7123823032819331215e-06j'),\n",
       " np.clongdouble('0.9996243166203740768+2.9703407760300022804e-21j'),\n",
       " np.clongdouble('0.99961887896428077213-9.568983222380366751e-07j'),\n",
       " np.clongdouble('0.99961432429126069026-2.709071204161235191e-07j'),\n",
       " np.clongdouble('0.99960902980666884013+5.707072538171151023e-07j'),\n",
       " np.clongdouble('0.999603005026227566-9.5348452733234017825e-07j'),\n",
       " np.clongdouble('0.99959890506490130854+1.4581251658069775813e-07j'),\n",
       " np.clongdouble('0.99959463781180939336-1.4258098664626589186e-07j'),\n",
       " np.clongdouble('0.99958835018068218313-7.172238286411424136e-07j'),\n",
       " np.clongdouble('0.99958394152858418805+3.8121953369688078166e-07j'),\n",
       " np.clongdouble('0.9995793065256646735-2.7025278602381634593e-07j'),\n",
       " np.clongdouble('0.9995733088088895149-1.4573027993302549906e-06j'),\n",
       " np.clongdouble('0.99956941667018885583-2.5520337127020183346e-07j'),\n",
       " np.clongdouble('0.99956395137460748583+3.807640489497044972e-07j'),\n",
       " np.clongdouble('0.999559325337443543+4.196694331362810338e-07j'),\n",
       " np.clongdouble('0.9995539597683116218+1.1574801164056382868e-06j'),\n",
       " np.clongdouble('0.99954960909657679434+7.2774489579652449915e-07j'),\n",
       " np.clongdouble('0.9995444964391328227+9.694499287180781738e-07j'),\n",
       " np.clongdouble('0.9995392681906236891+6.5237662948054875105e-07j'),\n",
       " np.clongdouble('0.9995352260663399283-2.6502230665484370228e-24j'),\n",
       " np.clongdouble('0.9995292472960320063+6.530016890142835408e-07j'),\n",
       " np.clongdouble('0.99952441964593240117+7.574613492645783524e-08j'),\n",
       " np.clongdouble('0.9995192858102077999-1.6516047715309819005e-07j'),\n",
       " np.clongdouble('0.999514603990552673-7.3198278964542270685e-07j'),\n",
       " np.clongdouble('0.99950926377645543403+9.534399781141922937e-07j'),\n",
       " np.clongdouble('0.9995044287321064544+7.309111605401019653e-08j'),\n",
       " np.clongdouble('0.9994993994746378121+1.32315766897665432775e-23j'),\n",
       " np.clongdouble('0.9994944443717862514+8.269714932122086558e-25j'),\n",
       " np.clongdouble('0.99949002966516759975-3.209813440779370884e-07j'),\n",
       " np.clongdouble('0.99948501843859716186+3.2070470555105588214e-07j'),\n",
       " np.clongdouble('0.9994802062706679021+4.2186099946760510022e-22j'),\n",
       " np.clongdouble('0.9994742546301703102+6.561850071356907288e-07j'),\n",
       " np.clongdouble('0.99946956318201146707-7.463295204300324795e-07j'),\n",
       " np.clongdouble('0.9994645264795953106+9.811493365788172627e-07j'),\n",
       " np.clongdouble('0.99945997168011580116+1.2711754636526318267e-07j'),\n",
       " np.clongdouble('0.99945477489291130934+2.3835354140827852995e-07j'),\n",
       " np.clongdouble('0.9994505065575320226+6.8599288403603355953e-08j'),\n",
       " np.clongdouble('0.9994450346955217154+5.5445999771524678968e-08j'),\n",
       " np.clongdouble('0.9994401376580949609-3.8760836447457983605e-08j'),\n",
       " np.clongdouble('0.9994351014317690934-2.6645164537219326252e-08j'),\n",
       " np.clongdouble('0.99943011326728625065+1.9739253998601981288e-08j'),\n",
       " np.clongdouble('0.99942512097819931924-1.4853106762984982044e-24j'),\n",
       " np.clongdouble('0.9994201308366773819-2.5363992835448423347e-08j'),\n",
       " np.clongdouble('0.99941512227431886873+2.8834754420608314443e-08j'),\n",
       " np.clongdouble('0.99941006728784646904-2.8664920017096179017e-08j'),\n",
       " np.clongdouble('0.9994050374425606491+1.2943756269094192848e-25j'),\n",
       " np.clongdouble('0.99940009008013898747-7.628257934132352646e-09j'),\n",
       " np.clongdouble('0.9993950751298888082+2.8283528668949470454e-08j')]"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fid_vector"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "696ff0a1-9182-4908-b1e4-c02657b8681b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[np.float64(0.33177345340558295),\n",
       " np.float64(0.3235546364837192),\n",
       " np.float64(0.2958736006132631),\n",
       " np.float64(0.26483660066327314),\n",
       " np.float64(0.24994170522878176),\n",
       " np.float64(0.26021012029731777),\n",
       " np.float64(0.3051439283132864),\n",
       " np.float64(0.3662061401449652),\n",
       " np.float64(0.40348680412465615),\n",
       " np.float64(0.4163911981323247),\n",
       " np.float64(0.4206782692314153),\n",
       " np.float64(0.6367288773811254),\n",
       " np.float64(0.8174089183367402),\n",
       " np.float64(0.9036785545586213),\n",
       " np.float64(0.9463491001427973),\n",
       " np.float64(0.9684915213609858),\n",
       " np.float64(0.9684877179394813),\n",
       " np.float64(0.9684839143442391),\n",
       " np.float64(0.9684801105752939),\n",
       " np.float64(0.9684763066326809),\n",
       " np.float64(0.9684725025164344),\n",
       " np.float64(0.9711495254173848),\n",
       " np.float64(0.9717268253616466),\n",
       " np.float64(0.9718477290449665),\n",
       " np.float64(0.9718691058446344),\n",
       " np.float64(0.9718687760149171),\n",
       " np.float64(0.9718679668480142),\n",
       " np.float64(0.971867145584883),\n",
       " np.float64(0.9718663122613503),\n",
       " np.float64(0.9718654669135788),\n",
       " np.float64(0.9718646095781027),\n",
       " np.float64(0.9737528469335404),\n",
       " np.float64(0.9741771142500216),\n",
       " np.float64(0.9742688435418643),\n",
       " np.float64(0.9742848236679111),\n",
       " np.float64(0.9742835375188093),\n",
       " np.float64(0.9743173854845106),\n",
       " np.float64(0.9743511674381978),\n",
       " np.float64(0.9743848834931982),\n",
       " np.float64(0.9744185337626187),\n",
       " np.float64(0.9744521183593488),\n",
       " np.float64(0.9829552421663813),\n",
       " np.float64(0.9885624012362628),\n",
       " np.float64(0.9922782274136508),\n",
       " np.float64(0.9947484862845024),\n",
       " np.float64(0.9963937911707119),\n",
       " np.float64(0.9989862976061671),\n",
       " np.float64(0.9995805222078945),\n",
       " np.float64(0.9997131864889651),\n",
       " np.float64(0.9997388431187738),\n",
       " np.float64(0.999739669870442),\n",
       " np.float64(0.9997413573291846),\n",
       " np.float64(0.9997389200652956),\n",
       " np.float64(0.9997343920973055),\n",
       " np.float64(0.9997288044315643),\n",
       " np.float64(0.9997226796749589),\n",
       " np.float64(0.9997164282861863),\n",
       " np.float64(0.9997098604441325),\n",
       " np.float64(0.9997032116806673),\n",
       " np.float64(0.9996965422949012),\n",
       " np.float64(0.9996898685035215),\n",
       " np.float64(0.9996831958562455),\n",
       " np.float64(0.9996765237255678),\n",
       " np.float64(0.9996698508911367),\n",
       " np.float64(0.9996631808787407),\n",
       " np.float64(0.9996565083145811),\n",
       " np.float64(0.9996513819622083),\n",
       " np.float64(0.9996452654685148),\n",
       " np.float64(0.9996387918673647),\n",
       " np.float64(0.9996322245584709),\n",
       " np.float64(0.9996255757999105),\n",
       " np.float64(0.9996189129906089),\n",
       " np.float64(0.9996122490769763),\n",
       " np.float64(0.9996055841869086),\n",
       " np.float64(0.9995989184350765),\n",
       " np.float64(0.9995922519242922),\n",
       " np.float64(0.999585580039858),\n",
       " np.float64(0.9995789083047235),\n",
       " np.float64(0.9995722367187944),\n",
       " np.float64(0.9995655654926073),\n",
       " np.float64(0.9995588955413469),\n",
       " np.float64(0.9995522553423122),\n",
       " np.float64(0.9995455925279529),\n",
       " np.float64(0.9995389222024107),\n",
       " np.float64(0.9995322671563195),\n",
       " np.float64(0.9995255998533604),\n",
       " np.float64(0.9995201833338375),\n",
       " np.float64(0.99951404932446),\n",
       " np.float64(0.9995076090826478),\n",
       " np.float64(0.9995010367912109),\n",
       " np.float64(0.999494407601265),\n",
       " np.float64(0.9994877383255059),\n",
       " np.float64(0.999481069902655),\n",
       " np.float64(0.9994744004101158),\n",
       " np.float64(0.9994677347828356),\n",
       " np.float64(0.9994610677308268),\n",
       " np.float64(0.9994544141232785),\n",
       " np.float64(0.9994478058009566),\n",
       " np.float64(0.999441142913267),\n",
       " np.float64(0.9994344833822529)]"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fid_autores"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "b0fae0be-351c-49ad-95bf-100cb5157776",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[ 5.00000000e-01+0.00000000e+00j,  4.99974997e-01+0.00000000e+00j,\n",
       "         4.99998254e-01+0.00000000e+00j,  4.99999025e-01+0.00000000e+00j,\n",
       "         4.99998874e-01+0.00000000e+00j,  4.99998611e-01+0.00000000e+00j,\n",
       "         5.43252420e-01+0.00000000e+00j,  5.79602265e-01+0.00000000e+00j,\n",
       "         5.98577624e-01+0.00000000e+00j,  6.05462326e-01+0.00000000e+00j,\n",
       "         6.08152689e-01+0.00000000e+00j,  7.89304452e-01+0.00000000e+00j,\n",
       "         9.03460206e-01+0.00000000e+00j,  9.51516290e-01+0.00000000e+00j,\n",
       "         9.74155611e-01+0.00000000e+00j,  9.85656722e-01+0.00000000e+00j,\n",
       "         9.85653195e-01+0.00000000e+00j,  9.85649668e-01+0.00000000e+00j,\n",
       "         9.85646141e-01+0.00000000e+00j,  9.85642614e-01+0.00000000e+00j,\n",
       "         9.85639087e-01+0.00000000e+00j,  9.85634267e-01+0.00000000e+00j,\n",
       "         9.85629449e-01+0.00000000e+00j,  9.85624631e-01+0.00000000e+00j,\n",
       "         9.85619814e-01+0.00000000e+00j,  9.85614996e-01+0.00000000e+00j,\n",
       "         9.85612979e-01+0.00000000e+00j,  9.85610955e-01+0.00000000e+00j,\n",
       "         9.85608925e-01+0.00000000e+00j,  9.85606890e-01+0.00000000e+00j,\n",
       "         9.85604848e-01+0.00000000e+00j,  9.86562107e-01+0.00000000e+00j,\n",
       "         9.86779132e-01+0.00000000e+00j,  9.86826428e-01+0.00000000e+00j,\n",
       "         9.86834229e-01+0.00000000e+00j,  9.86832630e-01+0.00000000e+00j,\n",
       "         9.86848249e-01+0.00000000e+00j,  9.86863834e-01+0.00000000e+00j,\n",
       "         9.86879385e-01+0.00000000e+00j,  9.86894902e-01+0.00000000e+00j,\n",
       "         9.86910386e-01+0.00000000e+00j,  9.91220354e-01+0.00000000e+00j,\n",
       "         9.94048203e-01+0.00000000e+00j,  9.95915720e-01+0.00000000e+00j,\n",
       "         9.97154086e-01+0.00000000e+00j,  9.97977195e-01+0.00000000e+00j,\n",
