{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "a49afec5",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "from iminuit import Minuit\n",
    "from scipy.stats import norm\n",
    "\n",
    "# Using the lognormal from numba_stats\n",
    "# unstead of scipy_stats speeds things\n",
    "# up by a big factor.\n",
    "# Be careful however because the call sequences\n",
    "# are not exactly the sameand not all\n",
    "# functions are implemented.\n",
    "# from scipy.stats import lognorm\n",
    "from numba_stats import lognorm"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "aa49c280",
   "metadata": {},
   "source": [
    "### This is fake data with 3 point"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "e1da7c51",
   "metadata": {},
   "outputs": [],
   "source": [
    "# This is some fake data in 3 bins\n",
    "data = np.array([ 7,  6, 1])  # observed\n",
    "sig  = np.array([ 2,  2, 2])  # signal predicted with mu=1\n",
    "bg   = np.array([10,  5, 2])  # bg predicted\n",
    "err  = 0.2*bg                 # bg uncertainty"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "ef904097",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# check that lognormal makese sense, compare with gaussian\n",
    "color = ('red', 'green', 'blue')\n",
    "ax=plt.subplot(111)\n",
    "for b,e,c in zip(bg, err, color):\n",
    "    x = np.linspace(0.01, 20., 400)\n",
    "    ax.plot(x, lognorm.pdf(x, np.log(1+e/b), 0, b), color=c, \n",
    "            label='numba logn  $\\mu$ = '+str(b) + '   $\\sigma$ = ' + str(e))\n",
    "    ax.plot(x, norm.pdf(x,    scale=e, loc=b), color=c, linestyle='dashed', \n",
    "            label='gaus  $\\mu$ = '+str(b) + '   $\\sigma$ = ' + str(e))\n",
    "\n",
    "ax.grid()\n",
    "ax.legend()\n",
    "ax.set_xlim([0, 20.])\n",
    "_ = ax.set_ylim(0,1.5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "8db9aeea",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAD8CAYAAAB6paOMAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8rg+JYAAAACXBIWXMAAAsTAAALEwEAmpwYAAAkW0lEQVR4nO3dfXRU9b3v8feXgAKSoiIqARXqMTwJARIRgdKggmhRr0hbEY/Y1juW6rV1cYq2eH2iWcej2NOeo62Nzz0FS02RigWtVwFRfICwEgR5EisWgoCoCCIo+L1/zEBDmJDJzCR7z8zntVZWZvb3t/d8fw7+vtlPv23ujoiI5K4WQScgIiLBUiEQEclxKgQiIjlOhUBEJMepEIiI5DgVAhGRHNdgITCzU8xsvpm9bWYrzezHseXHm9kLZrYu9vu4etafEGuzzswmpLsDIiKSGmvoPgIz6wR0cvdlZpYPVAL/C7gG+Mjd7zazW4Dj3P3mOuseDywFSgCPrVvs7h+nuyMiIpKcBvcI3H2zuy+Lvd4JrAI6A5cCT8SaPUG0ONR1AfCCu38UG/xfAEalIW8REUmTlo1pbGZdgf7AG8BJ7r45FvoAOCnOKp2Bf9R6vzG2LN62I0AE4Jhjjinu0aNHY1ITEclplZWVH7p7x2TWTbgQmFk74M/AT9z9UzM7GHN3N7OU5qpw93KgHKCkpMSXLl2ayuZERHKKmW1Idt2Erhoys1ZEi8B0d58VW7wldv7gwHmErXFW3QScUut9l9gyEREJiUSuGjLgEWCVu/+yVugZ4MBVQBOAv8RZ/XlgpJkdF7uqaGRsmYiIhEQiewRDgH8FzjWzqtjPRcDdwAgzWwecH3uPmZWY2cMA7v4RMBVYEvu5K7ZMRERCosHLR4OgcwQizefLL79k48aN7NmzJ+hUJAGtW7emS5cutGrV6pDlZlbp7iXJbLNRVw2JSPbZuHEj+fn5dO3aldoXgUj4uDvbt29n48aNdOvWLW3b1RQTIjluz549dOjQQUUgA5gZHTp0SPvemwqBiKgIZJCm+K5UCEREcpzOEYjIIWpq0ru9goKG2+Tl5dGnTx/cnby8PO6//34GDx4MwJtvvsnkyZPZtGkT+fn5dOrUibvvvps+ffqkN9EcpkIgIoFr06YNVVVVADz//PP87Gc/Y+HChWzZsoXvfOc7zJgx42BheOWVV1i/fr0KQRqpEIhIqHz66accd1x0Vvv777+fCRMmHCwCAEOHDg0qtaylQiAigfv888/p168fe/bsYfPmzbz00ksArFy5kgkT9BiTpqaTxSISuAOHhlavXs1zzz3H1VdfTbybXc8++2x69uzJj3/84wCyzF4qBCISKueccw4ffvgh27Zto3fv3ixbtuxg7I033mDq1Kns2LEjwAyzjwqBiITK6tWr2b9/Px06dOD666/n8ccfZ/HixQfju3fvDjC77KRzBCJyiEQu90y3A+cIIDqNwhNPPEFeXh4nn3wyM2fO5Oabb2bTpk2ceOKJnHDCCdx2223Nn2QWUyEQkcDt37+/3tigQYNYuHBhM2aTe3RoSEQkx6kQiIjkOBUCEZEcp0IgIpLjVAhERHJcg1cNmdmjwGhgq7ufGVs2E+gea3Is8Im794uz7nvATmA/sC/Zx6iJiEjTSeTy0ceB+4HfH1jg7t898NrM7gOOdJvfcHf/MNkERUSkaTVYCNz9ZTPrGi9m0UflfAc4N815iYhIM0n1HME3gC3uvq6euAN/M7NKM4uk+Fki0lwmTYL77ou+LiiIPq1mwQIoLY0ui0SgvDz6Oj8fdu6EOXPg4oujy668EmbMiL5O4dGKtaefbmrf//73OfHEEznzzDOb7TPDwuLN8HdYo+gewbMHzhHUWv5b4B13v6+e9Tq7+yYzOxF4Afg/7v5yPW0jQATg1FNPLd6wYUOjOiIiyVm1ahU9e/b854LiYqisDC6hgLz88su0a9eOq6++mhUrVgSdzhEd9p0BZlaZ7HnYpPcIzKwlMAaYWV8bd98U+70VeBoYeIS25e5e4u4lHTt2TDYtEUnVgb/00+XAnsERfPbZZ3zrW9+iqKiIM888k5kzo8NKu3btAJg6dSrdu3dn6NChjBs3jmnTpsXdTmlpKatXrwZg+/btjfrrftiwYRx//PEJt88mqcw1dD6w2t03xgua2TFAC3ffGXs9Ergrhc8TkeaQn5/e7T37bPRQ0RE899xzFBQU8Ne//hXgkGmmlyxZwp///Geqq6v58ssvGTBgAMXFxXG3884771BYWAjA8uXLDz7O8hvf+AY7d+48rP20adM4//zzk+pWNknk8tEngVLgBDPbCNzu7o8AVwBP1mlbADzs7hcBJwFPR88n0xKY4e7PpTd9EUm70aNh7dr0bS+BPYI+ffowadIkbr75ZkaPHs03vvGNg7FXX32VSy+9lNatW9O6dWsuPnAeoo4NGzbQuXNnWrSIHuhYvnw5ffv2BWDRokVp6Ej2SuSqoXH1LL8mzrIa4KLY63eBohTzE5Hmls4iANETyHPmHLFJYWEhy5YtY+7cudx6662cd955jZ5qurq6+uDAD1BZWcl3vxu90l17BEemO4tF5FB33JHe7UUavmCwpqaGtm3bctVVV/HTn/70kKeSDRkyhDlz5rBnzx527drFs88+G3cbVVVV7NmzB4B169bxl7/85eChoUWLFlFVVXXYj4pAlAqBiBzqzjv/WQwKC6N7CJWV0auJoPGXlh5YfgRvvfUWAwcOpF+/ftx5553ceuutB2NnnXUWl1xyCX379uXCCy+kT58+tG/f/rBtVFdX89VXX1FUVMRdd91Fr169eOKJJxLu9rhx4zjnnHNYs2YNXbp04ZFHHkl43UyX0OWjza2kpMSXLl0adBoiOSHepYhhs2vXLtq1a8fu3bsZNmwY5eXlDBgw4JA2Z5xxBsuWLSM/3Se7Qyjdl4/qCWUiEnqRSIS3336bPXv2MGHChMOKwM6dOzGznCgCTUGFQERCb0YDVx7l5+ezNt0nuXOIzhGIiOQ4FQIRkRynQiAikuNUCEREcpwKgYhIjlMhEBHJcSoEInKIBQugY8fo76aI1/Xee+9l3MNgfvWrX7F79+4G21177bW8/fbbR2wze/bsBts0NRUCETlEaSk89RR8+9vxB/NU45lu//79CReChx9+mF69eh2xjQqBiIRSOotBIvbt28f48ePp2bMnY8eOPTjIzp07lx49elBcXMyNN97I6NGjD1v38ccf54Ybbjj4fvTo0SyIJdWuXTumTJlCUVERgwYNYsuWLQBs2bKFyy67jKKiIoqKili8eDEAf/jDHw7OeXTdddexf//+g9uZNGkSRUVFlJWVUVNTw/Dhwxk+fDgAEydOpKSkhN69e3P77bfX+u9QyoHpcuLlsnjxYp555hl++tOf0q9fP9avX3/IXdPr1q077C7qpqBCICJxpasYJGLNmjX86Ec/YtWqVXzta1/jN7/5DXv27OG6665j3rx5VFZWsm3btkb34bPPPmPQoEFUV1czbNgwHnroIQBuvPFGvvnNb1JdXc2yZcvo3bs3q1atYubMmbz66qtUVVWRl5fH9OnTD27n7LPPprq6mttuu42CggLmz5/P/PnzASgrK2Pp0qUsX76chQsXsnz58oRyGTx4MJdccgn33nsvVVVVnH766bRv356qqioAHnvsMb73ve81ut+NpUIgIvVKRzFIxCmnnMKQIUMAuOqqq3jllVdYvXo1X//61+nWrRsQnR20sY466qiDexHFxcW89957ALz00ktMnDgRgLy8PNq3b8+LL75IZWUlZ511Fv369ePFF1/k3XffPdjm8ssvr/dz/vSnPzFgwAD69+/PypUr4x7qqS+Xuq699loee+wx9u/fz8yZM7mygae7pYPmGhKRI6o92D/11OGDe0PxRMSeZFjv+yNp2bIlX3311cH3B55JANCqVauD28rLy2Pfvn31bsfdmTBhAv/+7/9+WKx169bk5eXFXe/vf/8706ZNY8mSJRx33HFcc801h+TQ2Fwuv/xy7rzzTs4991yKi4vp0KFDvTmni/YIROQQQZwgfv/993nttdeA6ARzQ4cOpXv37rz77rsH/3I+8ED7urp27UpVVRVfffUV//jHP3jzzTcb/LzzzjuP3/72t0D05O+OHTs477zzqKioYOvWrQB89NFHbNiwIe76+fn5B5949umnn3LMMcfQvn17tmzZwrx58xrV99rbgmjRueCCC5g4cWKzHBYCFQIRqaO+v+hLS2HbtuTjR9K9e3ceeOABevbsyccff8