{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "System\n",
      "os name: posix\n",
      "system: Darwin\n",
      "release: 18.7.0\n",
      "\n",
      "Python\n",
      "version: 3.7.3\n",
      "\n",
      "Python Packages\n",
      "jupterlab==1.1.5\n",
      "pandas==1.0.0\n",
      "numpy==1.17.4\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "\n",
    "import os\n",
    "import platform\n",
    "from platform import python_version\n",
    "import jupyterlab\n",
    "\n",
    "import matplotlib.pyplot as plt\n",
    "from datetime import datetime\n",
    "\n",
    "print(\"System\")\n",
    "print(\"os name: %s\" % os.name)\n",
    "print(\"system: %s\" % platform.system())\n",
    "print(\"release: %s\" % platform.release())\n",
    "print()\n",
    "print(\"Python\")\n",
    "print(\"version: %s\" % python_version())\n",
    "print()\n",
    "print(\"Python Packages\")\n",
    "print(\"jupterlab==%s\" % jupyterlab.__version__)\n",
    "print(\"pandas==%s\" % pd.__version__)\n",
    "print(\"numpy==%s\" % np.__version__)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.rcParams[\"figure.facecolor\"] = \"w\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 134,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(5, 2)"
      ]
     },
     "execution_count": 134,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.DataFrame({\"bin\": [0, 1, 2, 4, 5], \"value\": [1, 2, 3, 2, 5]})\n",
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 135,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>bin</th>\n",
       "      <th>value</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   bin  value\n",
       "0    0      1\n",
       "1    1      2\n",
       "2    2      3\n",
       "3    4      2\n",
       "4    5      5"
      ]
     },
     "execution_count": 135,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 136,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "3.1538461538461537"
      ]
     },
     "execution_count": 136,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "weighted_average = (df.bin * df.value).sum() / df.value.sum()\n",
    "weighted_average"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 137,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.lines.Line2D at 0x12298aa90>"
      ]
     },
     "execution_count": 