diff --git a/Aula 12_Exemplos.ipynb b/Aula 12_Exemplos.ipynb new file mode 100644 index 0000000..6c9b4dc --- /dev/null +++ b/Aula 12_Exemplos.ipynb @@ -0,0 +1,292 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "___\n", + "# Exemplos:

Distribuições Uniforme e Exponencial\n", + "\n", + "___\n", + "## Aula 12\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "___\n", + "## Lista de comandos:\n", + "\n", + "### Distribuição Uniforme\n", + "\n", + "Comandos quando $X\\sim Uniforme(a, b)$.\n", + "\n", + "* $f(x)$: `stats.uniform.pdf(x, loc=a, scale=b-a)`\n", + "\n", + "* $P(X\\leq x)$: `stats.uniform.cdf(x, loc=a, scale=b-a)`\n", + "\n", + "* $x$ tal que $p=P(X\\leq x)$: `stats.uniform.ppf(p, loc=a, scale=b-a)`\n", + "\n", + "* $E(X)$: `stats.uniform.mean(loc=a, scale=b-a)`\n", + "\n", + "* $Var(X)$: `stats.uniform.var(loc=a, scale=b-a)`\n", + "\n", + "* $DP(X)$: `stats.uniform.std(loc=a, scale=b-a)`\n", + "\n", + "Link: https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.uniform.html" + ] + }, + { + "cell_type": "code", + "execution_count": 66, + "metadata": {}, + "outputs": [], + "source": [ + "from scipy import stats" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "___\n", + "\n", + "## Exemplo 1:\n", + "\n", + "O torque suportado por parafusos de uma linha de montagem varia segundo uma distribuição uniforme entre 100 Nm e 200Nm. (sendo Nm: Newton metros)\n", + "\n", + "### Item a\n", + "\n", + "Qual a probabilidade de o torque de um parafuso qualquer estar entre 150Nm e 175Nm?\n", + "\n", + "*Resposta esperada: 0.25*" + ] + }, + { + "cell_type": "code", + "execution_count": 67, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0.25" + ] + }, + "execution_count": 67, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# ESCREVA SUA RESPOSTA AQUI\n", + "stats.uniform.cdf(175, scale=200-100, loc=100)-stats.uniform.cdf(150, scale=200-100, loc=100)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Item b\n", + "\n", + "Um parafuso sobreviveu a um teste de torque que garante que ele suporta pelo menos 150Nm. Qual a probabilidade que suporte até 175Nm?\n", + "\n", + "*Resposta esperada: 0.5*" + ] + }, + { + "cell_type": "code", + "execution_count": 68, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0.5" + ] + }, + "execution_count": 68, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# ESCREVA SUA RESPOSTA AQUI\n", + "stats.uniform.cdf(175, scale=200-150, loc=150)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Item c\n", + "\n", + "Construa um gráfico que mostre o formato da função densidade de probabilidade de uma Uniforme com a=100 e b=200.**" + ] + }, + { + "cell_type": "code", + "execution_count": 69, + "metadata": {}, + "outputs": [], + "source": [ + "import numpy as np\n", + "import matplotlib.pyplot as plt\n", + "%matplotlib inline" + ] + }, + { + "cell_type": "code", + "execution_count": 70, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "[]" + ] + }, + "execution_count": 70, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAj4AAAGdCAYAAAASUnlxAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8pXeV/AAAACXBIWXMAAA9hAAAPYQGoP6dpAAAkYUlEQVR4nO3dfUzV993/8deRc0ctsFZTjhTKTd1E7Gb1WC1Gxn5LB2qd7dYrpZe5mPtjjVyrNeDivJvprnW/wZbezSkaE9KlNrFmQ63ZWgvN9IxWdBbRWiWzmVQsSghLe45WKwf4/P7o5fn1lCNw8J7P85GcTL7nfb43n7ieZ74c0GGMMQIAALDAqBt9AgAAANcL4QMAAKxB+AAAAGsQPgAAwBqEDwAAsAbhAwAArEH4AAAAaxA+AADAGs4bfQI3k76+Pp0+fVpJSUlyOBw3+nQAAMAQGGN09uxZpaWladSoge/pED5fcvr0aWVkZNzo0wAAAMNw6tQppaenDzhD+HxJUlKSpC8WLjk5+QafDQAAGIpQKKSMjIzI+/hACJ8vufTtreTkZMIHAIBbzFA+psKHmwEAgDUIHwAAYA3CBwAAWIPwAQAA1iB8AACANQgfAABgDcIHAABYg/ABAADWIHwAAIA1CB8AAGANwgcAAFiD8AEAANYgfAAAgDUIHwAAYA3CBwAAWIPwAQAA1iB8AACANQgfAABgDcIHAABYg/ABAADWIHwAAIA1CB8AAGANwgcAAFiD8AEAANYgfAAAgDUIHwAAYA3CBwAAWIPwAQAA1iB8AACANQgfAABgDcIHAABYg/ABAADWIHwAAIA1CB8AAGANwgcAAFiD8AEAANYgfAAAgDUIHwAAYA3CBwAAWIPwAQAA1iB8AACANQgfAABgDcIHAABYY1jhU11drezsbHm9Xvn9fjU0NAw4HwgE5Pf75fV6lZOTo40bN0Y9f/ToUT322GPKysqSw+HQSy+9dMXHXbRo0YD7AgAA9ok7fLZu3ary8nKtXr1azc3NKigo0Jw5c9TW1hZzvrW1VXPnzlVBQYGam5u1atUqLVmyRLW1tZGZ8+fPKycnR1VVVfL5fFd83B07dmj//v1KS0uL9/IAAMBIZuI0ffp0U1ZWFrUtNzfXrFixIub8z3/+c5Obmxu1bdGiRebBBx+MOZ+ZmWlefPHFYR/3448/Nnfffbf54IMPLruvywkGg0aSCQaDQ34NAAC4seJ5/47rjk93d7eamppUVFQUtb2oqEh79+6N+ZrGxsZ+88XFxXrvvfcUDoev6nH7+vpUWlqqZcuWadKkSYPu9+LFiwqFQlEPAAAwcsUVPl1dXert7VVqamrU9tTUVHV0dMR8TUdHR8z5np4edXV1XdXj/va3v5XT6dSSJUuGtN/KykqlpKREHhkZGUN6HQAAuDUN68PNDocj6mtjTL9tg83H2n4lx21qatLvf/97/fGPfxzyfleuXKlgMBh5nDp1Kq7zAQAAt5a4wmfs2LFKSEjod3ens7Oz392YS3w+X8x5p9OpMWPGXLXjNjQ0qLOzU/fcc4+cTqecTqdOnjypn/3sZ8rKyoq5X4/Ho+Tk5KgHAAAYueIKH7fbLb/fr/r6+qjt9fX1mjlzZszX5Ofn95uvq6vTtGnT5HK5rtpxS0tL9f777+vQoUORR1pampYtW6a33nprqJcIAABGMGe8L1i6dKlKS0s1bdo05efna9OmTWpra1NZWZmkL7591N7erldeeUWSVFZWpnXr1mnp0qV68skn1djYqJqaGm3ZsiWyz+7ubh07dizy5/b2dh06dEi33367xo8fP6Tjjhkzpt8dJJfLJZ/PpwkTJgxjaQAAwEgTd/iUlJTo3//+t371q1/pzJkzuu+++/TGG28oMzNTknTmzJmo362TnZ2tN954QxUVFVq/fr3S0tK0du1aPfbYY5GZ06dPa8qUKZGvn3vuOT333HMqLCzUnj17hnRcAACAwTjMpU8aQ6FQSCkpKQoGg3zeBwCAW0Q879/8W10AAMAahA8AALAG4QMAAKxB+AAAAGsQPgAAwBqEDwAAsAbhAwAArEH4AAAAaxA+AADAGoQPAACwBuEDAACsQfgAAABrED4AAMAahA8AALAG4QMAAKxB+AAAAGsQPgAAwBqEDwAAsAbhAwAArEH4AAAAaxA+AADAGoQPAACwBuEDAACsQfgAAABrED4AAMAahA8AALAG4QMAAKxB+AAAAGsQPgAAwBqEDwAAsAbhAwAArEH4AAAAaxA+AADAGoQPAACwBuEDAACsQfgAAABrED4AAMAahA8AALAG4QMAAKxB+AAAAGsQPgAAwBqEDwAAsAbhAwAArEH4AAAAaxA+AADAGoQPAACwBuEDAACsQfgAAABrED4AAMAahA8AALAG4QMAAKxB+AAAAGsQPgAAwBqEDwAAsAbhAwAArEH4AAAAawwrfKqrq5WdnS2v1yu/36+GhoYB5wOBgPx+v7xer3JycrRx48ao548eParHHntMWVlZcjgceumll+I+bjgc1vLly/XNb35To0ePVlpamn70ox/p9OnTw7lEAAAwAsUdPlu3blV5eblWr16t5uZmFRQUaM6cOWpra4s539raqrlz56qgoEDNzc1atWqVlixZotra2sjM+fPnlZOTo6qqKvl8vmEd9/z58zp48KDWrFmjgwcPatu2bTp+/Ljmz58f7yUCAIARymGMMfG8YMaMGZo6dao2bNgQ2TZx4kQ9+uijqqys7De/fPly7dy5Uy0tLZFtZWVlOnz4sBobG/vNZ2Vlqby8XOXl5Vd0XEk6cOCApk+frpMnT+qee+4Z9NpCoZBSUlIUDAaVnJw86DwAALjx4nn/juuOT3d3t5qamlRUVBS1vaioSHv37o35msbGxn7zxcXFeu+99xQOh6/ZcSUpGAzK4XDoa1/7WsznL168qFAoFPUAAAAjV1zh09XVpd7eXqWmpkZtT01NVUdHR8zXdHR0xJzv6elRV1fXNTvu559/rhUrVmjBggWXrb/KykqlpKREHhkZGUM6HwAAcGsa1oebHQ5H1NfGmH7bBpuPtf1qHTccDuuJJ55QX1+fqqurL7u/lStXKhgMRh6nTp2K63wAAMCtxRnP8NixY5WQkNDvLktnZ2e/uzGX+Hy+mPNOp1Njxoy56scNh8N6/PHH1draqr/97W8Dfq/P4/HI4/EM6RwAAMCtL647Pm63W36/X/X19VHb6+vrNXPmzJivyc/P7zdfV1enadOmyeVyXdXjXoqeDz/8UG+//faQwwoAANghrjs+krR06VKVlpZq2rRpys/P16ZNm9TW1qaysjJJX3z7qL29Xa+88oqkL36Ca926dVq6dKmefPJJNTY2qqamRlu2bInss7u7W8eOHYv8ub29XYcOHdLtt9+u8ePHD+m4PT09+o//+A8dPHhQf/nLX9Tb2xu5Q3TnnXfK7XZfwTIBAIARwQzD+vXrTWZmpnG73Wbq1KkmEAhEnlu4cKEpLCyMmt+zZ4+ZMmWKcbvdJisry2zYsCHq+dbWViOp3+Or+xnouJfbhySze/fuIV1XMBg0kkwwGIxrPQAAwI0Tz/t33L/HZyTj9/gAAHDruWa/xwcAAOBWRvgAAABrED4AAMAahA8AALAG4QMAAKxB+AAAAGsQPgAAwBqEDwAAsAbhAwAArEH4AAAAaxA+AADAGoQPAACwBuEDAACsQfgAAABrED4AAMAahA8AALAG4QMAAKxB+AAAAGsQPgAAwBqEDwAAsAbhAwAArEH4AAAAaxA+AADAGoQPAACwBuEDAACsQfgAAABrED4AAMAahA8AALAG4QMAAKxB+AAAAGsQPgAAwBqEDwAAsAbhAwAArEH4AAAAaxA+AADAGoQPAACwBuEDAACsQfgAAABrED4AAMAahA8AALAG4QMAAKxB+AAAAGsQPgAAwBqEDwAAsAbhAwAArEH4AAAAaxA+AADAGoQPAACwBuEDAACsQfgAAABrED4AAMAahA8AALAG4QMAAKxB+AAAAGsQPgAAwBqEDwAAsMawwqe6ulrZ2dnyer3y+/1qaGgYcD4QCMjv98vr9SonJ0cbN26Mev7o0aN67LHHlJWVJYfDoZdeemlYxzXG6Je//KXS0tKUmJio73znOzp69OhwLhEAAIxAcYfP1q1bVV5ertWrV6u5uVkFBQWaM2eO2traYs63trZq7ty5KigoUHNzs1atWqUlS5aotrY2MnP+/Hnl5OSoqqpKPp9v2Mf93e9+pxdeeEHr1q3TgQMH5PP59L3vfU9nz56N9zIBAMBIZOI0ffp0U1ZWFrUtNzfXrFixIub8z3/+c5Obmxu1bdGiRebBBx+MOZ+ZmWlefPHFuI/b19dnfD6fqaqqijz/+eefm5SUFLNx48ZBr8sYY4LBoJFkgsHgkOYBAMCNF8/7tzOeSOru7lZTU5NWrFgRtb2oqEh79+6N+ZrGxkYVFRVFbSsuLlZNTY3C4bBcLtdVOW5ra6s6OjqijuXxeFRYWKi9e/dq0aJF/fZ78eJFXbx4MfJ1KBQa9FyGo6e3T//3jZZrsm8AAG4lzlEOrX4478YdP57hrq4u9fb2KjU1NWp7amqqOjo6Yr6mo6Mj5nxPT4+6uro0bty4q3LcS/8ba+bkyZMx91tZWan/+Z//GfT4V6rPSC+/+9E1Pw4AADc7t3PUrRM+lzgcjqivjTH9tg02H2v71ThuPOe2cuVKLV26NPJ1KBRSRkZGXOc0FKMc0lP/596rvl8AAG41CaNu7A+UxxU+Y8eOVUJCQr+7O52dnf3utFzi8/lizjudTo0ZM+aqHffSh6I7Ojqi7iINdG4ej0cej2dI53AlnAmjtKw495ofBwAADCyu7HK73fL7/aqvr4/aXl9fr5kzZ8Z8TX5+fr/5uro6TZs2bUif7xnqcbOzs+Xz+aJmuru7FQgELntuAADALnF/q2vp0qUqLS3VtGnTlJ+fr02bNqmtrU1lZWWSvvj2UXt7u1555RVJUllZmdatW6elS5fqySefVGNjo2pqarRly5bIPru7u3Xs2LHIn9vb23Xo0CHdfvvtGj9+/JCO63A4VF5ert/85jf6+te/rq9//ev6zW9+o9tuu00LFiy4slUCAAAjw3B+bGz9+vUmMzPTuN1uM3XqVBMIBCLPLVy40BQWFkbN79mzx0yZMsW43W6TlZVlNmzYEPV8a2urkdTv8dX9DHRcY774kfZnnnnG+Hw+4/F4zLe//W1z5MiRIV8XP84OAMCtJ573b4cx//tJYygUCiklJUXBYFDJyck3+nQAAMAQxPP+zb/VBQAArEH4AAAAaxA+AADAGoQPAACwBuEDAACsQfgAAABrED4AAMAahA8AALAG4QMAAKxB+AAAAGsQPgAAwBqEDwAAsAbhAwAArEH4AAAAaxA+AADAGoQPAACwBuEDAACsQfgAAABrED4AAMAahA8AALAG4QMAAKxB+AAAAGsQPgAAwBqEDwAAsAbhAwAArEH4AAAAaxA+AADAGoQPAACwBuEDAACsQfgAAABrED4AAMAahA8AALAG4QMAAKxB+AAAAGsQPgAAwBqEDwAAsAbhAwAArEH4AAAAaxA+AADAGoQPAACwBuEDAACsQfgAAABrED4AAMAahA8AALAG4QMAAKxB+AAAAGsQPgAAwBqEDwAAsAbhAwAArEH4AAAAaxA+AADAGoQPAACwBuEDAACsQfgAAABrED4AAMAahA8AALAG4QMAAKwxrPCprq5Wdna2vF6v/H6/GhoaBpwPBALy+/3yer3KycnRxo0b+83U1tYqLy9PHo9HeXl52r59e9TzZ8+eVXl5uTIzM5WYmKiZM2fqwIEDUTPnzp3T4sWLlZ6ersTERE2cOFEbNmwYziUCAIARKO7w2bp1q8rLy7V69Wo1NzeroKBAc+bMUVtbW8z51tZWzZ07VwUFBWpubtaqVau0ZMkS1dbWRmYaGxtVUlKi0tJSHT58WKWlpXr88ce1f//+yMxPfvIT1dfXa/PmzTpy5IiKior00EMPqb29PTJTUVGhXbt26dVXX1VLS4sqKir09NNP6/XXX4/3MgEAwAjkMMaYeF4wY8YMTZ06NepOysSJE/Xoo4+qsrKy3/zy5cu1c+dOtbS0RLaVlZXp8OHDamxslCSVlJQoFArpzTffjMzMnj1bd9xxh7Zs2aILFy4oKSlJr7/+uh5++OHIzP3336958+bp17/+tSTpvvvuU0lJidasWROZ8fv9mjt3rp599tlBry0UCiklJUXBYFDJyclxrAoAALhR4nn/juuOT3d3t5qamlRUVBS1vaioSHv37o35msbGxn7zxcXFeu+99xQOhwecubTPnp4e9fb2yuv1Rs0kJibqnXfeiXw9a9Ys7dy5U+3t7TLGaPfu3Tp+/LiKi4tjntvFixcVCoWiHgAAYOSKK3y6urrU29ur1NTUqO2pqanq6OiI+ZqOjo6Y8z09Perq6hpw5tI+k5KSlJ+fr2effVanT59Wb2+vXn31Ve3fv19nzpyJvGbt2rXKy8tTenq63G63Zs+ererqas2aNSvmuVVWViolJSXyyMjIiGc5AADALWZYH252OBxRXxtj+m0bbP6r2wfb5+bNm2WM0d133y2Px6O1a9dqwYIFSkhIiMysXbtW+/bt086dO9XU1KTnn39eP/3pT/X222/HPK+VK1cqGAxGHqdOnRrkygEAwK3MGc/w2LFjlZCQ0O/uTmdnZ787Npf4fL6Y806nU2PGjBlw5sv7vPfeexUIBPTZZ58pFApp3LhxKikpUXZ2tiTpwoULWrVqlbZv3x75HNC3vvUtHTp0SM8995weeuihfufm8Xjk8XjiWQIAAHALi+uOj9vtlt/vV319fdT2+vp6zZw5M+Zr8vPz+83X1dVp2rRpcrlcA87E2ufo0aM1btw4ffLJJ3rrrbf0yCOPSJLC4bDC4bBGjYq+pISEBPX19cVzmQAAYKQycXrttdeMy+UyNTU15tixY6a8vNyMHj3afPTRR8YYY1asWGFKS0sj8ydOnDC33XabqaioMMeOHTM1NTXG5XKZP//5z5GZd9991yQkJJiqqirT0tJiqqqqjNPpNPv27YvM7Nq1y7z55pvmxIkTpq6uzkyePNlMnz7ddHd3R2YKCwvNpEmTzO7du82JEyfMyy+/bLxer6murh7StQWDQSPJBIPBeJcFAADcIPG8f8cdPsYYs379epOZmWncbreZOnWqCQQCkecWLlxoCgsLo+b37NljpkyZYtxut8nKyjIbNmzot88//elPZsKECcblcpnc3FxTW1sb9fzWrVtNTk6Ocbvdxufzmaeeesp8+umnUTNnzpwxP/7xj01aWprxer1mwoQJ5vnnnzd9fX1Dui7CBwCAW088799x/x6fkYzf4wMAwK3nmv0eHwAAgFsZ4QMAAKxB+AAAAGsQPgAAwBqEDwAAsAbhAwAArEH4AAAAaxA+AADAGoQPAACwBuEDAACsQfgAAABrED4AAMAahA8AALAG4QMAAKxB+AAAAGsQPgAAwBqEDwAAsAbhAwAArEH4AAAAaxA+AADAGoQPAACwBuEDAACsQfgAAABrED4AAMAahA8AALAG4QMAAKxB+AAAAGsQPgAAwBqEDwAAsAbhAwAArEH4AAAAaxA+AADAGoQPAACwBuEDAACsQfgAAABrED4AAMAahA8AALAG4QMAAKxB+AAAAGsQPgAAwBqEDwAAsAbhAwAArEH4AAAAaxA+AADAGoQPAACwBuEDAACsQfgAAABrED4AAMAahA8AALAG4QMAAKxB+AAAAGsQPgAAwBqEDwAAsAbhAwAArEH4AAAAaxA+AADAGsMKn+rqamVnZ8vr9crv96uhoWHA+UAgIL/fL6/Xq5ycHG3cuLHfTG1trfLy8uTxeJSXl6ft27dHPX/27FmVl5crMzNTiYmJmjlzpg4cONBvPy0tLZo/f75SUlKUlJSkBx98UG1tbcO5TAAAMMLEHT5bt25VeXm5Vq9erebmZhUUFGjOnDmXjYvW1lbNnTtXBQUFam5u1qpVq7RkyRLV1tZGZhobG1VSUqLS0lIdPnxYpaWlevzxx7V///7IzE9+8hPV19dr8+bNOnLkiIqKivTQQw+pvb09MvOvf/1Ls2bNUm5urvbs2aPDhw9rzZo18nq98V4mAAAYgRzGGBPPC2bMmKGpU6dqw4YNkW0TJ07Uo48+qsrKyn7zy5cv186dO9XS0hLZVlZWpsOHD6uxsVGSVFJSolAopDfffDMyM3v2bN1xxx3asmWLLly4oKSkJL3++ut6+OGHIzP333+/5s2bp1//+teSpCeeeEIul0ubN2+O55IiQqGQUlJSFAwGlZycPKx9AACA6yue9++47vh0d3erqalJRUVFUduLioq0d+/emK9pbGzsN19cXKz33ntP4XB4wJlL++zp6VFvb2+/OzeJiYl65513JEl9fX3661//qm984xsqLi7WXXfdpRkzZmjHjh2XvZ6LFy8qFApFPQAAwMgVV/h0dXWpt7dXqampUdtTU1PV0dER8zUdHR0x53t6etTV1TXgzKV9JiUlKT8/X88++6xOnz6t3t5evfrqq9q/f7/OnDkjSers7NS5c+dUVVWl2bNnq66uTj/4wQ/0wx/+UIFAIOa5VVZWKiUlJfLIyMiIZzkAAMAtZlgfbnY4HFFfG2P6bRts/qvbB9vn5s2bZYzR3XffLY/Ho7Vr12rBggVKSEiQ9MUdH0l65JFHVFFRofvvv18rVqzQvHnzYn6YWpJWrlypYDAYeZw6dWqwSwcAALewuMJn7NixSkhI6Hd3p7Ozs98dm0t8Pl/MeafTqTFjxgw48+V93nvvvQoEAjp37pxOnTqlf/zjHwqHw8rOzo6cm9PpVF5eXtR+Jk6ceNkPXns8HiUnJ0c9AADAyBVX+Ljdbvn9ftXX10dtr6+v18yZM2O+Jj8/v998XV2dpk2bJpfLNeBMrH2OHj1a48aN0yeffKK33npLjzzySOTcHnjgAf3zn/+Mmj9+/LgyMzPjuUwAADBSmTi99tprxuVymZqaGnPs2DFTXl5uRo8ebT766CNjjDErVqwwpaWlkfkTJ06Y2267zVRUVJhjx46Zmpoa43K5zJ///OfIzLvvvmsSEhJMVVWVaWlpMVVVVcbpdJp9+/ZFZnbt2mXefPNNc+LECVNXV2cmT55spk+fbrq7uyMz27ZtMy6Xy2zatMl8+OGH5g9/+INJSEgwDQ0NQ7q2YDBoJJlgMBjvsgAAgBsknvfvuMPHGGPWr19vMjMzjdvtNlOnTjWBQCDy3MKFC01hYWHU/J49e8yUKVOM2+02WVlZZsOGDf32+ac//clMmDDBuFwuk5uba2pra6Oe37p1q8nJyTFut9v4fD7z1FNPmU8//bTffmpqasz48eON1+s1kydPNjt27BjydRE+AADceuJ5/4779/iMZPweHwAAbj3X7Pf4AAAA3MoIHwAAYA3CBwAAWIPwAQAA1iB8AACANQgfAABgDcIHAABYg/ABAADWIHwAAIA1CB8AAGANwgcAAFiD8AEAANYgfAAAgDUIHwAAYA3CBwAAWIPwAQAA1iB8AACANQgfAABgDcIHAABYg/ABAADWIHwAAIA1CB8AAGANwgcAAFiD8AEAANYgfAAAgDUIHwAAYA3CBwAAWIPwAQAA1iB8AACANQgfAABgDcIHAABYg/ABAADWIHwAAIA1CB8AAGANwgcAAFiD8AEAANYgfAAAgDUIHwAAYA3CBwAAWIPwAQAA1iB8AACANQgfAABgDeeNPoGbiTFGkhQKhW7wmQAAgKG69L596X18IITPl5w9e1aSlJGRcYPPBAAAxOvs2bNKSUkZcMZhhpJHlujr69Pp06eVlJQkh8NxVfcdCoWUkZGhU6dOKTk5+aruG/8f63x9sM7XD2t9fbDO18e1WmdjjM6ePau0tDSNGjXwp3i44/Mlo0aNUnp6+jU9RnJyMv+nug5Y5+uDdb5+WOvrg3W+Pq7FOg92p+cSPtwMAACsQfgAAABrED7Xicfj0TPPPCOPx3OjT2VEY52vD9b5+mGtrw/W+fq4GdaZDzcDAABrcMcHAABYg/ABAADWIHwAAIA1CB8AAGANwucK/P3vf9f3v/99paWlyeFwaMeOHVHPG2P0y1/+UmlpaUpMTNR3vvMdHT16NGrm4sWLevrppzV27FiNHj1a8+fP18cff3wdr+LmN9A6h8NhLV++XN/85jc1evRopaWl6Uc/+pFOnz4dtQ/WeWgG+zv9ZYsWLZLD4dBLL70UtZ21HtxQ1rmlpUXz589XSkqKkpKS9OCDD6qtrS3yPOs8uMHW+dy5c1q8eLHS09OVmJioiRMnasOGDVEzrPPgKisr9cADDygpKUl33XWXHn30Uf3zn/+MmrmZ3g8Jnyvw2WefafLkyVq3bl3M53/3u9/phRde0Lp163TgwAH5fD5973vfi/ybYJJUXl6u7du367XXXtM777yjc+fOad68eert7b1el3HTG2idz58/r4MHD2rNmjU6ePCgtm3bpuPHj2v+/PlRc6zz0Az2d/qSHTt2aP/+/UpLS+v3HGs9uMHW+V//+pdmzZql3Nxc7dmzR4cPH9aaNWvk9XojM6zz4AZb54qKCu3atUuvvvqqWlpaVFFRoaefflqvv/56ZIZ1HlwgENBTTz2lffv2qb6+Xj09PSoqKtJnn30Wmbmp3g8NrgpJZvv27ZGv+/r6jM/nM1VVVZFtn3/+uUlJSTEbN240xhjz6aefGpfLZV577bXITHt7uxk1apTZtWvXdTv3W8lX1zmWf/zjH0aSOXnypDGGdR6uy631xx9/bO6++27zwQcfmMzMTPPiiy9GnmOt4xdrnUtKSsx//dd/XfY1rHP8Yq3zpEmTzK9+9auobVOnTjW/+MUvjDGs83B1dnYaSSYQCBhjbr73Q+74XCOtra3q6OhQUVFRZJvH41FhYaH27t0rSWpqalI4HI6aSUtL03333ReZQfyCwaAcDoe+9rWvSWKdr6a+vj6VlpZq2bJlmjRpUr/nWesr19fXp7/+9a/6xje+oeLiYt11112aMWNG1LdpWOerY9asWdq5c6fa29tljNHu3bt1/PhxFRcXS2KdhysYDEqS7rzzTkk33/sh4XONdHR0SJJSU1Ojtqempkae6+jokNvt1h133HHZGcTn888/14oVK7RgwYLIP4DHOl89v/3tb+V0OrVkyZKYz7PWV66zs1Pnzp1TVVWVZs+erbq6Ov3gBz/QD3/4QwUCAUms89Wydu1a5eXlKT09XW63W7Nnz1Z1dbVmzZoliXUeDmOMli5dqlmzZum+++6TdPO9H/Kvs19jDocj6mtjTL9tXzWUGfQXDof1xBNPqK+vT9XV1YPOs87xaWpq0u9//3sdPHgw7nVjrYeur69PkvTII4+ooqJCknT//fdr79692rhxowoLCy/7WtY5PmvXrtW+ffu0c+dOZWZm6u9//7t++tOfaty4cXrooYcu+zrW+fIWL16s999/X++8806/526W90Pu+FwjPp9PkvqVamdnZ6R6fT6furu79cknn1x2BkMTDof1+OOPq7W1VfX19ZG7PRLrfLU0NDSos7NT99xzj5xOp5xOp06ePKmf/exnysrKksRaXw1jx46V0+lUXl5e1PaJEydGfqqLdb5yFy5c0KpVq/TCCy/o+9//vr71rW9p8eLFKikp0XPPPSeJdY7X008/rZ07d2r37t1KT0+PbL/Z3g8Jn2skOztbPp9P9fX1kW3d3d0KBAKaOXOmJMnv98vlckXNnDlzRh988EFkBoO7FD0ffvih3n77bY0ZMybqedb56igtLdX777+vQ4cORR5paWlatmyZ3nrrLUms9dXgdrv1wAMP9Ptx4OPHjyszM1MS63w1hMNhhcNhjRoV/TaYkJAQuevGOg+NMUaLFy/Wtm3b9Le//U3Z2dlRz99074dX9aPSljl79qxpbm42zc3NRpJ54YUXTHNzc+SniaqqqkxKSorZtm2bOXLkiPnP//xPM27cOBMKhSL7KCsrM+np6ebtt982Bw8eNN/97nfN5MmTTU9Pz426rJvOQOscDofN/PnzTXp6ujl06JA5c+ZM5HHx4sXIPljnoRns7/RXffWnuoxhrYdisHXetm2bcblcZtOmTebDDz80f/jDH0xCQoJpaGiI7IN1Htxg61xYWGgmTZpkdu/ebU6cOGFefvll4/V6TXV1dWQfrPPg/vu//9ukpKSYPXv2RP03+Pz585GZm+n9kPC5Art37zaS+j0WLlxojPniR/ieeeYZ4/P5jMfjMd/+9rfNkSNHovZx4cIFs3jxYnPnnXeaxMREM2/ePNPW1nYDrubmNdA6t7a2xnxOktm9e3dkH6zz0Az2d/qrYoUPaz24oaxzTU2NGT9+vPF6vWby5Mlmx44dUftgnQc32DqfOXPG/PjHPzZpaWnG6/WaCRMmmOeff9709fVF9sE6D+5y/w1++eWXIzM30/uh439PGgAAYMTjMz4AAMAahA8AALAG4QMAAKxB+AAAAGsQPgAAwBqEDwAAsAbhAwAArEH4AAAAaxA+AADAGoQPAACwBuEDAACsQfgAAABr/D/KIydrCpZHSgAAAABJRU5ErkJggg==", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# ESCREVA SUA RESPOSTA AQUI\n", + "b = 200\n", + "a = 100\n", + "x = np.arange(a,b,1e-3)\n", + "f = [1/(b-a) for i in x]\n", + "plt.plot(x, f)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "___\n", + "## Lista de comandos:\n", + "\n", + "### Distribuição Exponencial\n", + "\n", + "Comandos quando $X\\sim Exp(\\lambda)$. Lembrando que nesse caso $E(X) = \\mu = 1/\\lambda$.