       "         9.99268908e-01+0.00000000e+00j,  9.99563388e-01+0.00000000e+00j,\n",
       "         9.99627814e-01+0.00000000e+00j,  9.99638921e-01+0.00000000e+00j,\n",
       "         9.99637658e-01+0.00000000e+00j,  9.99632658e-01+0.00000000e+00j,\n",
       "         9.99627657e-01+0.00000000e+00j,  9.99622657e-01+0.00000000e+00j,\n",
       "         9.99617658e-01+0.00000000e+00j,  9.99612658e-01+0.00000000e+00j,\n",
       "         9.99607658e-01+0.00000000e+00j,  9.99602658e-01+0.00000000e+00j,\n",
       "         9.99597658e-01+0.00000000e+00j,  9.99592659e-01+0.00000000e+00j,\n",
       "         9.99587659e-01+0.00000000e+00j,  9.99582661e-01+0.00000000e+00j,\n",
       "         9.99577662e-01+0.00000000e+00j,  9.99572664e-01+0.00000000e+00j,\n",
       "         9.99567665e-01+0.00000000e+00j,  9.99562667e-01+0.00000000e+00j,\n",
       "         9.99558452e-01+0.00000000e+00j,  9.99553739e-01+0.00000000e+00j,\n",
       "         9.99548844e-01+0.00000000e+00j,  9.99543883e-01+0.00000000e+00j,\n",
       "         9.99538898e-01+0.00000000e+00j,  9.99533900e-01+0.00000000e+00j,\n",
       "         9.99528901e-01+0.00000000e+00j,  9.99523902e-01+0.00000000e+00j,\n",
       "         9.99518904e-01+0.00000000e+00j,  9.99513906e-01+0.00000000e+00j,\n",
       "         9.99508908e-01+0.00000000e+00j,  9.99503910e-01+0.00000000e+00j,\n",
       "         9.99498912e-01+0.00000000e+00j,  9.99493915e-01+0.00000000e+00j,\n",
       "         9.99488916e-01+0.00000000e+00j,  9.99483918e-01+0.00000000e+00j,\n",
       "         9.99478920e-01+0.00000000e+00j,  9.99473922e-01+0.00000000e+00j,\n",
       "         9.99468924e-01+0.00000000e+00j,  9.99463926e-01+0.00000000e+00j,\n",
       "         9.99459556e-01+0.00000000e+00j,  9.99454828e-01+0.00000000e+00j,\n",
       "         9.99449946e-01+0.00000000e+00j,  9.99444998e-01+0.00000000e+00j,\n",
       "         9.99440021e-01+0.00000000e+00j,  9.99435023e-01+0.00000000e+00j,\n",
       "         9.99430027e-01+0.00000000e+00j,  9.99425029e-01+0.00000000e+00j,\n",
       "         9.99420033e-01+0.00000000e+00j,  9.99415036e-01+0.00000000e+00j,\n",
       "         9.99410047e-01+0.00000000e+00j,  9.99405052e-01+0.00000000e+00j,\n",
       "         9.99400057e-01+0.00000000e+00j,  9.99395062e-01+0.00000000e+00j],\n",
       "       [ 4.99999995e-01+0.00000000e+00j,  4.88971145e-01-1.03322994e-01j,\n",
       "         4.13817271e-01-2.80218481e-01j,  2.72054897e-01-4.19212755e-01j,\n",
       "         8.73671964e-02-4.92042930e-01j, -1.11097701e-01-4.87219298e-01j,\n",
       "        -1.02328875e-01-4.87219322e-01j, -7.74893830e-02-4.87219297e-01j,\n",
       "        -5.12883118e-02-4.87219200e-01j, -3.50581370e-02-4.87219036e-01j,\n",
       "        -2.56024622e-02-4.87218785e-01j, -2.56054997e-02-4.06653626e-01j,\n",
       "        -2.56058700e-02-2.93765565e-01j, -2.56054956e-02-2.12717263e-01j,\n",
       "        -2.56050804e-02-1.55879141e-01j, -2.56047614e-02-1.15145424e-01j,\n",
       "        -2.56044952e-02-1.15139853e-01j, -2.56042289e-02-1.15134282e-01j,\n",
       "        -2.56039625e-02-1.15128711e-01j, -2.56036961e-02-1.15123140e-01j,\n",
       "        -2.56034296e-02-1.15117570e-01j, -3.07136769e-02-1.13864643e-01j,\n",
       "        -3.30729592e-02-1.13202579e-01j, -3.41698539e-02-1.12876334e-01j,\n",
       "        -3.46815098e-02-1.12720031e-01j, -3.49210178e-02-1.12645880e-01j,\n",
       "        -3.48845719e-02-1.12644914e-01j, -3.48482227e-02-1.12643933e-01j,\n",
       "        -3.48119733e-02-1.12642934e-01j, -3.47758266e-02-1.12641919e-01j,\n",
       "        -3.47397860e-02-1.12640884e-01j, -1.67603949e-02-1.12642837e-01j,\n",
       "        -8.19195351e-03-1.12642894e-01j, -4.10159725e-03-1.12642850e-01j,\n",
       "        -2.14723369e-03-1.12642779e-01j, -1.21090880e-03-1.12642697e-01j,\n",
       "        -1.19925673e-03-1.12554219e-01j, -1.18747143e-03-1.12465815e-01j,\n",
       "        -1.17554737e-03-1.12377485e-01j, -1.16347865e-03-1.12289229e-01j,\n",
       "        -1.15125895e-03-1.12201046e-01j, -1.14134097e-03-9.14812371e-02j,\n",
       "        -1.13492635e-03-7.46854224e-02j, -1.13070750e-03-6.10272343e-02j,\n",
       "        -1.12788142e-03-4.98965114e-02j, -1.12594688e-03-4.08122605e-02j,\n",
       "        -1.12501160e-03-1.96368665e-02j, -1.12461210e-03-9.45722399e-03j,\n",
       "        -1.12432987e-03-4.55546720e-03j, -1.12407281e-03-2.19420948e-03j,\n",
       "        -1.12381952e-03-1.05658386e-03j, -1.12179050e-03-1.05816551e-03j,\n",
       "        -1.12026698e-03-1.05919864e-03j, -1.11910312e-03-1.05984106e-03j,\n",
       "        -1.11819465e-03-1.06020466e-03j, -1.11746707e-03-1.06036891e-03j,\n",
       "        -1.11663472e-03-1.06063510e-03j, -1.11607319e-03-1.06060781e-03j,\n",
       "        -1.11564534e-03-1.06043176e-03j, -1.11527881e-03-1.06018315e-03j,\n",
       "        -1.11492330e-03-1.05991494e-03j, -1.11428438e-03-1.05953915e-03j,\n",
       "        -1.11364706e-03-1.05915381e-03j, -1.11291065e-03-1.05886471e-03j,\n",
       "        -1.11235664e-03-1.05837601e-03j, -1.11165854e-03-1.05803081e-03j,\n",
       "        -6.72702577e-04-1.05768030e-03j, -4.08825477e-04-1.05732240e-03j,\n",
       "        -2.49943977e-04-1.05695912e-03j, -1.53431131e-04-1.05668394e-03j,\n",
       "        -9.46868504e-05-1.05630277e-03j, -9.01890864e-05-1.05591519e-03j,\n",
       "        -8.53542998e-05-1.05552355e-03j, -8.01095647e-05-1.05512782e-03j,\n",
       "        -7.43495302e-05-1.05472801e-03j, -6.79116320e-05-1.05432411e-03j,\n",
       "        -6.05007160e-05-1.05374606e-03j, -5.15866191e-05-1.05316375e-03j,\n",
       "        -3.96908244e-05-1.05257719e-03j,  2.22824981e-06-1.05198642e-03j,\n",
       "        -5.12821093e-05-1.05139136e-03j, -3.89628247e-05-1.05095602e-03j,\n",
       "        -5.48084996e-05-1.05052063e-03j, -4.35347981e-05-1.05008141e-03j,\n",
       "        -2.28613288e-05-1.04964228e-03j, -3.42711914e-05-1.04919490e-03j,\n",
       "         4.57957410e-05-6.89731137e-04j,  3.82154032e-05-4.53372516e-04j,\n",
       "         2.92169084e-05-2.97734751e-04j,  1.75860148e-05-1.94903230e-04j,\n",
       "        -3.64452218e-06-1.26406374e-04j, -1.37590041e-06-1.22352980e-04j,\n",
       "         1.27582486e-05-1.18118839e-04j, -1.63309172e-05-1.13683878e-04j,\n",
       "         7.79455671e-06-1.09023825e-04j, -2.66169088e-06-1.04105234e-04j,\n",
       "        -1.97848010e-06-5.31562624e-05j,  2.66886331e-07-1.57489819e-05j,\n",
       "         1.00069689e-05-1.89055618e-05j, -1.13662243e-05-3.56554210e-05j],\n",
       "       [ 4.99999995e-01+0.00000000e+00j,  4.88971145e-01+1.03322994e-01j,\n",
       "         4.13817271e-01+2.80218481e-01j,  2.72054897e-01+4.19212755e-01j,\n",
       "         8.73671964e-02+4.92042930e-01j, -1.11097701e-01+4.87219298e-01j,\n",
       "        -1.02328875e-01+4.87219322e-01j, -7.74893830e-02+4.87219297e-01j,\n",
       "        -5.12883118e-02+4.87219200e-01j, -3.50581370e-02+4.87219036e-01j,\n",
       "        -2.56024622e-02+4.87218785e-01j, -2.56054997e-02+4.06653626e-01j,\n",
       "        -2.56058700e-02+2.93765565e-01j, -2.56054956e-02+2.12717263e-01j,\n",
       "        -2.56050804e-02+1.55879141e-01j, -2.56047614e-02+1.15145424e-01j,\n",
       "        -2.56044952e-02+1.15139853e-01j, -2.56042289e-02+1.15134282e-01j,\n",
       "        -2.56039625e-02+1.15128711e-01j, -2.56036961e-02+1.15123140e-01j,\n",
       "        -2.56034296e-02+1.15117570e-01j, -3.07136769e-02+1.13864643e-01j,\n",
       "        -3.30729592e-02+1.13202579e-01j, -3.41698539e-02+1.12876334e-01j,\n",
       "        -3.46815098e-02+1.12720031e-01j, -3.49210178e-02+1.12645880e-01j,\n",
       "        -3.48845719e-02+1.12644914e-01j, -3.48482227e-02+1.12643933e-01j,\n",
       "        -3.48119733e-02+1.12642934e-01j, -3.47758266e-02+1.12641919e-01j,\n",
       "        -3.47397860e-02+1.12640884e-01j, -1.67603949e-02+1.12642837e-01j,\n",
       "        -8.19195351e-03+1.12642894e-01j, -4.10159725e-03+1.12642850e-01j,\n",
       "        -2.14723369e-03+1.12642779e-01j, -1.21090880e-03+1.12642697e-01j,\n",
       "        -1.19925673e-03+1.12554219e-01j, -1.18747143e-03+1.12465815e-01j,\n",
       "        -1.17554737e-03+1.12377485e-01j, -1.16347865e-03+1.12289229e-01j,\n",
       "        -1.15125895e-03+1.12201046e-01j, -1.14134097e-03+9.14812371e-02j,\n",
       "        -1.13492635e-03+7.46854224e-02j, -1.13070750e-03+6.10272343e-02j,\n",
       "        -1.12788142e-03+4.98965114e-02j, -1.12594688e-03+4.08122605e-02j,\n",
       "        -1.12501160e-03+1.96368665e-02j, -1.12461210e-03+9.45722399e-03j,\n",
       "        -1.12432987e-03+4.55546720e-03j, -1.12407281e-03+2.19420948e-03j,\n",
       "        -1.12381952e-03+1.05658386e-03j, -1.12179050e-03+1.05816551e-03j,\n",
       "        -1.12026698e-03+1.05919864e-03j, -1.11910312e-03+1.05984106e-03j,\n",
       "        -1.11819465e-03+1.06020466e-03j, -1.11746707e-03+1.06036891e-03j,\n",
       "        -1.11663472e-03+1.06063510e-03j, -1.11607319e-03+1.06060781e-03j,\n",
       "        -1.11564534e-03+1.06043176e-03j, -1.11527881e-03+1.06018315e-03j,\n",
       "        -1.11492330e-03+1.05991494e-03j, -1.11428438e-03+1.05953915e-03j,\n",
       "        -1.11364706e-03+1.05915381e-03j, -1.11291065e-03+1.05886471e-03j,\n",
       "        -1.11235664e-03+1.05837601e-03j, -1.11165854e-03+1.05803081e-03j,\n",
       "        -6.72702577e-04+1.05768030e-03j, -4.08825477e-04+1.05732240e-03j,\n",
       "        -2.49943977e-04+1.05695912e-03j, -1.53431131e-04+1.05668394e-03j,\n",
       "        -9.46868504e-05+1.05630277e-03j, -9.01890864e-05+1.05591519e-03j,\n",
       "        -8.53542998e-05+1.05552355e-03j, -8.01095647e-05+1.05512782e-03j,\n",
       "        -7.43495302e-05+1.05472801e-03j, -6.79116320e-05+1.05432411e-03j,\n",
       "        -6.05007160e-05+1.05374606e-03j, -5.15866191e-05+1.05316375e-03j,\n",
       "        -3.96908244e-05+1.05257719e-03j,  2.22824981e-06+1.05198642e-03j,\n",
       "        -5.12821093e-05+1.05139136e-03j, -3.89628247e-05+1.05095602e-03j,\n",
       "        -5.48084996e-05+1.05052063e-03j, -4.35347981e-05+1.05008141e-03j,\n",
       "        -2.28613288e-05+1.04964228e-03j, -3.42711914e-05+1.04919490e-03j,\n",
       "         4.57957410e-05+6.89731137e-04j,  3.82154032e-05+4.53372516e-04j,\n",
       "         2.92169084e-05+2.97734751e-04j,  1.75860148e-05+1.94903230e-04j,\n",
       "        -3.64452218e-06+1.26406374e-04j, -1.37590041e-06+1.22352980e-04j,\n",
       "         1.27582486e-05+1.18118839e-04j, -1.63309172e-05+1.13683878e-04j,\n",
       "         7.79455671e-06+1.09023825e-04j, -2.66169088e-06+1.04105234e-04j,\n",