zEiRNp06YNv/nNbxg1ahTFxcXk5+fHfSDNkCFD6NatG7169eLGG29M6OTqr3/9a+bPn0+fPn0oLi7m7bffplevXvziF79g5MiR9O3blxEjRrB58+a460ciEUaNGsXw4cMpKiqif//+9OjRgyuvvPLgIa5EXXHFFdx7773079+f9evXAzB+/HhatGjByJEjG7WtZDX4YBozexQYDWx19zNjy+4A/jdw4OzNz919bpx1RwG/BvKIPtT+7kSS0oNpRJpPmB9Mc+CBNO7O9ddfzxlnnMFNN90UdFpNbtq0aezYsYOpU6fGjQfxYJrHgfuB39dZ/p/uPq2+lcwsD3gAGAFsBJaY2TPuHuwFsyKSMR566CGeeOIJvvjiC/r37891110XdEpN7rLLLmP9+vW89NJLzfaZDRYCd3/ZzLomse2BwDvu/i6Amf0RuBRQIRCRhNx00005sQdQ29NPP93sn5nKOYIbzGy5mT1qZsfFiXcG/lHr/cbYsrjMLGJmS81saTLXC4uISHKSLQS/BU4H+gGbgftSTcTdy929xN1LOnbsmOrmREQkQUkVAnff4u773f0r4CGih4Hq2gScUut9l9gyEREJkaQKgZl1qvX2MmBFnGZLgDPMrJuZHQVcATyTzOeJSLiUlpZSmsx1ohJKDRYCM3sSeA3obmYbzewHwD1m9paZLQeGAzfF2haY2VwAd98H3AA8D6wC/uTuK5uoHyKSRe644w6mTav3osRQzNiZTRK5aijeBB+P1NO2Brio1vu5wGH3F4hI5po+fTqvv/46e/fupWvXrpSVlTF+/PhmzWH27NmMHj26wSmeJTG6s1hEEjZ9+nQikQh79+4FYMOGDUQikYOzdKairKyMwsJChg4dypo1a4DofQRnnXUWRUVFXH755ezevTvu1M3x2kniVAhEJGFTpkw5bJDdvXs3U6ZMSWm7lZWV/PGPf6Sqqoq5c+eyZMkSAMaMGcOSJUuorq6mZ8+ePPLII3Gnbo7XThKn2UdFJGHvv/9+o5YnatGiRVx22WW0bdsWgEsuuQSAFStWcOutt/LJJ5+wa9cuLrjggrjrJ9pO4tMegYgk7NRTT23U8lRdc8013H///bz11lvcfvvtcad3bkw7iU+FQEQSVlZWdvCv9gPatm1LWVlZStsdNmwYs2fP5vPPP2fnzp3MmTMHgJ07d9KpUye+/PLLQ85D1J26ub52khgVAhFJ2Pjx4ykvL+foo48G4LTTTqO8vDzlq4YGDBjAd7/7XYqKirjwwgs566yzAJg6dSpnn302Q4YMoUePHgfb1526ub52kpgGp6EOgqahFmk+yUxDfeBmsgXJPIVGUhbENNQiIodQAcguOjQkIpLjVAhEhDAeIpb4muK7UiEQyXGtW7dm+/btKgYZwN3Zvn07rVu3Tut2dY5AJMd16dKFjRs3ogdCZYbWrVvTpUuXtG5ThUAkx7Vq1Ypu3boFnYYESIeGRERynAqBiEiOUyEQEclxKgQiIjlOhUBEJMcl8sziR81sq5mtqLXsXjNbbWbLzexpMzu2nnXfiz3buMrMNHmQiEgIJbJH8Dgwqs6yF4Az3b0vsBb42RHWH+7u/ZKdDElERJpWg4XA3V8GPqqz7G/uvi/29nUgvXc3iIhIs0nHOYLvA/PqiTnwNzOrNLPIkTZiZhEzW2pmS3WHo4hI80mpEJjZFGAfUN8jgYa6+wDgQuB6MxtW37bcvdzdS9y9pGPHjqmkJSIijZB0ITCza4DRwHivZ7Yqd98U+70VeBoYmOzniYhI00iqEJjZKGAycIm7766nzTFmln/gNTASWBGvrYiIBCeRy0efBF4DupvZRjP7AXA/kA+8ELs09MFY2wIzmxtb9STgFTOrBt4E/uruzzVJL0REJGmJXDU0zt07uXsrd+/i7o+4+7+4+ymxy0L7ufsPY21r3P2i2Ot33b0o9tPb3cuSSXDBAujYMfpb8cyLi0gGcPfQ/RQXF3tt8+e7n3BC9Hc8ioc7LiJND1jqSY65gQ/68X7qFgL34AczxROLi0gwsq4QFBYeXgjcwzPYKV5/XESCkXWFoGXL4lAPdopr0BcJm6wrBIWFxaEe7BRXMRAJm6wrBMXFxYEPZoqrGIhkkqwsBO7BD2aKqxiIZIqsLQTuwQ9miqsYiGSCrC4E7sEPZoqrGIiEXdYXAvfgBzPFdR+BSJhlXSHQfQSZGxeRYGRdIdB9BJkbF5FgZF0h0H0EmR0XkeaXdYVA9xFkflxEmldWFgL34AczxVUMRDJF1hYC9+AHM8VVDEQyQVYXAvfgBzPFVQxEwi7rC4F78IOZ4rqPQCTMmrwQAI8CW4EVtZYdD7wArIv9Pq6edSfE2qwDJiTyebqPIHPjIhKM5igEw4ABdQrBPcAtsde3AP8RZ73jgXdjv4+LvY5bMGr/6D6CzI2LSDCa5dAQ0LVOIVgDdIq97gSsibPOOOB3td7/DhjX0GfpPoLMjotI80ulEFh0/YaZWVfgWXc/M/b+E3c/NvbagI8PvK+1zr8Brd39F7H3/xf43N2nxdl+BIgAdO58avGvfrWBSATKy2Hw4MPzWbwYxUMYLyg4vK2IND0zq3T3kmTWbZGOBGLVKLGKUv82yt29xN1LOnToyODB0UEmEokOOnUpHu64iGSOVArBFjPrBBD7vTVOm03AKbXed4ktS0jQg5niKgYiuSCVQvAM0SuCiP3+S5w2zwMjzew4MzsOGBlblrCgBzPFVQxEsl1ChcDMngReA7qb2UYz+wFwNzDCzNYB58feY2YlZvYwgLt/BEwFlsR+7oota5SgB7N0xceNK2XEiNLQ5peOuIhknoRPFjen008v8UWLlh62PKwnSBONjxhRytq18OSTC0KZXzriY8cevlxEml7gJ4vTbcOG4P+ybYp4+/ZQWBje/NIRF5HME8pCcNpp4R7sUi0GYc5P5wREck8oC0G7duEe7BRXMRDJJqEsBBD8YKa4ioFIrghtIYDgBzPFVQxEckGoCwEEP5ilM75jR7jzUzEQyU2hLwQQ/GCWrvjatdlfDEQk84SyEOzadfiyMA12ycYLC6PFIKz5pSMuIpknlIVA9xFkblxEMk8oC4HuI8jcuIhknlAWAt1HkNlxEcksoSwEEPxgpriKQV2lpaWUlpYGnYZI2oW2EEDwg5niKgYiuSDUhQCCH8x0H4GKgUi2C30hgOAHM91HoPsIRLJZKAuB7iPI3LiIZJ5QPpimqKjE5807/ME0mW7s2FIAKioWBJpHUyooCDqDpnPgRPGCBQsCzUMknqx7MI2IiDSfpAuBmXU3s6paP5+a2U/qtCk1sx212tyWcsYiIpJWLZNd0d3XAP0AzCwP2AQ8HafpIncfnezniIhI00rXoaHzgPXuviFN2xMRkWaSrkJwBfBkPbFzzKzazOaZWe/6NmBmETNbamZLt2/flqa0RESkISkXAjM7CrgEeCpOeBlwmrsXAf8NzK5vO+5e7u4l7l7SoUPHVNMSEZEEpWOP4EJgmbtvqRtw90/dfVfs9VyglZmdkIbPFBGRNElHIRhHPYeFzOxkM7PY64Gxz9uehs/MOLNmTaey8nVee20hAwd2Zdas6UGnJCICpHDVEICZHQOMAK6rteyHAO7+IDAWmGhm+4DPgSs8jHewNbFZs6YzeXKEL77YC8CmTRuYPDk6H8OYMeODTE1ERHcWN4eBA7uyadPhF1R17nwab775XvMn1IR0Z7FIMHRnccjV1LzfqOUiIs1JhaAZFBSc2qjlIiLNSYWgGdxySxlt2rQ9ZFmbNm255ZaygDISEfknFYJmMGbMeO65p5yjjjoaiJ4buOeecp0oFpFQSOmqIUncmDHjmTHjISC7p6EWkcyjPQIRkRynQiAikuNUCEREcpwKgUgCpk+fzuuvv87ChQvp2rUr06drihDJHioEIg2YPn06kUiEvXujU4Rs2LCBSCSiYiBZQ4VApAFTpkxh9+7dhyzbvXs3U6ZMCSgjkfRSIZC0qm8angULoGPHzIy//378qUBqLw9z/o2JS25SIZC0+va34w82paXw1FOZGT/11PhTgdReHub8GxOX3KRCIGkVhsEs3fGysjLatj10ipCjj25LWVlZQutnUlxykwqBpFUYBrN0x8ePH095eTlHHx2dIuSkk06jVatyOnc+fIqQMObfmLjkJhUCSbugB7OmKgaDBg3im9/8Jh988B5z5owPVX7pjEvuUSGQJhH0YKa4ioEkToVAmkzQg5niKgaSmJQLgZm9Z2ZvmVmVmR32fEmL+i8ze8fMlpvZgFQ/UzJH0INZOuOffBLu/FQMJFnp2iMY7u796nle5oXAGbGfCPDbNH2mhFAYB7N0xVeuzP5iILmpOQ4NXQr83qNeB441s07N8LkSgDAMZk0V7907WgzCmp/uI5BkmbuntgGzvwMfAw78zt3L68SfBe5291di718Ebnb3pXXaRYjuMdC586nFb765IaW8wmjs2FIgux9Ms3gxRCJQXg6DB2dXfOzYUnbsgM2bF4Qyv3TECwoOXyaZwcwq6zkq06B07BEMdfcBRA8BXW9mw5LZiLuXu3uJu5d06NAxDWlJEAYPjg4ykUh00Mm2ePv24c4v1bjkppQLgbtviv3eCjwNDKzTZBNwSq33XWLLJEsFPZgprmIgjZNSITCzY8ws/8BrYCSwok6zZ4CrY1cPDQJ2uPvmVD5Xwi/owUxxFQNJXKp7BCcBr5hZNfAm8Fd3f87MfmhmP4y1mQu8C7wDPAT8KMXPlAwR9GCmuIqBJCalQuDu77p7Ueynt7uXxZY/6O4Pxl67u1/v7qe7e5+6J4kluwU9mKUzvmNHuPNTMZBk6c5iSaswDmbpiq9dm/3FQHKTCkEzqqhYkNWXjkI4BrOmihcWRotBWPNLR1xykwqBpFUYBrOmvHS0sDC8+aUjLrlJhUDSKgyDme4j0DkBaRwVAkm7oAczxVUMpHFSnmKiKRQVlfi8ebq4SMIlF6YI0RQTmSvoKSZERCSDqRCIiOQ4FQIRkRynQiAikuNaBp2ASKbI5pPEktu0RyAikuNUCEREcpwKgYhIjlMhEBHJcSoEIiI5ToVARCTHqRCIiOS4pAuBmZ1iZvPN7G0zW2lmP47TptTMdphZVeznttTSFRGRdEvlhrJ9wCR3X2Zm+UClmb3g7m/XabfI3Uen8DkiItKEkt4jcPfN7r4s9nonsAronK7ERESkeaTlHIGZdQX6A2/ECZ9jZtVmNs/Meqfj80REJH1SnmvIzNoBfwZ+4u6f1gkvA05z911mdhEwGzijnu1EgAhA586nppqWiIgkKKU9AjNrRbQITHf3WXXj7v6pu++KvZ4LtDKzE+Jty93L3b3E3Us6dOiYSloikkYLFkDHjtHfioc3nopUrhoy4BFglbv/sp42J8faYWYDY5+3PdnPFJGmFW+wKS2Fp56Cb39b8TDHU5HKHsEQ4F+Bc2tdHnqRmf3QzH4YazMWWGFm1cB/AVd4GB+SLCJA8IOZ4snHU6GH14vIQWvXRgebp56KP7gsWKB4WONZ9/D6ln9/B4Bjr7+SNk/PAKCgswHQ5ukZHHv9lQAcP+Fijv7bHGzXTk4uzAeg7R/KaT85AkCHsaUctXgBLT6o4aQBBQAc8+B9fO3OSQCcMKqYVssryVu/lhOHFgKQf98d5N93BwAnDi0kb/1aWi2v5IRRxQB87c5JHPPgfQCcNKCAFh/UcNTiBXQYWwpA+8kR2v6hHICTC/OxXTs5+m9zOH7CxeqT+hT6PvV5bw4P/XInxcPzqaiAT+4p57OrItTUwN7BpZz54QIeK6uh+7kFVFTAjtvuY9d1k6ipgS/6FtN7TyX/83/X0uW8QioqYOekO9g56Q5qamDf1wvpmbeWJ/+tkmPPL6aiAnZdN4kdt91HTQ3sP7mAHl+roeKGBbQcUUpFBXx2VYRP7imnpga+apdP94KdzP7BHPaMvJiKCth92ZV8/MAMamoAMwoL4dkrZ/DhyCupqIA9Iy5m++Nz2Lx2J5/lteTnPy/luTHlbLggQkVFtE8fVizgg2U17D+5gMJC+H8X3cfKUZOoqIj2adtzlWxZtJZ9Xy+ksBAWDr+DNy68g4qKaJ+2LFrLtucq+aJvMYWF8OqgSbx40X1UVET79MGyGj6sWMDewaUUFsIbRRH+8q1yKiqifdq8difbH5/DnhEXU1gIld2vZProGVRURPtUUwMfPzCD3ZddSWEhVJ92Mb8bPYfZ/7OTr9rlU1MT/Z5SEco9gn7dzvC5r64LOg2RnLV4MUQiUF4OgwdnR3xsrGBWVCwIZX6pxjt3zrI9Aj8mP+gURHLa4MHRQSYSiQ46imdWvLFCWQharaoOOgWRnBf0YKZ48xWDUB4a0sliEUm32oeGslHWHRpqsX1b0CmIiOSMUBYC+3x30CmIiOSMUBaC/V1OCzoFEZGcEcpC0HL9mqBTEJEsMmvWdCorX+e11xYycGBXZs2aHnRKoRLKQrD/pIKgUxCRLDFr1nQmT47wxRd7Adi0aQOTJ0dUDGoJZSHwo1sHnYKIZIm7757C53XOO37++W7uvntKQBmFTygLQat1q4JOQUSyRE3N+41anotCWQi+7NU36BREJEsUFMR/0FV9y3NRKAtBi21bgk5BRLLELbeU0aZN20OWtWnTlltuKQsoo/AJZSGwL78MOgURyRJjxoznnnvKOeqoowHo3Pk07rmnnDFjxgecWXik/MziprC/oEvQKYhIFhkzZjwzZjwEZO8UE6kI5R5BS50sFhFpNqEsBLqzWESk+YSyEHiLUKYlIpKVUhpxzWyUma0xs3fM7JY48aPNbGYs/oaZdU1kuwceVSkiIk0v6UJgZnnAA8CFQC9gnJn1qtPsB8DH7v4vwH8C/5HItvf1ODPZtEREpJFS2SMYCLzj7u+6+xfAH4FL67S5FHgi9roCOM/MrKEN522pSSEtERFpjFQuH+0M/KPW+43A2fW1cfd9ZrYD6AB8WHdjZhYBIrG3ezt3thUp5BZmJxCn/1lE/ctsWd+/zp0tW/vXPdkVQ3MfgbuXA+UAZrY02UeuhV029w3Uv0yn/mUuM0v6+b6pHBraBJxS632X2LK4bcysJdAe2J7CZ4qISJqlUgiWAGeYWTczOwq4AnimTptngAmx12OBl9zdU/hMERFJs6QPDcWO+d8APA/kAY+6+0ozuwtY6u7PAI8A/2Nm7wAfES0WiShPNq8MkM19A/Uv06l/mSvpvpn+QBcRyW26hVdEJMepEIiI5LjACkEC01NcY2bbzKwq9nNtEHkmy8weNbOtZvHvh7Co/4r1f7mZDWjuHJOVQN9KzWxHre/utubOMRVmdoqZzTezt81spZn9OE6bTP7+EulfRn6HZtbazN40s+pY3+6M0yapqW/CIMH+NX7sdPdm/yF6cnk98HXgKKAa6FWnzTXA/UHkl6Y+DgMGACvqiV8EzAMMGAS8EXTOaexbKfBs0Hmm0L9OwIDY63xgbZx/n5n8/SXSv4z8DmPfR7vY61bAG8CgOm1+BDwYe30FMDPovNPcv0aPnUHtESQyPUVGc/eXiV4pVZ9Lgd971OvAsWbWqXmyS00Cfcto7r7Z3ZfFXu8EVhG9S762TP7+EulfRop9H7tib1vFfupeEZPU1DdhkGD/Gi2oQhBveop4/xAvj+12V5jZKXHimSzR/waZ6pzY7us8M+sddDLJih026E/0L6/asuL7O0L/IEO/QzPLM7MqYCvwgrvX+925+z7gwNQ3GSGB/kEjx84wnyyeA3R1977AC/yzgkv4LQNOc/ci4L+B2cGmkxwzawf8GfiJu38adD7p1kD/MvY7dPf97t6P6GwHA80sq6YzTqB/jR47gyoEDU5P4e7b3X1v7O3DQHEz5dZcEpmiIyO5+6cHdl/dfS7QysxOCDitRjGzVkQHyenuPitOk4z+/hrqXzZ8h+7+CTAfGFUnlBVT39TXv2TGzqAKQYPTU9Q53noJ0eOY2eQZ4OrY1SeDgB3uvjnopNLBzE4+cMzVzAYS/XeWMf+jxXJ/BFjl7r+sp1nGfn+J9C9Tv0Mz62hmx8ZetwFGAKvrNMvYqW8S6V8yY2cgs496YtNT3GhmlwD7iJ6YvCaIXJNlZk8SvfLiBDPbCNxO9MQO7v4gMJfolSfvALuB7wWTaeMl0LexwEQz2wd8DlyRKf+jxQwB/hV4K3YsFuDnwKmQ+d8fifUvU7/DTsATFn1wVgvgT+7+rKVn6pswSKR/jR47NcWEiEiOC/PJYhERaQYqBCIiOU6FQEQkx6kQiIjkOBUCEZEcp0IgIpLjVAhERHLc/wd4e3t3r11UFQAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# plot it\n",
    "x = np.array([1.,2.,3.])\n",
    "b = np.array([0.5, 1.5, 2.5, 3.5, 4.5])\n",
    "ax = plt.subplot(111)\n",
    "ax.hist(x, b, weights=bg,  alpha=0.1, color='blue', label='BG', histtype='stepfilled')\n",
    "\n",
    "n1,b1,p1 = ax.hist(x, b, weights=bg+err, histtype='stepfilled',\n",
    "                   facecolor='none', edgecolor='none', linestyle='--')\n",
    "n2,b2,p2 = ax.hist(x, b, weights=bg-err, histtype='stepfilled', \n",
    "                   facecolor='none', edgecolor='none', linestyle='--')\n",
    "ax.bar(x=b1[:-1], height=n2-n1, bottom=n1, width=np.diff(b1),\n",
    "       align='edge', linewidth=0, edgecolor='blue', color='none', zorder=-1, \n",
    "       label='bg uncertainty', hatch='\\\\\\\\\\\\')\n",
    "\n",
    "ax.hist(x, b, weights=sig, color='red', label='sig $\\mu$=1', histtype='step',\n",
    "        linestyle='dotted')\n",
    "ax.errorbar(x, data, yerr=np.sqrt(data), fmt='o', color='black', label='data')\n",
    "# ax.bar(x, sig, align='center',width=1, color='None', edgecolor='red', label='sig ($\\mu$=1)')\n",
    "\n",
    "ax.set_xlim((0.5, 3.5))\n",
    "ax.legend()\n",
    "_ = ax.set_ylim((0,20))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "a0d6cb03",
   "metadata": {},
   "outputs": [],
   "source": [
    "class myFit:\n",
    "    \"\"\"\n",
    "    Simplest example of wrapper around a minuit function\n",
    "    NLL fit to bins of data = mu*signal + background\n",
    "    including sigma of background (absolute)\n",
    "    \n",
    "    Sample usage:\n",
    "    Example of 3 bins, np.arrays are to be passed.\n",
    "    The fit parameters ordered for pinit are\n",
    "       mu, 1st bin bg, 2bd bin bg, 3rd bin bg\n",
    "    \n",
    "    f = myFit(data, signal, background, sigma)\n",
    "    m = Minuit(f.myNLL, pinit, name=(\"mu\", \"b1\", \"b2\", 'b3'))\n",
    "    m.errordef = Minuit.LIKELIHOOD\n",
    "    m.simplex()\n",
    "    m.migrad()\n",
    "    m.minos()\n",
    "    \n",
    "    After defining \"f\" can change data members as\n",
    "    f.d  = newData\n",
    "    f.b  = newBG\n",
    "    f.s  = newSignal\n",
    "    f.eb = newBGsigma\n",
    "    \"\"\"\n",
    "    def __init__(self, d, s, b, eb):\n",
    "        self.d     = d\n",
    "        self.b     = b\n",
    "        self.eb    = eb\n",
    "        self.s     = s\n",
    "        self.blah  = np.log(1+eb/b)\n",
    "\n",
    "    # This should really protect against logs of negative numbers\n",
    "    def myNLL(self, p):\n",
    "        mu = p[0]\n",
    "        fitbg = p[1:]\n",
    "        temp1 = (-self.d * np.log(mu*self.s + fitbg) + mu*self.s + fitbg).sum()\n",
    "        #temp2 = 0\n",
    "        #for bb,ee,fit in zip(self.b, self.eb, fitbg):\n",
    "        #    pdf = lognorm.pdf(fit, np.log(1+ee/bb), scale=bb)\n",
    "        #   temp2 = temp2 - np.log(pdf)\n",
    "        #return temp1+temp2\n",
    "        return temp1 - (np.log(lognorm.pdf(fitbg, self.blah, 0, self.b))).sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "88d5277f",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Initialize a myFit object that contains the\n",
    "# data, the signal model (mu=1), the pre-fit bg\n",
    "# prediction, its uncertainty, as well as the\n",
    "# negative log-likelihood function\n",
    "thisFit = myFit(data, sig, bg, err)\n",
    "\n",
    "# initialize a Minuit object with pinit as the initial guess\n",
    "pinit     = np.array([1, bg[0], bg[1], bg[2]])\n",
    "mData = Minuit(thisFit.myNLL, pinit, name=(\"mu\", \"b1\", \"b2\", 'b3'))\n",
    "mData.errordef = Minuit.LIKELIHOOD\n",
    "mData.limits['mu'] = (0, None)   # force mu>=0 \n",
    "#mData.simplex()\n",
    "#mData.migrad()\n",
    "#mData.minos()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "e95e1994",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table>\n",
       "    <tr>\n",