\n", + "\n", + "* $f(x)$: `stats.expon.pdf(x, loc=0, scale=mu)`\n", + "\n", + "* $P(X\\leq x)$: `stats.expon.cdf(x, loc=0, scale=mu)`\n", + "\n", + "* $x$ tal que $p=P(X\\leq x)$: `stats.expon.ppf(p, loc=0, scale=mu)`\n", + "\n", + "* $E(X)$: `stats.expon.mean(loc=0, scale=mu)`\n", + "\n", + "* $Var(X)$: `stats.expon.var(loc=0, scale=mu)`\n", + "\n", + "* $DP(X)$: `stats.expon.std(loc=0, scale=mu)`\n", + "\n", + "Link: https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.expon.html" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "___\n", + "\n", + "## Exemplo 2:\n", + "\n", + "Admita que o tempo até que uma venda seja realizada em uma loja siga um modelo (distribuição) exponencial com média de 0,2 horas (12 minutos).\n", + "\n", + "### Item a\n", + "\n", + "Qual é a probabilidade de uma venda demorar mais de meia hora para ser feita?\n", + "\n", + "*Resposta esperada: 0.08208499862389884*" + ] + }, + { + "cell_type": "code", + "execution_count": 71, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0.08208499862389884" + ] + }, + "execution_count": 71, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# ESCREVA SUA RESPOSTA AQUI\n", + "1-stats.expon.cdf(0.5, loc=0, scale=0.2)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Item b\n", + "\n", + "Dado que você sabe que a próxima venda vai ser feita em menos de meia hora, qual a probabilidade de que seja em menos de 5 minutos?\n", + "\n", + "*Resposta esperada: 0.37123194335935633*" + ] + }, + { + "cell_type": "code", + "execution_count": 72, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0.37123194335935633" + ] + }, + "execution_count": 72, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# ESCREVA SUA RESPOSTA AQUI\n", + "stats.expon.cdf(1/12, loc=0, scale=0.2)/stats.expon.cdf(0.5, loc=0, scale=0.2)" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.10.13" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git "a/Aula08_Exerc\303\255cio_VariaveisAleatoriasDiscretas.ipynb" "b/Aula08_Exerc\303\255cio_VariaveisAleatoriasDiscretas.ipynb" index 4c8140c..531daae 100644 --- "a/Aula08_Exerc\303\255cio_VariaveisAleatoriasDiscretas.ipynb" +++ "b/Aula08_Exerc\303\255cio_VariaveisAleatoriasDiscretas.ipynb" @@ -243,7 +243,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.10.9" + "version": "3.10.13" } }, "nbformat": 4, diff --git a/Aula09_Atividade_ExplorandoDuasVariaveisQuantitativas_Mundo.ipynb b/Aula09_Atividade_ExplorandoDuasVariaveisQuantitativas_Mundo.ipynb index 519e9c9..4638fbc 100644 --- a/Aula09_Atividade_ExplorandoDuasVariaveisQuantitativas_Mundo.ipynb +++ b/Aula09_Atividade_ExplorandoDuasVariaveisQuantitativas_Mundo.ipynb @@ -862,7 +862,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.10.9" + "version": "3.10.13" } }, "nbformat": 4, diff --git a/Aula09_Exercicio_ExplorandoDuasVariaveisQuantitativas_Discriminacao.ipynb b/Aula09_Exercicio_ExplorandoDuasVariaveisQuantitativas_Discriminacao.ipynb index 436d8c0..0f0a58e 100644 --- a/Aula09_Exercicio_ExplorandoDuasVariaveisQuantitativas_Discriminacao.ipynb +++ b/Aula09_Exercicio_ExplorandoDuasVariaveisQuantitativas_Discriminacao.ipynb @@ -36,9 +36,18 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 164, "metadata": {}, - "outputs": [], + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Esperamos trabalhar no diretório\n", + "c:\\Users\\ribei\\OneDrive\\Área de Trabalho\\cdados\\cdados\n" + ] + } + ], "source": [ "#%matplotlib inline\n", "import pandas as pd\n", @@ -81,7 +90,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 165, "metadata": {}, "outputs": [], "source": [ @@ -90,11 +99,191 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 166, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
SexoAnosSalario
47masc2242
48masc1255
49masc2139
50masc637
51masc2568
52masc2764
53masc935
54masc1548
55masc042
56masc331
57masc038
58masc426
59masc035
60masc1233
61masc1340
62masc1029
63masc027
64masc1131
65masc224
66masc1533
\n", + "
" + ], + "text/plain": [ + " Sexo Anos Salario\n", + "47 masc 22 42\n", + "48 masc 12 55\n", + "49 masc 21 39\n", + "50 masc 6 37\n", + "51 masc 25 68\n", + "52 masc 27 64\n", + "53 masc 9 35\n", + "54 masc 15 48\n", + "55 masc 0 42\n", + "56 masc 3 31\n", + "57 masc 0 38\n", + "58 masc 4 26\n", + "59 masc 0 35\n", + "60 masc 12 33\n", + "61 masc 13 40\n", + "62 masc 10 29\n", + "63 masc 0 27\n", + "64 masc 11 31\n", + "65 masc 2 24\n", + "66 masc 15 33" + ] + }, + "execution_count": 166, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "dados.head()" + "dados.tail(20)" ] }, { @@ -118,11 +307,87 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 167, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "count 67.000000\n", + "mean 38.343284\n", + "std 10.221119\n", + "min 22.000000\n", + "25% 31.000000\n", + "50% 37.000000\n", + "75% 42.000000\n", + "max 69.000000\n", + "Name: Salario, dtype: float64" + ] + }, + "execution_count": 167, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Escreva seu código aqui" + "# Escreva seu código aqui\n", + "dados.Salario.describe()" + ] + }, + { + "cell_type": "code", + "execution_count": 168, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "count 35.000000\n", + "mean 40.971429\n", + "std 11.733526\n", + "min 24.000000\n", + "25% 33.000000\n", + "50% 39.000000\n", + "75% 47.000000\n", + "max 69.000000\n", + "Name: Salario, dtype: float64" + ] + }, + "execution_count": 168, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "dados.loc[dados.Sexo == 'masc', :]['Salario'].describe()" + ] + }, + { + "cell_type": "code", + "execution_count": 169, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "count 32.000000\n", + "mean 35.468750\n", + "std 7.422652\n", + "min 22.000000\n", + "25% 29.750000\n", + "50% 35.000000\n", + "75% 40.000000\n", + "max 52.000000\n", + "Name: Salario, dtype: float64" + ] + }, + "execution_count": 169, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "dados.loc[dados.Sexo == 'fem', :]['Salario'].describe()" ] }, { @@ -156,11 +421,43 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 170, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "61.4781512605042" + ] + }, + "execution_count": 170, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Escreva seu código aqui" + "# Escreva seu código aqui\n", + "dados.loc[dados.Sexo == 'masc', :]['Salario'].cov(dados.loc[dados.Sexo == 'masc', :]['Anos'])" + ] + }, + { + "cell_type": "code", + "execution_count": 171, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "28.933467741935484" + ] + }, + "execution_count": 171, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "dados.loc[dados.Sexo == 'fem', :]['Salario'].cov(dados.loc[dados.Sexo == 'fem', :]['Anos'])" ] }, { @@ -191,7 +488,8 @@ "cell_type": "raw", "metadata": {}, "source": [ - "ESCREVA SUA RESPOSTA AQUI" + "ESCREVA SUA RESPOSTA AQUI\n", + "CD" ] }, { @@ -207,11 +505,43 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 172, "metadata": {}, - "outputs": [], + "outputs": [ + { + "data": { + "text/plain": [ + "0.6739986401774645" + ] + }, + "execution_count": 172, + "metadata": {}, + "output_type": "execute_result" + } + ], "source": [ - "# Escreva seu código aqui" + "# Escreva seu código aqui\n", + "dados.loc[dados.Sexo == 'masc', :]['Salario'].corr(dados.loc[dados.Sexo == 'masc', :]['Anos'])" + ] + }, + { + "cell_type": "code", + "execution_count": 173, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0.8022389898226462" + ] + }, + "execution_count": 173, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "dados.loc[dados.Sexo == 'fem', :]['Salario'].corr(dados.loc[dados.Sexo == 'fem', :]['Anos'])" ] }, { @@ -242,7 +572,8 @@ "cell_type": "raw", "metadata": {}, "source": [ - "ESCREVA SUA RESPOSTA AQUI" + "ESCREVA SUA RESPOSTA AQUI\n", + "CDGH" ] }, { @@ -258,7 +589,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 174, "metadata": {}, "outputs": [], "source": [ @@ -296,7 +627,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 175, "metadata": {}, "outputs": [], "source": [ @@ -316,7 +647,7 @@ }, { "cell_type": "code", - "execution_count": null, + "execution_count": 176, "metadata": {}, "outputs": [], "source": [ @@ -359,7 +690,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.7.4" + "version": "3.10.13" } }, "nbformat": 4, diff --git a/Aula11.ipynb b/Aula11.ipynb new file mode 100644 index 0000000..9581104 --- /dev/null +++ b/Aula11.ipynb @@ -0,0 +1,111 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 36, + "metadata": {}, + "outputs": [], + "source": [ + "import math as m\n", + "from scipy import stats" + ] + }, + { + "cell_type": "code", + "execution_count": 37, + "metadata": {}, + "outputs": [], + "source": [ + "def binomio (n, a, b):\n", + " termos = []\n", + " for k in range(n+1):\n", + " termos.append((m.factorial(n)/(m.factorial(k)*m.factorial(n-k)))*a**(n-k)*b**k)\n", + " return termos" + ] + }, + { + "cell_type": "code", + "execution_count": 38, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "0.512 0.384 0.096 0.008\n" + ] + } + ], + "source": [ + "P_F = 0.2\n", + "P_Fc = 1 - P_F\n", + "P0_3 = round(binomio(3, P_Fc, P_F)[0], 4)\n", + "P1_3 = round(binomio(3, P_Fc, P_F)[1], 4)\n", + "P2_3 = round(binomio(3, P_Fc, P_F)[2], 4)\n", + "P3_3 = round(binomio(3, P_Fc, P_F)[3], 4)\n", + "\n", + "print(P0_3, P1_3, P2_3, P3_3)" + ] + }, + { + "cell_type": "code", + "execution_count": 39, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "0.096\n" + ] + } + ], + "source": [ + "print(P2_3)" + ] + }, + { + "cell_type": "code", + "execution_count": 40, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "0.09930021480882523\n", + "0.09930021480882459\n" + ] + } + ], + "source": [ + "P20_100 = binomio(100, P_Fc, P_F)[20]\n", + "Pteste = stats.binom.pmf(20, 100, 0.2)\n", + "print(P20_100)\n", + "print(Pteste)" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "base", + "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": "3.10.13" + }, + "orig_nbformat": 4 + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git "a/Aula11_Atividade_ModelosProbabil\303\255sticosDiscretos.ipynb" "b/Aula11_Atividade_ModelosProbabil\303\255sticosDiscretos.ipynb" new file mode 100644 index 0000000..df5d3f0 --- /dev/null +++ "b/Aula11_Atividade_ModelosProbabil\303\255sticosDiscretos.ipynb" @@ -0,0 +1,672 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "___\n", + "# Atividade:

Modelos probabilísticos discretos e Dados\n", + "___\n", + "\n", + "## Aula 11\n", + "\n", + "**Objetivo da aula:** Ao final desta aula, o aluno deve ser capaz de especificar as distribuições de probabilidades adequadas para variáveis aleatórias discretas considerando modelos probabilísticos discretos já bem definidos na literatura estatística.\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "___\n", + "
\n", + "\n", + "## Índice\n", + "\n", + "- [Teoria: Distribuição Binomial](#teoria)\n", + " - [Esperança e Variância](#esperanca-variancia)\n", + "- [DETRAN](#detran)\n", + " - [Modelo teórico](#modelo-teorico)\n", + " - [Exercício 1](#ex1)\n", + " - [Exercício 2](#ex2)\n", + " - [Resultados empíricos](#resultados-empiricos)\n", + " - [Exercício 3](#ex3)\n", + " - [Exercício 4](#ex4)\n", + " - [Comparação: resultados empíricos X modelo teórico](#comparacao)\n", + " - [Opção 1: Frequências relativas X Probabilidades teóricas](#opcao1)\n", + " - [Opção 2: Frequência relativa acumulada X Probabilidade acumulada](#opcao2)\n", + " - [Exercício 5](#ex5)\n", + " - [Exercício 6](#ex6)\n", + " - [Exercício 7](#ex7)\n", + "- [Lista de comandos utilizados neste notebook](#comandos)" + ] + }, + { + "cell_type": "code", + "execution_count": 86, + "metadata": {}, + "outputs": [], + "source": [ + "%matplotlib inline\n", + "import pandas as pd\n", + "import matplotlib.pyplot as plt\n", + "import numpy as np\n", + "\n", + "from scipy import stats #importa apenas as funções de estatísticas da biblioteca SciPy." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "
\n", + "\n", + "# DETRAN \n", + "\n", + "Esse exercício irá explorar uma modelagem de dados reais.\n", + "\n", + "> **Confira alguns itens obrigatórios verificados durante a vistoria do Detran**\n", + ">\n", + "> *Todos os veículos, novos ou velhos, precisam passar por uma vistoria todos os anos. (...) O motorista precisa estar atento a alguns itens obrigatórios. Tudo deve funcionar perfeitamente, apresentar bom estado de conservação e estar dentro do prazo de validade.*\n", + ">\n", + "> Fonte: http://extra.globo.com/noticias/brasil/transito-seguro/confira-alguns-itens-obrigatorios-verificados-durante-vistoria-do-detran-10190355.html\n", + "\n", + "Essa matéria lista 14 itens que são inspecionados pelo Detran, dentre os quais têm-se: extintor de incêndio deve estar dentro do prazo de validade; pneus devem estar em bom estado de conservação; buzina deve funcionar perfeitamente; e cintos de segurança para todos os ocupantes do carro. \n", + "\n", + "Se, ao final da inspeção, todos os 14 itens estiverem funcionando perfeitamente, o motorista irá feliz para casa assegurado de que seu carro está sem problemas com a vistoria." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "
\n", + "\n", + "## Modelo teórico" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "___\n", + "\n", + "
\n", + "\n", + "## Teoria: Distribuição Binomial\n", + "\n", + "A distribuição binomial modela a número de sucessos (o evento de interesse) em uma determinada quantidade de tentativas. Mais formalmente, dizemos que uma variável aleatória $Y$ segue uma distribuição binomial utilizando a seguinte notação: $Y$~$Bin(n,p)$. Essa notação pode ser lida como: $Y$ segue uma distribuição binomial com $n$ tentativas e $p$ como probabilidade de sucesso em cada evento independente.\n", + "\n", + "A função de probabilidade (lembrando: que associa uma probabilidade a cada valor possível de $Y$) é dada por:\n", + "\n", + "$$P(Y=y)=\\left(\n", + "\\begin{array}{c}\n", + " n \\\\\n", + " y\n", + "\\end{array}\\right) p^y (1-p)^{(n-y)}$$\n", + "\n", + "Para que um experimento possa ser modelado por uma distribuição binomial, ele precisa ter as seguintes propriedades:\n", + "\n", + "- ser uma contagem de $n$ repetições (ou tentativas, ou ensaios) idênticas;\n", + "- cada repetição tem apenas 2 resultados possíveis: um é denominado sucesso (o resultado de interesse, que não necessariamente é positivo) e o outro, fracasso;\n", + "- a probabilidade de sucesso para cada ensaio é denominada $p$ e será constante em cada repetição. Consequentemente, a probabilidade de fracasso $(1-p)$ também não varia de tentativa para tentativa;\n", + "- as tentativas são independentes." + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "
\n", + "\n", + "### Esperança e Variância\n", + "\n", + "Se $Y$~$Bin(n,p)$, o valor esperado $E(Y)$ e a variância $Var(Y)$ são dados por:\n", + "\n", + "$\\qquad\\qquad E(Y) = np$\n", + "\n", + "$\\qquad\\qquad Var(Y) = np(1-p)$\n", + "\n", + "___" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "
\n", + "\n", + "### EXERCÍCIO 1\n", + "\n", + "Assuma que a variável **Quantidade de itens vistoriados em não conformidade em 14 itens vistoriados** possa ser ajustada pelo modelo binomial com parâmetros $n=14$ e $p=0,10$. Interprete esses parâmetros para o problema em questão e, ainda, discuta se as propriedades da distribuição binomial estão satisfeitas para o problema aqui me questão." + ] + }, + { + "cell_type": "raw", + "metadata": {}, + "source": [ + "PREENCHA COM AS SUAS RESPOSTAS:\n", + " \n", + "- n = 14: SUBSTITUA ESTE TEXTO PELA SUA INTERPRETAÇÃO DESTE PARÂMETRO\n", + "- p = 0,10: SUBSTITUA ESTE TEXTO PELA SUA INTERPRETAÇÃO DESTE PARÂMETRO\n", + "\n", + "As propriedades da distribuição binomial [estão satisfeitas/não estão satisfeitas] para o problema em questão?\n", + "Verifique as propriedades de um ensaio Binomial: \n", + "[COMPLETE COM A SUA RESPOSTA]" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "**Independente da sua resposta anterior, considere que a distribuição binomial seja adequada para modelar a variável de interesse nos próximos exercícios!**\n", + "\n", + "
\n", + "\n", + "### EXERCÍCIO 2\n", + "\n", + "
\n", + "\n", + "1. Consulte a [documentação do método `stats.binom.pmf`](https://docs.scipy.org/doc/scipy-0.14.0/reference/generated/scipy.stats.binom.html). Utilizando esse método, obtenha a probabilidade de cada uma das quantidades de itens em não conformidade, ou seja, de 0 a 14, quando $n=14$ e $p=0,10$. Armazene as probabilidades em uma lista (probabilidades de todas as quantidades possíveis, de 0 a 14) e guarde esta lista em uma variável chamada `probabilidades_teoricas`.\n", + "1. Calcule o valor esperado e a variância da quantidade de itens em não conformidade utilizando os métodos `stats.binom.mean` e `stats.binom.var` (a documentação está na mesma página do método `stats.binom.pmf`) e compare com a esperança e variância calculados a partir das [fórmulas da distribuição binomial](#esperanca-variancia).\n", + "\n", + "*Respostas esperadas para esperança e variância respectivamente: 1.4000000000000001 ; 1.2600000000000002*" + ] + }, + { + "cell_type": "code", + "execution_count": 87, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "1.4000000000000001 1.2600000000000002 1.4000000000000001 1.2600000000000002\n" + ] + } + ], + "source": [ + "# ESCREVA SEU CÓDIGO AQUI\n", + "n = 14\n", + "p = 0.1\n", + "probabilidades_teoricas = []\n", + "for i in range(n+1):\n", + " probabilidades_teoricas.append(stats.binom.pmf(i, n, p))\n", + "esp = stats.binom.mean(n, p)\n", + "var = stats.binom.var(n, p)\n", + "print(esp, var, n*p, n*p*(1-p))\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "
\n", + "\n", + "## Resultados empíricos" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "A base de dados `Carros.txt` apresenta, para cada um dos três mil carros de passeio vistoriados, duas informações:\n", + "\n", + "- **Tipo**: tipo de carro (1: Popular e 2: Não Popular)\n", + "- **Quantidade**: quantidade de itens vistoriados em não conformidade (que pode variar de 0 a 14) em 14 itens vistoriados\n", + "\n", + "Vamos começar carregando a base em um `DataFrame`:" + ] + }, + { + "cell_type": "code", + "execution_count": 88, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Esperamos trabalhar no diretório: \n", + "c:\\Users\\ribei\\OneDrive\\Área de Trabalho\\cdados\\cdados\n", + "\n" + ] + } + ], + "source": [ + "import os\n", + "print(f'Esperamos trabalhar no diretório: \\n{os.getcwd()}\\n')" + ] + }, + { + "cell_type": "code", + "execution_count": 89, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "Parece que o arquivo Carros.txt está na mesma pasta do notebook, yay!\n" + ] + } + ], + "source": [ + "filename = 'Carros.txt'\n", + "\n", + "if filename in os.listdir():\n", + " print(f'Parece que o arquivo {filename} está na mesma pasta do notebook, yay!')\n", + " \n", + "else:\n", + " print(f'Não encontrei o arquivo {filename}')" + ] + }, + { + "cell_type": "code", + "execution_count": 90, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "
\n", + "\n", + "\n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + " \n", + "
TipoQuantidade
110
212
312
413
511
\n", + "
" + ], + "text/plain": [ + " Tipo Quantidade\n", + "1 1 0\n", + "2 1 2\n", + "3 1 2\n", + "4 1 3\n", + "5 1 1" + ] + }, + "execution_count": 90, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "carros = pd.read_table('Carros.txt', sep=' ')\n", + "carros.head()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "
\n", + "\n", + "### EXERCÍCIO 3\n", + "\n", + "Considerando todos os carros, gere uma tabela de frequências relativas da quantidade de itens vistoriados em não conformidade (variável **Quantidade**). Armazene essa tabela em uma variável chamada `frequencias_relativas`. \n", + "\n", + "**Observação:** utilize o método `.sort_index()` no resultado do `.value_counts()` para corrigir a ordenação." + ] + }, + { + "cell_type": "code", + "execution_count": 91, + "metadata": {}, + "outputs": [ + { + "ename": "KeyError", + "evalue": "False", + "output_type": "error", + "traceback": [ + "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[1;31mKeyError\u001b[0m Traceback (most recent call last)", + "File \u001b[1;32mc:\\Users\\ribei\\anaconda3\\lib\\site-packages\\pandas\\core\\indexes\\base.py:3653\u001b[0m, in \u001b[0;36mIndex.get_loc\u001b[1;34m(self, key)\u001b[0m\n\u001b[0;32m 3652\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[1;32m-> 3653\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_engine\u001b[39m.\u001b[39;49mget_loc(casted_key)\n\u001b[0;32m 3654\u001b[0m \u001b[39mexcept\u001b[39;00m \u001b[39mKeyError\u001b[39;00m \u001b[39mas\u001b[39;00m err:\n", + "File \u001b[1;32mc:\\Users\\ribei\\anaconda3\\lib\\site-packages\\pandas\\_libs\\index.pyx:147\u001b[0m, in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[1;34m()\u001b[0m\n", + "File \u001b[1;32mc:\\Users\\ribei\\anaconda3\\lib\\site-packages\\pandas\\_libs\\index.pyx:155\u001b[0m, in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[1;34m()\u001b[0m\n", + "File \u001b[1;32mpandas\\_libs\\index_class_helper.pxi:70\u001b[0m, in \u001b[0;36mpandas._libs.index.Int64Engine._check_type\u001b[1;34m()\u001b[0m\n", + "\u001b[1;31mKeyError\u001b[0m: False", + "\nThe above exception was the direct cause of the following exception:\n", + "\u001b[1;31mKeyError\u001b[0m Traceback (most recent call last)", + "\u001b[1;32mc:\\Users\\ribei\\OneDrive\\Área de Trabalho\\cdados\\cdados\\Aula11_Atividade_ModelosProbabilísticosDiscretos.ipynb Cell 18\u001b[0m line \u001b[0;36m3\n\u001b[0;32m 1\u001b[0m \u001b[39m# ESCREVA O CÓDIGO DA SUA RESPOSTA AQUI\u001b[39;00m\n\u001b[0;32m 2\u001b[0m frequencias_relativas \u001b[39m=\u001b[39m carros\u001b[39m.\u001b[39mvalue_counts(normalize\u001b[39m=\u001b[39m\u001b[39mTrue\u001b[39;00m)\u001b[39m.\u001b[39msort_index()\n\u001b[1;32m----> 3\u001b[0m frequencias_relativas\u001b[39m.\u001b[39;49mloc[\u001b[39m\"\u001b[39;49m\u001b[39mQuantidade\u001b[39;49m\u001b[39m\"\u001b[39;49m \u001b[39m==\u001b[39;49m \u001b[39m0\u001b[39;49m, :]\n", + "File \u001b[1;32mc:\\Users\\ribei\\anaconda3\\lib\\site-packages\\pandas\\core\\indexing.py:1097\u001b[0m, in \u001b[0;36m_LocationIndexer.__getitem__\u001b[1;34m(self, key)\u001b[0m\n\u001b[0;32m 1095\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_is_scalar_access(key):\n\u001b[0;32m 1096\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mobj\u001b[39m.\u001b[39m_get_value(\u001b[39m*\u001b[39mkey, takeable\u001b[39m=\u001b[39m\u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_takeable)\n\u001b[1;32m-> 1097\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_getitem_tuple(key)\n\u001b[0;32m 1098\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[0;32m 1099\u001b[0m \u001b[39m# we by definition only have the 0th axis\u001b[39;00m\n\u001b[0;32m 1100\u001b[0m axis \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39maxis \u001b[39mor\u001b[39;00m \u001b[39m0\u001b[39m\n", + "File \u001b[1;32mc:\\Users\\ribei\\anaconda3\\lib\\site-packages\\pandas\\core\\indexing.py:1280\u001b[0m, in \u001b[0;36m_LocIndexer._getitem_tuple\u001b[1;34m(self, tup)\u001b[0m\n\u001b[0;32m 1278\u001b[0m \u001b[39mwith\u001b[39;00m suppress(IndexingError):\n\u001b[0;32m 1279\u001b[0m tup \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_expand_ellipsis(tup)\n\u001b[1;32m-> 1280\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_getitem_lowerdim(tup)\n\u001b[0;32m 1282\u001b[0m \u001b[39m# no multi-index, so validate all of the indexers\u001b[39;00m\n\u001b[0;32m 1283\u001b[0m tup \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_validate_tuple_indexer(tup)\n", + "File \u001b[1;32mc:\\Users\\ribei\\anaconda3\\lib\\site-packages\\pandas\\core\\indexing.py:976\u001b[0m, in \u001b[0;36m_LocationIndexer._getitem_lowerdim\u001b[1;34m(self, tup)\u001b[0m\n\u001b[0;32m 974\u001b[0m \u001b[39m# we may have a nested tuples indexer here\u001b[39;00m\n\u001b[0;32m 975\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_is_nested_tuple_indexer(tup):\n\u001b[1;32m--> 976\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_getitem_nested_tuple(tup)\n\u001b[0;32m 978\u001b[0m \u001b[39m# we maybe be using a tuple to represent multiple dimensions here\u001b[39;00m\n\u001b[0;32m 979\u001b[0m ax0 \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mobj\u001b[39m.\u001b[39m_get_axis(\u001b[39m0\u001b[39m)\n", + "File \u001b[1;32mc:\\Users\\ribei\\anaconda3\\lib\\site-packages\\pandas\\core\\indexing.py:1048\u001b[0m, in \u001b[0;36m_LocationIndexer._getitem_nested_tuple\u001b[1;34m(self, tup)\u001b[0m\n\u001b[0;32m 1043\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mall\u001b[39m(is_hashable(x) \u001b[39mor\u001b[39;00m com\u001b[39m.\u001b[39mis_null_slice(x) \u001b[39mfor\u001b[39;00m x \u001b[39min\u001b[39;00m tup):\n\u001b[0;32m 1044\u001b[0m \u001b[39m# GH#10521 Series should reduce MultiIndex dimensions instead of\u001b[39;00m\n\u001b[0;32m 1045\u001b[0m \u001b[39m# DataFrame, IndexingError is not raised when slice(None,None,None)\u001b[39;00m\n\u001b[0;32m 1046\u001b[0m \u001b[39m# with one row.\u001b[39;00m\n\u001b[0;32m 1047\u001b[0m \u001b[39mwith\u001b[39;00m suppress(IndexingError):\n\u001b[1;32m-> 1048\u001b[0m \u001b[39mreturn\u001b[39;00m cast(_LocIndexer, \u001b[39mself\u001b[39;49m)\u001b[39m.\u001b[39;49m_handle_lowerdim_multi_index_axis0(\n\u001b[0;32m 1049\u001b[0m tup\n\u001b[0;32m 1050\u001b[0m )\n\u001b[0;32m 1051\u001b[0m \u001b[39melif\u001b[39;00m \u001b[39misinstance\u001b[39m(\u001b[39mself\u001b[39m\u001b[39m.\u001b[39mobj, ABCSeries) \u001b[39mand\u001b[39;00m \u001b[39many\u001b[39m(\n\u001b[0;32m 1052\u001b[0m \u001b[39misinstance\u001b[39m(k, \u001b[39mtuple\u001b[39m) \u001b[39mfor\u001b[39;00m k \u001b[39min\u001b[39;00m tup\n\u001b[0;32m 1053\u001b[0m ):\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 1057\u001b[0m \u001b[39m# that themselves contain a slice entry\u001b[39;00m\n\u001b[0;32m 1058\u001b[0m \u001b[39m# See test_loc_series_getitem_too_many_dimensions\u001b[39;00m\n\u001b[0;32m 1059\u001b[0m \u001b[39mraise\u001b[39;00m IndexingError(\u001b[39m\"\u001b[39m\u001b[39mToo many indexers\u001b[39m\u001b[39m\"\u001b[39m)\n", + "File \u001b[1;32mc:\\Users\\ribei\\anaconda3\\lib\\site-packages\\pandas\\core\\indexing.py:1306\u001b[0m, in \u001b[0;36m_LocIndexer._handle_lowerdim_multi_index_axis0\u001b[1;34m(self, tup)\u001b[0m\n\u001b[0;32m 1302\u001b[0m \u001b[39mexcept\u001b[39;00m \u001b[39mKeyError\u001b[39;00m \u001b[39mas\u001b[39;00m ek:\n\u001b[0;32m 1303\u001b[0m \u001b[39m# raise KeyError if number of indexers match\u001b[39;00m\n\u001b[0;32m 1304\u001b[0m \u001b[39m# else IndexingError will be raised\u001b[39;00m\n\u001b[0;32m 1305\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mndim \u001b[39m<\u001b[39m \u001b[39mlen\u001b[39m(tup) \u001b[39m<\u001b[39m\u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mobj\u001b[39m.\u001b[39mindex\u001b[39m.\u001b[39mnlevels:\n\u001b[1;32m-> 1306\u001b[0m \u001b[39mraise\u001b[39;00m ek\n\u001b[0;32m 1307\u001b[0m \u001b[39mraise\u001b[39;00m IndexingError(\u001b[39m\"\u001b[39m\u001b[39mNo label returned\u001b[39m\u001b[39m\"\u001b[39m) \u001b[39mfrom\u001b[39;00m \u001b[39mek\u001b[39;00m\n", + "File \u001b[1;32mc:\\Users\\ribei\\anaconda3\\lib\\site-packages\\pandas\\core\\indexing.py:1300\u001b[0m, in \u001b[0;36m_LocIndexer._handle_lowerdim_multi_index_axis0\u001b[1;34m(self, tup)\u001b[0m\n\u001b[0;32m 1297\u001b[0m axis \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39maxis \u001b[39mor\u001b[39;00m \u001b[39m0\u001b[39m\n\u001b[0;32m 1298\u001b[0m \u001b[39mtry\u001b[39;00m:\n\u001b[0;32m 1299\u001b[0m \u001b[39m# fast path for series or for tup devoid of slices\u001b[39;00m\n\u001b[1;32m-> 1300\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_get_label(tup, axis\u001b[39m=\u001b[39;49maxis)\n\u001b[0;32m 1302\u001b[0m \u001b[39mexcept\u001b[39;00m \u001b[39mKeyError\u001b[39;00m \u001b[39mas\u001b[39;00m ek:\n\u001b[0;32m 1303\u001b[0m \u001b[39m# raise KeyError if number of indexers match\u001b[39;00m\n\u001b[0;32m 1304\u001b[0m \u001b[39m# else IndexingError will be raised\u001b[39;00m\n\u001b[0;32m 1305\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mndim \u001b[39m<\u001b[39m \u001b[39mlen\u001b[39m(tup) \u001b[39m<\u001b[39m\u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mobj\u001b[39m.\u001b[39mindex\u001b[39m.\u001b[39mnlevels:\n", + "File \u001b[1;32mc:\\Users\\ribei\\anaconda3\\lib\\site-packages\\pandas\\core\\indexing.py:1293\u001b[0m, in \u001b[0;36m_LocIndexer._get_label\u001b[1;34m(self, label, axis)\u001b[0m\n\u001b[0;32m 1291\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39m_get_label\u001b[39m(\u001b[39mself\u001b[39m, label, axis: AxisInt):\n\u001b[0;32m 1292\u001b[0m \u001b[39m# GH#5567 this will fail if the label is not present in the axis.\u001b[39;00m\n\u001b[1;32m-> 1293\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49mobj\u001b[39m.