       "        -1.97848010e-06+5.31562624e-05j,  2.66886331e-07+1.57489819e-05j,\n",
       "         1.00069689e-05+1.89055618e-05j, -1.13662243e-05+3.56554210e-05j],\n",
       "       [ 5.00000000e-01+0.00000000e+00j,  5.00025003e-01+0.00000000e+00j,\n",
       "         5.00001746e-01+0.00000000e+00j,  5.00000975e-01+0.00000000e+00j,\n",
       "         5.00001126e-01+0.00000000e+00j,  5.00001389e-01+0.00000000e+00j,\n",
       "         4.56747580e-01+0.00000000e+00j,  4.20397735e-01+0.00000000e+00j,\n",
       "         4.01422376e-01+0.00000000e+00j,  3.94537674e-01+0.00000000e+00j,\n",
       "         3.91847311e-01+0.00000000e+00j,  2.10695548e-01+0.00000000e+00j,\n",
       "         9.65397943e-02+0.00000000e+00j,  4.84837100e-02+0.00000000e+00j,\n",
       "         2.58443889e-02+0.00000000e+00j,  1.43432784e-02+0.00000000e+00j,\n",
       "         1.43468051e-02+0.00000000e+00j,  1.43503319e-02+0.00000000e+00j,\n",
       "         1.43538588e-02+0.00000000e+00j,  1.43573859e-02+0.00000000e+00j,\n",
       "         1.43609130e-02+0.00000000e+00j,  1.43657326e-02+0.00000000e+00j,\n",
       "         1.43705509e-02+0.00000000e+00j,  1.43753686e-02+0.00000000e+00j,\n",
       "         1.43801862e-02+0.00000000e+00j,  1.43850035e-02+0.00000000e+00j,\n",
       "         1.43870213e-02+0.00000000e+00j,  1.43890450e-02+0.00000000e+00j,\n",
       "         1.43910747e-02+0.00000000e+00j,  1.43931104e-02+0.00000000e+00j,\n",
       "         1.43951520e-02+0.00000000e+00j,  1.34378931e-02+0.00000000e+00j,\n",
       "         1.32208682e-02+0.00000000e+00j,  1.31735725e-02+0.00000000e+00j,\n",
       "         1.31657707e-02+0.00000000e+00j,  1.31673698e-02+0.00000000e+00j,\n",
       "         1.31517510e-02+0.00000000e+00j,  1.31361661e-02+0.00000000e+00j,\n",
       "         1.31206151e-02+0.00000000e+00j,  1.31050978e-02+0.00000000e+00j,\n",
       "         1.30896143e-02+0.00000000e+00j,  8.77964597e-03+0.00000000e+00j,\n",
       "         5.95179651e-03+0.00000000e+00j,  4.08427976e-03+0.00000000e+00j,\n",
       "         2.84591448e-03+0.00000000e+00j,  2.02280474e-03+0.00000000e+00j,\n",
       "         7.31092106e-04+0.00000000e+00j,  4.36611961e-04+0.00000000e+00j,\n",
       "         3.72186199e-04+0.00000000e+00j,  3.61079100e-04+0.00000000e+00j,\n",
       "         3.62342300e-04+0.00000000e+00j,  3.67342436e-04+0.00000000e+00j,\n",
       "         3.72342504e-04+0.00000000e+00j,  3.77342506e-04+0.00000000e+00j,\n",
       "         3.82342441e-04+0.00000000e+00j,  3.87342310e-04+0.00000000e+00j,\n",
       "         3.92342112e-04+0.00000000e+00j,  3.97341847e-04+0.00000000e+00j,\n",
       "         4.02341515e-04+0.00000000e+00j,  4.07341117e-04+0.00000000e+00j,\n",
       "         4.12340651e-04+0.00000000e+00j,  4.17339276e-04+0.00000000e+00j,\n",
       "         4.22337836e-04+0.00000000e+00j,  4.27336329e-04+0.00000000e+00j,\n",
       "         4.32334757e-04+0.00000000e+00j,  4.37333119e-04+0.00000000e+00j,\n",
       "         4.41547508e-04+0.00000000e+00j,  4.46261115e-04+0.00000000e+00j,\n",
       "         4.51155899e-04+0.00000000e+00j,  4.56116727e-04+0.00000000e+00j,\n",
       "         4.61101719e-04+0.00000000e+00j,  4.66100426e-04+0.00000000e+00j,\n",
       "         4.71099059e-04+0.00000000e+00j,  4.76097613e-04+0.00000000e+00j,\n",
       "         4.81096088e-04+0.00000000e+00j,  4.86094477e-04+0.00000000e+00j,\n",
       "         4.91092414e-04+0.00000000e+00j,  4.96090245e-04+0.00000000e+00j,\n",
       "         5.01087931e-04+0.00000000e+00j,  5.06084758e-04+0.00000000e+00j,\n",
       "         5.11084039e-04+0.00000000e+00j,  5.16081869e-04+0.00000000e+00j,\n",
       "         5.21080384e-04+0.00000000e+00j,  5.26078110e-04+0.00000000e+00j,\n",
       "         5.31075521e-04+0.00000000e+00j,  5.36073719e-04+0.00000000e+00j,\n",
       "         5.40444057e-04+0.00000000e+00j,  5.45172281e-04+0.00000000e+00j,\n",
       "         5.50054065e-04+0.00000000e+00j,  5.55002234e-04+0.00000000e+00j,\n",
       "         5.59979308e-04+0.00000000e+00j,  5.64976551e-04+0.00000000e+00j,\n",
       "         5.69973269e-04+0.00000000e+00j,  5.74971233e-04+0.00000000e+00j,\n",
       "         5.79966842e-04+0.00000000e+00j,  5.84963785e-04+0.00000000e+00j,\n",
       "         5.89953399e-04+0.00000000e+00j,  5.94948318e-04+0.00000000e+00j,\n",
       "         5.99943313e-04+0.00000000e+00j,  6.04937915e-04+0.00000000e+00j]])"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "rho_vector"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "def9781a-309e-472a-acaf-91479c9fef00",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "np.float64(0.018924052774781968)"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sum(distance_vector[30:])/(len(distance_vector)-30)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "86e0bd52-fd39-48c7-9447-10e76b087469",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[np.float64(7.9811932072647656),\n",
       " np.float64(7.8791159087277505),\n",
       " np.float64(7.484557753257289),\n",
       " np.float64(6.846694686583045),\n",
       " np.float64(6.074925893147009),\n",
       " np.float64(5.29103122641491),\n",
       " np.float64(4.367610917412917),\n",
       " np.float64(3.6334497589535193),\n",
       " np.float64(3.2831326305416138),\n",
       " np.float64(3.1722800322384175),\n",
       " np.float64(3.1363825084066894),\n",
       " np.float64(1.690162742052615),\n",
       " np.float64(0.780096954900441),\n",
       " np.float64(0.39783412278982916),\n",
       " np.float64(0.21799124089015884),\n",
       " np.float64(0.12680725443937316),\n",
       " np.float64(0.12679592782156116),\n",
       " np.float64(0.12678460246373377),\n",
       " np.float64(0.1267732783657417),\n",
       " np.float64(0.12676195552743566),\n",
       " np.float64(0.12675063394866634),\n",
       " np.float64(0.11597434925498255),\n",
       " np.float64(0.11363157032631907),\n",
       " np.float64(0.11312010985527104),\n",
       " np.float64(0.11300792077666688),\n",
       " np.float64(0.11298280702140409),\n",
       " np.float64(0.11295925749483453),\n",
       " np.float64(0.11293575782456645),\n",
       " np.float64(0.11291230786443056),\n",
       " np.float64(0.11288890746689259),\n",
       " np.float64(0.1128655564829026),\n",
       " np.float64(0.10525585798733966),\n",
       " np.float64(0.10352651670080835),\n",
       " np.float64(0.1031319192230805),\n",
       " np.float64(0.10304131600659679),\n",
       " np.float64(0.10302000348912725),\n",
       " np.float64(0.10285540206680825),\n",
       " np.float64(0.1026910734004197),\n",
       " np.float64(0.1025270170087186),\n",
       " np.float64(0.1023632324114371),\n",
       " np.float64(0.10219971912928223),\n",
       " np.float64(0.06767054355551838),\n",
       " np.float64(0.04500136565619523),\n",
       " np.float64(0.03001692081299169),\n",
       " np.float64(0.020067091416977295),\n",
       " np.float64(0.013440256276006857),\n",
       " np.float64(0.0031677871497244425),\n",
       " np.float64(0.000794746611403742),\n",
       " np.float64(0.000244567169800783),\n",
       " np.float64(0.00011690613151944758),\n",
       " np.float64(8.728131511822086e-05),\n",
       " np.float64(5.383719630323523e-05),\n",
       " np.float64(3.688704708936075e-05),\n",
       " np.float64(2.8297491538834863e-05),\n",
       " np.float64(2.3945897043010597e-05),\n",
       " np.float64(2.1742545061092923e-05),\n",
       " np.float64(2.0061448142314466e-05),\n",
       " np.float64(1.9634874339636993e-05),\n",
       " np.float64(1.952954016482748e-05),\n",
       " np.float64(1.9506511660934375e-05),\n",
       " np.float64(1.9506502944565978e-05),\n",
       " np.float64(1.9505738195988143e-05),\n",
       " np.float64(1.950940334522027e-05),\n",
       " np.float64(1.950285659302643e-05),\n",
       " np.float64(1.9528398680913383e-05),\n",
       " np.float64(1.9521554382174812e-05),\n",
       " np.float64(1.3345666159470541e-05),\n",
       " np.float64(1.1121175213804902e-05),\n",
       " np.float64(1.032218848669096e-05),\n",
       " np.float64(1.0459005323576186e-05),\n",
       " np.float64(1.0360125570207451e-05),\n",
       " np.float64(1.0317818402416692e-05),\n",
       " np.float64(1.0280529371812524e-05),\n",
       " np.float64(1.0247746828288841e-05),\n",
       " np.float64(1.021901201912679e-05),\n",
       " np.float64(1.0193913627086522e-05),\n",
       " np.float64(1.0190914262013782e-05),\n",
       " np.float64(1.0187917526081416e-05),\n",
       " np.float64(1.018492245143662e-05),\n",
       " np.float64(1.0184456389826948e-05),\n",
       " np.float64(1.0197498056447329e-05),\n",
       " np.float64(1.0071519697082688e-05),\n",
       " np.float64(1.0055873010430466e-05),\n",
       " np.float64(1.0055921480645142e-05),\n",
       " np.float64(1.0082829616640543e-05),\n",
       " np.float64(1.0079466173649489e-05),\n",
       " np.float64(5.185839224214971e-06),\n",
       " np.float64(3.0398452928183597e-06),\n",
       " np.float64(2.1182664885725855e-06),\n",
       " np.float64(1.7250056786704525e-06),\n",
       " np.float64(1.5597262864635692e-06),\n",
       " np.float64(1.5670616022525895e-06),\n",
       " np.float64(1.5783800578488185e-06),\n",
       " np.float64(1.5800405970486513e-06),\n",
       " np.float64(1.5987137889371372e-06),\n",
       " np.float64(1.6137232165524847e-06),\n",
       " np.float64(1.5742540554540893e-06),\n",
       " np.float64(2.247056411512981e-06),\n",
       " np.float64(2.266401061970467e-06),\n",
       " np.float64(2.2844140468049634e-06)]"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "distance_vector"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "cefd2f5e-8308-450c-a9dc-5791d460c58c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[np.float64(137.1717730127981),\n",
       " np.float64(-0.0028492177654750165),\n",
       " np.float64(-0.0014619465912436578),\n",
       " np.float64(-0.000986964185474115),\n",
       " np.float64(-0.0006807345974665951),\n",
       " np.float64(-0.0003931535978164901),\n",
       " np.float64(-5.409510478175577e-05),\n",
       " np.float64(0.00019027826750527785),\n",
       " np.float64(0.0003360425765483653),\n",
       " np.float64(0.00038870229248137445),\n",
       " np.float64(0.00040474125186274444),\n",
       " 400,\n",
       " np.float64(239.7672167647543),\n",
       " np.float64(148.45445314737185),\n",
       " np.float64(100.27562964612096),\n",
       " np.float64(70.84701379806492),\n",
       " np.float64(0.011441148062060346),\n",
       " np.float64(0.011440561020962107),\n",