       "        <th colspan=\"5\" style=\"text-align:center\" title=\"Minimizer\"> Migrad </th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td colspan=\"2\" style=\"text-align:left\" title=\"Minimum value of function\"> FCN = -7.475 </td>\n",
       "        <td colspan=\"3\" style=\"text-align:center\" title=\"No. of function evaluations in last call and total number\"> Nfcn = 155 </td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td colspan=\"2\" style=\"text-align:left\" title=\"Estimated distance to minimum and goal\"> EDM = 4.2e-05 (Goal: 0.0001) </td>\n",
       "        <td colspan=\"3\" style=\"text-align:center\" title=\"No. of gradient evaluations in last call and total number\">  </td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td colspan=\"2\" style=\"text-align:center;background-color:#92CCA6;color:black\"> Valid Minimum </td>\n",
       "        <td colspan=\"3\" style=\"text-align:center;background-color:#FFF79A;color:black\"> SOME Parameters at limit </td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td colspan=\"2\" style=\"text-align:center;background-color:#92CCA6;color:black\"> Below EDM threshold (goal x 10) </td>\n",
       "        <td colspan=\"3\" style=\"text-align:center;background-color:#92CCA6;color:black\"> Below call limit </td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td style=\"text-align:center;background-color:#92CCA6;color:black\"> Covariance </td>\n",
       "        <td style=\"text-align:center;background-color:#92CCA6;color:black\"> Hesse ok </td>\n",
       "        <td style=\"text-align:center;background-color:#92CCA6;color:black\" title=\"Is covariance matrix accurate?\"> Accurate </td>\n",
       "        <td style=\"text-align:center;background-color:#92CCA6;color:black\" title=\"Is covariance matrix positive definite?\"> Pos. def. </td>\n",
       "        <td style=\"text-align:center;background-color:#92CCA6;color:black\" title=\"Was positive definiteness enforced by Minuit?\"> Not forced </td>\n",
       "    </tr>\n",
       "</table><table>\n",
       "    <tr>\n",
       "        <td></td>\n",
       "        <th title=\"Variable name\"> Name </th>\n",
       "        <th title=\"Value of parameter\"> Value </th>\n",
       "        <th title=\"Hesse error\"> Hesse Error </th>\n",
       "        <th title=\"Minos lower error\"> Minos Error- </th>\n",
       "        <th title=\"Minos upper error\"> Minos Error+ </th>\n",
       "        <th title=\"Lower limit of the parameter\"> Limit- </th>\n",
       "        <th title=\"Upper limit of the parameter\"> Limit+ </th>\n",
       "        <th title=\"Is the parameter fixed in the fit\"> Fixed </th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <th> 0 </th>\n",
       "        <td> mu </td>\n",
       "        <td> 0.0 </td>\n",
       "        <td> 0.4 </td>\n",
       "        <td>  </td>\n",
       "        <td>  </td>\n",
       "        <td> 0 </td>\n",
       "        <td>  </td>\n",
       "        <td>  </td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <th> 1 </th>\n",
       "        <td> b1 </td>\n",
       "        <td> 9.0 </td>\n",
       "        <td> 1.4 </td>\n",
       "        <td>  </td>\n",
       "        <td>  </td>\n",
       "        <td>  </td>\n",
       "        <td>  </td>\n",
       "        <td>  </td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <th> 2 </th>\n",
       "        <td> b2 </td>\n",
       "        <td> 5.0 </td>\n",
       "        <td> 0.8 </td>\n",
       "        <td>  </td>\n",
       "        <td>  </td>\n",
       "        <td>  </td>\n",
       "        <td>  </td>\n",
       "        <td>  </td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <th> 3 </th>\n",
       "        <td> b3 </td>\n",
       "        <td> 1.88 </td>\n",
       "        <td> 0.33 </td>\n",
       "        <td>  </td>\n",
       "        <td>  </td>\n",
       "        <td>  </td>\n",
       "        <td>  </td>\n",
       "        <td>  </td>\n",
       "    </tr>\n",
       "</table><table>\n",
       "    <tr>\n",
       "        <td></td>\n",
       "        <th> mu </th>\n",
       "        <th> b1 </th>\n",
       "        <th> b2 </th>\n",
       "        <th> b3 </th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <th> mu </th>\n",
       "        <td> 1.67e-05 </td>\n",
       "        <td style=\"background-color:rgb(250,250,250);color:black\"> -4.5e-06 </td>\n",
       "        <td style=\"background-color:rgb(250,250,250);color:black\"> -4.31e-06 <strong>(-0.001)</strong> </td>\n",
       "        <td style=\"background-color:rgb(250,250,250);color:black\"> -7.88e-07 </td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <th> b1 </th>\n",
       "        <td style=\"background-color:rgb(250,250,250);color:black\"> -4.5e-06 </td>\n",
       "        <td> 2.09 </td>\n",
       "        <td style=\"background-color:rgb(250,250,250);color:black\"> 1.16e-06 </td>\n",
       "        <td style=\"background-color:rgb(250,250,250);color:black\"> 2.13e-07 </td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <th> b2 </th>\n",
       "        <td style=\"background-color:rgb(250,250,250);color:black\"> -4.31e-06 <strong>(-0.001)</strong> </td>\n",
       "        <td style=\"background-color:rgb(250,250,250);color:black\"> 1.16e-06 </td>\n",
       "        <td> 0.713 </td>\n",
       "        <td style=\"background-color:rgb(250,250,250);color:black\"> 2.04e-07 </td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <th> b3 </th>\n",
       "        <td style=\"background-color:rgb(250,250,250);color:black\"> -7.88e-07 </td>\n",
       "        <td style=\"background-color:rgb(250,250,250);color:black\"> 2.13e-07 </td>\n",
       "        <td style=\"background-color:rgb(250,250,250);color:black\"> 2.04e-07 </td>\n",
       "        <td> 0.111 </td>\n",
       "    </tr>\n",
       "</table>"
      ],
      "text/plain": [
       "┌─────────────────────────────────────────────────────────────────────────┐\n",
       "│                                Migrad                                   │\n",
       "├──────────────────────────────────┬──────────────────────────────────────┤\n",
       "│ FCN = -7.475                     │              Nfcn = 155              │\n",