\u001b[39;49mxs(label, axis\u001b[39m=\u001b[39;49maxis)\n", + "File \u001b[1;32mc:\\Users\\ribei\\anaconda3\\lib\\site-packages\\pandas\\core\\generic.py:4088\u001b[0m, in \u001b[0;36mNDFrame.xs\u001b[1;34m(self, key, axis, level, drop_level)\u001b[0m\n\u001b[0;32m 4085\u001b[0m index \u001b[39m=\u001b[39m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39mindex\n\u001b[0;32m 4087\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39misinstance\u001b[39m(index, MultiIndex):\n\u001b[1;32m-> 4088\u001b[0m loc, new_index \u001b[39m=\u001b[39m index\u001b[39m.\u001b[39;49m_get_loc_level(key, level\u001b[39m=\u001b[39;49m\u001b[39m0\u001b[39;49m)\n\u001b[0;32m 4089\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mnot\u001b[39;00m drop_level:\n\u001b[0;32m 4090\u001b[0m \u001b[39mif\u001b[39;00m lib\u001b[39m.\u001b[39mis_integer(loc):\n", + "File \u001b[1;32mc:\\Users\\ribei\\anaconda3\\lib\\site-packages\\pandas\\core\\indexes\\multi.py:3026\u001b[0m, in \u001b[0;36mMultiIndex._get_loc_level\u001b[1;34m(self, key, level)\u001b[0m\n\u001b[0;32m 3024\u001b[0m \u001b[39mfor\u001b[39;00m i, k \u001b[39min\u001b[39;00m \u001b[39menumerate\u001b[39m(key):\n\u001b[0;32m 3025\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39mnot\u001b[39;00m \u001b[39misinstance\u001b[39m(k, \u001b[39mslice\u001b[39m):\n\u001b[1;32m-> 3026\u001b[0m loc_level \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_get_level_indexer(k, level\u001b[39m=\u001b[39;49mi)\n\u001b[0;32m 3027\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39misinstance\u001b[39m(loc_level, \u001b[39mslice\u001b[39m):\n\u001b[0;32m 3028\u001b[0m \u001b[39mif\u001b[39;00m com\u001b[39m.\u001b[39mis_null_slice(loc_level) \u001b[39mor\u001b[39;00m com\u001b[39m.\u001b[39mis_full_slice(\n\u001b[0;32m 3029\u001b[0m loc_level, \u001b[39mlen\u001b[39m(\u001b[39mself\u001b[39m)\n\u001b[0;32m 3030\u001b[0m ):\n\u001b[0;32m 3031\u001b[0m \u001b[39m# everything\u001b[39;00m\n", + "File \u001b[1;32mc:\\Users\\ribei\\anaconda3\\lib\\site-packages\\pandas\\core\\indexes\\multi.py:3160\u001b[0m, in \u001b[0;36mMultiIndex._get_level_indexer\u001b[1;34m(self, key, level, indexer)\u001b[0m\n\u001b[0;32m 3157\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mslice\u001b[39m(i, j, step)\n\u001b[0;32m 3159\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[1;32m-> 3160\u001b[0m idx \u001b[39m=\u001b[39m \u001b[39mself\u001b[39;49m\u001b[39m.\u001b[39;49m_get_loc_single_level_index(level_index, key)\n\u001b[0;32m 3162\u001b[0m \u001b[39mif\u001b[39;00m level \u001b[39m>\u001b[39m \u001b[39m0\u001b[39m \u001b[39mor\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_lexsort_depth \u001b[39m==\u001b[39m \u001b[39m0\u001b[39m:\n\u001b[0;32m 3163\u001b[0m \u001b[39m# Desired level is not sorted\u001b[39;00m\n\u001b[0;32m 3164\u001b[0m \u001b[39mif\u001b[39;00m \u001b[39misinstance\u001b[39m(idx, \u001b[39mslice\u001b[39m):\n\u001b[0;32m 3165\u001b[0m \u001b[39m# test_get_loc_partial_timestamp_multiindex\u001b[39;00m\n", + "File \u001b[1;32mc:\\Users\\ribei\\anaconda3\\lib\\site-packages\\pandas\\core\\indexes\\multi.py:2752\u001b[0m, in \u001b[0;36mMultiIndex._get_loc_single_level_index\u001b[1;34m(self, level_index, key)\u001b[0m\n\u001b[0;32m 2750\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39m-\u001b[39m\u001b[39m1\u001b[39m\n\u001b[0;32m 2751\u001b[0m \u001b[39melse\u001b[39;00m:\n\u001b[1;32m-> 2752\u001b[0m \u001b[39mreturn\u001b[39;00m level_index\u001b[39m.\u001b[39;49mget_loc(key)\n", + "File \u001b[1;32mc:\\Users\\ribei\\anaconda3\\lib\\site-packages\\pandas\\core\\indexes\\base.py:3655\u001b[0m, in \u001b[0;36mIndex.get_loc\u001b[1;34m(self, key)\u001b[0m\n\u001b[0;32m 3653\u001b[0m \u001b[39mreturn\u001b[39;00m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_engine\u001b[39m.\u001b[39mget_loc(casted_key)\n\u001b[0;32m 3654\u001b[0m \u001b[39mexcept\u001b[39;00m \u001b[39mKeyError\u001b[39;00m \u001b[39mas\u001b[39;00m err:\n\u001b[1;32m-> 3655\u001b[0m \u001b[39mraise\u001b[39;00m \u001b[39mKeyError\u001b[39;00m(key) \u001b[39mfrom\u001b[39;00m \u001b[39merr\u001b[39;00m\n\u001b[0;32m 3656\u001b[0m \u001b[39mexcept\u001b[39;00m \u001b[39mTypeError\u001b[39;00m:\n\u001b[0;32m 3657\u001b[0m \u001b[39m# If we have a listlike key, _check_indexing_error will raise\u001b[39;00m\n\u001b[0;32m 3658\u001b[0m \u001b[39m# InvalidIndexError. Otherwise we fall through and re-raise\u001b[39;00m\n\u001b[0;32m 3659\u001b[0m \u001b[39m# the TypeError.\u001b[39;00m\n\u001b[0;32m 3660\u001b[0m \u001b[39mself\u001b[39m\u001b[39m.\u001b[39m_check_indexing_error(key)\n", + "\u001b[1;31mKeyError\u001b[0m: False" + ] + } + ], + "source": [ + "# ESCREVA O CÓDIGO DA SUA RESPOSTA AQUI\n", + "frequencias_relativas = carros.value_counts(normalize=True).sort_index()\n", + "frequencias_relativas.loc[\"Quantidade\" == 0, :]" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "
\n", + "\n", + "### EXERCÍCIO 4\n", + "\n", + "1. **A partir da tabela de frequências relativas**, calcule a média, variância e desvio padrão da quantidade de itens vistoriados em não conformidade. Ou seja, sem utilizar as funções `.mean()`, `.var(ddof=0)` e `std(ddof=0)`. Para isso, será necessário utilizar as fórmulas vistas em aula:\n", + "\n", + " $\\qquad\\qquad\\overline{y} = \\sum\\limits_y y\\cdot fr_y$\n", + "\n", + " $\\qquad\\qquad var(y) = \\sum\\limits_y (y-\\overline{y})^2\\cdot fr_y$\n", + " \n", + " $\\qquad\\qquad dp(y) = \\sqrt{var(y)}$\n", + "\n", + "sendo $fr_y$ a frequência relativa da quantidade $y$ na amostra.\n", + "\n", + "1. Compare os resultados com a média, variância populacional e desvio padrão populacional obtidos a partir das funções `.mean()` `.var(ddof=0)` e `.std(ddof=0)`.\n", + "\n", + "1. Explique sucintamente o que você pode concluir a partir desses valores.\n", + "\n", + "*Respostas esperadas Média, Variância e Desvio Padrão respectivamente: 1.3713333 ; 1.5794449 ; 1.25675967*" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [ + { + "ename": "SyntaxError", + "evalue": "incomplete input (1279670733.py, line 4)", + "output_type": "error", + "traceback": [ + "\u001b[1;36m Cell \u001b[1;32mIn[67], line 4\u001b[1;36m\u001b[0m\n\u001b[1;33m \u001b[0m\n\u001b[1;37m ^\u001b[0m\n\u001b[1;31mSyntaxError\u001b[0m\u001b[1;31m:\u001b[0m incomplete input\n" + ] + } + ], + "source": [ + "# ESCREVA O CÓDIGO DA SUA RESPOSTA AQUI\n", + "media = 0\n", + "for i in range(len(frequencias_relativas)):\n", + " media += *frequencias_relativas[i]" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "raw", + "metadata": {}, + "source": [ + "ESCREVA SUAS CONCLUSÕES AQUI" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "
\n", + "\n", + "## Comparação: resultados empíricos *vs* modelo teórico\n", + "\n", + "Vamos comparar as probabilidades teóricas ([exercício 2](#ex2)) com as frequências relativas observadas nos dados ([exercício 4](#ex4)). Para isso, temos, por exemplo, as duas opções gráficas a seguir para verificar se os resultados empíricos se encaixam no modelo teórico proposto. Procure entender pelo menos a ideia do código que gera os gráficos abaixo (pode ser necessário procurar alguma documentação, mas não se preocupe em entender todos os detalhes), eles serão úteis na última questão.\n", + "\n", + "
\n", + "\n", + "### Opção 1: Frequências relativas *vs* Probabilidades teóricas\n", + "\n", + "A primeira opção gráfica contrasta a frequência relativa e a probabilidade teórica para uma determinada quantidade de itens em não conformidade. Essa opção contrasta a frequência relativa $fr$ para um valor de $y$ com a probabilidade pontual $P(Y=y)$." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "fr = frequencias_relativas #Calculadas no Exercício 4 - Amostra\n", + "pr = probabilidades_teoricas #Calculadas no Exercício 1 - Modelo teórico\n", + "\n", + "plt.figure(figsize=(10,6))\n", + "plt.plot(range(len(fr)), fr, 'o', alpha=0.8)\n", + "plt.plot(range(len(pr)), pr, 'D', alpha=0.8)\n", + "plt.legend(('Freq.relativa','P(Y=y)'), loc='upper right')\n", + "plt.title('Frequência relativa VS Probabilidade teórica')\n", + "plt.xlim(-1,15)\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "
\n", + "\n", + "### Opção 2: Frequência relativa acumulada *vs* Probabilidade acumulada\n", + "\n", + "A segunda opção gráfica contrasta a frequência relativa acumulada com a probabilidade acumulada até determinada quantidade de itens em não conformidade. Ou seja, compara a frequência relativa acumulada $fra$ até $y$ com a probabilidade acumulada $P(Y\\leq y)$." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [ + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "fra = fr.cumsum() #fra contem as frequencias relativas acumuladas calculadas no Exercício 1 - Amostra\n", + "n = 14\n", + "p = 0.1\n", + "fda = stats.binom.cdf(range(n), n=n, p=p) #fda contem as probabilidades acumuladas pelo modelo teorico\n", + "\n", + "plt.figure(figsize=(10,6))\n", + "plt.plot(range(len(fra)), fra, 'o', alpha=0.8)\n", + "plt.plot(range(n), fda, 'D', alpha=0.8)\n", + "plt.legend(('Freq.rel.acumulada','P(Y<=y)'), loc='lower right')\n", + "plt.title('Frequência relativa acumulada VS Probabilidade teórica acumulada')\n", + "plt.xlim(-1,15)\n", + "plt.show()" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "
\n", + "\n", + "### EXERCÍCIO 5\n", + "\n", + "Baseado nos gráficos acima, refine sua conclusão quanto ao uso do modelo teórico para ajustar a variável em questão ([exercício 1](#ex1))." + ] + }, + { + "cell_type": "raw", + "metadata": {}, + "source": [ + "ESCREVA SUA RESPOSTA AQUI" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "
\n", + "\n", + "### EXERCÍCIO 6\n", + "\n", + "Na prática, qual a necessidade de um modelo probabilístico já que temos os dados observados?" + ] + }, + { + "cell_type": "raw", + "metadata": {}, + "source": [ + "ESCREVA SUA RESPOSTA AQUI" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "
\n", + "\n", + "### EXERCÍCIO 7\n", + "\n", + "Considerando apenas os carros populares, o modelo binomial com parâmetros $n=14$ e $p=0,10$ é adequado para ajustar a variável **Quantidade**? Se sim, justifique; caso não, sugira novos valores para os parâmetros da distribuição para que ela se ajuste aos dados. **Dica**: utilize a [fórmula de $E(Y)$](#esperanca-variancia).\n", + "\n", + "*Resposta esperada para probabilide de sucesso estimada a partir dos carros populares: 0.13103174603174603*" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [ + "# ESCREVA SEU CÓDIGO AQUI" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "
\n", + "\n", + "___\n", + "\n", + "## Lista de comandos utilizados neste notebook\n", + "\n", + "Os seguintes comandos foram utilizados neste jupyter notebook. Para facilitar sua consulta, escreva um resumo do que cada um deles faz:\n", + "\n", + "- [`stats.binom.pmf`](#pmf-stats): ESCREVA AQUI O RESUMO\n", + "- [`stats.binom.mean`](#pmf-stats): ESCREVA AQUI O RESUMO\n", + "- [`stats.binom.var`](#pmf-stats): ESCREVA AQUI O RESUMO\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "anaconda-cloud": {}, + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.10.13" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +} diff --git "a/Aula11_Exercicio_ModelosProbabil\303\255sticosDiscretos.ipynb" "b/Aula11_Exercicio_ModelosProbabil\303\255sticosDiscretos.ipynb" new file mode 100644 index 0000000..39efa7a --- /dev/null +++ "b/Aula11_Exercicio_ModelosProbabil\303\255sticosDiscretos.ipynb" @@ -0,0 +1,410 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "___\n", + "# Exercício:

Modelos probabilísticos discretos\n", + "___\n", + "\n", + "## Aula 11" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "___\n", + "
\n", + "\n", + "## Índice\n", + "\n", + " - [Exercício 1](#ex1) **- APS6 disponível no Blackboard**\n", + " - [Exercício 2](#ex2) \n", + " - [Exercício 3](#ex3) **- APS6 disponível no Blackboard**\n", + " - [Exercício 4](#ex4) \n", + " \n", + " - [Respostas esperadas](#resps)" + ] + }, + { + "cell_type": "code", + "execution_count": 212, + "metadata": {}, + "outputs": [], + "source": [ + "from scipy import stats #importa apenas as funções de estatísticas da biblioteca SciPy.\n", + "\n", + "# Importe outras bibliotecas se julgar necessário" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "___\n", + "
\n", + "\n", + "### EXERCÍCIO 1\n", + "A mortalidade de microempresas no 1º ano de funcionamento é da ordem de 55%.
\n", + "Deseja-se avaliar as causas da mortalidade.

\n", + "Numa amostra de 10 empresas:
\n", + "(a) qual á a probabilidade de exatamente 5 terem falido ao final do 1º ano?
\n", + "(b) qual é a probabilidade de pelo menos 3 virem a falir no 1º ano?
\n", + "(c) sabe-se que pelo menos 3 faliram no 1º ano, qual é a probabilidade de no máximo 5 terem falido?
\n", + "(d) qual o número esperado de empresas que irão à falência no 1º ano na amostra? E o desvio padrão?
\n" + ] + }, + { + "cell_type": "code", + "execution_count": 213, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0.23403270759257822" + ] + }, + "execution_count": 213, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# item (a)\n", + "# ESCREVA SUA RESPOSTA AQUI\n", + "stats.binom.pmf(5, 10, .55)" + ] + }, + { + "cell_type": "code", + "execution_count": 214, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0.9726081607386718" + ] + }, + "execution_count": 214, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# item (b)\n", + "# ESCREVA SUA RESPOSTA AQUI\n", + "1 - stats.binom.cdf(2, 10, .55)" + ] + }, + { + "cell_type": "code", + "execution_count": 215, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0.48138971888756615" + ] + }, + "execution_count": 215, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# item (c)\n", + "# ESCREVA SUA RESPOSTA AQUI\n", + "((1 - stats.binom.cdf(2, 10, .55)) - (1 - stats.binom.cdf(5, 10, .55)))/(1 - stats.binom.cdf(2, 10, .55))" + ] + }, + { + "cell_type": "code", + "execution_count": 216, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "5.5 2.4749999999999996\n" + ] + } + ], + "source": [ + "# item (d)\n", + "# ESCREVA SUA RESPOSTA AQUI\n", + "E = 10*.55\n", + "var = 10*.55*(1-0.55)\n", + "print(E, var)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "[Volte ao Índice](#indice)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "

\n", + "\n", + "### EXERCÍCIO 2\n", + "\n", + "O número médio de clientes satisfeitos com o atendimento de uma loja, em amostras de 40 clientes escolhidos ao acaso, é de 5,5.
\n", + "Qual é a probabilidade de, numa amostra de 40 clientes escolhidos ao acaso, encontrarmos pelo menos 2 satisfeitos?\n" + ] + }, + { + "cell_type": "code", + "execution_count": 217, + "metadata": {}, + "outputs": [], + "source": [ + "# ESCREVA SUA RESPOSTA AQUI" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "[Volte ao Índice](#indice)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "
\n", + "\n", + "### EXERCÍCIO 3\n", + "\n", + "Um supermercado que tem um cartão de fidelidade classifica os clientes em regular e diamante.
\n", + "Atualmente 70 % dos clientes são regulares.
\n", + "A direção do supermercado deseja premiar os clientes que, num determinado mês, comprem mais de 1 mil reais.