       " np.float64(0.011439974031451012),\n",
       " np.float64(0.011439387093523004),\n",
       " np.float64(0.011438800207174022),\n",
       " np.float64(0.00020423149882781096),\n",
       " np.float64(0.0002050962611448809),\n",
       " np.float64(0.00020548176578505725),\n",
       " np.float64(0.00020568879916094105),\n",
       " np.float64(0.00020582265900246773),\n",
       " np.float64(0.0002058550673307524),\n",
       " np.float64(0.00020589389283146803),\n",
       " np.float64(0.0002059328122898696),\n",
       " np.float64(0.0002059718262664035),\n",
       " np.float64(0.00020601093539620677),\n",
       " np.float64(0.0001917554719758292),\n",
       " np.float64(0.0001901897509171327),\n",
       " np.float64(0.0001898781287430746),\n",
       " np.float64(0.00018986046235369168),\n",
       " np.float64(0.0001899123002082352),\n",
       " np.float64(0.18167415076610055),\n",
       " np.float64(0.18151663906763563),\n",
       " np.float64(0.18135929155307276),\n",
       " np.float64(0.18120210796346548),\n",
       " np.float64(0.18104508803868327),\n",
       " np.float64(37.84611058454746),\n",
       " np.float64(30.560168672856864),\n",
       " np.float64(24.789269423723166),\n",
       " np.float64(20.16911337771758),\n",
       " np.float64(16.443258801085214),\n",
       " np.float64(26.153084217134445),\n",
       " np.float64(12.591339309044844),\n",
       " np.float64(6.065248043728614),\n",
       " np.float64(2.922099746679227),\n",
       " np.float64(1.4080913468454863),\n",
       " np.float64(0.0006079845320002743),\n",
       " np.float64(0.0006160587501818726),\n",
       " np.float64(0.0006242442397128045),\n",
       " np.float64(0.0006325117845916019),\n",
       " np.float64(0.0006408405297431353),\n",
       " np.float64(0.0006491287845049779),\n",
       " np.float64(0.0006575276368032249),\n",
       " np.float64(0.0006659745413077484),\n",
       " np.float64(0.0006744488845469063),\n",
       " np.float64(0.0006829162122411333),\n",
       " np.float64(0.0006914699379716953),\n",
       " np.float64(0.000699971279921461),\n",
       " np.float64(0.0007085086128524742),\n",
       " np.float64(0.000717112612205088),\n",
       " np.float64(0.0007256317822961914),\n",
       " np.float64(0.0007328469087308541),\n",
       " np.float64(0.0007409857132887999),\n",
       " np.float64(0.0007494051514724997),\n",
       " np.float64(0.0007578301706416471),\n",
       " np.float64(0.0007664562386764023),\n",
       " np.float64(0.0007750609569720789),\n",
       " np.float64(0.0007836739692781154),\n",
       " np.float64(0.0007922965503234548),\n",
       " np.float64(0.000800928808919186),\n",
       " np.float64(0.0008095708470227615),\n",
       " np.float64(0.001160848869551049),\n",
       " np.float64(0.001169454784105976),\n",
       " np.float64(0.0011780722115536369),\n",
       " np.float64(0.001186700318851349),\n",
       " np.float64(0.0011953404588519495),\n",
       " np.float64(0.0008623400067143823),\n",
       " np.float64(0.0008710620594853016),\n",
       " np.float64(0.0008797994355210545),\n",
       " np.float64(0.0008885434907475765),\n",
       " np.float64(0.0008972982707985252),\n",
       " np.float64(0.5728832506286317),\n",
       " np.float64(0.37695870996752356),\n",
       " np.float64(0.24861161413565225),\n",
       " np.float64(0.1648733680977741),\n",
       " np.float64(0.11081839273917879),\n",
       " np.float64(0.008290785011502239),\n",
       " np.float64(0.008671952636199602),\n",
       " np.float64(0.00909866688522107),\n",
       " np.float64(0.009581669529367747),\n",
       " np.float64(0.01013493076052684),\n",
       " np.float64(0.07910773710416265),\n",
       " np.float64(0.08775110607086303),\n",
       " np.float64(-0.07243847183293992),\n",
       " np.float64(-0.0710740640147538)]"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fx_vector"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "723c677a-9498-4237-9951-82ef21ba7e59",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[np.float64(0.0),\n",
       " np.float64(-0.22296032502168284),\n",
       " np.float64(-0.005688861324408552),\n",
       " np.float64(-0.0017896435327334934),\n",
       " np.float64(-0.0007404434170417706),\n",
       " np.float64(-0.00028410954579799133),\n",
       " 400,\n",
       " np.float64(394.15173435864915),\n",
       " np.float64(211.21450437499738),\n",
       " np.float64(113.6574157322495),\n",
       " np.float64(63.503987868933855),\n",
       " np.float64(0.004552675183933058),\n",
       " np.float64(0.0028496458534506717),\n",
       " np.float64(0.0017482818870658478),\n",
       " np.float64(0.0010846004553442972),\n",
       " np.float64(0.0006679367578443571),\n",
       " np.float64(0.0006745324951874999),\n",
       " np.float64(0.0006747319457293122),\n",
       " np.float64(0.0006749314115405311),\n",
       " np.float64(0.0006751308926231839),\n",
       " np.float64(0.0006753303889792956),\n",
       " np.float64(0.0006211550110727309),\n",
       " np.float64(0.0006017431008031698),\n",
       " np.float64(0.00059298202153398),\n",
       " np.float64(0.0005890418131010653),\n",
       " np.float64(0.000587319118938372),\n",
       " np.float64(0.08075322933434845),\n",
       " np.float64(0.08066515825154369),\n",
       " np.float64(0.0805772595466396),\n",
       " np.float64(0.08048953680385598),\n",
       " np.float64(0.08040199396988794),\n",
       " np.float64(22.55283179374856),\n",
       " np.float64(10.7690280575952),\n",
       " np.float64(5.143253529968796),\n",
       " np.float64(2.460788432096251),\n",
       " np.float64(1.1865030845327302),\n",
       " np.float64(0.022480413860847648),\n",
       " np.float64(0.022760665409132866),\n",
       " np.float64(0.023052627271755128),\n",
       " np.float64(0.02335712008275948),\n",
       " np.float64(0.023675047185823656),\n",
       " np.float64(0.015146359962252656),\n",
       " np.float64(0.009903844858108132),\n",
       " np.float64(0.006597512989588109),\n",
       " np.float64(0.004485373290241472),\n",
       " np.float64(0.0031235314125252905),\n",
       " np.float64(0.000848320288153744),\n",
       " np.float64(0.0005736482064520776),\n",
       " np.float64(0.0005136860757666534),\n",
       " np.float64(0.0005039713330372154),\n",
       " np.float64(0.0005065010541966474),\n",
       " np.float64(0.0005147739937683573),\n",
       " np.float64(0.0005222064544129375),\n",
       " np.float64(0.000529566964516451),\n",
       " np.float64(0.0005368766077906556),\n",
       " np.float64(0.0005441508496602948),\n",
       " np.float64(0.000551467910610598),\n",
       " np.float64(0.0005587114102866799),\n",
       " np.float64(0.0005659294054490232),\n",
       " np.float64(0.0005731379826043942),\n",
       " np.float64(0.0005803639801165414),\n",
       " np.float64(0.0013441359536709957),\n",
       " np.float64(0.0013510774680171077),\n",
       " np.float64(0.0013580335786315513),\n",
       " np.float64(0.001365008993001156),\n",
       " np.float64(0.0013719754973733557),\n",
       " np.float64(0.6588934316622055),\n",
       " np.float64(0.39637260256032264),\n",
       " np.float64(0.2391298214867327),\n",
       " np.float64(0.144750618195252),\n",
       " np.float64(0.09054291848430845),\n",
       " np.float64(0.009377811814118842),\n",
       " np.float64(0.010114887652905245),\n",
       " np.float64(0.011025047772688463),\n",
       " np.float64(0.01219202321372051),\n",
       " np.float64(0.013770381424822098),\n",
       " np.float64(0.016091052568177514),\n",
       " np.float64(0.02002532928988108),\n",
       " np.float64(0.029243866771619068),\n",
       " np.float64(0.2973171315510179),\n",
       " np.float64(-0.03558884364431124),\n",
       " np.float64(0.031048910023104),\n",
       " np.float64(-0.42080293778906164),\n",
       " np.float64(0.026955089742134952),\n",
       " np.float64(0.07395442916344402),\n",
       " np.float64(-0.14475906409097933),\n",
       " np.float64(-0.004837906998306763),\n",
       " np.float64(-0.016378566392923528),\n",
       " np.float64(-0.02001678607812465),\n",
       " np.float64(-0.027754097804551313),\n",
       " np.float64(-0.0766753182950457),\n",
       " np.float64(0.07289610345866657),\n",
       " np.float64(0.09990227677682255),\n",
       " np.float64(0.047340159616715734),\n",
       " np.float64(-0.04545722960467999),\n",
       " np.float64(-0.05102373734983284),\n",
       " np.float64(0.06668488780578764),\n",
       " np.float64(0.06728637011330718),\n",
       " np.float64(0.06611427009202527),\n",
       " np.float64(-0.08993962301204686)]"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fy_vector"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "5f8f0d78-bee6-4ca8-8aa2-5bd7f82cae5a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[np.float64(0.0),\n",
       " np.float64(329.7308320906885),\n",
       " 400,\n",
       " 400,\n",
       " 400,\n",
       " 400,\n",
       " np.float64(-8.191038495899526e-05),\n",
       " np.float64(0.0005123159700257218),\n",
       " np.float64(0.001822040408487282),\n",
       " np.float64(0.004501319714974481),\n",
       " np.float64(0.011198280835457831),\n",
       " np.float64(0.006649134198829866),\n",
       " np.float64(0.0031546207698321047),\n",
       " np.float64(0.001657705462678241),\n",
       " np.float64(0.0009274584653342263),\n",
       " np.float64(0.0005293643742215174),\n",
       " np.float64(0.0005350284565678569),\n",
       " np.float64(0.0005351783931321314),\n",
       " np.float64(0.0005353283365734651),\n",
       " np.float64(0.0005354782868924492),\n",
       " np.float64(0.0005356282440896723),\n",
       " np.float64(26.54081043144285),\n",
       " np.float64(12.397862141389695),\n",
       " np.float64(5.796460465656138),\n",
       " np.float64(2.7153596396263433),\n",
       " np.float64(1.282926149429801),\n",
       " np.float64(0.025009411953267863),\n",
       " np.float64(0.02550034702754334),\n",
       " np.float64(0.026018145156461035),\n",
       " np.float64(0.02656535011237563),\n",
       " np.float64(0.02714485616001007),\n",
       " np.float64(-0.015484248554520137),\n",
       " np.float64(-0.00899182899513677),\n",
       " np.float64(-0.007587127651612804),\n",
       " np.float64(-0.007068364311801857),\n",
       " np.float64(-0.006850435369899262),\n",
       " np.float64(-0.006869856508626669),\n",
       " np.float64(-0.006867609360171712),\n",
       " np.float64(-0.006865334257518312),\n",
       " np.float64(-0.006863029605685815),\n",
       " np.float64(-0.00686069369858922),\n",
       " np.float64(-0.004729361767644432),\n",