       "│ EDM = 4.2e-05 (Goal: 0.0001)     │                                      │\n",
       "├──────────────────────────────────┼──────────────────────────────────────┤\n",
       "│          Valid Minimum           │       SOME Parameters at limit       │\n",
       "├──────────────────────────────────┼──────────────────────────────────────┤\n",
       "│ Below EDM threshold (goal x 10)  │           Below call limit           │\n",
       "├───────────────┬──────────────────┼───────────┬─────────────┬────────────┤\n",
       "│  Covariance   │     Hesse ok     │ Accurate  │  Pos. def.  │ Not forced │\n",
       "└───────────────┴──────────────────┴───────────┴─────────────┴────────────┘\n",
       "┌───┬──────┬───────────┬───────────┬────────────┬────────────┬─────────┬─────────┬───────┐\n",
       "│   │ Name │   Value   │ Hesse Err │ Minos Err- │ Minos Err+ │ Limit-  │ Limit+  │ Fixed │\n",
       "├───┼──────┼───────────┼───────────┼────────────┼────────────┼─────────┼─────────┼───────┤\n",
       "│ 0 │ mu   │    0.0    │    0.4    │            │            │    0    │         │       │\n",
       "│ 1 │ b1   │    9.0    │    1.4    │            │            │         │         │       │\n",
       "│ 2 │ b2   │    5.0    │    0.8    │            │            │         │         │       │\n",
       "│ 3 │ b3   │   1.88    │   0.33    │            │            │         │         │       │\n",
       "└───┴──────┴───────────┴───────────┴────────────┴────────────┴─────────┴─────────┴───────┘\n",
       "┌────┬─────────────────────────────────────────┐\n",
       "│    │        mu        b1        b2        b3 │\n",
       "├────┼─────────────────────────────────────────┤\n",
       "│ mu │  1.67e-05  -4.5e-06 -4.31e-06 -7.88e-07 │\n",
       "│ b1 │  -4.5e-06      2.09  1.16e-06  2.13e-07 │\n",
       "│ b2 │ -4.31e-06  1.16e-06     0.713  2.04e-07 │\n",
       "│ b3 │ -7.88e-07  2.13e-07  2.04e-07     0.111 │\n",
       "└────┴─────────────────────────────────────────┘"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mData.simplex()\n",
    "mData.migrad()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "138bf496",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<table>\n",
       "    <tr>\n",
       "        <th colspan=\"5\" style=\"text-align:center\" title=\"Minimizer\"> Migrad </th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td colspan=\"2\" style=\"text-align:left\" title=\"Minimum value of function\"> FCN = -7.475 </td>\n",
       "        <td colspan=\"3\" style=\"text-align:center\" title=\"No. of function evaluations in last call and total number\"> Nfcn = 594 </td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td colspan=\"2\" style=\"text-align:left\" title=\"Estimated distance to minimum and goal\"> EDM = 4.2e-05 (Goal: 0.0001) </td>\n",
       "        <td colspan=\"3\" style=\"text-align:center\" title=\"No. of gradient evaluations in last call and total number\">  </td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td colspan=\"2\" style=\"text-align:center;background-color:#92CCA6;color:black\"> Valid Minimum </td>\n",
       "        <td colspan=\"3\" style=\"text-align:center;background-color:#FFF79A;color:black\"> SOME Parameters at limit </td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td colspan=\"2\" style=\"text-align:center;background-color:#92CCA6;color:black\"> Below EDM threshold (goal x 10) </td>\n",
       "        <td colspan=\"3\" style=\"text-align:center;background-color:#92CCA6;color:black\"> Below call limit </td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <td style=\"text-align:center;background-color:#92CCA6;color:black\"> Covariance </td>\n",
       "        <td style=\"text-align:center;background-color:#92CCA6;color:black\"> Hesse ok </td>\n",
       "        <td style=\"text-align:center;background-color:#92CCA6;color:black\" title=\"Is covariance matrix accurate?\"> Accurate </td>\n",
       "        <td style=\"text-align:center;background-color:#92CCA6;color:black\" title=\"Is covariance matrix positive definite?\"> Pos. def. </td>\n",
       "        <td style=\"text-align:center;background-color:#92CCA6;color:black\" title=\"Was positive definiteness enforced by Minuit?\"> Not forced </td>\n",
       "    </tr>\n",
       "</table><table>\n",
       "    <tr>\n",
       "        <td></td>\n",
       "        <th title=\"Variable name\"> Name </th>\n",
       "        <th title=\"Value of parameter\"> Value </th>\n",
       "        <th title=\"Hesse error\"> Hesse Error </th>\n",
       "        <th title=\"Minos lower error\"> Minos Error- </th>\n",
       "        <th title=\"Minos upper error\"> Minos Error+ </th>\n",
       "        <th title=\"Lower limit of the parameter\"> Limit- </th>\n",
       "        <th title=\"Upper limit of the parameter\"> Limit+ </th>\n",
       "        <th title=\"Is the parameter fixed in the fit\"> Fixed </th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <th> 0 </th>\n",
       "        <td> mu </td>\n",
       "        <td> 8e-6 </td>\n",
       "        <td> 417915e-6 </td>\n",
       "        <td> -8e-6 </td>\n",
       "        <td> 372808e-6 </td>\n",
       "        <td> 0 </td>\n",
       "        <td>  </td>\n",
       "        <td>  </td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <th> 1 </th>\n",
       "        <td> b1 </td>\n",
       "        <td> 9.0 </td>\n",
       "        <td> 1.4 </td>\n",
       "        <td> -1.4 </td>\n",
       "        <td> 1.6 </td>\n",
       "        <td>  </td>\n",
       "        <td>  </td>\n",
       "        <td>  </td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <th> 2 </th>\n",
       "        <td> b2 </td>\n",
       "        <td> 5.0 </td>\n",
       "        <td> 0.8 </td>\n",
       "        <td> -0.8 </td>\n",
       "        <td> 0.9 </td>\n",
       "        <td>  </td>\n",
       "        <td>  </td>\n",
       "        <td>  </td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <th> 3 </th>\n",
       "        <td> b3 </td>\n",
       "        <td> 1.88 </td>\n",
       "        <td> 0.33 </td>\n",
       "        <td> -0.31 </td>\n",
       "        <td> 0.36 </td>\n",