\n", + "Sabemos que se o cliente é diamante a probabilidade dele fazer uma compra acima de 1 mil reais é de 75%; já para o cliente regular, essa probabilidade é de 5%.

\n", + "\n", + "(a) Sorteada uma amostra de 20 clientes diamante, qual é a probabilidade de exatamente 12 fazerem uma compra acima de 1 mil reais?
\n", + "(b) Sorteados 20 clientes com a mesma classificação ao acaso, qual a probabilidade de exatamente 12 fazerem uma compra acima de 1 mil reais?
\n", + "(c) Sorteados 20 clientes ao acaso, qual a probabilidade de exatamente 12 fazerem uma compra acima de 1 mil reais?
\n", + "(d) Um gerente está analisando 200 compras efetuadas em um caixa, dessas 120 foram superiores a 1 mil reais. Dessas compras sob análise, deseja-se sortear uma amostra de 20 compras, sendo que a mesma compra não pode ser sorteada mais de uma vez, qual é a probabilidade de 15 terem sido superiores a 1 mil reais?
" + ] + }, + { + "cell_type": "code", + "execution_count": 218, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0.06088668921620408" + ] + }, + "execution_count": 218, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# item (a)\n", + "# ESCREVA SUA RESPOSTA AQUI\n", + "stats.binom.pmf(12, 20, 0.75)" + ] + }, + { + "cell_type": "code", + "execution_count": 219, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0.01826600677914339" + ] + }, + "execution_count": 219, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# item (b)\n", + "# ESCREVA SUA RESPOSTA AQUI\n", + "stats.binom.pmf(12, 20, 0.75) * 0.3 + stats.binom.pmf(12, 20, 0.05) * 0.7" + ] + }, + { + "cell_type": "code", + "execution_count": 220, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0.0010809386926081336" + ] + }, + "execution_count": 220, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# item (c)\n", + "# ESCREVA SUA RESPOSTA AQUI\n", + "stats.binom.pmf(12, 20, 0.75*0.3 + 0.05*0.7)" + ] + }, + { + "cell_type": "code", + "execution_count": 221, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0.07047763575173921" + ] + }, + "execution_count": 221, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# item (d)\n", + "# ESCREVA SUA RESPOSTA AQUI\n", + "\n", + "Pc1000 = 120/200\n", + "stats.binom.pmf(15,120, Pc1000) * stats.binom.pmf(5,80, Pc1000)/stats.binom.pmf(20,200, Pc1000)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "[Volte ao Índice](#indice)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "

\n", + "\n", + "### EXERCÍCIO 4\n", + "\n", + "Um agricultor cultiva laranjas e também produz mudas para vender.
\n", + "Após alguns meses a muda pode ser atacada por fungos com probabilidade 0,05 e, nesse caso, ela é escolhida para ser recuperada com probabilidade 0,5.
\n", + "Admita que o processo de recuperação é infalível. O custo de cada muda produzida é R\\\\$ 1,00; acrescido de R\\\\$1,50 se for para o processo de recuperação.
\n", + "Cada muda é vendida a R\\\\$ 4,00 e são descartadas as mudas que não foram para o processo de recuperação de ataque de fungos. \n", + "\n", + "Responda:
\n", + "(a) Qual é a distribuição de probabilidades do lucro (ou seja, pode haver ganho ou prejuízo) por muda produzida pelo agricultor? Justifique claramente todas as contas feitas para obtenção do resultado.
\n", + "(b) O agricultor seleciona aleatoriamente 3 mudas da sua produção de mudas de laranjas para verificar se houve ataque por fungos após alguns meses. Nesse caso:
\n", + "(b.1) Qual é a probabilidade dele encontrar pelo menos 2 mudas que foram atacadas por fungos? Justifique claramente todas as contas feitas para obtenção do resultado.
\n", + "(b.2) Sabendo que o agricultor já encontrou pelo menos 2 mudas que foram atacadas por fungos, qual é a probabilidade de encontrar menos de 3 atacadas por fungos? Justifique claramente todas as contas feitas para obtenção do resultado.\n" + ] + }, + { + "cell_type": "code", + "execution_count": 222, + "metadata": {}, + "outputs": [], + "source": [ + "# item (a)\n", + "# ESCREVA SUA RESPOSTA AQUI" + ] + }, + { + "cell_type": "code", + "execution_count": 223, + "metadata": {}, + "outputs": [], + "source": [ + "# item (b.1)\n", + "# ESCREVA SUA RESPOSTA AQUI" + ] + }, + { + "cell_type": "code", + "execution_count": 224, + "metadata": {}, + "outputs": [], + "source": [ + "# item (b.2)\n", + "# ESCREVA SUA RESPOSTA AQUI" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "[Volte ao Índice](#indice)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "
\n", + "\n", + "## Respostas Esperadas:" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### EXERCÍCIO 2
\n", + "*Resposta esperada: p=0,1375. Logo, P(X>=2)=98,02%*" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "#### EXERCÍCIO 4
\n", + "*Respostas esperadas:*
\n", + "*(a) Considere que X represente o lucro por muda e x, seus respectivos valores*
\n", + "
x |
P(X=x) \n", + "----------------- | ----------------- \n", + "
-1,00 |
0.025 \n", + "
1,50 |
0.025 \n", + "
3,00 |
0.95 \n", + " \n", + "*(b.1) 0.725% (b.2) 98.3%* " + ] + } + ], + "metadata": { + "anaconda-cloud": {}, + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.10.13" + } + }, + "nbformat": 4, + "nbformat_minor": 1 +} diff --git a/Aula13_Exemplos.ipynb b/Aula13_Exemplos.ipynb new file mode 100644 index 0000000..02044d9 --- /dev/null +++ b/Aula13_Exemplos.ipynb @@ -0,0 +1,321 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "___\n", + "# Exemplo:

Distribuição Normal\n", + "___\n", + "\n", + "## Aula 13\n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "___\n", + "## Lista de comandos:\n", + "\n", + "### Distribuição Normal\n", + "\n", + "Comandos quando $X\\sim N(\\mu, \\sigma^2)$ a partir da biblioteca `from scipy import stats`:\n", + "\n", + "* $f(x)$: `stats.norm.pdf(x, loc=mu, scale=sigma)`\n", + "\n", + "* $P(X\\leq x)$: `stats.norm.cdf(x, loc=mu, scale=sigma)`\n", + "\n", + "* $x$ tal que $p=P(X\\leq x)$: `stats.norm.ppf(p, loc=mu, scale=sigma)`\n", + "\n", + "* $E(X)$: `stats.norm.mean(loc=mu, scale=sigma)`\n", + "\n", + "* $Var(X)$: `stats.norm.var(loc=mu, scale=sigma)`\n", + "\n", + "* $DP(X)$: `stats.norm.std(loc=mu, scale=sigma)`\n", + "\n", + "\n", + "Link: https://docs.scipy.org/doc/scipy/reference/generated/scipy.stats.norm.html" + ] + }, + { + "cell_type": "code", + "execution_count": 67, + "metadata": {}, + "outputs": [], + "source": [ + "from scipy import stats" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "___\n", + "\n", + "# Exemplo 1:\n", + "\n", + "Assuma que a variável de interesse $X$ represente notas de alunos, cuja média vale 5 e o desvio padrão, 1,5. Ainda, considere que essa variável seja modelada por uma normal. Ou seja, $X\\sim N(5; 1,5^2)$. \n", + "\n", + "**Responda:**" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Item a\n", + "\n", + "Qual a probabilidade de encontrar um aluno com nota abaixo de 6,5?\n", + "\n", + "*Resposta esperada: 0.8413447460685429*" + ] + }, + { + "cell_type": "code", + "execution_count": 68, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "P(X < 6.5) = 0.8413447460685429\n" + ] + } + ], + "source": [ + "# ESCREVA SUA RESPOSTA AQUI\n", + "\n", + "# P(X < 6,5) = P (X < mu + 1*sigma) = ?\n", + "u = 5\n", + "dp = 1.5\n", + "item_a = stats.norm.cdf(6.5, loc=u, scale=dp)\n", + "\n", + "print(f'P(X < 6.5) = {item_a}')" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Item b\n", + "\n", + "Qual a probabilidade de encontrar um aluno nota acima de 8?\n", + "\n", + "*Resposta esperada: 0.02275013194817921*" + ] + }, + { + "cell_type": "code", + "execution_count": 69, + "metadata": { + "scrolled": true + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "P(X > 8) = 0.02275013194817921\n" + ] + } + ], + "source": [ + "# ESCREVA SUA RESPOSTA AQUI\n", + "\n", + "# P(X > 8) = P (X > mu + 2*sigma) = ?\n", + "item_b = 1 - stats.norm.cdf(8, loc=u, scale=dp)\n", + "\n", + "print(f'P(X > 8) = {item_b}')" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Item c\n", + "\n", + "E da nota ser superior a 9?\n", + "\n", + "*Resposta esperada: 0.003830380567589775*" + ] + }, + { + "cell_type": "code", + "execution_count": 70, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "P(X > 9) = 0.003830380567589775\n" + ] + } + ], + "source": [ + "# P(X > 8) = P (X > mu + 2*sigma) = ?\n", + "item_c = 1 - stats.norm.cdf(9, loc=u, scale=dp)\n", + "\n", + "print(f'P(X > 9) = {item_c}')" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Item d\n", + "\n", + "Qual a maior nota dos 20% piores alunos? E a pior nota dos 20% melhores alunos?\n", + "\n", + "*Resposta esperada: 3.737568149640629 e 6.262431850359372*" + ] + }, + { + "cell_type": "code", + "execution_count": 71, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "3.737568149640629" + ] + }, + "execution_count": 71, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# ESCREVA SUA RESPOSTA AQUI\n", + "stats.norm.ppf(0.2, loc=u, scale=dp)" + ] + }, + { + "cell_type": "code", + "execution_count": 72, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "6.262431850359372" + ] + }, + "execution_count": 72, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "stats.norm.ppf(1-0.2, loc=u, scale=dp)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Item e\n", + "\n", + "Considerando alunos que tiraram acima de 5, qual a probabilidade de ser abaixo de 7?\n", + "\n", + "*Resposta esperada: 0.8175775605482642*" + ] + }, + { + "cell_type": "code", + "execution_count": 73, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "0.8175775605482642" + ] + }, + "execution_count": 73, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "# ESCREVA SUA RESPOSTA AQUI\n", + "(stats.norm.cdf(7, loc=u, scale=dp) - stats.norm.cdf(5, loc=u, scale=dp))/stats.norm.cdf(5, loc=u, scale=dp)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "### Item f\n", + "\n", + "Construa o gráfico da distribuição normal que modela as notas." + ] + }, + { + "cell_type": "code", + "execution_count": 74, + "metadata": {}, + "outputs": [], + "source": [ + "%matplotlib inline\n", + "import matplotlib.pyplot as plt\n", + "import numpy as np" + ] + }, + { + "cell_type": "code", + "execution_count": 75, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "[]" + ] + }, + "execution_count": 75, + "metadata": {}, + "output_type": "execute_result" + }, + { + "data": { + "image/png": "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", + "text/plain": [ + "