       " np.float64(-0.0032757744051976068),\n",
       " np.float64(-0.0022831958832601916),\n",
       " np.float64(-0.0016090381423452926),\n",
       " np.float64(-0.0011531749646864174),\n",
       " np.float64(-0.0003367987614847615),\n",
       " np.float64(-0.00023423708472926152),\n",
       " np.float64(-0.00021254320296408555),\n",
       " np.float64(-0.00020982429584092554),\n",
       " np.float64(-0.00021148641204528202),\n",
       " np.float64(-1.4012864169017716),\n",
       " np.float64(-0.9977751282352834),\n",
       " np.float64(-0.7105417793461942),\n",
       " np.float64(-0.5061106797984124),\n",
       " np.float64(-0.36065969554286514),\n",
       " np.float64(-0.34374944966897997),\n",
       " np.float64(-0.17639858941953648),\n",
       " np.float64(-0.0945195732386285),\n",
       " np.float64(-0.062074540714337524),\n",
       " np.float64(0.0643067807563909),\n",
       " np.float64(-0.02836619600853705),\n",
       " np.float64(0.1881833366840047),\n",
       " np.float64(-0.15057747542297653),\n",
       " np.float64(-0.008165616153521672),\n",
       " np.float64(-0.014647966768834276),\n",
       " np.float64(-0.01733559321038352),\n",
       " np.float64(-0.02244206182436557),\n",
       " np.float64(-0.03852892009214092),\n",
       " np.float64(0.001145785996229847),\n",
       " np.float64(0.0034601270620960994),\n",
       " np.float64(0.026958425710070313),\n",
       " np.float64(0.025807686142324458),\n",
       " np.float64(0.024745238202416496),\n",
       " np.float64(0.023770512963225503),\n",
       " np.float64(0.02288398450587696),\n",
       " np.float64(0.005198200640084545),\n",
       " np.float64(0.005338931369059294),\n",
       " np.float64(0.005487102627923716),\n",
       " np.float64(0.005643829789941993),\n",
       " np.float64(0.0058095450026536734),\n",
       " np.float64(0.10422290428197205),\n",
       " np.float64(0.06861994697910631),\n",
       " np.float64(-0.16762230379485807),\n",
       " np.float64(-0.08539350025362982),\n",
       " np.float64(0.07494778519217916),\n",
       " np.float64(0.04686853816562106),\n",
       " np.float64(-0.012178572658621878),\n",
       " np.float64(-0.013410402718209351),\n",
       " np.float64(-0.015061595719466686),\n",
       " np.float64(-0.01744599003500103),\n",
       " np.float64(-0.021356522863740877),\n",
       " np.float64(-0.029744919378543067),\n",
       " np.float64(-0.08688186828303192),\n",
       " np.float64(0.08598231683409867),\n",
       " np.float64(0.1424963863406632),\n",
       " np.float64(-0.012500473548052641),\n",
       " np.float64(-0.05849473299918707),\n",
       " np.float64(0.0035517452296211964),\n",
       " np.float64(0.0036037709438992197)]"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fz_vector"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "aaf4aa95-dcf3-4f17-9292-59a58c511b0e",
   "metadata": {},
   "outputs": [],
   "source": [
    "def densidade(rho, quant_pontos, lbda):\n",
    "    ts = np.linspace(0, 0.1, quant_pontos)\n",
    "\n",
    "    fig, ax = plt.subplots()\n",
    "\n",
    "    ax.set_ylabel('Valores da matriz de densidade') \n",
    "    ax.set_xlabel('Tempo (u. a.)') \n",
    "    ax.plot(ts, abs(rho[0]), color='g', marker='o', linewidth=1, markersize=1, label=r\"$\\rho_{00}$\")\n",
    "    ax.plot(ts, abs(rho[1]), color='b', marker='8', linewidth=1, markersize=1, label=r\"$\\rho_{01}$\")\n",
    "    ax.plot(ts, abs(rho[2]), color='r', marker='.', linewidth=1, markersize=1, label=r\"$\\rho_{10}$\")\n",
    "    ax.plot(ts, abs(rho[3]), color='y', marker='*', linewidth=1, markersize=1, label=r\"$\\rho_{11}$\")\n",
    "    ax.legend(loc=\"center right\")\n",
    "    ax.set_title(fr\"Evolução da matriz de densidade $\\gamma = {lbda}$\")\n",
    "\n",
    "    x1, x2, y1, y2 = 2.5, 4, 0, max(max(abs(rho[0])), max(abs(rho[1])), max(abs(rho[2])), max(abs(rho[3])))\n",
    "    axins = inset_axes(ax, width=\"30%\", height=\"30%\", loc='upper center', borderpad=3)\n",
    "    axins.set_xlim(0.030, 0.050)\n",
    "    axins.set_ylim(0.98, 1)\n",
    "\n",
    "    axins.plot(ts, abs(rho[0]), color='g', marker='o', linewidth=1, markersize=1, label=r\"$\\rho_{00}$\")\n",
    "    axins.plot(ts, abs(rho[1]), color='b', marker='8', linewidth=1, markersize=1, label=r\"$\\rho_{01}$\")\n",
    "    axins.plot(ts, abs(rho[2]), color='r', marker='.', linewidth=1, markersize=1, label=r\"$\\rho_{10}$\")\n",
    "    axins.plot(ts, abs(rho[3]), color='y', marker='*', linewidth=1, markersize=1, label=r\"$\\rho_{11}$\")\n",
    "\n",
    "    ax.indicate_inset_zoom(axins)\n",
    "    \n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "09f7a9a0-8465-46a9-8dbf-fc64dabf8556",
   "metadata": {},
   "outputs": [],
   "source": [
    "def distance(fid, quant_pontos, lbda):\n",
    "    ts = np.linspace(0, 0.1, quant_pontos)\n",
    "\n",
    "    fig, ax = plt.subplots()\n",
    "\n",
    "    ax.set_ylabel(\"Valores de distância\") \n",
    "    ax.set_xlabel('Tempo (u. a.)') \n",
    "    ax.plot(ts, np.abs(fid), color='g', marker='*', linewidth=1, markersize=1, label=fr\"$\\gamma = {lbda}$\")\n",
    "    ax.legend(loc=\"center right\")\n",
    "    ax.set_title(fr\"Distância entre os operadores de evolução com $\\gamma = {lbda}$\")\n",
    "\n",
    "    #x1, x2, y1, y2 = 2.5, 4, 0, max(np.abs(fid))\n",
    "    #axins = inset_axes(ax, width=\"30%\", height=\"30%\", loc='upper center', borderpad=3)\n",
    "    #axins.set_xlim(0.009, 0.020)\n",
    "    #axins.set_ylim(0.98, 1)\n",
    "\n",
    "    #axins.plot(ts, np.abs(fid), color='g', marker='*', linewidth=1, markersize=1, label=fr\"$\\gamma = {lbda}$\")\n",
    "    #ax.indicate_inset_zoom(axins)\n",
    "    \n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "6a143821-61a7-4a38-8c12-ebc9c741df22",
   "metadata": {},
   "outputs": [],
   "source": [
    "def fidelidade(fid, quant_pontos, lbda):\n",
    "    ts = np.linspace(0, 0.1, quant_pontos)\n",
    "\n",
    "    fig, ax = plt.subplots()\n",
    "\n",
    "    ax.set_ylabel(\"Valores de fidelidade\") \n",
    "    ax.set_xlabel('Tempo (u. a.)') \n",
    "    ax.plot(ts, np.abs(fid), color='g', marker='*', linewidth=1, markersize=1, label=fr\"$\\gamma = {lbda}$\")\n",
    "    ax.legend(loc=\"center right\")\n",
    "    ax.set_title(fr\"Fidelidade com $\\gamma = {lbda}$\")\n",
    "\n",
    "    x1, x2, y1, y2 = 2.5, 4, 0, max(np.abs(fid))\n",
    "    axins = inset_axes(ax, width=\"30%\", height=\"30%\", loc='upper center', borderpad=3)\n",
    "    axins.set_xlim(0.009, 0.020)\n",
    "    axins.set_ylim(0.98, 1)\n",
    "\n",
    "    axins.plot(ts, np.abs(fid), color='g', marker='*', linewidth=1, markersize=1, label=fr\"$\\gamma = {lbda}$\")\n",
    "    ax.indicate_inset_zoom(axins)\n",
    "    \n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "529614df-411a-4d11-b9ee-699aa669e711",
   "metadata": {},
   "outputs": [],
   "source": [
    "def leis_controle(fx, fy, fz, quant_pontos, lbda):\n",
    "    ts = np.linspace(0, 0.1, quant_pontos)\n",
    "\n",
    "    plt.ylabel(\"Valores das leis de controle\") \n",
    "    plt.xlabel('Tempo (u. a.)') \n",
    "    plt.plot(ts, fx, color='g', marker='o', linewidth=1, markersize=1, label=\"$f_x(t)$\")\n",
    "    plt.plot(ts, fy, color='b', marker='_', linewidth=1, markersize=1, label=\"$f_y(t)$\")\n",
    "    plt.plot(ts, fz, color='r', marker='.', linewidth=1, markersize=1, label=\"$f_z(t)$\")\n",
    "    plt.legend(loc=\"upper right\")\n",
    "    plt.title(fr\"Leis de controle para $\\gamma = {lbda}$\")\n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "8834e3af-0e29-4f75-b817-5ad1f3e749fc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAjcAAAHJCAYAAAB5WBhaAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjkuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8hTgPZAAAACXBIWXMAAA9hAAAPYQGoP6dpAABlBUlEQVR4nO3deVxUVf8H8M/MwDCggCICguAC7gvmAqGmlvwiNX2sntQWNVLL0sp4cisV29Q2s0wzzaWnNC237NE0xS0TRUVcUlQUBREQRIadGWbO7w9jamJxBme4zPB5v17zijlzzrnfeyXn67nn3CMTQggQERER2Qm51AEQERERWRKTGyIiIrIrTG6IiIjIrjC5ISIiIrvC5IaIiIjsCpMbIiIisitMboiIiMiuMLkhIiIiu8LkhoiIiOwKkxsiIiKyK0xuiIiIyK4wuSGqRWvWrIFMJsPVq1fvWnfu3LmQyWQWOUZtHLe2+iMiuhsmN0QWUp5AVPaaMWOG1OFRPVJaWorp06fD19cXzs7OCA0Nxe7duy3atqCgANHR0XjkkUfg4eEBmUyGNWvWWPhMiGrGQeoAiOzNO++8g1atWhmVde7cGQAwevRojBo1Ck5OTrUak1THJWk899xz2LhxI6ZMmYI2bdpgzZo1GDx4MPbt24e+fftapG12djbeeecdBAQEIDg4GPv377fyWRGZjskNkYUNGjQIPXv2rPQzhUIBhUJRyxFJd1yqfXFxcVi/fj0++ugjvPHGGwCAMWPGoHPnzpg2bRoOHz5skbbNmjVDeno6fHx8cPz4cfTq1cu6J0ZkBt6WIqpFVc19OXToEHr16gWVSoXAwEB89dVXlbZPS0vD888/D29vbzg5OaFTp05YtWqVVY977do1vPzyy2jXrh2cnZ3RpEkTPPnkk5XO3zH1PO7lXP7efty4cfD19YWTkxNatWqFl156CRqNxlDn5MmTGDRoENzc3NCwYUMMHDgQR44cMeqnfE7QxYsX8eyzz8Ld3R1NmzbF7NmzIYRAamoq/vWvf8HNzQ0+Pj745JNP7hrb+PHj4enpiQ0bNlT47JdffoFMJsP27dtNPldzbNy4EQqFAi+88IKhTKVSYdy4cYiNjUVqaqpF2jo5OcHHx8cq50B0rzhyQ2RharUa2dnZRmWenp5V1j9z5gwefvhhNG3aFHPnzkVZWRmio6Ph7e1tVC8zMxP3338/ZDIZJk+ejKZNm+KXX37BuHHjkJeXhylTppgVp6nHPXbsGA4fPoxRo0ahefPmuHr1Kr788ksMGDAA586dg4uLi1n9WeJcbty4gZCQEOTm5uKFF15A+/btkZaWho0bN6KoqAhKpRJ//PEHHnjgAbi5uWHatGlwdHTEV199hQEDBuDAgQMIDQ016nPkyJHo0KEDFixYgO3bt+O9996Dh4cHvvrqKzz00EP44IMPsHbtWrzxxhvo1asX+vXrV2V8Tz75JA4ePIi3334bI0eONJQLITBz5kz069cPQ4YMMWqj1WqhVqurPe9yHh4ekMsr/7fpyZMn0bZtW7i5uRmVh4SEAAASEhLg7+9v8bZEdYogIotYvXq1AFDp6591kpOTDWXDhw8XKpVKXLt2zVB27tw5oVAojNqOGzdONGvWTGRnZxsdd9SoUcLd3V0UFRVVeYx7OW55v38XGxsrAIj//ve/ZvdnzrlUZcyYMUIul4tjx45V+Eyv1xviUSqV4vLly4bPbty4IVxdXUW/fv0MZdHR0QKAeOGFFwxlZWVlonnz5kImk4kFCxYYym/fvi2cnZ3F2LFjq41PCCE+/vhjoVAohEajMZR9++23AoA4fPhwhfr79u2r8vfnn6+//zn+U6dOncRDDz1UofyPP/4QAMSyZcss3vbYsWMCgFi9enWVfRPVJo7cEFnYkiVL0LZtW5Pq6nQ67Nq1C8OHD0dAQIChvEOHDoiIiMCOHTsA3PkX/6ZNmzBixAgIIYxGhiIiIrB+/XrEx8ejT58+Fj0uADg7Oxt+1mq1yMvLQ1BQEBo1aoT4+HiMHj3arP7u9Vz0ej22bt2KoUOHVjq3SSaTQafT4ddff8Xw4cPRunVrw2fNmjXD008/jRUrViAvL89ohGL8+PGGnxUKBXr27Inr169j3LhxhvJGjRqhXbt2uHLlStUX909t27aFTqdDcnIy2rZtC41Ggzlz5mD48OEICwurUD84ONjkFU3V3Q4qLi6udOK4SqUyfG6NtkR1CZMbIgsLCQmpckLxP2VlZaG4uBht2rSp8Fm7du0MSUFWVhZyc3OxfPlyLF++vNK+bt68aXKMph4XuPOFNn/+fKxevRppaWkQQhg+K7+NYk5/93ouWVlZyMvLM6xAq6pOUVER2rVrV+GzDh06QK/XIzU1FZ06dTKU/z0pAwB3d3eoVKoKtxTd3d1x69atKo9dLigoCABw8eJFtG3bFl9++SVSUlKqnGvTuHFjhIeH37Xfu3F2dkZpaWmF8pKSEsPn1mhLVJcwuSGyAXq9HgDw7LPPYuzYsZXW6dq1q1WO/corr2D16tWYMmUKwsLC4O7uDplMhlGjRhniMoeU51KdylaTVbXC7O8JXlVat24NuVyOS5cuIT8/H++//z6ee+45dOjQodL6Go0GOTk5JsXatGnTKmNr1qwZ0tLSKpSnp6cDAHx9favs917aEtUlTG6IJNS0aVM4Ozvj0qVLFT67cOGCUT1XV1fodDqL/Ove1OMCd1bQjB071miVUElJCXJzc2vU372eS9OmTeHm5oazZ89WW8fFxaXCsQEgMTERcrnc6hNjnZyc4Ofnh0uXLuGjjz5Cfn4+5s6dW2X9w4cP48EHHzSp7+TkZLRs2bLSz7p164Z9+/ZVuO129OhRw+dVuZe2RHUJl4ITSUihUCAiIgJbt25FSkqKofz8+fPYtWuXUb0nnngCmzZtqvRLPSsryyrHLa/7z5GKxYsXQ6fT1bi/ezkXuVyO4cOH4+eff8bx48crfC6EgEKhwMMPP4yffvrJaMl6ZmYm1q1bh759+1ZYEWQNQUFBOHz4MBYuXIhXXnkFzZs3r7Ju+ZwbU17Vzbn597//DZ1OZ3TLr7S0FKtXr0ZoaKghqSsqKkJiYqLRnCdT2xLVdRy5IZLY22+/jZ07d+KBBx7Ayy+/jLKyMixevBidOnXC6dOnDfUWLFiAffv2ITQ0FBMmTEDHjh2Rk5OD+Ph47Nmzx+RbGuYe99FHH8W3334Ld3d3dOzYEbGxsdizZw+aNGlSo/4scS7z5s3Dr7/+iv79++OFF15Ahw4dkJ6ejh9//BGHDh1Co0aN8N5772H37t3o27cvXn75ZTg4OOCrr75CaWkpPvzwQ7OuVU0FBQVhxYoVaNSoEWbOnFltXUvNuQkNDcWTTz6JmTNn4ubNmwgKCsI333yDq1evYuXKlYZ6cXFxePDBBxEdHW0YUTK1bbkvvvgCubm5uHHjBgDg559/xvXr1wHcuZ3p7u5+z+dDVCPSLdQisi/ly60rW578zzr/XMp74MAB0aNHD6FUKkXr1q3FsmXLDEuU/y4zM1NMmjRJ+Pv7C0dHR+Hj4yMGDhwoli9fXu0x7uW4t2/fFpGRkcLT01M0bNhQREREiMTERNGiRYsKS6JNPQ9Tz6U6165dE2PGjBFNmzYVTk5OonXr1mLSpEmitLTUUCc+Pl5ERESIhg0bChcXF/Hggw9WWIZdHl9WVpZR+dixY0WDBg0qHLd///6iU6dOJsW4YMECAcBoOXltKC4uFm+88Ybw8fERTk5OolevXmLnzp1GdcqXnkdHR5vdtlyLFi1qtFydyNpkQpgwM46IiMz26aefIioqCjk5OWjcuLHU4RDVG5xzQ0RkJWfPnkXz5s2Z2BDVMiY3RERWcubMGXTp0kXqMIjqHSY3RERWIITAuXPnqn3YIBFZB+fcEBERkV3hyA0RERHZFSY3REREZFfq3UP89Ho9bty4AVdXV8hkMqnDISIiIhMIIZCfnw9fX1/I5dWPzdS75ObGjRt8hDgREZGNSk1NrXYrE6AeJjeurq4A7lyc2thbhoiIiO5dXl4e/P39Dd/j1al3yU35rSg3NzcmN0RERDbGlCklnFBMREREdoXJDREREdkVJjdERERkV5jcEBERkV1hckNERER2hckNERER2RUmN0RERGRXmNwQERGRXWFyQ0RERHaFyQ0RERHZFUmTm4MHD2Lo0KHw9fWFTCbD1q1b79pm//796N69O5ycnBAUFIQ1a9ZYPU4iIiKyHZImN4WFhQgODsaSJUtMqp+cnIwhQ4bgwQcfREJCAqZMmYLx48dj165dVo6UiIiIbIWkG2cOGjQIgwYNMrn+smXL0KpVK3zyyScAgA4dOuDQoUP49NNPERERYa0wiYiIyIbY1K7gsbGxCA8PNyqLiIjAlClTqmxTWlqK0tJSw/u8vDxrhWcTSkpKoNVqpQ7jnjk6OkKlUkkdBlmQXuixM2knPjn8CQa1GQQPZw8UagqRlJOEA9cOoLd/b3i6eCI9Px2x12Nxv9/98GzgCQDIKszC0bSjCPULRdMGTSstK39/v9/9Ferc3/x+Q50j14/g/ub3w6uBFwDgZuFNHEk7grDmYfBq4IWbhTcRez0WvZv3NqoTez0Wvf17G+ocTj2MPv59jOr8nvp7hbLDqYfRJ6CPod3vKb+jT0AfeDfwBgBkFmYa+vJu6I3Mgkz8nvo7+vr3hXfDP+sUZOJQ6iE8EPCAoc5vKb8Z3hvqpFSs069FP6M6B1MOol9AP/g09AEAZBRkGOr5NPRBRkEGDl47iP4t+hvVOXDtAAa0HGCos//qfsN7Q52rFes82OpBozrl7Zo1bIb0gvQ7dVo+iGauzQAA6fnp2Hd1Hx5q+VDFslZ3ytLz07E3ea/hfXmdvcl7MbDVQEOdmOQYDGw9EL6uvgCAG/k3DHV8XX1xI/8GYpJjEN463KhOzJW/ym7k38CeK3vwf4H/Z1Rn95Xd+L/WFcsebv2wod2vV37Fw4EPw8/VDwCQlp+G3Zd3G8rS8tPw6+VfEREYAT+3P+vkGZel5aVh1+VdFersurILjwQ+Yqiz8/JODAocZFRn5+WdeCToETR3aw4AuJ53HTuTdmJQ0CA0d2uO63nX8UvSLxjcZrBRnV8u/VV2Pe86dlzagSFthxjVOXr9KN4f+D46e3U2428By5EJIYQkR/4HmUyGLVu2YPjw4VXWadu2LSIjIzFz5kxD2Y4dOzBkyBAUFRXB2dm5Qpu5c+fi7bffrlCuVqvh5uZmkdhtRUlJCeLi4qDX66UO5Z7J5XKEhIQwwbFBxdpiXFNfw9Xcq/g95Xf88McPcHZ0xuXbl1GgKTCq66Rwgl7oodVr4aRwglcDL2QVZaGkrATODs5o5toMMsiQnp+OorIiuDi4GH2Z/b2s/H15u/I6xWXFcHZwNnzh/v09AKOy8qSguKwYKgeVUQJSUlYClYPKkKSUlJVApVAZEqmbhTdRqiuFk8LJKLkqL/N08UR2UbbhfROXJgCAW0W3jMr+/t7D2eNOneJb0Og0UCqU8HD2QE5xzp33ciUaOzcGANwuvg2N/k5ZI+dGyC3OhUavgaPcEY1UjQAAuSW50Oq1cJQ7wl3lDgBQl6iNyv7+3s3pzt+heaV5hjJXJ1fkl+ZDq9fCQe4AV6UrACBfk48yfRkc5A5oqGyIAk3BnfcyBzRQNgAAFGgKoBM6KGQKNFA2QKGm0Og9AKMyF0cXAECRtshQ5uzojGJtMXRCB7lMDmeHO98LxWXF0As95DI5VA4qlJSV3HkPOZwcnAAApWWl0OOvsr+/VzooDXUEBGSQQalQQqPTGN47KhwBAFqd1lDmIL8zhqDV//WPSge5A8r0ZYb3CpkCAKATOqOyv7+Xy+7MItGLv/7+lkEGgTrxFV6pwW0GY/vT2y3WX15eHtzd3U37/hZ1BACxZcuWauu0adNGzJs3z6hs+/btAoAoKiqqtE1JSYlQq9WGV2pqqgAg1Gq1pUK3GXl5eWLfvn0iIyND5OXl2ewrIyND7Nu3T+Tl5Ul9SakaRZoicTztuFgZv1K89stroufynkL1rkpgLiq8fD/xFR8c+kBsPrdZhH8TLq7lXhNanVYIIURuca4Yum6oyC3OrfS9qWV1rY7Ux2eM9SvGR9c+Km4X3RZ6vV7o9XqRU5QjHl37qMgpyhE6vU7o9LoKZeXvbxXeEmW6MlGmKxPZhdliyNohIrswW2h1WsP7rIIsoSnTCE2ZRmQVZIlH1z5qFJMlqNVqk7+/bWrkpl+/fujevTsWLVpkKFu9ejWmTJkCtVpt0nHMyvzsTH5+Pk6cOIEePXrA1dVV6nBqzF7Ow97ohR7x6fHYfXk3fr3yKw5dO4Qycedfp22btEVeaR4yCjLQ1bsrPn/kc7Rq3AoNHBsg8qdIfPvYt4aRAiKiypjz/W1Tc27CwsKwY8cOo7Ldu3cjLCxMooiIKCEjAe8dfA8/X/gZGr0GDZUN8WDLB9HWsy3OZZ1DRGAEdj67E+oSNUZvGV0hkdn21DYJoycieyRpclNQUICkpCTD++TkZCQkJMDDwwMBAQGYOXMm0tLS8N///hcAMHHiRHzxxReYNm0ann/+eezduxc//PADtm+33D09Irq70rJSbDy3EUuPL8Xh1MNwUjhBo9fg/ub34+BzB+GocDRKZgDAXeXORIaIaoWkz7k5fvw47rvvPtx3330AgKioKNx3332YM2cOACA9PR0pKSmG+q1atcL27duxe/duBAcH45NPPsHXX3/NZeBEtUQIge9Ofwe/hX54dsuzKNOXYdOITUiLSsPQtkOx85mdhkmV5ckMbzcRUW2TdORmwIABqG7KT2VPHx4wYABOnjxpxaiIqDJXbl/BxP9NxO4ru9Gs4Z3VRp4unni8w+MAeHuJiOoO7i1FVE8IIar9xwRwZ1KwVqc1ehVri/Hh7x+i89LOuHjrIrY/vR3nJ53H0LZDse7xdbUUPRGR6WxqQjHZFp1eh7M3z0Iuk0MhV0AhU0AhV0AIgTJ9GXRCB51eZ3hOg1wmhwwyyGQyw38BGH7W6XXQCR0KCwpx9uZZLNqyCGN6jUHHph3hIHeAo9wRAgJ6ob/zRf6PfuUyuVE/5f8trw/A0Obv9eUyeYU+5DI59EJ/5zz0OpTpy6AX+jtxKBzhKHeEg9wBMpkMQvwZEwRKykpw5fYVXLp1CZdyLuFk+kmczz5veM5ISVkJCjWFKNIWwVFx53zKdHeulYPcAQ5yB8PzLkrLSqGQ33k+Rvn1dJA5QC6XG+podBrIIYceeqPnYyhkCsO5lOnK7lyXvz1TozJjuo7BkiFL0FDZEABHaoio7mJyQ1Yz9Puh+CXpF4v32xAN0RM9cRzH8VPyTxbvvzY4KZwQ5BGE7KJs3C65jUaqRhjVeRRUDiqsO7MOF25dQJtGbTCx50QsP7Ecf2T9gTZN2uDFHi9CL/T46sRXSMxORFuPtnip50tYdnwZ/sj6A+0822Fiz4kQQuDL41/ifPZ5dGjaAZNDJmPpsaU4c/MMOnt1xqRek6DT67D0+FKcyzqHTp6d8Groq/gi7gucuXkGXb27Iur+KADAwiMLcTrzNLKLsw2JDRFRnWbRJ+zYAHMeAmRvyh/iVxsPv9uXvM/wgLbeK3uL31N+FweuHhChK0IF5kKEfR0mDqccFn1W9hGYC9FnZR9x9PpRcST1iOj9dW9DnUPXDomwr8MM74+kHhG/XfpNrNmyRgxcMVDsubxH/HbtN0O/oStCRcyVGLH3yl6jsj2X94hfk34VIctDDGUHrh4w9N17ZW9xJPXIneOvvHP83l/3Njp+6IpQsffKXrHn8h5DP/evuF8cunbI0Cbs6zCxP3m/2HN5j+i1vJfAXIhey3uJXUm7RMiKO20eWvOQ0Ol1Qoi6+bAvUx5IRkRU28z5/mZyU4/UVnKj1WlFl6VdRK/lvSo8pdISX7iVnYetPCWUSQIRUc3Y5BOKawufUHwCHTp0gIuLi9WOs+bkGry17y3seGYHgr2DLd5/UVERzp8/zycUExHVI3b7hGK6N46OjpDL5Th//rzVjlGkLcKOozsw3mc8yq6X4cT1E1Y5jlwuh6Ojo1X6JiIi28bkph5RqVQICQmBVqu9e+UamrFnBk4pTmHp8KXwdPG02nEcHR25IzgREVWKyU09o1KprJYUJGQkYNmZZfj4/z5GK+9WVjkGERHR3fAhfmQRQgiM+2kcGiobYkDLAVKHQ0RE9RiTG7KIE+knEJ8Rj7zSPMzaN0vqcIiIqB7jbSmyiG0XtsHdyR19A/pi7eNrpQ6HiIjqMSY3ZBE/X/wZg9sMxronuNcQERFJi7el6J6lqlORkJGAoW2HSh0KERERkxu6d/+7+D8oZAo8EvSI1KHcs4MHD2Lo0KHw9fWFTCbD1q1b79pm//796N69O5ycnBAUFIQ1a9ZUqLNkyRK0bNkSKpUKoaGhiIuLs3zwREQEgMkNWcDPF3/GAy0eQGPnxlKHcs8KCwsRHByMJUuWmFQ/OTkZQ4YMwYMPPoiEhARMmTIF48ePx65duwx1NmzYgKioKERHRyM+Ph7BwcGIiIjAzZs3rXUaRET1GrdfoHtSqClEkw+bYN7AeYgKi5I6HIuSyWTYsmULhg8fXmWd6dOnY/v27Th79qyhbNSoUcjNzcXOnTsBAKGhoejVqxe++OILAIBer4e/vz9eeeUVzJgxw6rnQERkL7j9AtWa3Vd2o1RXWm/n28TGxiI8PNyoLCIiAlOmTAEAaDQanDhxAjNnzjR8LpfLER4ejtjY2Cr7LS0tRWlpqeG9Xq9HTk4OmjRpAplMZtmToHpJCIH8/Hz4+vpCLucgPtkXJjd0T36+8DPaNWmHNk3aSB2KJDIyMuDt7W1U5u3tjby8PBQXF+P27dvQ6XSV1klMTKyy3/nz5+Ptt9+2SsxEf5eamormzZtLHQaRRTG5oRrTCz22X9qO0V1HSx2K3Zk5cyaiov66zadWqxEQEIDU1FTeTiWLyMvLg7+/P1xdXaUOhcjimNxQjR2/cRyZhZkY2q5+3pICAB8fH2RmZhqVZWZmws3NDc7OzlAoFFAoFJXW8fHxqbJfJycnODk5VSh3c3NjckMWxducZI94o5Vq7OcLP6OxqjF6+/eWOhTJhIWFISYmxqhs9+7dCAsLAwAolUr06NHDqI5er0dMTIyhDhERWRaTG6qx8qcSO8jtZwCwoKAACQkJSEhIAHBnqXdCQgJSUlIA3LldNGbMGEP9iRMn4sqVK5g2bRoSExOxdOlS/PDDD3j99dcNdaKiorBixQp88803OH/+PF566SUUFhYiMjKyVs+NiKi+sJ9vJapVKeoUnMo8hZl9Z969sg05fvw4HnzwQcP78nkvY8eOxZo1a5Cenm5IdACgVatW2L59O15//XV89tlnaN68Ob7++mtEREQY6owcORJZWVmYM2cOMjIy0K1bN+zcubPCJGMiIrIMPueGamTW3lmY99s8/P787wjz5+0Va+PvLVkaf6fI1pjzO8vbUlQjK+NXQkDgvd/ekzoUIiIiI7wtRTXi4ewBJwcnrHucu4ATEVHdwpEbMpsQAsm5yXgt9DW4q9ylDoeIiMgIkxsyW3pBOorLihHkESR1KERERBUwuSGzJeUkAQCTGyIiqpOY3JDZknKSIIMMrRq3kjoUIiKiCpjckNmScpLg7+4PlYNK6lCIiIgqYHJDZkvKSeItKSIiqrOY3JDZknKSENSYyQ0REdVNTG7ILEIIjtwQEVGdxuSGzHKz8CbyNflo06SN1KEQERFViskNmYXLwImIqK5jckNmKU9uWjduLXEkRERElWNyQ2ZJykmCn6sfXBxdpA6FiIioUkxuyCxJtzmZmIiI6jYmN2QWrpQiIqK6jskNmUwIgUu3LjG5ISKiOo3JDZkspzgH6lI1kxsiIqrTmNyQybgMnIiIbAGTGzLZpZxLAIDAxoESR0JERFQ1JjdksqScJPg09IGrk6vUoRAREVWJyQ2ZjCuliIjIFjC5IZMxuSEiIlvA5IZMlpSThKDGTG6IiKhuY3JDJrldfBu3im9x5IaIiOo8Jjdkksu3LwPgMnAiIqr7mNyQScqfcRPowWXgRERUtzG5IZMk5STB08UTjVSNpA6FiIioWkxuyCSXcrinFBER2QYmN2SSpJwktPFoI3UYREREd8XkhkzCZ9wQEZGtkDy5WbJkCVq2bAmVSoXQ0FDExcVVWVer1eKdd95BYGAgVCoVgoODsXPnzlqMtn7KK83DzcKbTG6IiMgmSJrcbNiwAVFRUYiOjkZ8fDyCg4MRERGBmzdvVlp/1qxZ+Oqrr7B48WKcO3cOEydOxGOPPYaTJ0/WcuT1y6+Xf73zg5A2DiIiIlNImtwsXLgQEyZMQGRkJDp27Ihly5bBxcUFq1atqrT+t99+izfffBODBw9G69at8dJLL2Hw4MH45JNPajny+uWjwx8BAL4++bXEkRAREd2dZMmNRqPBiRMnEB4e/lcwcjnCw8MRGxtbaZvS0lKoVCqjMmdnZxw6dKjK45SWliIvL8/oReaZ1GsSAGDVvypPOomIiOoSyZKb7Oxs6HQ6eHt7G5V7e3sjIyOj0jYRERFYuHAhLl26BL1ej927d2Pz5s1IT0+v8jjz58+Hu7u74eXv72/R86gPyvRlAIDmbs0ljoSIiOjuJJ9QbI7PPvsMbdq0Qfv27aFUKjF58mRERkZCLq/6NGbOnAm1Wm14paam1mLE9kFdokYDxwZwkDtIHQoREdFdSZbceHp6QqFQIDMz06g8MzMTPj4+lbZp2rQptm7disLCQly7dg2JiYlo2LAhWrduXeVxnJyc4ObmZvQi8+SW5PLJxEREZDMkS26USiV69OiBmJgYQ5ler0dMTAzCwsKqbatSqeDn54eysjJs2rQJ//rXv6wdbr2mLlXDXeUudRhEREQmkfQ+Q1RUFMaOHYuePXsiJCQEixYtQmFhISIjIwEAY8aMgZ+fH+bPnw8AOHr0KNLS0tCtWzekpaVh7ty50Ov1mDZtmpSnYffUpWq4OzG5ISIi2yBpcjNy5EhkZWVhzpw5yMjIQLdu3bBz507DJOOUlBSj+TQlJSWYNWsWrly5goYNG2Lw4MH49ttv0ahRI4nOoH5Ql3DkhoiIbIdMCFGvHs2Wl5cHd3d3qNVqzr8x0cD/DkRTl6ZY/+/1UodSb/H3liyNv1Nka8z5nbWp1VIkDXWJmhOKiYjIZjC5obvKLcnlnBsiIrIZTG7orurbailLb+aan5+PKVOmoEWLFnB2dkbv3r1x7Ngxa58GEVG9xeSGqiWEuDOhuJ6M3FhjM9fx48dj9+7d+Pbbb3HmzBk8/PDDCA8PR1paWm2dFhFRvcLkhqpVUlYCrV5bb0ZuLL2Za3FxMTZt2oQPP/wQ/fr1Q1BQEObOnYugoCB8+eWXtXlqRET1BpMbqpa6VA0A9WJCsTU2cy0rK4NOp+OGr0REtYjJDVUrtyQXAOrFbSlrbObq6uqKsLAwvPvuu7hx4wZ0Oh2+++47xMbGcsNXIiIrYXJD1VKX3Bm5qS+3pcxlymau3377LYQQ8PPzg5OTEz7//HM89dRT3PCViMhKmNxQtcpvS9WHkRtrbeYaGBiIAwcOoKCgAKmpqYiLi4NWq+WGr0REVsLkhqpVn0ZurL2Za4MGDdCsWTPcvn0bu3bt4oavRERWIuneUlT3lY/cuCpdJY6kdlhjM9ddu3ZBCIF27dohKSkJU6dORfv27Q19EhGRZTG5oWrlluTCzckNCrlC6lBqhTU2c1Wr1Zg5cyauX78ODw8PPPHEE3j//ffh6OhY26dHRFQvcONMqtbsvbPxzalvkPJ6itSh1Gv8vSVL4+8U2RpunEkWU9+2XiAiItvH5IaqpS6tP1svEBGRfWByQ9VSl3DkhoiIbAuTG6pWbkluvdh6gYiI7AeTG6oWb0sREZGtYXJD1VKXMLkhIiLbwuSGqsXVUkREZGuY3FCVhBAcuSEiIpvD5IaqVKQtgk7oOKGYiIhsCpMbqlJuSS6A+rFpJhER2Y8aJTe//fYbnn32WYSFhSEtLQ0A8O233+LQoUMWDY6kVb5pJm9LERGRLTE7udm0aRMiIiLg7OyMkydPorS0FMCdzQHnzZtn8QBJOuqSP5MbjtwQEZENMTu5ee+997Bs2TKsWLHCaFfjPn36ID4+3qLBkbQ4ckNERLbI7OTmwoUL6NevX4Vyd3d35ObmWiImqiPKR244oZiIiGyJ2cmNj48PkpKSKpQfOnQIrVu3tkhQVDfkluRCLpOjobKh1KEQERGZzOzkZsKECXjttddw9OhRyGQy3LhxA2vXrsUbb7yBl156yRoxkkTUpWq4OblBJpNJHQoREZHJHMxtMGPGDOj1egwcOBBFRUXo168fnJyc8MYbb+CVV16xRowkET7Aj+xR9L5oLDqyCD6uPvBw9oCzgzOcHZ3h7OAMF0cXo/d/L79VdAs7knZgQIsBaOTcCMXaYpSUlaC4rPjOz7oSFGuLUVz2Z7m2GDnFOUgvSIdXAy80cGwAB7kDFHIFFDJFtT8XaApw8dZFdPLqBA9nD8hlcihkCshl8oo/y//6+VbRLRy5fgRdvbvCRemCkrKSKl9FBUVS/1EQWY3ZyY1MJsNbb72FqVOnIikpCQUFBejYsSMaNuStC3vDrRfIHi2OW4w8TR4alzVGB88OhuQkX5OPm4U3De/L/1ukLUJxWTE0Og0A4NiNY2isagxnR2eoHFRwdvjzv38mQioHFdwauMHZwRkxyTHIK82Dh8oDfVr3gU7oUKYvg07ooNNX/nNxWTFOpp9EdnE28jX56OzVGTq9Dnqhh17ooRN/+/kf5dfzrqNIW4Qb+TfQyasTVA4qQ4yNVY0N71UOKshKZViIhRL/aRBZh9nJTTmlUomOHTtaMhaqY9Slak4mJrui1WlRrC1GR8+OODzusFnJ++3i2xizZQy+e/w7k9upS9QYvWU0vn3sW7OOVRvt8vLymNyQ3TIpuXn88cdN7nDz5s01DobqltySXN6WIrty9uZZlOhK8NXQr8welWzs3Bg/P/2zWW3cVe7Y9tQ2s9pI0Y7I3pg0odjd3d3wcnNzQ0xMDI4fP274/MSJE4iJiYG7O78I7Ym6hLelyL7EpcVBIVOge7PuUodCRFZk0sjN6tWrDT9Pnz4dI0aMwLJly6BQKAAAOp0OL7/8Mtzc3KwTJUlCXcoJxWRfjqYdRRfvLnBxdJE6FCKyIrOXgq9atQpvvPGGIbEBAIVCgaioKKxatcqiwZG0uFqK7E1cWhxC/UKlDoOIrMzs5KasrAyJiYkVyhMTE6HX6y0SFNUNXC1F9iS/NB/nss4hxC9E6lCIyMrMXi0VGRmJcePG4fLlywgJufOXxNGjR7FgwQJERkZaPECShl7ooS7haimyH8dvHIeA4MgNUT1gdnLz8ccfw8fHB5988gnS09MBAM2aNcPUqVPxn//8x+IBkjQKNAUQELwtRXYjLi0ODZUN0d6zvdShEJGVmZ3cyOVyTJs2DdOmTUNeXh4AcCKxHSrfNJO3pcheHE07ip6+PaGQK+5emYhsmtlzbv7Ozc2NiY2dUpf+mdxw5IbsBCcTE9UfNXpC8caNG/HDDz8gJSUFGo3G6LP4+HiLBEbS4sgN2ZO0vDSk5adxMjFRPWH2yM3nn3+OyMhIeHt74+TJkwgJCUGTJk1w5coVDBo0yBoxkgTKR