       "        <td>  </td>\n",
       "        <td>  </td>\n",
       "        <td>  </td>\n",
       "    </tr>\n",
       "</table><table>\n",
       "    <tr>\n",
       "        <td></td>\n",
       "        <th colspan=\"2\" style=\"text-align:center\" title=\"Parameter name\"> mu </th>\n",
       "        <th colspan=\"2\" style=\"text-align:center\" title=\"Parameter name\"> b1 </th>\n",
       "        <th colspan=\"2\" style=\"text-align:center\" title=\"Parameter name\"> b2 </th>\n",
       "        <th colspan=\"2\" style=\"text-align:center\" title=\"Parameter name\"> b3 </th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <th title=\"Lower and upper minos error of the parameter\"> Error </th>\n",
       "        <td> -8e-6 </td>\n",
       "        <td> 372808e-6 </td>\n",
       "        <td> -1.4 </td>\n",
       "        <td> 1.6 </td>\n",
       "        <td> -0.8 </td>\n",
       "        <td> 0.9 </td>\n",
       "        <td> -0.31 </td>\n",
       "        <td> 0.36 </td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <th title=\"Validity of lower/upper minos error\"> Valid </th>\n",
       "        <td style=\"background-color:#92CCA6;color:black\"> True </td>\n",
       "        <td style=\"background-color:#92CCA6;color:black\"> True </td>\n",
       "        <td style=\"background-color:#92CCA6;color:black\"> True </td>\n",
       "        <td style=\"background-color:#92CCA6;color:black\"> True </td>\n",
       "        <td style=\"background-color:#92CCA6;color:black\"> True </td>\n",
       "        <td style=\"background-color:#92CCA6;color:black\"> True </td>\n",
       "        <td style=\"background-color:#92CCA6;color:black\"> True </td>\n",
       "        <td style=\"background-color:#92CCA6;color:black\"> True </td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <th title=\"Did scan hit limit of any parameter?\"> At Limit </th>\n",
       "        <td style=\"background-color:#c15ef7;color:black\"> True </td>\n",
       "        <td style=\"background-color:#92CCA6;color:black\"> False </td>\n",
       "        <td style=\"background-color:#92CCA6;color:black\"> False </td>\n",
       "        <td style=\"background-color:#92CCA6;color:black\"> False </td>\n",
       "        <td style=\"background-color:#92CCA6;color:black\"> False </td>\n",
       "        <td style=\"background-color:#92CCA6;color:black\"> False </td>\n",
       "        <td style=\"background-color:#92CCA6;color:black\"> False </td>\n",
       "        <td style=\"background-color:#92CCA6;color:black\"> False </td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <th title=\"Did scan hit function call limit?\"> Max FCN </th>\n",
       "        <td style=\"background-color:#92CCA6;color:black\"> False </td>\n",
       "        <td style=\"background-color:#92CCA6;color:black\"> False </td>\n",
       "        <td style=\"background-color:#92CCA6;color:black\"> False </td>\n",
       "        <td style=\"background-color:#92CCA6;color:black\"> False </td>\n",
       "        <td style=\"background-color:#92CCA6;color:black\"> False </td>\n",
       "        <td style=\"background-color:#92CCA6;color:black\"> False </td>\n",
       "        <td style=\"background-color:#92CCA6;color:black\"> False </td>\n",
       "        <td style=\"background-color:#92CCA6;color:black\"> False </td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <th title=\"New minimum found when doing scan?\"> New Min </th>\n",
       "        <td style=\"background-color:#92CCA6;color:black\"> False </td>\n",
       "        <td style=\"background-color:#92CCA6;color:black\"> False </td>\n",
       "        <td style=\"background-color:#92CCA6;color:black\"> False </td>\n",
       "        <td style=\"background-color:#92CCA6;color:black\"> False </td>\n",
       "        <td style=\"background-color:#92CCA6;color:black\"> False </td>\n",
       "        <td style=\"background-color:#92CCA6;color:black\"> False </td>\n",
       "        <td style=\"background-color:#92CCA6;color:black\"> False </td>\n",
       "        <td style=\"background-color:#92CCA6;color:black\"> False </td>\n",
       "    </tr>\n",
       "</table><table>\n",
       "    <tr>\n",
       "        <td></td>\n",
       "        <th> mu </th>\n",
       "        <th> b1 </th>\n",
       "        <th> b2 </th>\n",
       "        <th> b3 </th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <th> mu </th>\n",
       "        <td> 1.67e-05 </td>\n",
       "        <td style=\"background-color:rgb(250,250,250);color:black\"> -4.5e-06 </td>\n",
       "        <td style=\"background-color:rgb(250,250,250);color:black\"> -4.31e-06 <strong>(-0.001)</strong> </td>\n",
       "        <td style=\"background-color:rgb(250,250,250);color:black\"> -7.88e-07 </td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <th> b1 </th>\n",
       "        <td style=\"background-color:rgb(250,250,250);color:black\"> -4.5e-06 </td>\n",
       "        <td> 2.09 </td>\n",
       "        <td style=\"background-color:rgb(250,250,250);color:black\"> 1.16e-06 </td>\n",
       "        <td style=\"background-color:rgb(250,250,250);color:black\"> 2.13e-07 </td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <th> b2 </th>\n",
       "        <td style=\"background-color:rgb(250,250,250);color:black\"> -4.31e-06 <strong>(-0.001)</strong> </td>\n",
       "        <td style=\"background-color:rgb(250,250,250);color:black\"> 1.16e-06 </td>\n",
       "        <td> 0.713 </td>\n",
       "        <td style=\"background-color:rgb(250,250,250);color:black\"> 2.04e-07 </td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "        <th> b3 </th>\n",
       "        <td style=\"background-color:rgb(250,250,250);color:black\"> -7.88e-07 </td>\n",
       "        <td style=\"background-color:rgb(250,250,250);color:black\"> 2.13e-07 </td>\n",
       "        <td style=\"background-color:rgb(250,250,250);color:black\"> 2.04e-07 </td>\n",
       "        <td> 0.111 </td>\n",
       "    </tr>\n",
       "</table>"
      ],
      "text/plain": [
       "┌─────────────────────────────────────────────────────────────────────────┐\n",
       "│                                Migrad                                   │\n",
       "├──────────────────────────────────┬──────────────────────────────────────┤\n",
       "│ FCN = -7.475                     │              Nfcn = 594              │\n",
       "│ EDM = 4.2e-05 (Goal: 0.0001)     │                                      │\n",
       "├──────────────────────────────────┼──────────────────────────────────────┤\n",
       "│          Valid Minimum           │       SOME Parameters at limit       │\n",
       "├──────────────────────────────────┼──────────────────────────────────────┤\n",
       "│ Below EDM threshold (goal x 10)  │           Below call limit           │\n",
       "├───────────────┬──────────────────┼───────────┬─────────────┬────────────┤\n",
       "│  Covariance   │     Hesse ok     │ Accurate  │  Pos. def.  │ Not forced │\n",
       "└───────────────┴──────────────────┴───────────┴─────────────┴────────────┘\n",
       "┌───┬──────┬───────────┬───────────┬────────────┬────────────┬─────────┬─────────┬───────┐\n",
       "│   │ Name │   Value   │ Hesse Err │ Minos Err- │ Minos Err+ │ Limit-  │ Limit+  │ Fixed │\n",
       "├───┼──────┼───────────┼───────────┼────────────┼────────────┼─────────┼─────────┼───────┤\n",
       "│ 0 │ mu   │   8e-6    │ 417915e-6 │   -8e-6    │ 372808e-6  │    0    │         │       │\n",
       "│ 1 │ b1   │    9.0    │    1.4    │    -1.4    │    1.6     │         │         │       │\n",
       "│ 2 │ b2   │    5.0    │    0.8    │    -0.8    │    0.9     │         │         │       │\n",
       "│ 3 │ b3   │   1.88    │   0.33    │   -0.31    │    0.36    │         │         │       │\n",
       "└───┴──────┴───────────┴───────────┴────────────┴────────────┴─────────┴─────────┴───────┘\n",
       "┌──────────┬───────────────────────┬───────────────────────┬───────────────────────┬───────────────────────┐\n",
       "│          │          mu           │          b1           │          b2           │          b3           │\n",
       "├──────────┼───────────┬───────────┼───────────┬───────────┼───────────┬───────────┼───────────┬───────────┤\n",
       "│  Error   │   -8e-6   │ 372808e-6 │   -1.4    │    1.6    │   -0.8    │    0.9    │   -0.31   │   0.36    │\n",
       "│  Valid   │   True    │   True    │   True    │   True    │   True    │   True    │   True    │   True    │\n",
       "│ At Limit │   True    │   False   │   False   │   False   │   False   │   False   │   False   │   False   │\n",
       "│ Max FCN  │   False   │   False   │   False   │   False   │   False   │   False   │   False   │   False   │\n",
       "│ New Min  │   False   │   False   │   False   │   False   │   False   │   False   │   False   │   False   │\n",
       "└──────────┴───────────┴───────────┴───────────┴───────────┴───────────┴───────────┴───────────┴───────────┘\n",
       "┌────┬─────────────────────────────────────────┐\n",
       "│    │        mu        b1        b2        b3 │\n",
       "├────┼─────────────────────────────────────────┤\n",
       "│ mu │  1.67e-05  -4.5e-06 -4.31e-06 -7.88e-07 │\n",
       "│ b1 │  -4.5e-06      2.09  1.16e-06  2.13e-07 │\n",
       "│ b2 │ -4.31e-06  1.16e-06     0.713  2.04e-07 │\n",
       "│ b3 │ -7.88e-07  2.13e-07  2.04e-07     0.111 │\n",
       "└────┴─────────────────────────────────────────┘"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mData.minos()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "067318e0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Show a profile log likelihood scan (this is just for fun)\n",
    "mu, loglik= mData.draw_mnprofile(\"mu\",size=100, bound=[-0.8,2], subtract_min=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "94610a3f",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, '$\\\\Delta$log-lik')"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# It does not look so pretty, but we can redraw it\n",
    "ax = plt.subplot(111)\n",
    "ax.plot(mu,loglik)\n",
    "ax.set_xlim(mu[0], mu[-1])\n",
    "ax.set_ylim(bottom=0)\n",
    "ax.grid()\n",
    "ax.plot([0,0],[0,ax.get_ylim()[1]], color='black',linestyle='dotted')\n",
    "ax.plot([mu[0], mu[-1]], [0.5, 0.5], color='red', linestyle='dashed')\n",
    "ax.plot([mu[0], mu[-1]], [2.0, 2.0], color='red', linestyle='dashed')\n",
    "ax.set_xlabel(\"Signal Strength\", size=15)\n",
    "ax.set_ylabel(\"$\\Delta$log-lik\", size=15)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "1e9acf18",
   "metadata": {},
   "outputs": [],
   "source": [
    " def getTestStat(theFit, theMu, theFitVal):\n",
    "    \"\"\"\"\n",
    "    Calculate the LHC-style test statistic\n",
    "    Input:\n",
    "        theFit    = a myFit object that has already been fit\n",
    "        theMu     = the value of mu at which we calculate the test statistics\n",
    "        theFitVal = the \"best\" value of mu\n",
    "    Outputs:\n",
    "        test_statistics, fitted_values_at_mu=theMu\n",
    "    \"\"\"\n",
    "    pinit = np.array([theMu, bg[0], bg[1], bg[2]])  # initial guesses\n",
    "    m1 = Minuit(theFit.myNLL, pinit, name=(\"mu\", \"b1\", \"b2\", \"b3\"))\n",
    "    m1.fixed['mu'] = True\n",
    "    m1.errordef = Minuit.LIKELIHOOD\n",
    "    m1.simplex()\n",
    "    m1.migrad()\n",
    "    \n",
    "    mu0 = max(theFitVal, 0)\n",
    "    pinit = np.array([mu0, bg[0], bg[1], bg[2]])  # initial guesses\n",
    "    m0 = Minuit(theFit.myNLL, pinit, name=(\"mu\", \"b1\", \"b2\", \"b3\"))\n",
    "    m0.fixed['mu'] = True\n",
    "    m0.errordef = Minuit.LIKELIHOOD\n",
    "    m0.simplex()\n",
    "    m0.migrad()\n",
    "    \n",
    "    return 2*(m1.fval-m0.fval), m1.values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "2cf11449",
   "metadata": {},
   "outputs": [],
   "source": [
    "# This is not being used\n",
    "def plotCL(ax, clb, clsb, qmu):\n",
    "    \"\"\"\n",
    "    plot CLS as a function of qmu of axis ax give CL_b and CL_s+b\n",
    "    \"\"\"\n",
    "    # make sure that qmu is on a bin boundary...put it in the middle\n",
    "    nbin = 30\n",
    "    minx = np.amin(clsb)-2\n",
    "    maxx = np.amax(clb)+2\n",