" + ] + }, + "metadata": {}, + "output_type": "display_data" + } + ], + "source": [ + "# ESCREVA SUA RESPOSTA AQUI\n", + "plt.plot(np.arange(0,10.1, 1e-3), stats.norm.pdf(np.arange(0,10.1, 1e-3), loc=u, scale=dp))" + ] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.10.13" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +} diff --git a/Carros.txt b/Carros.txt new file mode 100644 index 0000000..38252e7 --- /dev/null +++ b/Carros.txt @@ -0,0 +1,3001 @@ +"Tipo" "Quantidade" +"1" 1 0 +"2" 1 2 +"3" 1 2 +"4" 1 3 +"5" 1 1 +"6" 1 4 +"7" 1 4 +"8" 1 4 +"9" 1 2 +"10" 1 1 +"11" 1 2 +"12" 1 2 +"13" 1 4 +"14" 1 0 +"15" 1 3 +"16" 1 1 +"17" 1 2 +"18" 1 1 +"19" 1 0 +"20" 1 0 +"21" 1 3 +"22" 1 2 +"23" 1 2 +"24" 1 3 +"25" 1 2 +"26" 1 2 +"27" 1 2 +"28" 1 2 +"29" 1 1 +"30" 1 2 +"31" 1 0 +"32" 1 3 +"33" 1 1 +"34" 1 2 +"35" 1 4 +"36" 1 2 +"37" 1 3 +"38" 1 3 +"39" 1 4 +"40" 1 1 +"41" 1 5 +"42" 1 1 +"43" 1 1 +"44" 1 2 +"45" 1 2 +"46" 1 1 +"47" 1 0 +"48" 1 0 +"49" 1 2 +"50" 1 4 +"51" 1 2 +"52" 1 5 +"53" 1 1 +"54" 1 2 +"55" 1 3 +"56" 1 4 +"57" 1 1 +"58" 1 4 +"59" 1 1 +"60" 1 1 +"61" 1 0 +"62" 1 1 +"63" 1 2 +"64" 1 1 +"65" 1 2 +"66" 1 1 +"67" 1 1 +"68" 1 3 +"69" 1 2 +"70" 1 2 +"71" 1 1 +"72" 1 2 +"73" 1 4 +"74" 1 0 +"75" 1 3 +"76" 1 3 +"77" 1 1 +"78" 1 3 +"79" 1 2 +"80" 1 3 +"81" 1 2 +"82" 1 0 +"83" 1 0 +"84" 1 1 +"85" 1 2 +"86" 1 1 +"87" 1 1 +"88" 1 0 +"89" 1 0 +"90" 1 1 +"91" 1 0 +"92" 1 2 +"93" 1 3 +"94" 1 3 +"95" 1 2 +"96" 1 3 +"97" 1 4 +"98" 1 2 +"99" 1 4 +"100" 1 2 +"101" 1 1 +"102" 1 3 +"103" 1 2 +"104" 1 1 +"105" 1 2 +"106" 1 1 +"107" 1 2 +"108" 1 2 +"109" 1 4 +"110" 1 3 +"111" 1 2 +"112" 1 4 +"113" 1 2 +"114" 1 2 +"115" 1 2 +"116" 1 1 +"117" 1 1 +"118" 1 3 +"119" 1 1 +"120" 1 1 +"121" 1 2 +"122" 1 4 +"123" 1 0 +"124" 1 1 +"125" 1 0 +"126" 1 0 +"127" 1 3 +"128" 1 4 +"129" 1 1 +"130" 1 2 +"131" 1 2 +"132" 1 1 +"133" 1 2 +"134" 1 1 +"135" 1 4 +"136" 1 3 +"137" 1 1 +"138" 1 1 +"139" 1 0 +"140" 1 3 +"141" 1 3 +"142" 1 2 +"143" 1 4 +"144" 1 1 +"145" 1 0 +"146" 1 4 +"147" 1 2 +"148" 1 1 +"149" 1 3 +"150" 1 1 +"151" 1 3 +"152" 1 1 +"153" 1 4 +"154" 1 2 +"155" 1 2 +"156" 1 3 +"157" 1 2 +"158" 1 1 +"159" 1 3 +"160" 1 2 +"161" 1 1 +"162" 1 2 +"163" 1 0 +"164" 1 3 +"165" 1 0 +"166" 1 0 +"167" 1 2 +"168" 1 0 +"169" 1 2 +"170" 1 0 +"171" 1 3 +"172" 1 2 +"173" 1 1 +"174" 1 3 +"175" 1 2 +"176" 1 1 +"177" 1 3 +"178" 1 2 +"179" 1 1 +"180" 1 4 +"181" 1 0 +"182" 1 1 +"183" 1 0 +"184" 1 2 +"185" 1 0 +"186" 1 2 +"187" 1 1 +"188" 1 2 +"189" 1 0 +"190" 1 4 +"191" 1 3 +"192" 1 2 +"193" 1 2 +"194" 1 2 +"195" 1 2 +"196" 1 1 +"197" 1 4 +"198" 1 4 +"199" 1 2 +"200" 1 3 +"201" 1 5 +"202" 1 4 +"203" 1 2 +"204" 1 3 +"205" 1 2 +"206" 1 3 +"207" 1 2 +"208" 1 2 +"209" 1 1 +"210" 1 1 +"211" 1 2 +"212" 1 2 +"213" 1 2 +"214" 1 2 +"215" 1 2 +"216" 1 2 +"217" 1 1 +"218" 1 1 +"219" 1 1 +"220" 1 2 +"221" 1 2 +"222" 1 2 +"223" 1 4 +"224" 1 4 +"225" 1 4 +"226" 1 4 +"227" 1 4 +"228" 1 1 +"229" 1 0 +"230" 1 2 +"231" 1 1 +"232" 1 0 +"233" 1 3 +"234" 1 3 +"235" 1 1 +"236" 1 1 +"237" 1 3 +"238" 1 2 +"239" 1 4 +"240" 1 1 +"241" 1 2 +"242" 1 1 +"243" 1 4 +"244" 1 5 +"245" 1 1 +"246" 1 3 +"247" 1 2 +"248" 1 0 +"249" 1 2 +"250" 1 1 +"251" 1 1 +"252" 1 2 +"253" 1 5 +"254" 1 1 +"255" 1 2 +"256" 1 0 +"257" 1 0 +"258" 1 2 +"259" 1 1 +"260" 1 1 +"261" 1 3 +"262" 1 2 +"263" 1 2 +"264" 1 1 +"265" 1 0 +"266" 1 1 +"267" 1 2 +"268" 1 1 +"269" 1 4 +"270" 1 3 +"271" 1 1 +"272" 1 0 +"273" 1 2 +"274" 1 0 +"275" 1 1 +"276" 1 2 +"277" 1 1 +"278" 1 2 +"279" 1 1 +"280" 1 1 +"281" 1 2 +"282" 1 3 +"283" 1 0 +"284" 1 1 +"285" 1 1 +"286" 1 2 +"287" 1 5 +"288" 1 2 +"289" 1 0 +"290" 1 2 +"291" 1 0 +"292" 1 4 +"293" 1 3 +"294" 1 1 +"295" 1 2 +"296" 1 1 +"297" 1 2 +"298" 1 3 +"299" 1 1 +"300" 1 1 +"301" 1 1 +"302" 1 0 +"303" 1 1 +"304" 1 2 +"305" 1 2 +"306" 1 0 +"307" 1 2 +"308" 1 2 +"309" 1 1 +"310" 1 0 +"311" 1 2 +"312" 1 1 +"313" 1 1 +"314" 1 2 +"315" 1 2 +"316" 1 1 +"317" 1 1 +"318" 1 7 +"319" 1 1 +"320" 1 3 +"321" 1 1 +"322" 1 2 +"323" 1 4 +"324" 1 3 +"325" 1 3 +"326" 1 1 +"327" 1 0 +"328" 1 3 +"329" 1 2 +"330" 1 1 +"331" 1 0 +"332" 1 1 +"333" 1 2 +"334" 1 2 +"335" 1 1 +"336" 1 0 +"337" 1 0 +"338" 1 1 +"339" 1 1 +"340" 1 2 +"341" 1 0 +"342" 1 0 +"343" 1 3 +"344" 1 1 +"345" 1 2 +"346" 1 1 +"347" 1 3 +"348" 1 3 +"349" 1 4 +"350" 1 0 +"351" 1 2 +"352" 1 3 +"353" 1 4 +"354" 1 2 +"355" 1 1 +"356" 1 2 +"357" 1 4 +"358" 1 2 +"359" 1 3 +"360" 1 1 +"361" 1 1 +"362" 1 2 +"363" 1 3 +"364" 1 1 +"365" 1 1 +"366" 1 2 +"367" 1 2 +"368" 1 0 +"369" 1 1 +"370" 1 1 +"371" 1 2 +"372" 1 4 +"373" 1 3 +"374" 1 3 +"375" 1 4 +"376" 1 1 +"377" 1 2 +"378" 1 2 +"379" 1 1 +"380" 1 4 +"381" 1 2 +"382" 1 1 +"383" 1 2 +"384" 1 1 +"385" 1 2 +"386" 1 2 +"387" 1 1 +"388" 1 0 +"389" 1 0 +"390" 1 0 +"391" 1 0 +"392" 1 2 +"393" 1 2 +"394" 1 2 +"395" 1 3 +"396" 1 2 +"397" 1 0 +"398" 1 3 +"399" 1 1 +"400" 1 3 +"401" 1 2 +"402" 1 2 +"403" 1 2 +"404" 1 3 +"405" 1 1 +"406" 1 1 +"407" 1 3 +"408" 1 0 +"409" 1 2 +"410" 1 1 +"411" 1 1 +"412" 1 2 +"413" 1 1 +"414" 1 1 +"415" 1 1 +"416" 1 2 +"417" 1 5 +"418" 1 1 +"419" 1 1 +"420" 1 1 +"421" 1 0 +"422" 1 5 +"423" 1 5 +"424" 1 1 +"425" 1 0 +"426" 1 2 +"427" 1 2 +"428" 1 4 +"429" 1 1 +"430" 1 4 +"431" 1 2 +"432" 1 1 +"433" 1 4 +"434" 1 4 +"435" 1 2 +"436" 1 2 +"437" 1 0 +"438" 1 4 +"439" 1 1 +"440" 1 0 +"441" 1 1 +"442" 1 0 +"443" 1 0 +"444" 1 2 +"445" 1 2 +"446" 1 3 +"447" 1 0 +"448" 1 4 +"449" 1 1 +"450" 1 1 +"451" 1 0 +"452" 1 3 +"453" 1 3 +"454" 1 1 +"455" 1 1 +"456" 1 1 +"457" 1 2 +"458" 1 2 +"459" 1 0 +"460" 1 2 +"461" 1 2 +"462" 1 3 +"463" 1 2 +"464" 1 1 +"465" 1 1 +"466" 1 2 +"467" 1 3 +"468" 1 0 +"469" 1 4 +"470" 1 5 +"471" 1 1 +"472" 1 1 +"473" 1 1 +"474" 1 3 +"475" 1 4 +"476" 1 3 +"477" 1 1 +"478" 1 0 +"479" 1 2 +"480" 1 0 +"481" 1 2 +"482" 1 0 +"483" 1 3 +"484" 1 0 +"485" 1 0 +"486" 1 1 +"487" 1 3 +"488" 1 3 +"489" 1 1 +"490" 1 1 +"491" 1 6 +"492" 1 2 +"493" 1 4 +"494" 1 0 +"495" 1 0 +"496" 1 2 +"497" 1 1 +"498" 1 0 +"499" 1 1 +"500" 1 3 +"501" 1 2 +"502" 1 1 +"503" 1 1 +"504" 1 2 +"505" 1 3 +"506" 1 4 +"507" 1 3 +"508" 1 1 +"509" 1 1 +"510" 1 2 +"511" 1 3 +"512" 1 3 +"513" 1 3 +"514" 1 6 +"515" 1 1 +"516" 1 0 +"517" 1 2 +"518" 1 3 +"519" 1 2 +"520" 1 1 +"521" 1 1 +"522" 1 1 +"523" 1 2 +"524" 1 3 +"525" 1 2 +"526" 1 2 +"527" 1 3 +"528" 1 0 +"529" 1 1 +"530" 1 0 +"531" 1 5 +"532" 1 0 +"533" 1 0 +"534" 1 2 +"535" 1 1 +"536" 1 2 +"537" 1 1 +"538" 1 1 +"539" 1 4 +"540" 1 4 +"541" 1 2 +"542" 1 2 +"543" 1 0 +"544" 1 2 +"545" 1 3 +"546" 1 2 +"547" 1 6 +"548" 1 2 +"549" 1 2 +"550" 1 0 +"551" 1 3 +"552" 1 1 +"553" 1 3 +"554" 1 1 +"555" 1 2 +"556" 1 0 +"557" 1 5 +"558" 1 2 +"559" 1 1 +"560" 1 4 +"561" 1 3 +"562" 1 3 +"563" 1 0 +"564" 1 4 +"565" 1 2 +"566" 1 3 +"567" 1 2 +"568" 1 1 +"569" 1 2 +"570" 1 3 +"571" 1 1 +"572" 1 2 +"573" 1 2 +"574" 1 2 +"575" 1 1 +"576" 1 1 +"577" 1 1 +"578" 1 5 +"579" 1 2 +"580" 1 0 +"581" 1 1 +"582" 1 3 +"583" 1 4 +"584" 1 3 +"585" 1 2 +"586" 1 5 +"587" 1 1 +"588" 1 0 +"589" 1 2 +"590" 1 0 +"591" 1 3 +"592" 1 3 +"593" 1 2 +"594" 1 1 +"595" 1 1 +"596" 1 2 +"597" 1 2 +"598" 1 3 +"599" 1 0 +"600" 1 0 +"601" 1 2 +"602" 1 4 +"603" 1 1 +"604" 1 2 +"605" 1 2 +"606" 1 3 +"607" 1 1 +"608" 1 2 +"609" 1 3 +"610" 1 0 +"611" 1 4 +"612" 1 2 +"613" 1 2 +"614" 1 2 +"615" 1 2 +"616" 1 2 +"617" 1 0 +"618" 1 2 +"619" 1 2 +"620" 1 1 +"621" 1 0 +"622" 1 2 +"623" 1 1 +"624" 1 2 +"625" 1 1 +"626" 1 0 +"627" 1 5 +"628" 1 1 +"629" 1 3 +"630" 1 3 +"631" 1 1 +"632" 1 4 +"633" 1 3 +"634" 1 0 +"635" 1 1 +"636" 1 4 +"637" 1 1 +"638" 1 0 +"639" 1 1 +"640" 1 3 +"641" 1 2 +"642" 1 2 +"643" 1 1 +"644" 1 0 +"645" 1 2 +"646" 1 1 +"647" 1 0 +"648" 1 2 +"649" 1 5 +"650" 1 1 +"651" 1 2 +"652" 1 2 +"653" 1 2 +"654" 1 3 +"655" 1 1 +"656" 1 1 +"657" 1 3 +"658" 1 2 +"659" 1 3 +"660" 1 1 +"661" 1 0 +"662" 1 1 +"663" 1 2 +"664" 1 1 +"665" 1 1 +"666" 1 1 +"667" 1 2 +"668" 1 2 +"669" 1 0 +"670" 1 1 +"671" 1 2 +"672" 1 2 +"673" 1 0 +"674" 1 2 +"675" 1 0 +"676" 1 3 +"677" 1 0 +"678" 1 2 +"679" 1 3 +"680" 1 2 +"681" 1 1 +"682" 1 1 +"683" 1 1 +"684" 1 3 +"685" 1 2 +"686" 1 3 +"687" 1 2 +"688" 1 1 +"689" 1 2 +"690" 1 1 +"691" 1 1 +"692" 1 1 +"693" 1 0 +"694" 1 3 +"695" 1 2 +"696" 1 1 +"697" 1 1 +"698" 1 3 +"699" 1 0 +"700" 1 0 +"701" 1 1 +"702" 1 3 +"703" 1 3 +"704" 1 2 +"705" 1 5 +"706" 1 3 +"707" 1 3 +"708" 1 1 +"709" 1 2 +"710" 1 4 +"711" 1 3 +"712" 1 1 +"713" 1 4 +"714" 1 1 +"715" 1 2 +"716" 1 2 +"717" 1 3 +"718" 1 2 +"719" 1 1 +"720" 1 3 +"721" 1 1 +"722" 1 4 +"723" 1 3 +"724" 1 2 +"725" 1 7 +"726" 1 4 +"727" 1 1 +"728" 1 4 +"729" 1 1 +"730" 1 0 +"731" 1 2 +"732" 1 1 +"733" 1 4 +"734" 1 2 +"735" 1 2 +"736" 1 1 +"737" 1 3 +"738" 1 2 +"739" 1 2 +"740" 1 1 +"741" 1 0 +"742" 1 2 +"743" 1 2 +"744" 1 1 +"745" 1 1 +"746" 1 2 +"747" 1 2 +"748" 1 2 +"749" 1 3 +"750" 1 5 +"751" 1 3 +"752" 1 0 +"753" 1 2 +"754" 1 3 +"755" 1 2 +"756" 1 1 +"757" 1 1 +"758" 1 1 +"759" 1 1 +"760" 1 1 +"761" 1 4 +"762" 1 2 +"763" 1 2 +"764" 1 0 +"765" 1 2 +"766" 1 1 +"767" 1 1 +"768" 1 5 +"769" 1 3 +"770" 1 1 +"771" 1 3 +"772" 1 2 +"773" 1 3 +"774" 1 1 +"775" 1 1 +"776" 1 1 +"777" 1 2 +"778" 1 3 +"779" 1 1 +"780" 1 3 +"781" 1 1 +"782" 1 0 +"783" 1 1 +"784" 1 2 +"785" 1 1 +"786" 1 2 +"787" 1 2 +"788" 1 2 +"789" 1 0 +"790" 1 5 +"791" 1 3 +"792" 1 1 +"793" 1 0 +"794" 1 3 +"795" 1 4 +"796" 1 0 +"797" 1 2 +"798" 1 2 +"799" 1 0 +"800" 1 3 +"801" 1 2 +"802" 1 1 +"803" 1 3 +"804" 1 3 +"805" 1 2 +"806" 1 3 +"807" 1 2 +"808" 1 1 +"809" 1 2 +"810" 1 0 +"811" 1 1 +"812" 1 3 +"813" 1 2 +"814" 1 2 +"815" 1 4 +"816" 1 3 +"817" 1 2 +"818" 1 3 +"819" 1 3 +"820" 1 4 +"821" 1 2 +"822" 1 2 +"823" 1 3 +"824" 1 1 +"825" 1 0 +"826" 1 1 +"827" 1 1 +"828" 1 4 +"829" 1 1 +"830" 1 1 +"831" 1 1 +"832" 1 2 +"833" 1 2 +"834" 1 1 +"835" 1 0 +"836" 1 1 +"837" 1 1 +"838" 1 2 +"839" 1 3 +"840" 1 1 +"841" 1 2 +"842" 1 1 +"843" 1 1 +"844" 1 3 +"845" 1 1 +"846" 1 2 +"847" 1 2 +"848" 1 1 +"849" 1 3 +"850" 1 1 +"851" 1 0 +"852" 1 3 +"853" 1 1 +"854" 1 1 +"855" 1 1 +"856" 1 2 +"857" 1 0 +"858" 1 1 +"859" 1 0 +"860" 1 2 +"861" 1 1 +"862" 1 1 +"863" 1 3 +"864" 1 2 +"865" 1 2 +"866" 1 1 +"867" 1 4 +"868" 1 4 +"869" 1 2 +"870" 1 1 +"871" 1 2 +"872" 1 4 +"873" 1 3 +"874" 1 0 +"875" 1 2 +"876" 1 0 +"877" 1 2 +"878" 1 1 +"879" 1 0 +"880" 1 3 +"881" 1 2 +"882" 1 3 +"883" 1 1 +"884" 1 2 +"885" 1 0 +"886" 1 2 +"887" 1 3 +"888" 1 2 +"889" 1 1 +"890" 1 1 +"891" 1 3 +"892" 1 2 +"893" 1 0 +"894" 1 2 +"895" 1 3 +"896" 1 0 +"897" 1 2 +"898" 1 3 +"899" 1 1 +"900" 1 1 +"901" 1 1 +"902" 1 2 +"903" 1 1 +"904" 1 0 +"905" 1 2 +"906" 1 5 +"907" 1 2 +"908" 1 2 +"909" 1 1 +"910" 1 5 +"911" 1 2 +"912" 1 3 +"913" 1 0 +"914" 1 2 +"915" 1 1 +"916" 1 1 +"917" 1 2 +"918" 1 1 +"919" 1 4 +"920" 1 1 +"921" 1 2 +"922" 1 0 +"923" 1 3 +"924" 1 0 +"925" 1 2 +"926" 1 5 +"927" 1 2 +"928" 1 3 +"929" 1 0 +"930" 1 2 +"931" 1 3 +"932" 1 2 +"933" 1 1 +"934" 1 4 +"935" 1 3 +"936" 1 2 +"937" 1 2 +"938" 1 3 +"939" 1 2 +"940" 1 1 +"941" 1 1 +"942" 1 3 +"943" 1 4 +"944" 1 2 +"945" 1 3 +"946" 1 2 +"947" 1 3 +"948" 1 1 +"949" 1 3 +"950" 1 1 +"951" 1 0 +"952" 1 3 +"953" 1 2 +"954" 1 2 +"955" 1 0 +"956" 1 2 +"957" 1 0 +"958" 1 1 +"959" 1 2 +"960" 1 2 +"961" 1 2 +"962" 1 1 +"963" 1 5 +"964" 1 2 +"965" 1 1 +"966" 1 1 +"967" 1 2 +"968" 1 2 +"969" 1 1 +"970" 1 0 +"971" 1 4 +"972" 1 0 +"973" 1 2 +"974" 1 3 +"975" 1 2 +"976" 1 2 +"977" 1 2 +"978" 1 2 +"979" 1 2 +"980" 1 2 +"981" 1 0 +"982" 1 1 +"983" 1 1 +"984" 1 0 +"985" 1 4 +"986" 1 1 +"987" 1 3 +"988" 1 1 +"989" 1 5 +"990" 1 2 +"991" 1 0 +"992" 1 4 +"993" 1 3 +"994" 1 4 +"995" 1 1 +"996" 1 1 +"997" 1 0 +"998" 1 1 +"999" 1 2 +"1000" 1 2 +"1001" 1 2 +"1002" 1 2 +"1003" 1 3 +"1004" 1 1 +"1005" 1 1 +"1006" 1 3 +"1007" 1 1 +"1008" 1 3 +"1009" 1 0 +"1010" 1 1 +"1011" 1 1 +"1012" 1 1 +"1013" 1 2 +"1014" 1 1 +"1015" 1 1 +"1016" 1 1 +"1017" 1 2 +"1018" 1 5 +"1019" 1 1 +"1020" 1 5 +"1021" 1 1 +"1022" 1 1 +"1023" 1 4 +"1024" 1 2 +"1025" 1 0 +"1026" 1 2 +"1027" 1 1 +"1028" 1 2 +"1029" 1 1 +"1030" 1 3 +"1031" 1 2 +"1032" 1 3 +"1033" 1 3 +"1034" 1 4 +"1035" 1 4 +"1036" 1 3 +"1037" 1 2 +"1038" 1 2 +"1039" 1 1 +"1040" 1 1 +"1041" 1 4 +"1042" 1 0 +"1043" 1 1 +"1044" 1 0 +"1045" 1 1 +"1046" 1 2 +"1047" 1 3 +"1048" 1 2 +"1049" 1 2 +"1050" 1 2 +"1051" 1 0 +"1052" 1 0 +"1053" 1 3 +"1054" 1 1 +"1055" 1 1 +"1056" 1 0 +"1057" 1 1 +"1058" 1 3 +"1059" 1 2 +"1060" 1 2 +"1061" 1 3 +"1062" 1 3 +"1063" 1 2 +"1064" 1 3 +"1065" 1 4 +"1066" 1 0 +"1067" 1 0 +"1068" 1 2 +"1069" 1 2 +"1070" 1 0 +"1071" 1 1 +"1072" 1 4 +"1073" 1 2 +"1074" 1 2 +"1075" 1 1 +"1076" 1 3 +"1077" 1 3 +"1078" 1 2 +"1079" 1 2 +"1080" 1 1 +"1081" 1 1 +"1082" 1 1 +"1083" 1 1 +"1084" 1 3 +"1085" 1 4 +"1086" 1 0 +"1087" 1 1 +"1088" 1 2 +"1089" 1 2 +"1090" 1 2 +"1091" 1 1 +"1092" 1 0 +"1093" 1 1 +"1094" 1 2 +"1095" 