244oZjsQVxaHABw5IaonjA7uVm6dCmWL1+OxYsXQ6lUYtq0adi9ezdeffVVqNVqa8RIEsgtyQXA21JkH46mHYWvqy/83PykDoWIaoHZyU1KSgp69+4NAHB2dkZ+fj4AYPTo0fj+++8tGx1JRl2ihkKm4JNcyS5wvg1R/WJ2cuPj44OcnBwAQEBAAI4cOQIASE5OhhDCstGRZMof4CeTyaQOheie6PQ6HL9xnPNtiOoRs5Obhx56CNu23dl1NjIyEq+//jr+7//+DyNHjsRjjz1m8QBJGtx6gexFYnYi8jX5HLkhqkfMXi21fPlywzYLkyZNQpMmTXD48GEMGzYML774osUDJGmoS/l0YrIPcWlxkEGGHr49pA6FiGpJjR7iJ5f/NeAzatQojBo1yqJBkfRyS3K5DJzswtG0o+jQtAPcnPhMLqL6wqTk5vTp0yZ32LVr1xoHQ3WHupS3pcg+cDIxUf1jUnLTrVs3yGQyCCHuOsFUp9NZJDCSlrpEjUCPQKnDILonRdoinM48jRd6vCB1KERUi0yaUJycnIwrV64gOTkZmzZtQqtWrbB06VKcPHkSJ0+exNKlSxEYGIhNmzZZO16qJRy5IXtwMv0kdELHkRuiesakkZsWLVoYfn7yySfx+eefY/DgwYayrl27wt/fH7Nnz8bw4cMtHiTVPnUJJxST7TuadhQqBxU6e3WWOhQiqkVmLwU/c+YMWrVqVaG8VatWOHfunEWCIunlluRy5IZsXlxaHHo06wFHhaPUoRBRLTI7uenQoQPmz59vtGGmRqPB/Pnz0aFDB4sGR9LQ6XXI1+RztRTZvLi0OD68j6geMnsp+LJlyzB06FA0b97csDLq9OnTkMlk+Pnnny0eINW+fM2dLTU4ckO2LKswC8m5yUxuiOohs0duQkJCcOXKFbz33nvo2rUrunbtivfffx9XrlxBSIj5f4ksWbIELVu2hEqlQmhoKOLi4qqtv2jRIrRr1w7Ozs7w9/fH66+/jpKSErOPS1VTl9zZAJUjN2TLuBM4Uf1ldnIDAA0aNMALL7yAhQsXYuHChZgwYQIaNGhgdj8bNmxAVFQUoqOjER8fj+DgYERERODmzZuV1l+3bh1mzJiB6OhonD9/HitXrsSGDRvw5ptv1uQ0qArq0jvJTX2dUGxOwq3VavHOO+8gMDAQKpUKwcHB2Llzp1EdnU6H2bNno1WrVnB2dkZgYCDeffdd7sVmZUfTjsLTxRMtG7WUOhQiqmUm3Zbatm0bBg0aBEdHR8O+UlUZNmyYyQcvT4wiIyMB3LnltX37dqxatQozZsyoUP/w4cPo06cPnn76aQBAy5Yt8dRTT+Ho0aMmH5PuLrckF0D9vC1VnnAvW7YMoaGhWLRoESIiInDhwgV4eXlVqD9r1ix89913WLFiBdq3b49du3bhsccew+HDh3HfffcBAD744AN8+eWX+Oabb9CpUyccP34ckZGRcHd3x6uvvlrbp1hvlD+8j5u/EtVDwgQymUxkZmYafq7qJZfLTelOCCFEaWmpUCgUYsuWLUblY8aMEcOGDau0zdq1a4W7u7s4evSoEEKIy5cvi/bt24v333+/yuOUlJQItVpteKWmpgoAQq1WmxxrfbMtcZvAXIj0/HSpQ6l1ISEhYtKkSYb3Op1O+Pr6ivnz51dav1mzZuKLL74wKnv88cfFM888Y3g/ZMgQ8fzzz1db527UajV/b82g1+tF4wWNxdv735Y6lDqLv1Nka8z5nTXptpRerzf8q1Wv11f5MufpxNnZ2dDpdPD29jYq9/b2RkZGRqVtnn76abzzzjvo27cvHB0dERgYiAEDBlR7W2r+/Plwd3c3vPz9/U2Osb4qvy1V30ZuNBoNTpw4gfDwcEOZXC5HeHg4YmNjK21TWloKlUplVObs7IxDhw4Z3vfu3RsxMTG4ePEiAODUqVM4dOgQBg0aZIWzIABIyknC7ZLbnG9DVE+ZvVpKSvv378e8efOwdOlShIaGIikpCa+99hreffddzJ49u9I2M2fORFRUlOF9Xl4eE5y7UJeo4Sh3hMpBdffKdqS6hDsxMbHSNhEREVi4cCH69euHwMBAxMTEYPPmzUaJ/owZM5CXl4f27dtDoVBAp9Ph/fffxzPPPFNlLKWlpSgtLTW8V6vvJJx5eXn3cor1xv4L+4ESoJ1rO16zKpRfF8G5X2SHTEpuPv/8c5M7NHUOgaenJxQKBTIzM43KMzMz4ePjU2mb2bNnY/To0Rg/fjwAoEuXLigsLMQLL7yAt956y2i38nJOTk5wcnIyOX76c+sFlTvnKpjgs88+w4QJE9C+fXvIZDIEBgYiMjISq1atMtT54YcfsHbtWqxbtw6dOnVCQkICpkyZAl9fX4wdO7bSfufPn4+33367QjkTc/O0WlDxgaNk7NatW3B3r1+jtGT/TEpuPv30U5M6k8lkJic3SqUSPXr0QExMjGHLBr1ej5iYGEyePLnSNkVFRRUSGIVCAYD/+rCk+rr1Qk0S7qZNm2Lr1q0oKSnBrVu34OvrixkzZqB169aGOlOnTsWMGTMwatQoAHeS8mvXrmH+/PlVJjf/HHHU6/XIyclBkyZNTE46y0cpU1NT4ebmZlIbe8brYUytViMgIAAeHh5Sh0JkcSYlN8nJyVY5eFRUFMaOHYuePXsiJCQEixYtQmFhoWH11JgxY+Dn54f58+cDAIYOHYqFCxfivvvuM9yWmj17NoYOHWpIcuje1detF2qScJdTqVTw8/ODVqvFpk2bMGLECMNnVSXler2+yv4qG3Fs1KiReSf0Jzc3N36Z/w2vh7HKRryJbF2N59xoNBokJycjMDAQDg4162bkyJHIysrCnDlzkJGRgW7dumHnzp2GOQ8pKSlG/+PNmjULMpkMs2bNQlpaGpo2bYqhQ4fi/fffr+lpUCXKb0vVR+Ym3EePHkVaWhq6deuGtLQ0zJ07F3q9HtOmTTP0Wf47GhAQgE6dOuHkyZNYuHAhnn/+eUnOkYjI7pm7FKuwsFA8//zzQqFQCIVCIS5fviyEEGLy5MlVLpetS7j88e4e+e4R8dj6x6QOQzKLFy8WAQEBQqlUipCQEHHkyBHDZ/379xdjx441vN+/f7/o0KGDcHJyEk2aNBGjR48WaWlpRv3l5eWJ1157TQQEBAiVSiVat24t3nrrLVFaWmrV8+DvujFeD2O8HmRrzPmdNXvIZebMmTh16hT279+PRx55xFAeHh6OuXPnVvrwPbIt6fnpyNfk4+zNs+js1VnqcGrd5MmTq7wNtX//fqP3/fv3x7lz56rtz9XVFYsWLcKiRYssFKFpnJycEB0dzQn1f+L1MMbrQfZMJoR5M3FbtGiBDRs24P7774erqytOnTqF1q1bIykpCd27d6/zyy7z8vLg7u4OtVrN++5VcJvvhnxNPga3GYztT2+XOhwiIiKzvr/NHrnJysqq9DH0hYWFXDpsJ7waeKFpg6ZY9/g6qUMhIiIym9nT5Hv27Int2//613x5QvP1118jLCzMcpGRZEp1pXi2y7P1dlIxERHZNrNHbubNm4dBgwbh3LlzKCsrw2effYZz587h8OHDOHDggDVipFpWrC2Gs6Oz1GEQERHViNkjN3379kVCQgLKysrQpUsX/Prrr/Dy8kJsbCx69OhhjRiplhVpi+Di6CJ1GERERDVSo6c3BQYGYsWKFYiLi8O5c+fw3XffoUuXLpaOjSQghEBxWTGcHThyUxcsWbIELVu2hEqlQmhoKOLi4qqt/+OPP6J9+/ZQqVTo0qULduzYYfT55s2b8fDDDxuedJyQkFChj5KSEkyaNAlNmjRBw4YN8cQTT1R4arMUpLgWAwYMgEwmM3pNnDjRkqdVY5a8HlqtFtOnT0eXLl3QoEED+Pr6YsyYMbhx44ZRHzk5OXjmmWfg5uaGRo0aYdy4cSgoKLDK+RHdC5OSm7y8PJNfZNtKykoAgCM3dcCGDRsQFRWF6OhoxMfHIzg4GBEREbh582al9Q8fPoynnnoK48aNw8mTJzF8+HAMHz4cZ8+eNdQpLCxE37598cEHH1R53Ndffx0///wzfvzxRxw4cAA3btzA448/bvHzM4dU1wIAJkyYgPT0dMPrww8/tOi51YSlr0dRURHi4+Mxe/ZsxMfHY/Pmzbhw4QKGDRtm1M8zzzyDP/74A7t378b//vc/HDx4EC+88ILVz5fIbKY8OEcmkwm5XG7Sq67jg6uql12YLTAXYvO5zVKHUu+FhISISZMmGd7rdDrh6+tb5cMyR4wYIYYMGWJUFhoaKl588cUKdZOTkwUAcfLkSaPy3Nxc4ejoKH788UdD2fnz5wUAERsbew9nc2+kuBZC3Hlo42uvvXZPsVuDNa9Hubi4OAFAXLt2TQghxLlz5wQAcezYMUOdX375RchksgoPriSyBnO+v00audm3bx/27t2LvXv3YtWqVfDy8sK0adOwZcsWbNmyBdOmTYO3t7fRTshkm4rLigGAE4olptFocOLECYSHhxvK5HI5wsPDERsbW2mb2NhYo/oAEBERUWX9ypw4cQJardaon/bt2yMgIMCsfixJqmtRbu3atfD09ETnzp0xc+ZMFBUVmd2HJdXW9VCr1ZDJZIY9zWJjY9GoUSP07NnTUCc8PBxyuRxHjx69hzMisjyTVkv179/f8PM777yDhQsX4qmnnjKUDRs2DF26dMHy5cur3OWYbEOR9s5f3LwtJa3s7GzodDrDPmvlvL29kZiYWGmbjIyMSutnZGSYfNyMjAwolcoKm3Sa248lSXUtAODpp59GixYt4Ovri9OnT2P69Om4cOECNm/ebN5JWFBtXI+SkhJMnz4dTz31lOFhaRkZGRWecebg4AAPDw/JfjeIqmL2UvDY2FgsW7asQnnPnj0xfvx4iwRF0inW/jlywwnFREbzSbp06YJmzZph4MCBuHz5MgIDAyWMzHq0Wi1GjBgBIQS+/PJLqcMhqhGzkxt/f3+sWLGiwqS6r7/+Gv7+/hYLjKTBkZu6wdPTEwqFosIqpczMTPj4+FTaxsfHx6z6VfWh0WiQm5trNHpjbj+WJNW1qExoaCgAICkpSbLkxprXozyxuXbtGvbu3Wv0iHsfH58KE5bLysqQk5Mj2e9GTeh0Omi1WqnDoCoolUrI5TVayG3E7OTm008/xRNPPIFffvnF8D96XFwcLl26hE2bNt1zQCSt8uSGc26kpVQq0aNHD8TExGD48OEAAL1ej5iYmCo39QwLC0NMTAymTJliKNu9e7dZTw7v0aMHHB0dERMTgyeeeAIAcOHCBaSkpEj2BHKprkVlypeLN2vW7J76uRfWuh7lic2lS5ewb98+NGnSpEIfubm5OHHihOGZZnv37oVerzd8F9RlQghkZGQgNzdX6lCoGnK5HK1atYJSqbynfsxObgYPHoyLFy/iyy+/NNzfHTp0KCZOnMiRGztQPqGYIzfSi4qKwtixY9GzZ0+EhIRg0aJFKCwsRGRkJABgzJgx8PPzw/z58wEAr732Gvr3749PPvkEQ4YMwfr163H8+HEsX77c0GdOTg5SUlIMzy+5cOECgDv/Kvfx8YG7uzvGjRuHqKgoeHh4wM3NDa+88grCwsJw//331/IV+IsU1+Ly5ctYt24dBg8ejCZNmuD06dN4/fXX0a9fP3Tt2rWWr4AxS18PrVaLf//734iPj8f//vc/6HQ6wzwaDw8PKJVKdOjQAY888ggmTJiAZcuWQavVYvLkyRg1ahR8fX2luRBmKE9svLy84OLiwr0Q6yC9Xo8bN24gPT0dAQEB9/ZnZPW1W3UMl4JXb8PZDQJzIdQlvD51weLFi0VAQIBQKpUiJCREHDlyxPBZ//79xdixY43q//DDD6Jt27ZCqVSKTp06ie3btxt9vnr1agGgwis6OtpQp7i4WLz88suicePGwsXFRTz22GMiPT3dmqdpktq+FikpKaJfv37Cw8NDODk5iaCgIDF16tQ683eHJa9H+XL4yl779u0z1Lt165Z46qmnRMOGDYWbm5uIjIwU+fn51j7Ve1ZWVibOnTsnsrOzpQ6F7iI3N1ecO3dOaDSaCp+Z8/0tE0KIuyVAp0+fRufOnSGXy3H69Olq60r9L5q7MWfL9Prom4Rv8NxPz0EzSwNHhaPU4RAR3bOSkhIkJyejZcuWcHbmLfe6rLi4GFevXkWrVq2gUqmMPjPn+9uk21LdunUzLAPs1q0bZDIZKsuJZDIZdDqdGadBdU2RtggOcgcmNkRkd3grqu6z1J+RSclNcnIymjZtaviZ7Bf3lSIiIltnUnLz2GOPISYmBo0bN8Y333yDN954Ay4unHBqj7gjOBER2TqTFpOfP38ehYWFAIC3336bu8DaMSY3RERk60yecxMZGYm+fftCCIGPP/4YDRs2rLTunDlzLBog1a5ibTGfcUNEVA8tWbIEH330ETIyMhAcHIzFixcjJCTkntocPHgQH330EU6cOIH09HRs2bLF8HwmazIpuVmzZg2io6Pxv//9DzKZDL/88gscHCo2lclkTG5sHEduiIjqnw0bNiAqKgrLli1DaGgoFi1ahIiICFy4cKHCnmLmtCksLERwcDCef/55PP7447V2PiYtBf87uVxe6QZqtoJLwas3ZssYXM29ioORB6UOhYjIIsqXgle2vNgWtG3bFk2aNMHevXsNS9mFEAgLC8ODDz5oeFjjvQgNDUWvXr3wxRdfALjzQD1/f3+88sormDFjhkXayGSyu47cVPdnZc73t9kbOOj1eptNbOjuOHJDRFS3bNiwAfHx8fj9998NZWvXrsW1a9fw5ptvGsrmzZuHhg0bVvtKSUmp0L9Go8GJEycQHh5uKJPL5QgPD0dsbGylMdWkTW0ye/sFsm9F2iLOuSGieqFIW4TE7ESz2yXlJOGbU99gbPBYBHkEmd2+vWd7s/4Red9996Fbt25ITExEeHg4ioqKMHPmTLz33ntwdXU11Js4cSJGjBhRbV+VbZWRnZ0NnU4Hb29vo3Jvb2/DNkuWaFObmNyQkeKyYjR2bix1GEREVpeYnYgey3vUuP2OSztq1O7ECyfQvVl3s9q0bdvWsP/Zhx9+CE9PT8NeYuU8PDzg4eFRo5jsDZMbMlKkLYKLA29LEZH9a+/ZHideOGF2u3xNPmbvnY13H3oXrkrXuzeo5LjmateuHQ4ePIjr16/jo48+wvbt2yGXG88smTdvHubNm1dtP+fOnUNAQIBRmaenJxQKBTIzM43KMzMz4ePjU2k/NWlTm5jckBEuBSei+sLF0cXsEZRytb3oom3btlixYgVmzJiBhx9+GAMGDKhQp6a3pZRKJXr06IGYmBjDZF+9Xo+YmBhMnjy50n5q0qY21Si5yc3NxcaNG3H58mVMnToVHh4eiI+Ph7e3N/z8/CwdI9UiTigmIqp72rZti9TUVGzcuBFnz56ttM693JaKiorC2LFj0bNnT4SEhGDRokUoLCw0uvX1xRdfYMuWLYiJiTG5TUFBAZKSkgzvk5OTkZCQAA8PjwojSJZkdnJz+vRphIeHw93dHVevXsWECRPg4eGBzZs3IyUlBf/973+tESfVEu4tRURU97Rt2xYAMHnyZAQFmT+J+W5GjhyJrKwszJkzBxkZGejWrRt27txpNGE4Ozsbly9fNqvN8ePH8eCDDxreR0VFAQDGjh2LNWvWWPw8ypn9nJvw8HB0794dH374IVxdXXHq1Cm0bt0ahw8fxtNPP42rV69aKVTL4HNuqtf4g8Z4s++bmNpnqtShEBFZhK0/5wYAcnJy0KRJE5w6dQpdu3aVOhyrkew5N8eOHcOLL75YodzPzw8ZGRnmdkd1DJeCExHVPadOnYJSqUSHDh2kDsUmmJ3cODk5IS8vr0L5xYsX0bRpU4sERdLQ6XXQ6DScc0NEVMecOnUKHTt2hKOjo9Sh2ASzk5thw4bhnXfegVarBXDnccopKSmYPn06nnjiCYsHSLWnuKwYAJjcEBHVMVOmTMHJkyelDsNmmJ3cfPLJJygoKICXlxeKi4vRv39/BAUFwdXVFe+//741YqRaUqy9k9xwQjEREdkys1dLubu7Y/fu3Th06BBOnz6NgoICdO/e3Wh/CbJNRdoiABy5ISIi21bjh/j17dsXffv2tWQsJLHy5IYTiomIyJaZlNx8/vnnJnf46quv1jgYkhbn3BCRPTPzySckAUv9GZmU3Hz66adG77OyslBUVIRGjRoBuPPEYhcXF3h5eTG5sWG8LUVE9qh8hVFRURGcnTkyXZdpNBoAgEKhuKd+TEpukpOTDT+vW7cOS5cuxcqVK9GuXTsAwIULFzBhwoRKn39DtoMTionIHikUCjRq1Ag3b94EALi4uEAmk0kcFf2TXq9HVlYWXFxc4OBwb1tfmt169uzZ2LhxoyGxAe7sVvrpp5/i3//+N5555pl7Coikw5EbIrJX5TtVlyc4VDfJ5XIEBATcc/JpdnKTnp6OsrKyCuU6na7C1udkW8rn3HBCMRHZG5lMhmbNmsHLy8vwnDaqe5RKJeRys59SU4HZyc3AgQPx4osv4uuvv0b37ne2ij9x4gReeuklLge3cYbVUrwtRUR2SqFQ3PN8Dqr7zE6PVq1aBR8fH/Ts2RNOTk5wcnJCSEgIvL298fXXX1sjRqolRdoiKBVKKOT8H5+IiGyX2SM3TZs2xY4dO3Dp0iWcP38eANC+fXvDduxku4q1xZxvQ0RENq/G05HbtGmDNm3aWDIWkliRtojJDRER2bx7n7VDdqO4rJjzbYiIyOYxuSEDjtwQEZE9YHJDBkXaIi4DJyIim8fkhgyKyzihmIiIbJ/Zyc3OnTtx6NAhw/slS5agW7duePrpp3H79m2LBke1i7eliIjIHpid3EydOhV5eXkAgDNnzuA///kPBg8ejOTkZERFRVk8QKo9xVpOKCYiIttn9lLw5ORkdOzYEQCwadMmPProo5g3bx7i4+MxePBgiwdItadIWwSvBl5Sh0FERHRPzB65USqVKCq685j+PXv24OGHHwYAeHh4GEZ0yDZxKTgREdkDs0du+vbti6ioKPTp0wdxcXHYsGEDAODixYto3ry5xQOk2sM5N0REZA/MHrn54osv4ODggI0bN+LLL7+En58fAOCXX37BI488UqMglixZgpYtW0KlUiE0NBRxcXFV1h0wYABkMlmF15AhQ2p0bPoLl4ITEZE9MHvkJiAgAP/73/8qlH/66ac1CmDDhg2IiorCsmXLEBoaikWLFiEiIgIXLlyAl1fF+R+bN2+GRqMxvL916xaCg4Px5JNP1uj49BfuLUVERPagRs+5uXz5MmbNmoWnnnoKN2/eBHBn5OaPP/4wu6+FCxdiwoQJiIyMRMeOHbFs2TK4uLhg1apVldb38PCAj4+P4bV79264uLgwubEA3pYiIiJ7YHZyc+DAAXTp0gVHjx7F5s2bUVBQAAA4deoUoqOjzepLo9HgxIkTCA8P/ysguRzh4eGIjY01qY+VK1di1KhRaNCggVnHpoo4oZiIiOyB2cnNjBkz8N5772H37t1QKpWG8oceeghHjhwxq6/s7GzodDp4e3sblXt7eyMjI+Ou7ePi4nD27FmMHz++yjqlpaXIy8szelFFWp0WZfoyjtwQEZHNMzu5OXPmDB577LEK5V5eXsjOzrZIUKZauXIlunTpgpCQkCrrzJ8/H+7u7oaXv79/LUZoO4q0d5b3c0IxERHZOrOTm0aNGiE9Pb1C+cmTJw0rp0zl6ekJhUKBzMxMo/LMzEz4+PhU27awsBDr16/HuHHjqq03c+ZMqNVqwys1NdWsGOuL4rJiAODIDRER2Tyzk5tRo0Zh+vTpyMjIgEwmg16vx++//4433ngDY8aMMasvpVKJHj16ICYmxlCm1+sRExODsLCwatv++OOPKC0txbPPPlttPScnJ7i5uRm9qKLykRsmN0REZOvMTm7mzZuH9u3bw9/fHwUFBejYsSP69euH3r17Y9asWWYHEBUVhRUrVuCbb77B+fPn8dJLL6GwsBCRkZEAgDFjxmDmzJkV2q1cuRLDhw9HkyZNzD4mVVSsvTNywwnFRERk68x6zo0QAhkZGfj8888xZ84cnDlzBgUFBbjvvvvQpk2bGgUwcuRIZGVlYc6cOcjIyEC3bt2wc+dOwyTjlJQUyOXGOdiFCxdw6NAh/PrrrzU6JlXEkRsiIrIXMiGEMLWyXq+HSqXCH3/8UeNkRmp5eXlwd3eHWq3mLaq/OXD1AAZ8MwAXJl9A2yZtpQ6HiIjIiDnf32bdlpLL5WjTpg1u3bp1TwFS3cMJxUREZC/MnnOzYMECTJ06FWfPnrVGPCQRw1JwzrkhIiIbZ/beUmPGjEFRURGCg4OhVCrh7Gz8ZZiTk2Ox4Kj2lE8o5sgNERHZOrOTm0WLFlkhDJJa+ciNykElcSRERET3xuzkZuzYsdaIgyRWvq+UTCaTOhQiIqJ7YnZyAwA6nQ5bt27F+fPnAQCdOnXCsGHDoFAoLBoc1R7uCE5ERPbC7OQmKSkJgwcPRlpaGtq1awfgzv5N/v7+2L59OwIDAy0eJFlfkbaI+0oREZFdMHu11KuvvorAwECkpqYiPj4e8fHxSElJQatWrfDqq69aI0aqBcXaYo7cEBGRXTB75ObAgQM4cuQIPDw8DGVNmjTBggUL0KdPH4sGR7WnSFvEZeBERGQXzB65cXJyQn5+foXygoICKJVKiwRFta+4jCM3RERkH8xObh599FG88MILOHr0KIQQEELgyJEjmDhxIoYNG2aNGKkWcEIxERHZC7OTm88//xyBgYEICwuDSqWCSqVCnz59EBQUhM8++8waMVIt4IRiIiKyF2bPuWnUqBF++uknXLp0CYmJiQCADh06ICgoyOLBUe0pLiuGh7PH3SsSERHVcTV6zg0AtGnTxmZ3BqeKirRF8HP1kzoMIiKie2ZSchMVFWVyhwsXLqxxMCQdLgUnIiJ7YVJyc/LkSZM646P7bRcnFBMRkb0wKbnZt2+fteMgiZXvLUVERGTrzF4tRfaJIzdERGQvajSh+Pjx4/jhhx+QkpICjUZj9NnmzZstEhjVLi4FJyIie2H2yM369evRu3dvnD9/Hlu2bIFWq8Uff/yBvXv3wt3d3RoxkpUJITihmIiI7IbZyc28efPw6aef4ueff4ZSqcRnn32GxMREjBgxAgEBAdaIkaysVFcKAcE5N0REZBfMTm4uX76MIUOGAACUSiUKCwshk8nw+uuvY/ny5RYPkKyvWFsMABy5ISIiu2B2ctO4cWPDxpl+fn44e/YsACA3NxdFRUWWjY5qRZH2zp8bkxsiIrIHZk8o7tevH3bv3o0uXbrgySefxGuvvYa9e/di9+7dGDhwoDViJCsrT244oZiIiOyBycnN2bNn0blzZ3zxxRcoKSkBALz11ltwdHTE4cOH8cQTT2DWrFlWC5Ssp7iMt6WIiMh+mJzcdO3aFb169cL48eMxatQoAIBcLseMGTOsFhzVDsPIDScUExGRHTB5zs2BAwfQqVMn/Oc//0GzZs0wduxY/Pbbb9aMjWoJJxQTEZE9MTm5eeCBB7Bq1Sqkp6dj8eLFuHr1Kvr374+2bdvigw8+QEZGhjXjJCvihGIiIrInZq+WatCgASIjI3HgwAFcvHgRTz75JJYsWYKAgAAMGzbMGjGSlZXPueGEYiIisgf3tLdUUFAQ3nzzTcyaNQuurq7Yvn27peKiWsSRGyIisic12lsKAA4ePIhVq1Zh06ZNkMvlGDFiBMaNG2fJ2KiWFGmLIJfJ4Sh3lDoUIiKie2ZWcnPjxg2sWbMGa9asQVJSEnr37o3PP/8cI0aMQIMGDawVI1lZ+b5SMplM6lCIiIjumcnJzaBBg7Bnzx54enpizJgxeP7559GuXTtrxka1pEhbxGXgRERkN0xObhwdHbFx40Y8+uijUCgU1oyJallxGXcEJyIi+2FycrNt2zZrxkESKtIWMbkhIiK7cU+rpcg+FGmLuAyciIjsBpMb4m0pIiKyK0xuiBOKiYjIrjC5IcNScCIiInvA5IY454aIiOwKkxu6M+fGgSM3RERkH5jcEJeCExGRXWFyQ7wtRUREdoXJDXFCMRER2RUmN8Sl4EREZFeY3BAf4kdERHaFyU09pxd6lJSVMLkhIiK7weSmnivWFgMAJxQTEZHdYHJTzxWX3UluOHJDRET2gslNPVekLQIATigmIiK7weSmniu/LcWRGyIishdMbuo5w8gN59wQEZGdYHJTz3HODRER2RsmN/Vc+cgNkxsiIrIXTG7qMSEE9l/dDwC4mntV0liIiIgsxUHqAKj2Xci+gLVn1mLdmXW4fPsyAODD3z/EgJYDpA2MiIjIAiQfuVmyZAlatmwJlUqF0NBQxMXFVVs/NzcXkyZNQrNmzeDk5IS2bdtix44dtRStbcsvzUfvlb3Rfkl7LIxdiP4t+uOnUT/h0TaP4vsnvpc6PCIiIouQdORmw4YNiIqKwrJlyxAaGopFixYhIiICFy5cgJeXV4X6Go0G//d//wcvLy9s3LgRfn5+uHbtGho1alT7wduYkrIS/Gv9vxCXdid5fKDFA1j5r5UAgGHthkkZGhERkUXJhBBCqoOHhoaiV69e+OKLLwAAer0e/v7+eOWVVzBjxowK9ZctW4aPPvoIiYmJcHR0rNEx8/Ly4O7uDrVaDTc3t3uK31ZodVo88cMT2HNlDzaN2IQvj3+Jbx/7Fu4qd6lDIyIiMok539+S3ZbSaDQ4ceIEwsPD/wpGLkd4eDhiY2MrbbNt2zaEhYVh0qRJ8Pb2RufOnTFv3jzodLraCtvm6IUez/30HHYm7cTmkZsxqM0gbHtqGxMbIiKyW5LdlsrOzoZOp4O3t7dRube3NxITEyttc+XKFezduxfPPPMMduzYgaSkJLz88svQarWIjo6utE1paSlKS0sN7/Py8ix3EnWcEAKTtk/C+rPrsf6J9Xgk6BGpQyIiIrI6yScUm0Ov18PLywvLly9Hjx49MHLkSLz11ltYtmxZlW3mz58Pd3d3w8vf378WI5bWuwfexbITyxDdPxpPdnpS6nCIiIhqhWTJjaenJxQKBTIzM43KMzMz4ePjU2mbZs2aoW3btlAoFIayDh06ICMjAxqNptI2M2fOhFqtNrxSU1MtdxJ13KdHPgUAHE07KnEkREREtUey5EapVKJHjx6IiYkxlOn1esTExCAsLKzSNn369EFSUhL0er2h7OLFi2jWrBmUSmWlbZycnODm5mb0qg8u3bqE3NJcdPfpjnWPr5M6HCIioloj6W2pqKgorFixAt988w3Onz+Pl156CYWFhYiMjAQAjBkzBjNnzjTUf+mll5CTk4PXXnsNFy9exPbt2zFv3jxMmjRJqlOos9aeWQtXpSsOPX+Ik4eJiKhekfQ5NyNHjkRWVhbmzJmDjIwMdOvWDTt37jRMMk5JSYFc/lf+5e/vj127duH1119H165d4efnh9deew3Tp0+X6hTqJCEEvjv9Hf7d8d/c7ZuIiOodSZ9zI4X68JybI9ePIGxlGGLGxOChVg9JHQ4REdE9s4nn3JD1fHf6O/i5+qF/i/5Sh0JERFTrmNzYGY1Og/Vn1+PpLk9DIVfcvQEREZGdYXJjZ3Yl7cKt4lt4tuuzUodCREQkCSY3dua7M9+hq3dXdPXuKnUoREREkmByY0fUJWpsu7ANz3bhqA0REdVfTG7syKbzm1BaVoqnujwldShERESSYXJjR5YdXwbvBt7ILcmVOhQiIiLJMLmxEwWaAhy7cQwZhRmYvocPNSQiovqLyY2dOJN5BgDQL6Af95IiIqJ6TdLtF8hyEjIS4CB3wK+jf4WTg5PU4RAREUmGIzd24lTmKXTw7MDEhoiI6j0mN3YiISMB3Xy6SR0GERGR5Jjc2AGdXofTmacR7B0sdShERESSY3JjB5JyklBcVsyRGyIiIjC5sQsJGQkAgGAfjtwQERExubEDCRkJ8HP1g6eLp9ShEBERSY7JjR04lXmKt6SIiIj+xOTGDnClFBER0V+Y3Ni4m4U3kV6QzpVSREREf2JyY+NOZZwCAI7cEBER/YnJjY1LyEhAA8cGCPQIlDoUIiKiOoHJjY07lXkKXb27Qi7jHyURERHA5MbmcTIxERGRMSY3NqykrASJ2YmcTExERPQ3TG5s2B83/4BO6DhyQ0RE9DdMbmxYQkYCZJChs1dnqUMhIiKqM5jc2LCEjAS0bdIWDZQNpA6FiIiozmByY8O47QIREVFFTG5slBACpzJPcTIxERHRPzC5sVFXc68irzSPIzdERET/wOTGRiVkJADgtgtERET/xOTGRv16+Vc4KZyQXZQtdShERER1CpMbG7X1wlaU6koxI2aG1KEQERHVKQ5SB0A146HygJPCCeseXyd1KERERHUKR25skE6vw+XblxEVFgV3lbvU4RAREdUpTG5s0DX1NZTqStHes73UoRAREdU5TG5sUGJ2IgAwuSEiIqoEkxsblJidCBdHFzR3ay51KERERHUOkxsblJidiHZN2kEu4x8fERHRP/Hb0QYlZifylhQREVEVmNzYICY3REREVWNyY2NuFd1CVlEWkxsiIqIqMLmxMRduXQDAlVJERERVYXJjYxKzEyGDDG082kgdChERUZ3E5MbGJGYnomWjlnB2dJY6FCIiojqJyY2N4WRiIiKi6jG5sTFMboiIiKrH5MaGlJaV4srtK0xuiIiIqsHkxoZcvn0ZOqFDB88OUodCRERUZzG5sSHcMJOIiOjumNzYkMTsRHg4e8DTxVPqUIiIiOosJjc2pHwysUwmkzoUIiKiOovJjQ1JzE5E+ya8JUVERFQdJjc2QgjBZeBEREQmYHJjI9IL0pGvyWdyQ0REdBdMbmwEV0oRERGZhsmNjUjMToSj3BGtGreSOhQiIqI6rU4kN0uWLEHLli2hUqkQGhqKuLi4KuuuWbMGMpnM6KVSqWoxWmkkZieiTZM2cJA7SB0KERFRnSZ5crNhwwZERUUhOjoa8fHxCA4ORkREBG7evFllGzc3N6Snpxte165dq8WIpcHJxERERKaRPLlZuHAhJkyYgMjISHTs2BHLli2Di4sLVq1aVWUbmUwGHx8fw8vb27sWI5YGl4ETERGZRtJ7HBqNBidOnMDMmTMNZXK5HOHh4YiNja2yXUFBAVq0aAG9Xo/u3btj3rx56NSpU6V1S0tLUVpaanifl5dnuRP4h/D/hiMhIwFNXZrCUeGIAk0Bsouy0VjVGCpHFWSQQaPTIKc4B01cmkDloEJJWQluFd2CVwMvNFA2gEKmQKmuFBn5GfBz84OLowsAIDUvFQeuHcDZm2fR2auz1c6BiIjI1kk6cpOdnQ2dTldh5MXb2xsZGRmVtmnXrh1WrVqFn376Cd999x30ej169+6N69evV1p//vz5cHd3N7z8/f0tfh7lkm8n41bxLRSVFeHBlg8CAPI1+XCQO2Bo26EY0mYIhBBQl6qh1+vxcOuHodfroS5VQ6PToHfz3ujRrAfUJWpkF2fjVtEttPdsj/ae7RHgFoDfU3/H9D3TrRY/ERGRXRASSktLEwDE4cOHjcqnTp0qQkJCTOpDo9GIwMBAMWvWrEo/LykpEWq12vBKTU0VAIRarb7n+P8ptzhXDF03VOQW51b6vqZ1qiojIiKqL9Rqtcnf3zIhhJAqsdJoNHBxccHGjRsxfPhwQ/nYsWORm5uLn376yaR+nnzySTg4OOD777+/a928vDy4u7tDrVbDzc2tpqETERFRLTLn+1vS21JKpRI9evRATEyMoUyv1yMmJgZhYWEm9aHT6XDmzBk0a9bMWmESERGRDZH8oSlRUVEYO3YsevbsiZCQECxatAiFhYWIjIwEAIwZMwZ+fn6YP38+AOCdd97B/fffj6CgIOTm5uKjjz7CtWvXMH78eClPg4iIiOoIyZObkSNHIisrC3PmzEFGRga6deuGnTt3GiYZp6SkQC7/a4Dp9u3bmDBhAjIyMtC4cWP06NEDhw8fRseOHaU6BSIiIqpDJJ1zIwXOuSEiIrI9NjPnhoiIiMjSmNwQERGRXWFyQ0RERHaFyQ0RERHZFSY3REREZFeY3BAREZFdYXJDREREdoXJDREREdkVJjdERERkVyTffqG2lT+QOS8vT+JIiIiIyFTl39umbKxQ75Kb/Px8AIC/v7/EkRAREZG58vPz4e7uXm2dere3lF6vx40bN+Dq6gqZTGbRvvPy8uDv74/U1FTuW2VFvM61g9e5dvA61x5e69phresshEB+fj58fX2NNtSuTL0buZHL5WjevLlVj+Hm5sb/cWoBr3Pt4HWuHbzOtYfXunZY4zrfbcSmHCcUExERkV1hckNERER2hcmNBTk5OSE6OhpOTk5Sh2LXeJ1rB69z7eB1rj281rWjLlznejehmIiIiOwbR26IiIjIrjC5ISIiIrvC5IaIiIjsCpMbIiIisitMbqqxZMkStGzZEiqVCqGhoYiLi6u2/o8//oj27dtDpVKhS5cu2LFjh9HnQgjMmTMHzZo1g7OzM8LDw3Hp0iVrnoLNsOS11mq1mD59Orp06YIGDRrA19cXY8aMwY0bN6x9GnWepX+n/27ixImQyWRYtGiRhaO2Pda4zufPn8ewYcPg7u6OBg0aoFevXkhJSbHWKdgES1/ngoICTJ48Gc2bN4ezszM6duyIZcuWWfMUbII51/mPP/7AE088gZYtW1b794G5f3ZmE1Sp9evXC6VSKVatWiX++OMPMWHCBNGoUSORmZlZaf3ff/9dKBQK8eGHH4pz586JWbNmCUdHR3HmzBlDnQULFgh3d3exdetWcerUKTFs2DDRqlUrUVxcXFunVSdZ+lrn5uaK8PBwsWHDBpGYmChiY2NFSEiI6NGjR22eVp1jjd/pcps3bxbBwcHC19dXfPrpp1Y+k7rNGtc5KSlJeHh4iKlTp4r4+HiRlJQkfvrppyr7rA+scZ0nTJggAgMDxb59+0RycrL46quvhEKhED/99FNtnVadY+51jouLE2+88Yb4/vvvhY+PT6V/H5jbZ00wualCSEiImDRpkuG9TqcTvr6+Yv78+ZXWHzFihBgyZIhRWWhoqHjxxReFEELo9Xrh4+MjPvroI8Pnubm5wsnJSXz//fdWOAPbYelrXZm4uDgBQFy7ds0yQdsga13n69evCz8/P3H27FnRokWLep/cWOM6jxw5Ujz77LPWCdhGWeM6d+rUSbzzzjtGdbp37y7eeustC0ZuW8y9zn9X1d8H99KnqXhbqhIajQYnTpxAeHi4oUwulyM8PByxsbGVtomNjTWqDwARERGG+snJycjIyDCq4+7ujtDQ0Cr7rA+sca0ro1arIZPJ0KhRI4vEbWusdZ31ej1Gjx6NqVOnolOnTtYJ3oZY4zrr9Xps374dbdu2RUREBLy8vBAaGoqtW7da7TzqOmv9Pvfu3Rvbtm1DWloahBDYt28fLl68iIcfftg6J1LH1eQ6S9FnZZjcVCI7Oxs6nQ7e3t5G5d7e3sjIyKi0TUZGRrX1y/9rTp/1gTWu9T+VlJRg+vTpeOqpp+rtZnnWus4ffPABHBwc8Oqrr1o+aBtkjet88+ZNFBQUYMGCBXjkkUfw66+/4rHHHsPjjz+OAwcOWOdE6jhr/T4vXrwYHTt2RPPmzaFUKvHII49gyZIl6Nevn+VPwgbU5DpL0Wdl6t2u4FS/aLVajBgxAkIIfPnll1KHY1dOnDiBzz77DPHx8ZDJZFKHY7f0ej0A4F//+hdef/11AEC3bt1w+PBhLFu2DP3795cyPLuyePFiHDlyBNu2bUOLFi1w8OBBTJo0Cb6+vhVGfahu48hNJTw9PaFQKJCZmWlUnpmZCR8fn0rb+Pj4VFu//L/m9FkfWONalytPbK5du4bdu3fX21EbwDrX+bfffsPNmzcREBAABwcHODg44Nq1a/jPf/6Dli1bWuU86jprXGdPT084ODigY8eORnU6dOhQb1dLWeM6FxcX480338TChQsxdOhQdO3aFZMnT8bIkSPx8ccfW+dE6riaXGcp+qwMk5tKKJVK9OjRAzExMYYyvV6PmJgYhIWFVdomLCzMqD4A7N6921C/VatW8PHxMaqTl5eHo0ePVtlnfWCNaw38ldhcunQJe/bsQZMmTaxzAjbCGtd59OjROH36NBISEgwvX19fTJ06Fbt27bLeydRh1rjOSqUSvXr1woULF4zqXLx4ES1atLDwGdgGa1xnrVYLrVYLudz4a1GhUBhGz+qbmlxnKfqslMWmJtuZ9evXCycnJ7FmzRpx7tw58cILL4hGjRqJjIwMIYQQo0ePFjNmzDDU//3334WDg4P4+OOPxfnz50V0dHSlS8EbNWokfvrpJ3H69Gnxr3/9i0vBheWvtUajEcOGDRPNmzcXCQkJIj093fAqLS2V5BzrAmv8Tv8TV0tZ5zpv3rxZODo6iuXLl4tLly6JxYsXC4VCIX777bdaP7+6whrXuX///qJTp05i37594sqVK2L16tVCpVKJpUuX1vr51RXmXufS0lJx8uRJcfLkSdGsWTPxxhtviJMnT4pLly6Z3KclMLmpxuLFi0VAQIBQKpUiJCREHDlyxPBZ//79xdixY43q//DDD6Jt27ZCqVSKTp06ie3btxt9rtfrxezZs4W3t7dwcnISAwcOFBcuXKiNU6nzLHmtk5OTBYBKX/v27aulM6qbLP07/U9Mbu6wxnVeuXKlCAoKEiqVSgQHB4utW7da+zTqPEtf5/T0dPHcc88JX19foVKpRLt27cQnn3wi9Hp9bZxOnWXOda7q79/+/fub3KclyIQQwnLjQERERETS4pwbIiIisitMboiIiMiuMLkhIiIiu8LkhoiIiOwKkxsiIiKyK0xuiIiIyK4wuSEiIiK7wuSGiOqNCxcuwMfHB/n5+VKHgvvvvx+bNm2SOgwiu8TkhoiqJJPJqn3NnTtX6hDNMnPmTLzyyitwdXWVOhTMmjULM2bMqLf7FhFZE59QTERVysjIMPy8YcMGzJkzx2gDx4YNG6Jhw4ZShGa2lJQUBAUFITk5GX5+flKHA51OBz8/P6xcuRJDhgyROhwiu8KRGyKqko+Pj+Hl7u4OmUxmVLZ+/Xp06NABKpUK7du3x9KlSw1tr169CplMhh9++AEPPPAAnJ2d0atXL1y8eBHHjh1Dz5490bBhQwwaNAhZWVmGds899xyGDx+Ot99+G02bNoWbmxsmTpwIjUZjqFNaWopXX30VXl5eUKlU6Nu3L44dO1btufzwww8IDg42Smzmzp2Lbt26GdVbtGgRWrZsadZ1+vbbb9GzZ0+4urrCx8cHTz/9NG7evFltG4VCgcGDB2P9+vVmHYuI7o7JDRHVyNq1azFnzhy8//77OH/+PObNm4fZs2fjm2++MaoXHR2NWbNmIT4+Hg4ODnj66acxbdo0fPbZZ/jtt9+QlJSEOXPmGLWJiYnB+fPnsX//fnz//ffYvHkz3n77bcPn06ZNw6ZNm/DNN98gPj4eQUFBiIiIQE5OTpXx/vbbb+jZs6dlL8KftFot3n33XZw6dQpbt27F1atX8dxzz921XUhICH777TerxERUr1l0G04islurV68W7u7uhveBgYFi3bp1RnXeffddERYWJoT4a3fgr7/+2vD5999/LwCImJgYQ9n8+fNFu3btDO/Hjh0rPDw8RGFhoaHsyy+/FA0bNhQ6nU4UFBQIR0dHsXbtWsPnGo1G+Pr6ig8//LDK+IODg8U777xjVBYdHS2Cg4ONyj799FPRokWLqi+ECY4dOyYAiPz8/Grr/fTTT0IulwudTndPxyMiYw4S51ZEZIMKCwtx+fJljBs3DhMmTDCUl5WVwd3d3ahu165dDT97e3sDALp06WJU9s9bOMHBwXBxcTG8DwsLQ0FBAVJTU6FWq6HVatGnTx/D546OjggJCcH58+erjLm4uBgqlcrMMzXNiRMnMHfuXJw6dQq3b982TBJOSUlBx44dq2zn7OwMvV6P0tJSODs7WyU2ovqIyQ0Rma2goAAAsGLFCoSGhhp9plAojN47OjoafpbJZJWW1caKIU9PT9y+fduoTC6XQ/xjTYVWqzWr38LCQkRERCAiIgJr165F06ZNkZKSgoiICKN5QpXJyclBgwYNmNgQWRiTGyIym7e3N3x9fXHlyhU888wzFu//1KlTKC4uNnzpHzlyBA0bNoS/vz88PT2hVCrx+++/o0WLFgDuJCTHjh3DlClTquzzvvvuw7lz54zKmjZtioyMDAghDIlXQkKCWbEmJibi1q1bWLBgAfz9/QEAx48fN6nt2bNncd9995l1PCK6O04oJqIaefvttzF//nx8/vnnuHjxIs6cOYPVq1dj4cKF99y3RqPBuHHjcO7cOezYsQPR0dGYPHky5HI5GjRogJdeeglTp07Fzp07ce7cOUyYMAFFRUUYN25clX1GREQgNjYWOp3OUDZgwABkZWXhww8/xOXLl7FkyRL88ssvRu22bNmC9u3bV9lvQEAAlEolFi9ejCtXrmDbtm149913K9Rr3749tmzZYlT222+/4eGHHzb1shCRiZjcEFGNjB8/Hl9//TVWr16NLl26oH///lizZg1atWp1z30PHDgQbdq0Qb9+/TBy5EgMGzbM6IGBCxYswBNPPIHRo0eje/fuSEpKwq5du9C4ceMq+xw0aBAcHBywZ88eQ1mHDh2wdOlSLFmyBMHBwYiLi8Mbb7xh1E6tVhs92+efmjZtijVr1uDHH39Ex44dsWDBAnz88ccV6l24cAFqtdrwPi0tDYcPH0ZkZKQpl4SIzMCH+BFRnfLcc88hNzcXW7dutXjfS5YswbZt27Br1y6L922u6dOn4/bt21i+fLnUoRDZHc65IaJ648UXX0Rubi7y8/Ml34LBy8sLUVFRksZAZK84ckNEdYo1R26IqH5gckNERER2hROKiYiIyK4wuSEiIiK7wuSGiIiI7AqTGyIiIrIrTG6IiIjIrjC5ISIiIrvC5IaIiIjsCpMbIiIisitMboiIiMiu/D/ZtVvBGbKJDAAAAABJRU5ErkJggg==",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "t = 100\n",
    "lbda = 0.01\n",
    "leis_controle(fx_vector,fy_vector,fz_vector,t,lbda)\n",
    "densidade(rho_vector,t,lbda)\n",
    "fidelidade(fid_vector,t,lbda)\n",
    "fidelidade(fid_autores,t,lbda)\n",
    "distance(distance_vector,t,lbda)"
   ]
  }
 ],
 "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": "3.12.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}