    "    step = (maxx-minx)/nbin\n",
    "    # print((qmu-minx)/step)\n",
    "    minx = qmu-int((qmu-minx)/step)*step\n",
    "    bins = np.linspace(minx, minx+nbin*step, nbin+1)\n",
    "    _ = ax.hist(clb, bins, histtype='step', color='blue',   label=\"B-only\")\n",
    "    _ = ax.hist(clsb,bins, histtype='step', color='orange', label=\"S+B\")\n",
    "    _ = ax.hist(clb[clb<qmu],    bins, histtype='stepfilled', color='blue', alpha=0.2, label=\"1-CL$_B$\")\n",
    "    _ = ax.hist(clsb[clsb>qmu],  bins, histtype='stepfilled', color='orange', alpha=0.2, label=\"CL$_{S+B}$\")\n",
    "    ax.set_xlim([bins[0], bins[-1]])\n",
    "    ax.legend()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "ed9005d0",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Running  5000  toys for mu =  0.9\n",
      "Running  5000  toys for mu =  1.0\n",
      "Running  5000  toys for mu =  1.1\n",
      "Running  5000  toys for mu =  1.15\n",
      "Running  5000  toys for mu =  1.2\n",
      "Running  5000  toys for mu =  1.25\n",
      "Running  5000  toys for mu =  1.3\n",
      "Running  5000  toys for mu =  1.4\n",
      "Running  5000  toys for mu =  1.45\n"
     ]
    }
   ],
   "source": [
    "# %%timeit -n1 -r1\n",
    "# Scan mu, construct CLS and calculate its error\n",
    "np.random.seed(12345)\n",
    "Ntoys = 5000\n",
    "muToScan = np.array([0.9,1.0,1.1,1.15,1.2,1.25,1.3,1.4,1.45])\n",
    "CLS=[]\n",
    "CLS_Error=[]\n",
    "\n",
    "for mu in muToScan:\n",
    "    print(\"Running \", Ntoys, \" toys for mu = \",mu)\n",
    "    \n",
    "    # Get data (ie: observed) test stat at this mu\n",
    "    # and also the value of the BG fit at this mu\n",
    "    qmuobs, outVal = getTestStat(thisFit, mu, mData.values[0])\n",
    "    \n",
    "    # generate BG toys\n",
    "    tempB  = []\n",
    "    thisBG = np.array([outVal[1], outVal[2], outVal[3]])\n",
    "    for b in thisBG:\n",
    "            tempB.append(np.random.poisson(b,Ntoys))\n",
    "    bgToys = np.array(tempB)\n",
    "    \n",
    "    # generate signal toys\n",
    "    tempS  = []\n",
    "    for s in sig:\n",
    "        tempS.append(np.random.poisson(mu*s, Ntoys))\n",
    "    sigToys = np.array(tempS)\n",
    "    \n",
    "    # Now fit toys\n",
    "    CLB  = []\n",
    "    CLSB = []\n",
    "    for i in range(Ntoys):\n",
    "        # if i % 100 == 0: print(i, mu)\n",
    "            \n",
    "        # Fit B toys     \n",
    "        thisData = bgToys[:,i]\n",
    "        bgFit = myFit(thisData, sig, bg, err)\n",
    "        pinit = np.array([1, bg[0], bg[1], bg[2]])  # initial guesses\n",
    "        mB= Minuit(bgFit.myNLL, pinit, name=(\"mu\", \"b1\", \"b2\", \"b3\"))\n",
    "        mB.limits['mu'] = (0, None)\n",
    "        mB.errordef = Minuit.LIKELIHOOD\n",
    "        mB.simplex()\n",
    "        mB.migrad()   \n",
    "        if mB.values[0] > mu:\n",
    "            CLB.append(0)\n",
    "        else:\n",
    "            q, out = getTestStat(bgFit, mu, mB.values[0])   \n",
    "            CLB.append(q)\n",
    "        \n",
    "        \n",
    "        thisData = bgToys[:,i] + sigToys[:,i]\n",
    "        splusbFit = myFit(thisData, sig, bg, err)\n",
    "        pinit = np.array([1, bg[0], bg[1], bg[2]])  # initial guesses\n",
    "        mSB= Minuit(splusbFit.myNLL, pinit, name=(\"mu\", \"b1\", \"b2\", \"b3\"))\n",
    "        mSB.limits['mu'] = (0, None)\n",
    "        mSB.errordef = Minuit.LIKELIHOOD\n",
    "        mSB.simplex()\n",
    "        mSB.migrad()  \n",
    "        if mSB.values[0] > mu:\n",
    "            CLSB.append(0)\n",
    "        else:\n",
    "            q, out = getTestStat(splusbFit, mu, mSB.values[0])   \n",
    "            CLSB.append(q)\n",
    "    \n",
    "    # Calculates CLs \n",
    "    # (rely on the fact that the number of S and S+B toys are the same)\n",
    "    cl_b  = np.array(CLB)\n",
    "    cl_sb = np.array(CLSB)\n",
    "    num = (cl_sb>qmuobs).sum()\n",
    "    den = (cl_b>qmuobs).sum()\n",
    "    CLs = num/den\n",
    "    # print(num,den, num/den)\n",
    "    errCLs = CLs * np.sqrt(1/num + 1/den)\n",
    "    # print(CLs, errCLs)\n",
    "    CLS.append(CLs)\n",
    "    CLS_Error.append(errCLs)\n",
    "    \n",
    " "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "fe5a0c66",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0, 0.5, '$CL_S$')"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "ax = plt.subplot(111)\n",
    "ax.plot((1.20,1.20), (0,0.1), label='Combine limit', linestyle='dashed', color='orange')\n",
    "ax.plot((1.20+0.018,1.20+0.018), (0,0.1), linestyle='dashed', color='orange')\n",
    "ax.plot((1.20-0.018,1.20-0.018), (0,0.1), linestyle='dashed', color='orange')\n",
    "\n",
    "ax.errorbar(muToScan, np.array(CLS), yerr=np.array(CLS_Error), linestyle='dashed',\n",
    "           color='black', fmt='o')\n",
    "ax.grid()\n",
    "ax.legend(fontsize='x-large')\n",
    "ax.set_ylim(0, 0.15)\n",
    "ax.set_xlim([0.85,1.55])\n",
    "ax.plot((0.85, 1.55), (0.05,0.05), color='red', linestyle='dotted')\n",
    "ax.set_xlabel('$\\mu$', size=20)\n",
    "ax.set_ylabel('$CL_S$', size=20)"
   ]
  },
  {
   "attachments": {
    "image-2.png": {
     "image/png": "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"
    },
    "image-3.png": {
     "image/png": "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"
    },
    "image.png": {
     "image/png": "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"
    }
   },
   "cell_type": "markdown",
   "id": "c855851e",
   "metadata": {},
   "source": [
    "<hr style=\"border:2px solid blue\"> </hr>\n",
    "Do the exact same wth the CMS combine softare. <br>\n",
    "Here is the txt file\n",
    "\n",
    "![image.png](attachment:image.png)\n",
    "\n",
    "Here are the commads used\n",
    "\n",
    "![image-2.png](attachment:image-2.png)\n",
    "\n",
    "And here is the result\n",
    "\n",
    "![image-3.png](attachment:image-3.png)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5561b4cd",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8b64b787",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}