1 3 +"1096" 1 1 +"1097" 1 1 +"1098" 1 4 +"1099" 1 1 +"1100" 1 2 +"1101" 1 1 +"1102" 1 2 +"1103" 1 2 +"1104" 1 0 +"1105" 1 0 +"1106" 1 2 +"1107" 1 1 +"1108" 1 1 +"1109" 1 1 +"1110" 1 6 +"1111" 1 2 +"1112" 1 1 +"1113" 1 1 +"1114" 1 2 +"1115" 1 1 +"1116" 1 0 +"1117" 1 2 +"1118" 1 3 +"1119" 1 3 +"1120" 1 3 +"1121" 1 2 +"1122" 1 3 +"1123" 1 0 +"1124" 1 2 +"1125" 1 0 +"1126" 1 3 +"1127" 1 4 +"1128" 1 1 +"1129" 1 2 +"1130" 1 2 +"1131" 1 2 +"1132" 1 4 +"1133" 1 0 +"1134" 1 0 +"1135" 1 2 +"1136" 1 1 +"1137" 1 2 +"1138" 1 2 +"1139" 1 3 +"1140" 1 2 +"1141" 1 1 +"1142" 1 3 +"1143" 1 2 +"1144" 1 1 +"1145" 1 2 +"1146" 1 3 +"1147" 1 1 +"1148" 1 0 +"1149" 1 2 +"1150" 1 0 +"1151" 1 3 +"1152" 1 3 +"1153" 1 1 +"1154" 1 0 +"1155" 1 1 +"1156" 1 3 +"1157" 1 0 +"1158" 1 3 +"1159" 1 2 +"1160" 1 3 +"1161" 1 0 +"1162" 1 0 +"1163" 1 3 +"1164" 1 4 +"1165" 1 0 +"1166" 1 3 +"1167" 1 1 +"1168" 1 5 +"1169" 1 1 +"1170" 1 0 +"1171" 1 2 +"1172" 1 3 +"1173" 1 2 +"1174" 1 4 +"1175" 1 1 +"1176" 1 1 +"1177" 1 2 +"1178" 1 1 +"1179" 1 1 +"1180" 1 3 +"1181" 1 4 +"1182" 1 2 +"1183" 1 0 +"1184" 1 3 +"1185" 1 1 +"1186" 1 4 +"1187" 1 0 +"1188" 1 0 +"1189" 1 1 +"1190" 1 0 +"1191" 1 1 +"1192" 1 1 +"1193" 1 3 +"1194" 1 3 +"1195" 1 1 +"1196" 1 4 +"1197" 1 2 +"1198" 1 1 +"1199" 1 2 +"1200" 1 4 +"1201" 1 1 +"1202" 1 2 +"1203" 1 1 +"1204" 1 1 +"1205" 1 2 +"1206" 1 2 +"1207" 1 0 +"1208" 1 1 +"1209" 1 3 +"1210" 1 5 +"1211" 1 5 +"1212" 1 1 +"1213" 1 2 +"1214" 1 0 +"1215" 1 1 +"1216" 1 2 +"1217" 1 3 +"1218" 1 1 +"1219" 1 1 +"1220" 1 1 +"1221" 1 1 +"1222" 1 2 +"1223" 1 1 +"1224" 1 1 +"1225" 1 3 +"1226" 1 2 +"1227" 1 1 +"1228" 1 1 +"1229" 1 3 +"1230" 1 1 +"1231" 1 1 +"1232" 1 2 +"1233" 1 3 +"1234" 1 2 +"1235" 1 0 +"1236" 1 1 +"1237" 1 3 +"1238" 1 6 +"1239" 1 3 +"1240" 1 1 +"1241" 1 0 +"1242" 1 2 +"1243" 1 1 +"1244" 1 0 +"1245" 1 1 +"1246" 1 1 +"1247" 1 1 +"1248" 1 2 +"1249" 1 3 +"1250" 1 0 +"1251" 1 1 +"1252" 1 1 +"1253" 1 4 +"1254" 1 3 +"1255" 1 0 +"1256" 1 1 +"1257" 1 2 +"1258" 1 2 +"1259" 1 2 +"1260" 1 4 +"1261" 1 3 +"1262" 1 1 +"1263" 1 2 +"1264" 1 3 +"1265" 1 3 +"1266" 1 2 +"1267" 1 3 +"1268" 1 1 +"1269" 1 2 +"1270" 1 2 +"1271" 1 3 +"1272" 1 1 +"1273" 1 1 +"1274" 1 2 +"1275" 1 0 +"1276" 1 2 +"1277" 1 1 +"1278" 1 0 +"1279" 1 2 +"1280" 1 1 +"1281" 1 0 +"1282" 1 3 +"1283" 1 2 +"1284" 1 1 +"1285" 1 3 +"1286" 1 3 +"1287" 1 1 +"1288" 1 2 +"1289" 1 1 +"1290" 1 2 +"1291" 1 2 +"1292" 1 5 +"1293" 1 0 +"1294" 1 0 +"1295" 1 3 +"1296" 1 2 +"1297" 1 2 +"1298" 1 2 +"1299" 1 4 +"1300" 1 2 +"1301" 1 0 +"1302" 1 3 +"1303" 1 1 +"1304" 1 0 +"1305" 1 3 +"1306" 1 4 +"1307" 1 0 +"1308" 1 1 +"1309" 1 1 +"1310" 1 0 +"1311" 1 0 +"1312" 1 2 +"1313" 1 3 +"1314" 1 2 +"1315" 1 2 +"1316" 1 2 +"1317" 1 1 +"1318" 1 2 +"1319" 1 4 +"1320" 1 0 +"1321" 1 3 +"1322" 1 0 +"1323" 1 3 +"1324" 1 2 +"1325" 1 1 +"1326" 1 1 +"1327" 1 2 +"1328" 1 0 +"1329" 1 0 +"1330" 1 5 +"1331" 1 2 +"1332" 1 1 +"1333" 1 0 +"1334" 1 2 +"1335" 1 1 +"1336" 1 3 +"1337" 1 1 +"1338" 1 1 +"1339" 1 1 +"1340" 1 3 +"1341" 1 1 +"1342" 1 2 +"1343" 1 2 +"1344" 1 1 +"1345" 1 2 +"1346" 1 0 +"1347" 1 2 +"1348" 1 1 +"1349" 1 2 +"1350" 1 3 +"1351" 1 1 +"1352" 1 2 +"1353" 1 0 +"1354" 1 3 +"1355" 1 1 +"1356" 1 2 +"1357" 1 1 +"1358" 1 3 +"1359" 1 1 +"1360" 1 4 +"1361" 1 2 +"1362" 1 2 +"1363" 1 4 +"1364" 1 1 +"1365" 1 1 +"1366" 1 3 +"1367" 1 0 +"1368" 1 0 +"1369" 1 0 +"1370" 1 2 +"1371" 1 1 +"1372" 1 3 +"1373" 1 1 +"1374" 1 4 +"1375" 1 0 +"1376" 1 2 +"1377" 1 4 +"1378" 1 0 +"1379" 1 3 +"1380" 1 2 +"1381" 1 4 +"1382" 1 0 +"1383" 1 2 +"1384" 1 0 +"1385" 1 3 +"1386" 1 0 +"1387" 1 2 +"1388" 1 2 +"1389" 1 1 +"1390" 1 2 +"1391" 1 2 +"1392" 1 0 +"1393" 1 3 +"1394" 1 4 +"1395" 1 4 +"1396" 1 2 +"1397" 1 1 +"1398" 1 1 +"1399" 1 4 +"1400" 1 3 +"1401" 1 0 +"1402" 1 5 +"1403" 1 0 +"1404" 1 2 +"1405" 1 3 +"1406" 1 2 +"1407" 1 2 +"1408" 1 3 +"1409" 1 0 +"1410" 1 1 +"1411" 1 3 +"1412" 1 0 +"1413" 1 3 +"1414" 1 3 +"1415" 1 3 +"1416" 1 1 +"1417" 1 1 +"1418" 1 3 +"1419" 1 1 +"1420" 1 1 +"1421" 1 0 +"1422" 1 4 +"1423" 1 3 +"1424" 1 3 +"1425" 1 2 +"1426" 1 2 +"1427" 1 6 +"1428" 1 2 +"1429" 1 1 +"1430" 1 1 +"1431" 1 2 +"1432" 1 0 +"1433" 1 0 +"1434" 1 4 +"1435" 1 1 +"1436" 1 3 +"1437" 1 2 +"1438" 1 2 +"1439" 1 1 +"1440" 1 3 +"1441" 1 1 +"1442" 1 1 +"1443" 1 1 +"1444" 1 2 +"1445" 1 2 +"1446" 1 1 +"1447" 1 2 +"1448" 1 0 +"1449" 1 1 +"1450" 1 2 +"1451" 1 0 +"1452" 1 8 +"1453" 1 0 +"1454" 1 1 +"1455" 1 2 +"1456" 1 3 +"1457" 1 1 +"1458" 1 1 +"1459" 1 0 +"1460" 1 0 +"1461" 1 2 +"1462" 1 1 +"1463" 1 2 +"1464" 1 1 +"1465" 1 4 +"1466" 1 2 +"1467" 1 0 +"1468" 1 2 +"1469" 1 1 +"1470" 1 1 +"1471" 1 3 +"1472" 1 1 +"1473" 1 3 +"1474" 1 0 +"1475" 1 1 +"1476" 1 1 +"1477" 1 3 +"1478" 1 3 +"1479" 1 3 +"1480" 1 0 +"1481" 1 1 +"1482" 1 1 +"1483" 1 1 +"1484" 1 2 +"1485" 1 0 +"1486" 1 1 +"1487" 1 0 +"1488" 1 2 +"1489" 1 4 +"1490" 1 2 +"1491" 1 5 +"1492" 1 3 +"1493" 1 1 +"1494" 1 2 +"1495" 1 1 +"1496" 1 2 +"1497" 1 2 +"1498" 1 2 +"1499" 1 0 +"1500" 1 1 +"1501" 1 1 +"1502" 1 4 +"1503" 1 2 +"1504" 1 2 +"1505" 1 0 +"1506" 1 1 +"1507" 1 2 +"1508" 1 1 +"1509" 1 2 +"1510" 1 1 +"1511" 1 2 +"1512" 1 2 +"1513" 1 1 +"1514" 1 2 +"1515" 1 1 +"1516" 1 0 +"1517" 1 2 +"1518" 1 4 +"1519" 1 1 +"1520" 1 3 +"1521" 1 4 +"1522" 1 1 +"1523" 1 0 +"1524" 1 1 +"1525" 1 0 +"1526" 1 2 +"1527" 1 5 +"1528" 1 2 +"1529" 1 1 +"1530" 1 0 +"1531" 1 2 +"1532" 1 5 +"1533" 1 2 +"1534" 1 2 +"1535" 1 2 +"1536" 1 2 +"1537" 1 0 +"1538" 1 2 +"1539" 1 4 +"1540" 1 1 +"1541" 1 2 +"1542" 1 2 +"1543" 1 3 +"1544" 1 2 +"1545" 1 1 +"1546" 1 2 +"1547" 1 0 +"1548" 1 1 +"1549" 1 3 +"1550" 1 4 +"1551" 1 2 +"1552" 1 5 +"1553" 1 0 +"1554" 1 3 +"1555" 1 3 +"1556" 1 3 +"1557" 1 0 +"1558" 1 2 +"1559" 1 1 +"1560" 1 4 +"1561" 1 2 +"1562" 1 2 +"1563" 1 5 +"1564" 1 3 +"1565" 1 2 +"1566" 1 3 +"1567" 1 1 +"1568" 1 5 +"1569" 1 0 +"1570" 1 3 +"1571" 1 0 +"1572" 1 2 +"1573" 1 1 +"1574" 1 2 +"1575" 1 0 +"1576" 1 2 +"1577" 1 1 +"1578" 1 0 +"1579" 1 3 +"1580" 1 1 +"1581" 1 2 +"1582" 1 4 +"1583" 1 3 +"1584" 1 1 +"1585" 1 1 +"1586" 1 0 +"1587" 1 1 +"1588" 1 1 +"1589" 1 3 +"1590" 1 1 +"1591" 1 0 +"1592" 1 0 +"1593" 1 4 +"1594" 1 1 +"1595" 1 0 +"1596" 1 0 +"1597" 1 1 +"1598" 1 1 +"1599" 1 3 +"1600" 1 0 +"1601" 1 1 +"1602" 1 3 +"1603" 1 0 +"1604" 1 3 +"1605" 1 3 +"1606" 1 3 +"1607" 1 2 +"1608" 1 1 +"1609" 1 3 +"1610" 1 2 +"1611" 1 2 +"1612" 1 2 +"1613" 1 5 +"1614" 1 0 +"1615" 1 3 +"1616" 1 1 +"1617" 1 2 +"1618" 1 3 +"1619" 1 3 +"1620" 1 0 +"1621" 1 1 +"1622" 1 2 +"1623" 1 1 +"1624" 1 2 +"1625" 1 2 +"1626" 1 1 +"1627" 1 2 +"1628" 1 0 +"1629" 1 1 +"1630" 1 2 +"1631" 1 0 +"1632" 1 1 +"1633" 1 4 +"1634" 1 0 +"1635" 1 3 +"1636" 1 0 +"1637" 1 3 +"1638" 1 0 +"1639" 1 1 +"1640" 1 3 +"1641" 1 2 +"1642" 1 1 +"1643" 1 1 +"1644" 1 3 +"1645" 1 1 +"1646" 1 1 +"1647" 1 1 +"1648" 1 4 +"1649" 1 2 +"1650" 1 1 +"1651" 1 3 +"1652" 1 3 +"1653" 1 1 +"1654" 1 0 +"1655" 1 2 +"1656" 1 1 +"1657" 1 3 +"1658" 1 1 +"1659" 1 3 +"1660" 1 2 +"1661" 1 2 +"1662" 1 1 +"1663" 1 6 +"1664" 1 2 +"1665" 1 1 +"1666" 1 2 +"1667" 1 1 +"1668" 1 3 +"1669" 1 0 +"1670" 1 1 +"1671" 1 1 +"1672" 1 5 +"1673" 1 0 +"1674" 1 2 +"1675" 1 2 +"1676" 1 2 +"1677" 1 1 +"1678" 1 2 +"1679" 1 2 +"1680" 1 1 +"1681" 1 1 +"1682" 1 3 +"1683" 1 2 +"1684" 1 3 +"1685" 1 3 +"1686" 1 2 +"1687" 1 4 +"1688" 1 1 +"1689" 1 2 +"1690" 1 3 +"1691" 1 2 +"1692" 1 0 +"1693" 1 3 +"1694" 1 1 +"1695" 1 1 +"1696" 1 1 +"1697" 1 2 +"1698" 1 5 +"1699" 1 2 +"1700" 1 2 +"1701" 1 1 +"1702" 1 2 +"1703" 1 4 +"1704" 1 0 +"1705" 1 1 +"1706" 1 2 +"1707" 1 5 +"1708" 1 2 +"1709" 1 5 +"1710" 1 2 +"1711" 1 0 +"1712" 1 4 +"1713" 1 0 +"1714" 1 2 +"1715" 1 0 +"1716" 1 0 +"1717" 1 1 +"1718" 1 0 +"1719" 1 5 +"1720" 1 3 +"1721" 1 1 +"1722" 1 6 +"1723" 1 2 +"1724" 1 2 +"1725" 1 3 +"1726" 1 2 +"1727" 1 1 +"1728" 1 2 +"1729" 1 3 +"1730" 1 1 +"1731" 1 0 +"1732" 1 3 +"1733" 1 2 +"1734" 1 0 +"1735" 1 3 +"1736" 1 2 +"1737" 1 1 +"1738" 1 1 +"1739" 1 2 +"1740" 1 1 +"1741" 1 4 +"1742" 1 3 +"1743" 1 2 +"1744" 1 0 +"1745" 1 1 +"1746" 1 2 +"1747" 1 1 +"1748" 1 2 +"1749" 1 2 +"1750" 1 3 +"1751" 1 2 +"1752" 1 1 +"1753" 1 1 +"1754" 1 1 +"1755" 1 1 +"1756" 1 0 +"1757" 1 2 +"1758" 1 1 +"1759" 1 0 +"1760" 1 0 +"1761" 1 1 +"1762" 1 3 +"1763" 1 5 +"1764" 1 0 +"1765" 1 2 +"1766" 1 0 +"1767" 1 4 +"1768" 1 4 +"1769" 1 1 +"1770" 1 2 +"1771" 1 0 +"1772" 1 3 +"1773" 1 3 +"1774" 1 2 +"1775" 1 1 +"1776" 1 3 +"1777" 1 0 +"1778" 1 2 +"1779" 1 2 +"1780" 1 2 +"1781" 1 0 +"1782" 1 3 +"1783" 1 4 +"1784" 1 2 +"1785" 1 2 +"1786" 1 3 +"1787" 1 1 +"1788" 1 2 +"1789" 1 1 +"1790" 1 1 +"1791" 1 2 +"1792" 1 3 +"1793" 1 2 +"1794" 1 1 +"1795" 1 3 +"1796" 1 5 +"1797" 1 2 +"1798" 1 1 +"1799" 1 1 +"1800" 1 1 +"1801" 2 0 +"1802" 2 3 +"1803" 2 1 +"1804" 2 2 +"1805" 2 1 +"1806" 2 0 +"1807" 2 2 +"1808" 2 0 +"1809" 2 0 +"1810" 2 0 +"1811" 2 1 +"1812" 2 1 +"1813" 2 2 +"1814" 2 2 +"1815" 2 0 +"1816" 2 1 +"1817" 2 1 +"1818" 2 0 +"1819" 2 1 +"1820" 2 1 +"1821" 2 0 +"1822" 2 0 +"1823" 2 0 +"1824" 2 1 +"1825" 2 1 +"1826" 2 1 +"1827" 2 2 +"1828" 2 0 +"1829" 2 2 +"1830" 2 0 +"1831" 2 0 +"1832" 2 0 +"1833" 2 1 +"1834" 2 0 +"1835" 2 0 +"1836" 2 1 +"1837" 2 1 +"1838" 2 1 +"1839" 2 2 +"1840" 2 0 +"1841" 2 1 +"1842" 2 1 +"1843" 2 0 +"1844" 2 0 +"1845" 2 0 +"1846" 2 0 +"1847" 2 0 +"1848" 2 0 +"1849" 2 0 +"1850" 2 0 +"1851" 2 0 +"1852" 2 0 +"1853" 2 1 +"1854" 2 0 +"1855" 2 0 +"1856" 2 0 +"1857" 2 1 +"1858" 2 0 +"1859" 2 1 +"1860" 2 2 +"1861" 2 2 +"1862" 2 1 +"1863" 2 1 +"1864" 2 1 +"1865" 2 3 +"1866" 2 0 +"1867" 2 1 +"1868" 2 1 +"1869" 2 0 +"1870" 2 2 +"1871" 2 0 +"1872" 2 0 +"1873" 2 3 +"1874" 2 1 +"1875" 2 1 +"1876" 2 0 +"1877" 2 1 +"1878" 2 1 +"1879" 2 0 +"1880" 2 0 +"1881" 2 1 +"1882" 2 1 +"1883" 2 0 +"1884" 2 1 +"1885" 2 2 +"1886" 2 1 +"1887" 2 0 +"1888" 2 1 +"1889" 2 1 +"1890" 2 1 +"1891" 2 0 +"1892" 2 1 +"1893" 2 1 +"1894" 2 1 +"1895" 2 2 +"1896" 2 0 +"1897" 2 0 +"1898" 2 3 +"1899" 2 1 +"1900" 2 0 +"1901" 2 0 +"1902" 2 1 +"1903" 2 2 +"1904" 2 1 +"1905" 2 1 +"1906" 2 0 +"1907" 2 1 +"1908" 2 2 +"1909" 2 0 +"1910" 2 0 +"1911" 2 1 +"1912" 2 1 +"1913" 2 0 +"1914" 2 1 +"1915" 2 0 +"1916" 2 2 +"1917" 2 0 +"1918" 2 0 +"1919" 2 1 +"1920" 2 0 +"1921" 2 1 +"1922" 2 0 +"1923" 2 0 +"1924" 2 0 +"1925" 2 1 +"1926" 2 1 +"1927" 2 0 +"1928" 2 0 +"1929" 2 0 +"1930" 2 0 +"1931" 2 2 +"1932" 2 1 +"1933" 2 2 +"1934" 2 0 +"1935" 2 1 +"1936" 2 0 +"1937" 2 1 +"1938" 2 0 +"1939" 2 1 +"1940" 2 0 +"1941" 2 0 +"1942" 2 1 +"1943" 2 0 +"1944" 2 1 +"1945" 2 0 +"1946" 2 1 +"1947" 2 0 +"1948" 2 0 +"1949" 2 1 +"1950" 2 0 +"1951" 2 0 +"1952" 2 2 +"1953" 2 0 +"1954" 2 0 +"1955" 2 0 +"1956" 2 3 +"1957" 2 2 +"1958" 2 0 +"1959" 2 0 +"1960" 2 2 +"1961" 2 3 +"1962" 2 0 +"1963" 2 1 +"1964" 2 0 +"1965" 2 0 +"1966" 2 1 +"1967" 2 0 +"1968" 2 2 +"1969" 2 0 +"1970" 2 0 +"1971" 2 2 +"1972" 2 0 +"1973" 2 1 +"1974" 2 1 +"1975" 2 0 +"1976" 2 0 +"1977" 2 0 +"1978" 2 1 +"1979" 2 1 +"1980" 2 0 +"1981" 2 1 +"1982" 2 1 +"1983" 2 1 +"1984" 2 1 +"1985" 2 0 +"1986" 2 0 +"1987" 2 0 +"1988" 2 0 +"1989" 2 2 +"1990" 2 0 +"1991" 2 2 +"1992" 2 3 +"1993" 2 1 +"1994" 2 1 +"1995" 2 0 +"1996" 2 1 +"1997" 2 1 +"1998" 2 1 +"1999" 2 0 +"2000" 2 0 +"2001" 2 1 +"2002" 2 0 +"2003" 2 0 +"2004" 2 1 +"2005" 2 1 +"2006" 2 0 +"2007" 2 1 +"2008" 2 0 +"2009" 2 1 +"2010" 2 1 +"2011" 2 1 +"2012" 2 0 +"2013" 2 0 +"2014" 2 0 +"2015" 2 1 +"2016" 2 0 +"2017" 2 1 +"2018" 2 0 +"2019" 2 1 +"2020" 2 1 +"2021" 2 0 +"2022" 2 0 +"2023" 2 0 +"2024" 2 0 +"2025" 2 0 +"2026" 2 2 +"2027" 2 0 +"2028" 2 2 +"2029" 2 0 +"2030" 2 0 +"2031" 2 1 +"2032" 2 0 +"2033" 2 1 +"2034" 2 2 +"2035" 2 2 +"2036" 2 0 +"2037" 2 0 +"2038" 2 0 +"2039" 2 1 +"2040" 2 0 +"2041" 2 0 +"2042" 2 1 +"2043" 2 1 +"2044" 2 1 +"2045" 2 0 +"2046" 2 0 +"2047" 2 2 +"2048" 2 0 +"2049" 2 1 +"2050" 2 0 +"2051" 2 0 +"2052" 2 0 +"2053" 2 1 +"2054" 2 1 +"2055" 2 2 +"2056" 2 0 +"2057" 2 0 +"2058" 2 1 +"2059" 2 1 +"2060" 2 1 +"2061" 2 0 +"2062" 2 0 +"2063" 2 1 +"2064" 2 1 +"2065" 2 0 +"2066" 2 0 +"2067" 2 1 +"2068" 2 1 +"2069" 2 2 +"2070" 2 0 +"2071" 2 1 +"2072" 2 1 +"2073" 2 4 +"2074" 2 1 +"2075" 2 2 +"2076" 2 1 +"2077" 2 0 +"2078" 2 0 +"2079" 2 0 +"2080" 2 2 +"2081" 2 1 +"2082" 2 1 +"2083" 2 2 +"2084" 2 2 +"2085" 2 0 +"2086" 2 2 +"2087" 2 1 +"2088" 2 1 +"2089" 2 1 +"2090" 2 1 +"2091" 2 0 +"2092" 2 0 +"2093" 2 0 +"2094" 2 1 +"2095" 2 3 +"2096" 2 0 +"2097" 2 0 +"2098" 2 1 +"2099" 2 0 +"2100" 2 0 +"2101" 2 0 +"2102" 2 1 +"2103" 2 0 +"2104" 2 0 +"2105" 2 0 +"2106" 2 0 +"2107" 2 1 +"2108" 2 0 +"2109" 2 0 +"2110" 2 0 +"2111" 2 1 +"2112" 2 1 +"2113" 2 2 +"2114" 2 1 +"2115" 2 0 +"2116" 2 0 +"2117" 2 0 +"2118" 2 1 +"2119" 2 1 +"2120" 2 1 +"2121" 2 2 +"2122" 2 0 +"2123" 2 1 +"2124" 2 1 +"2125" 2 0 +"2126" 2 0 +"2127" 2 0 +"2128" 2 0 +"2129" 2 1 +"2130" 2 0 +"2131" 2 0 +"2132" 2 0 +"2133" 2 1 +"2134" 2 1 +"2135" 2 1 +"2136" 2 1 +"2137" 2 1 +"2138" 2 0 +"2139" 2 1 +"2140" 2 2 +"2141" 2 0 +"2142" 2 1 +"2143" 2 0 +"2144" 2 0 +"2145" 2 0 +"2146" 2 0 +"2147" 2 0 +"2148" 2 1 +"2149" 2 0 +"2150" 2 0 +"2151" 2 3 +"2152" 2 1 +"2153" 2 1 +"2154" 2 0 +"2155" 2 1 +"2156" 2 2 +"2157" 2 0 +"2158" 2 1 +"2159" 2 0 +"2160" 2 0 +"2161" 2 0 +"2162" 2 0 +"2163" 2 0 +"2164" 2 0 +"2165" 2 0 +"2166" 2 0 +"2167" 2 0 +"2168" 2 0 +"2169" 2 1 +"2170" 2 0 +"2171" 2 0 +"2172" 2 2 +"2173" 2 0 +"2174" 2 0 +"2175" 2 0 +"2176" 2 0 +"2177" 2 2 +"2178" 2 1 +"2179" 2 0 +"2180" 2 0 +"2181" 2 1 +"2182" 2 0 +"2183" 2 2 +"2184" 2 1 +"2185" 2 1 +"2186" 2 2 +"2187" 2 0 +"2188" 2 1 +"2189" 2 0 +"2190" 2 0 +"2191" 2 1 +"2192" 2 0 +"2193" 2 1 +"2194" 2 1 +"2195" 2 0 +"2196" 2 1 +"2197" 2 2 +"2198" 2 0 +"2199" 2 1 +"2200" 2 1 +"2201" 2 0 +"2202" 2 0 +"2203" 2 1 +"2204" 2 1 +"2205" 2 0 +"2206" 2 0 +"2207" 2 0 +"2208" 2 1 +"2209" 2 1 +"2210" 2 0 +"2211" 2 1 +"2212" 2 1 +"2213" 2 0 +"2214" 2 0 +"2215" 2 2 +"2216" 2 1 +"2217" 2 0 +"2218" 2 1 +"2219" 2 1 +"2220" 2 1 +"2221" 2 2 +"2222" 2 0 +"2223" 2 1 +"2224" 2 0 +"2225" 2 1 +"2226" 2 1 +"2227" 2 1 +"2228" 2 0 +"2229" 2 1 +"2230" 2 0 +"2231" 2 1 +"2232" 2 1 +"2233" 2 1 +"2234" 2 1 +"2235" 2 0 +"2236" 2 0 +"2237" 2 0 +"2238" 2 1 +"2239" 2 0 +"2240" 2 0 +"2241" 2 1 +"2242" 2 1 +"2243" 2 1 +"2244" 2 0 +"2245" 2 0 +"2246" 2 1 +"2247" 2 0 +"2248" 2 1 +"2249" 2 1 +"2250" 2 0 +"2251" 2 0 +"2252" 2 2 +"2253" 2 1 +"2254" 2 2 +"2255" 2 2 +"2256" 2 0 +"2257" 2 2 +"2258" 2 4 +"2259" 2 0 +"2260" 2 1 +"2261" 2 3 +"2262" 2 0 +"2263" 2 1 +"2264" 2 1 +"2265" 2 1 +"2266" 2 0 +"2267" 2 0 +"2268" 2 1 +"2269" 2 0 +"2270" 2 0 +"2271" 2 0 +"2272" 2 0 +"2273" 2 0 +"2274" 2 1 +"2275" 2 1 +"2276" 2 1 +"2277" 2 1 +"2278" 2 0 +"2279" 2 0 +"2280" 2 0 +"2281" 2 0 +"2282" 2 1 +"2283" 2 1 +"2284" 2 1 +"2285" 2 2 +"2286" 2 1 +"2287" 2 0 +"2288" 2 2 +"2289" 2 0 +"2290" 2 1 +"2291" 2 0 +"2292" 2 1 +"2293" 2 0 +"2294" 2 0 +"2295" 2 0 +"2296" 2 0 +"2297" 2 0 +"2298" 2 0 +"2299" 2 2 +"2300" 2 1 +"2301" 2 0 +"2302" 2 0 +"2303" 2 0 +"2304" 2 0 +"2305" 2 1 +"2306" 2 0 +"2307" 2 1 +"2308" 2 2 +"2309" 2 0 +"2310" 2 0 +"2311" 2 0 +"2312" 2 1 +"2313" 2 1 +"2314" 2 1 +"2315" 2 0 +"2316" 2 1 +"2317" 2 0 +"2318" 2 1 +"2319" 2 0 +"2320" 2 0 +"2321" 2 2 +"2322" 2 1 +"2323" 2 1 +"2324" 2 0 +"2325" 2 1 +"2326" 2 1 +"2327" 2 0 +"2328" 2 0 +"2329" 2 0 +"2330" 2 0 +"2331" 2 1 +"2332" 2 1 +"2333" 2 2 +"2334" 2 1 +"2335" 2 2 +"2336" 2 1 +"2337" 2 2 +"2338" 2 1 +"2339" 2 0 +"2340" 2 0 +"2341" 2 0 +"2342" 2 1 +"2343" 2 0 +"2344" 2 2 +"2345" 2 1 +"2346" 2 0 +"2347" 2 0 +"2348" 2 1 +"2349" 2 1 +"2350" 2 0 +"2351" 2 1 +"2352" 2 0 +"2353" 2 0 +"2354" 2 1 +"2355" 2 1 +"2356" 2 4 +"2357" 2 0 +"2358" 2 1 +"2359" 2 0 +"2360" 2 0 +"2361" 2 0 +"2362" 2 0 +"2363" 2 0 +"2364" 2 2 +"2365" 2 4 +"2366" 2 1 +"2367" 2 0 +"2368" 2 1 +"2369" 2 0 +"2370" 2 1 +"2371" 2 0 +"2372" 2 0 +"2373" 2 0 +"2374" 2 4 +"2375" 2 1 +"2376" 2 1 +"2377" 2 0 +"2378" 2 0 +"2379" 2 1 +"2380" 2 0 +"2381" 2 0 +"2382" 2 0 +"2383" 2 0 +"2384" 2 0 +"2385" 2 0 +"2386" 2 0 +"2387" 2 0 +"2388" 2 2 +"2389" 2 0 +"2390" 2 3 +"2391" 2 0 +"2392" 2 1 +"2393" 2 1 +"2394" 2 1 +"2395" 2 1 +"2396" 2 0 +"2397" 2 2 +"2398" 2 0 +"2399" 2 0 +"2400" 2 0 +"2401" 2 2 +"2402" 2 0 +"2403" 2 0 +"2404" 2 0 +"2405" 2 0 +"2406" 2 0 +"2407" 2 1 +"2408" 2 0 +"2409" 2 3 +"2410" 2 0 +"2411" 2 0 +"2412" 2 1 +"2413" 2 0 +"2414" 2 1 +"2415" 2 0 +"2416" 2 1 +"2417" 2 0 +"2418" 2 0 +"2419" 2 0 +"2420" 2 1 +"2421" 2 0 +"2422" 2 1 +"2423" 2 2 +"2424" 2 1 +"2425" 2 0 +"2426" 2 1 +"2427" 2 1 +"2428" 2 1 +"2429" 2 0 +"2430" 2 0 +"2431" 2 1 +"2432" 2 0 +"2433" 2 2 +"2434" 2 0 +"2435" 2 0 +"2436" 2 0 +"2437" 2 0 +"2438" 2 0 +"2439" 2 2 +"2440" 2 2 +"2441" 2 3 +"2442" 2 1 +"2443" 2 1 +"2444" 2 0 +"2445" 2 0 +"2446" 2 0 +"2447" 2 2 +"2448" 2 1 +"2449" 2 0 +"2450" 2 0 +"2451" 2 0 +"2452" 2 0 +"2453" 2 3 +"2454" 2 2 +"2455" 2 0 +"2456" 2 0 +"2457" 2 0 +"2458" 2 2 +"2459" 2 0 +"2460" 2 0 +"2461" 2 1 +"2462" 2 1 +"2463" 2 0 +"2464" 2 1 +"2465" 2 0 +"2466" 2 0 +"2467" 2 1 +"2468" 2 1 +"2469" 2 2 +"2470" 2 1 +"2471" 2 0 +"2472" 2 0 +"2473" 2 1 +"2474" 2 0 +"2475" 2 0 +"2476" 2 0 +"2477" 2 1 +"2478" 2 0 +"2479" 2 0 +"2480" 2 0 +"2481" 2 2 +"2482" 2 1 +"2483" 2 1 +"2484" 2 2 +"2485" 2 0 +"2486" 2 0 +"2487" 2 0 +"2488" 2 0 +"2489" 2 2 +"2490" 2 1 +"2491" 2 0 +"2492" 2 0 +"2493" 2 0 +"2494" 2 1 +"2495" 2 0 +"2496" 2 1 +"2497" 2 0 +"2498" 2 0 +"2499" 2 0 +"2500" 2 1 +"2501" 2 0 +"2502" 2 1 +"2503" 2 0 +"2504" 2 2 +"2505" 2 1 +"2506" 2 0 +"2507" 2 0 +"2508" 2 0 +"2509" 2 1 +"2510" 2 0 +"2511" 2 1 +"2512" 2 0 +"2513" 2 1 +"2514" 2 0 +"2515" 2 1 +"2516" 2 1 +"2517" 2 0 +"2518" 2 0 +"2519" 2 1 +"2520" 2 2 +"2521" 2 0 +"2522" 2 2 +"2523" 2 1 +"2524" 2 1 +"2525" 2 1 +"2526" 2 0 +"2527" 2 0 +"2528" 2 0 +"2529" 2 2 +"2530" 2 0 +"2531" 2 1 +"2532" 2 4 +"2533" 2 0 +"2534" 2 0 +"2535" 2 0 +"2536" 2 0 +"2537" 2 3 +"2538" 2 0 +"2539" 2 3 +"2540" 2 1 +"2541" 2 0 +"2542" 2 0 +"2543" 2 0 +"2544" 2 1 +"2545" 2 3 +"2546" 2 2 +"2547" 2 2 +"2548" 2 0 +"2549" 2 0 +"2550" 2 1 +"2551" 2 1 +"2552" 2 2 +"2553" 2 0 +"2554" 2 0 +"2555" 2 0 +"2556" 2 2 +"2557" 2 0 +"2558" 2 2 +"2559" 2 2 +"2560" 2 2 +"2561" 2 0 +"2562" 2 1 +"2563" 2 0 +"2564" 2 0 +"2565" 2 1 +"2566" 2 1 +"2567" 2 0 +"2568" 2 1 +"2569" 2 1 +"2570" 2 1 +"2571" 2 0 +"2572" 2 1 +"2573" 2 2 +"2574" 2 1 +"2575" 2 1 +"2576" 2 0 +"2577" 2 1 +"2578" 2 0 +"2579" 2 0 +"2580" 2 1 +"2581" 2 2 +"2582" 2 0 +"2583" 2 0 +"2584" 2 0 +"2585" 2 2 +"2586" 2 2 +"2587" 2 1 +"2588" 2 0 +"2589" 2 1 +"2590" 2 0 +"2591" 2 0 +"2592" 2 0 +"2593" 2 1 +"2594" 2 1 +"2595" 2 0 +"2596" 2 0 +"2597" 2 1 +"2598" 2 0 +"2599" 2 0 +"2600" 2 0 +"2601" 2 1 +"2602" 2 0 +"2603" 2 1 +"2604" 2 0 +"2605" 2 1 +"2606" 2 0 +"2607" 2 0 +"2608" 2 1 +"2609" 2 0 +"2610" 2 1 +"2611" 2 0 +"2612" 2 0 +"2613" 2 0 +"2614" 2 0 +"2615" 2 0 +"2616" 2 0 +"2617" 2 0 +"2618" 2 0 +"2619" 2 1 +"2620" 2 0 +"2621" 2 0 +"2622" 2 0 +"2623" 2 1 +"2624" 2 0 +"2625" 2 1 +"2626" 2 0 +"2627" 2 1 +"2628" 2 2 +"2629" 2 0 +"2630" 2 0 +"2631" 2 2 +"2632" 2 0 +"2633" 2 0 +"2634" 2 0 +"2635" 2 0 +"2636" 2 1 +"2637" 2 0 +"2638" 2 1 +"2639" 2 0 +"2640" 2 1 +"2641" 2 0 +"2642" 2 0 +"2643" 2 0 +"2644" 2 1 +"2645" 2 1 +"2646" 2 0 +"2647" 2 1 +"2648" 2 0 +"2649" 2 1 +"2650" 2 0 +"2651" 2 2 +"2652" 2 0 +"2653" 2 0 +"2654" 2 1 +"2655" 2 0 +"2656" 2 3 +"2657" 2 0 +"2658" 2 1 +"2659" 2 1 +"2660" 2 1 +"2661" 2 1 +"2662" 2 2 +"2663" 2 1 +"2664" 2 0 +"2665" 2 0 +"2666" 2 1 +"2667" 2 0 +"2668" 2 0 +"2669" 2 1 +"2670" 2 0 +"2671" 2 0 +"2672" 2 0 +"2673" 2 0 +"2674" 2 1 +"2675" 2 2 +"2676" 2 0 +"2677" 2 0 +"2678" 2 0 +"2679" 2 1 +"2680" 2 0 +"2681" 2 0 +"2682" 2 0 +"2683" 2 2 +"2684" 2 0 +"2685" 2 0 +"2686" 2 1 +"2687" 2 2 +"2688" 2 1 +"2689" 2 3 +"2690" 2 0 +"2691" 2 0 +"2692" 2 1 +"2693" 2 0 +"2694" 2 1 +"2695" 2 0 +"2696" 2 1 +"2697" 2 1 +"2698" 2 1 +"2699" 2 1 +"2700" 2 0 +"2701" 2 0 +"2702" 2 0 +"2703" 2 1 +"2704" 2 1 +"2705" 2 1 +"2706" 2 2 +"2707" 2 0 +"2708" 2 1 +"2709" 2 1 +"2710" 2 0 +"2711" 2 0 +"2712" 2 1 +"2713" 2 1 +"2714" 2 4 +"2715" 2 1 +"2716" 2 2 +"2717" 2 1 +"2718" 2 0 +"2719" 2 0 +"2720" 2 0 +"2721" 2 0 +"2722" 2 3 +"2723" 2 2 +"2724" 2 1 +"2725" 2 0 +"2726" 2 0 +"2727" 2 2 +"2728" 2 2 +"2729" 2 0 +"2730" 2 0 +"2731" 2 1 +"2732" 2 0 +"2733" 2 0 +"2734" 2 0 +"2735" 2 2 +"2736" 2 0 +"2737" 2 0 +"2738" 2 1 +"2739" 2 2 +"2740" 2 0 +"2741" 2 3 +"2742" 2 0 +"2743" 2 1 +"2744" 2 0 +"2745" 2 4 +"2746" 2 1 +"2747" 2 1 +"2748" 2 0 +"2749" 2 1 +"2750" 2 0 +"2751" 2 1 +"2752" 2 0 +"2753" 2 0 +"2754" 2 1 +"2755" 2 1 +"2756" 2 1 +"2757" 2 1 +"2758" 2 1 +"2759" 2 1 +"2760" 2 0 +"2761" 2 1 +"2762" 2 1 +"2763" 2 1 +"2764" 2 0 +"2765" 2 1 +"2766" 2 1 +"2767" 2 0 +"2768" 2 1 +"2769" 2 1 +"2770" 2 0 +"2771" 2 2 +"2772" 2 2 +"2773" 2 0 +"2774" 2 1 +"2775" 2 0 +"2776" 2 0 +"2777" 2 1 +"2778" 2 1 +"2779" 2 1 +"2780" 2 1 +"2781" 2 1 +"2782" 2 1 +"2783" 2 2 +"2784" 2 1 +"2785" 2 0 +"2786" 2 1 +"2787" 2 2 +"2788" 2 0 +"2789" 2 1 +"2790" 2 0 +"2791" 2 1 +"2792" 2 2 +"2793" 2 0 +"2794" 2 2 +"2795" 2 1 +"2796" 2 0 +"2797" 2 1 +"2798" 2 1 +"2799" 2 0 +"2800" 2 0 +"2801" 2 0 +"2802" 2 1 +"2803" 2 0 +"2804" 2 2 +"2805" 2 0 +"2806" 2 0 +"2807" 2 2 +"2808" 2 1 +"2809" 2 1 +"2810" 2 0 +"2811" 2 0 +"2812" 2 1 +"2813" 2 1 +"2814" 2 0 +"2815" 2 0 +"2816" 2 2 +"2817" 2 0 +"2818" 2 0 +"2819" 2 0 +"2820" 2 2 +"2821" 2 2 +"2822" 2 0 +"2823" 2 1 +"2824" 2 0 +"2825" 2 1 +"2826" 2 1 +"2827" 2 0 +"2828" 2 0 +"2829" 2 0 +"2830" 2 0 +"2831" 2 0 +"2832" 2 0 +"2833" 2 0 +"2834" 2 0 +"2835" 2 0 +"2836" 2 2 +"2837" 2 1 +"2838" 2 0 +"2839" 2 1 +"2840" 2 1 +"2841" 2 1 +"2842" 2 1 +"2843" 2 1 +"2844" 2 0 +"2845" 2 1 +"2846" 2 3 +"2847" 2 0 +"2848" 2 1 +"2849" 2 2 +"2850" 2 0 +"2851" 2 1 +"2852" 2 1 +"2853" 2 1 +"2854" 2 0 +"2855" 2 1 +"2856" 2 0 +"2857" 2 0 +"2858" 2 0 +"2859" 2 1 +"2860" 2 0 +"2861" 2 1 +"2862" 2 0 +"2863" 2 3 +"2864" 2 0 +"2865" 2 1 +"2866" 2 2 +"2867" 2 0 +"2868" 2 1 +"2869" 2 1 +"2870" 2 2 +"2871" 2 3 +"2872" 2 0 +"2873" 2 2 +"2874" 2 1 +"2875" 2 0 +"2876" 2 0 +"2877" 2 1 +"2878" 2 1 +"2879" 2 0 +"2880" 2 0 +"2881" 2 1 +"2882" 2 0 +"2883" 2 1 +"2884" 2 1 +"2885" 2 0 +"2886" 2 1 +"2887" 2 0 +"2888" 2 0 +"2889" 2 1 +"2890" 2 0 +"2891" 2 0 +"2892" 2 1 +"2893" 2 0 +"2894" 2 1 +"2895" 2 2 +"2896" 2 1 +"2897" 2 0 +"2898" 2 1 +"2899" 2 2 +"2900" 2 1 +"2901" 2 1 +"2902" 2 1 +"2903" 2 0 +"2904" 2 1 +"2905" 2 3 +"2906" 2 0 +"2907" 2 0 +"2908" 2 2 +"2909" 2 1 +"2910" 2 1 +"2911" 2 1 +"2912" 2 0 +"2913" 2 0 +"2914" 2 1 +"2915" 2 0 +"2916" 2 1 +"2917" 2 1 +"2918" 2 0 +"2919" 2 0 +"2920" 2 1 +"2921" 2 0 +"2922" 2 1 +"2923" 2 0 +"2924" 2 1 +"2925" 2 0 +"2926" 2 1 +"2927" 2 0 +"2928" 2 1 +"2929" 2 0 +"2930" 2 1 +"2931" 2 0 +"2932" 2 0 +"2933" 2 1 +"2934" 2 1 +"2935" 2 0 +"2936" 2 0 +"2937" 2 0 +"2938" 2 1 +"2939" 2 0 +"2940" 2 0 +"2941" 2 0 +"2942" 2 0 +"2943" 2 0 +"2944" 2 0 +"2945" 2 0 +"2946" 2 2 +"2947" 2 0 +"2948" 2 0 +"2949" 2 0 +"2950" 2 2 +"2951" 2 1 +"2952" 2 0 +"2953" 2 0 +"2954" 2 0 +"2955" 2 0 +"2956" 2 1 +"2957" 2 0 +"2958" 2 1 +"2959" 2 0 +"2960" 2 0 +"2961" 2 0 +"2962" 2 1 +"2963" 2 2 +"2964" 2 1 +"2965" 2 0 +"2966" 2 1 +"2967" 2 2 +"2968" 2 0 +"2969" 2 2 +"2970" 2 0 +"2971" 2 0 +"2972" 2 1 +"2973" 2 0 +"2974" 2 1 +"2975" 2 0 +"2976" 2 2 +"2977" 2 1 +"2978" 2 1 +"2979" 2 0 +"2980" 2 1 +"2981" 2 0 +"2982" 2 2 +"2983" 2 1 +"2984" 2 0 +"2985" 2 0 +"2986" 2 1 +"2987" 2 1 +"2988" 2 1 +"2989" 2 2 +"2990" 2 2 +"2991" 2 1 +"2992" 2 1 +"2993" 2 2 +"2994" 2 0 +"2995" 2 1 +"2996" 2 0 +"2997" 2 1 +"2998" 2 1 +"2999" 2 0 +"3000" 2 0