137,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAygAAAGmCAYAAACX0aBwAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjIsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy8li6FKAAAcgUlEQVR4nO3de5DWZd0/8M9yMFA0FUEdIFcfExHU5SAq+VNMTC2wn3lAE9MxZx3NCrOZPDXV6KNWOIOlOK428WglEuVjIFKB8vh4mJg118kT2tSqi4oLqYFILnD//mhicujXfq3dvS6ufb1mnOE+7L3v27lnZ997fa7rW1er1WoBAACQgT6pAwAAAPyNggIAAGRDQQEAALKhoAAAANlQUAAAgGwoKAAAQDb6dceL7rHHHlFfX98dLw0AkMzGjRsjImLAgAGJk8D2r7W1NdasWbPN/d1SUOrr66O5ubk7XhoAIJnJkydHRMTy5cuT5oASTJgw4R/eb8QLAADIhoICAABkQ0EBAACy0S17UP6Rjo6OaGtr27q5rLcYMGBADB8+PPr37586CgAAZK/HCkpbW1vsvPPOUV9fH3V1dT31bZOq1Wqxdu3aaGtri3333Td1HADg33T11VenjgDF67GCsnHjxl5VTiIi6urqYvDgwdHe3p46CgDQBaZMmZI6AhSvR/eg9KZy8je98T0DQKlaWlqipaUldQwoWo+toGxvBg0aFOvXr08dAwDIyMyZMyPCdVCgOyUrKPWX39+lr9d6w6e69PUAAICe12uOGb788svjlltu2Xr7m9/8Zlx77bVx3HHHxbhx4+Lggw+O++67b5uvW758eUydOnXr7UsuuSTmzp0bERFPPPFEHHPMMTF+/Pg44YQT4rXXXuv29wEAACXrNQVl+vTpMX/+/K2358+fH+eee27ce++98dvf/jYeeuihuOyyy6JWq1V6vY6OjvjiF78YCxYsiCeeeCLOP//8uOqqq7orPgAA9Aq9Zg/K2LFj44033ohXX3012tvbY7fddou99torLr300nj44YejT58+sWrVqli9enXstddenb7eypUr4+mnn47jjz8+IiI2b94ce++9d3e/DQAAKFqlglJfXx8777xz9O3bN/r16xfNzc3dnatbnH766bFgwYJ4/fXXY/r06fHjH/842tvb44knnoj+/ftHfX39NheS7NevX2zZsmXr7b89XqvVYvTo0fH444/36HsAANK57rrrUkeA4lUe8XrooYeipaVluy0nEX8d85o3b14sWLAgTj/99Hj77bdj6NCh0b9//3jooYfipZde2uZr9tlnn3j22WfjL3/5S7z11luxbNmyiIgYOXJktLe3by0oHR0d8cwzz/To+wEAetakSZNi0qRJqWNA0XrNiFdExOjRo2PdunUxbNiw2HvvvePss8+OadOmxcEHHxwTJkyIAw88cJuvGTFiRJxxxhkxZsyY2HfffWPs2LEREbHDDjvEggUL4ktf+lK8/fbbsWnTppg5c2aMHj26p98WANBDHnvssYgIJQW6UV2twq7wfffdN3bbbbeoq6uLCy+8MBobG//p8ydMmLDNSstzzz0Xo0aN+vfSbqd683sHgJJMnjw5IlwHBbrCP+oMERVXUB555JEYNmxYvPHGG3H88cfHgQceGEcfffT7ntPU1BRNTU0REdHe3t4FkQEA4K+6+hp6vcX2eK3ASntQhg0bFhERQ4cOjVNOOSVWrFixzXMaGxujubk5mpubY8iQIV2bEgAA6BU6LSjvvPNOrFu3buu/f/WrX8WYMWO6PRgAAND7dDritXr16jjllFMiImLTpk3x2c9+Nk488cR/6ZvVarWoq6v7l752e1X1wo8AAECFgrLffvvFU0899W9/owEDBsTatWtj8ODBvaak1Gq1WLt2bQwYMCB1FACgC8yePTt1BChejx0zPHz48Ghra+t1G+gHDBgQw4cPTx0DAOgCDQ0NqSNA8XqsoPTv3z/23Xffnvp2AABdbunSpRERMWXKlMRJoFy96kKNAAD/jmuvvTYiFBToTpWOGQYAAOgJCgoAAJANBQUAAMiGggIAAGTDJnkAgIpuu+221BGgeAoKAEBFI0eOTB0BimfECwCgooULF8bChQtTx4CiWUEBAKjoxhtvjIiIadOmJU4C5bKCAgAAZENBAQAAsqGgAAAA2VBQAACAbNgkDwBQ0V133ZU6AhRPQQEAqGjEiBGpI0DxjHgBAFR0zz33xD333JM6BhTNCgoAQEW33nprRERMnz49cRIolxUUAAAgGwoKAACQDQUFAADIhoICAABkwyZ5AICKFixYkDoCFE9BAQCoaI899kgdAYpnxAsAoKK5c+fG3LlzU8eAoikoAAAVKSjQ/RQUAAAgGwoKAACQDQUFAADIhoICAABkwzHDAAAVLV68OHUEKJ6CAgBQ0Y477pg6AhTPiBcAQEVz5syJOXPmpI4BRVNQAAAqmj9/fsyfPz91DCiaggIAAGRDQQEAALKhoAAAANlQUAAAgGw4ZhgAoKLly5enjgDFs4ICAABkQ0EBAKho1qxZMWvWrNQxoGgKCgBARYsWLYpFixaljgFFU1AAAIBsKCgAAEA2FBQAACAbjhkGAKho4MCBqSNA8RQUAICKHnjggdQRoHhGvAAAgGwoKAAAFV1zzTVxzTXXpI4BRVNQAAAqWrZsWSxbtix1DCiaggIAAGRDQQEAALKhoAAAANlwzDAAQEWDBw9OHQGKp6AAAFT0s5/9LHUEKJ4RLwAAIBsKCgBARVdccUVcccUVqWNA0Yx4AQBU9Pjjj6eOAMWzggIAAGRDQQEAALKhoAAAANmwBwUAoKLhw4enjgDFU1AAACr60Y9+lDoCFK/yiNfmzZtj7NixMXXq1O7MAwAA9GKVC8pNN90Uo0aN6s4sAABZmzlzZsycOTN1DChapYLS1tYW999/f1xwwQXdnQcAIFstLS3R0tKSOgYUrVJBmTlzZnznO9+JPn0c+gUAAHSfThvHokWLYujQoTF+/Ph/+rympqaYMGFCTJgwIdrb27ssIAAA0Ht0WlAeffTR+MUvfhH19fVx5plnxoMPPhgzZszY5nmNjY3R3Nwczc3NMWTIkG4JCwAAlK3TgnL99ddHW1tbtLa2xrx58+LjH/+4I/YAgF7pgAMOiAMOOCB1DCia66AAAFTU1NSUOgIU7wMVlMmTJ8fkyZO7KQoAANDbOZYLAKCixsbGaGxsTB0DimbECwCgohdeeCF1BCieFRQAACAbCgoAAJANBQUAAMiGPSgAABU1NDSkjgDFU1AAACqaPXt26ghQPCNeAABANhQUAICKZsyYETNmzEgdA4pmxAsAoKK2trbUEaB4VlAAAIBsKCgAAEA2FBQAACAb9qAAAFR05JFHpo4AxVNQAAAquv7661NHgOIZ8QIAALKhoAAAVHTqqafGqaeemjoGFM2IFwBARWvXrk0dAYpnBQUAAMiGggIAAGRDQQEAALJhDwoAQEXHHXdc6ghQPAUFAKCir3/966kjQPGMeAEAANlQUAAAKjrppJPipJNOSh0DimbECwCgonfffTd1BCieFRQAACAbCgoAAJANBQUAAMiGPSgAABVNnTo1dQQonoICAFDRV7/61dQRoHhGvAAAgGwoKAAAFU2ePDkmT56cOgYUTUEBAACyoaAAAADZUFAAAIBsKCgAAEA2HDMMAFDRGWeckToCFE9BAQCo6OKLL04dAYpnxAsAoKINGzbEhg0bUseAollBAQCo6JOf/GRERCxfvjxtECiYFRQAACAbCgoAAJANBQUAAMiGggIAAGTDJnkAgIrOO++81BGgeAoKAEBFCgp0PyNeAAAVrVmzJtasWZM6BhTNCgoAQEWnnXZaRLgOCnQnKygAAEA2FBQAACAbCgoAAJANBQUAAMiGTfIAABVddNFFqSNA8RQUAICKpk+fnjoCFM+IFwBARa+88kq88sorqWNA0aygAABUdM4550SE66BAd7KCAgAAZENBAQAAsqGgAAAA2VBQAACAbNgkDwBQ0WWXXZY6AhRPQQEAqGjatGmpI0DxOh3x2rhxY0ycODEOPfTQGD16dHzjG9/oiVwAANlZuXJlrFy5MnUMKFqnKygf+tCH4sEHH4xBgwZFR0dHHHXUUXHSSSfFEUcc0RP5AACyceGFF0aE66BAd+p0BaWuri4GDRoUEREdHR3R0dERdXV13R4MAADofSqd4rV58+ZoaGiIoUOHxvHHHx+HH354d+cCAAB6oUqb5Pv27RstLS3x1ltvxSmnnBJPP/10jBkz5n3PaWpqiqampoiIaG9v7/qkAPxT9ZffnzrCdqn1hk+ljgDA3/lA10HZdddd49hjj40lS5Zs81hjY2M0NzdHc3NzDBkypMsCAgAAvUenKyjt7e3Rv3//2HXXXePdd9+NX//61/G1r32tJ7IBAGTl6quvTh0BitdpQXnttdfi3HPPjc2bN8eWLVvijDPOiKlTp/ZENgCArEyZMiV1BChepwXlkEMOiSeffLInsgAAZK2lpSUiIhoaGhIngXK5kjwAQEUzZ86MCNdBge70gTbJAwAAdCcFBQAAyIaCAgAAZENBAQAAsmGTPABARdddd13qCFA8BQUAoKJJkyaljgDFM+IFAFDRY489Fo899ljqGFA0KygAABVdeeWVEeE6KNCdrKAAAADZUFAAAIBsKCgAAEA2FBQAACAbNskDAFQ0e/bs1BGgeAoKAEBFDQ0NqSNA8Yx4AQBUtHTp0li6dGnqGFA0KygAABVde+21ERExZcqUxEmgXFZQAACAbCgoAABANhQUAAAgGwoKAACQDZvkAQAquu2221JHgOIpKAAAFY0cOTJ1BCieES8AgIoWLlwYCxcuTB0DimYFBQCgohtvvDEiIqZNm5Y4CZTLCgoAAJANBQUAAMiGggIAAGRDQQEAALJhkzwAQEV33XVX6ghQPAUFAKCiESNGpI4AxTPiBQBQ0T333BP33HNP6hhQNCsoAAAV3XrrrRERMX369MRJoFxWUAAAgGwoKAAAQDYUFAAAIBsKCgAAkA2b5AEAKlqwYEHqCFA8BQUAoKI99tgjdQQonhEvAICK5s6dG3Pnzk0dA4qmoAAAVKSgQPdTUAAAgGwoKAAAQDYUFAAAIBsKCgAAkA3HDAMAVLR48eLUEaB4CgoAQEU77rhj6ghQPCNeAAAVzZkzJ+bMmZM6BhRNQQEAqGj+/Pkxf/781DGgaAoKAACQDQUFAADIhoICAABkQ0EBAACy4ZhhAICKli9fnjoCFM8KCgAAkA0FBQCgolmzZsWsWbNSx4CiKSgAABUtWrQoFi1alDoGFE1BAQAAsqGgAAAA2VBQAACAbDhmGACgooEDB6aOAMVTUAAAKnrggQdSR4DiGfECAACyoaAAAFR0zTXXxDXXXJM6BhSt04LyyiuvxLHHHhsHHXRQjB49Om666aaeyAUAkJ1ly5bFsmXLUseAonW6B6Vfv35x4403xrhx42LdunUxfvz4OP744+Oggw7qiXwAAEAv0ukKyt577x3jxo2LiIidd945Ro0aFatWrer2YAAAQO/zgU7xam1tjSeffDIOP/zwbR5ramqKpqamiIhob2/vmnSwnau//P7UEbZLrTd8KnUEoBO99efb639YGxH/+vv38w06V3mT/Pr16+PUU0+N2bNnxy677LLN442NjdHc3BzNzc0xZMiQLg0JAJCDvgN3ib4Dt/09COg6lVZQOjo64tRTT42zzz47PvOZz3R3JgCALA055crUEaB4na6g1Gq1+PznPx+jRo2Kr3zlKz2RCQAA6KU6LSiPPvpo3HXXXfHggw9GQ0NDNDQ0xOLFi3siGwBAVt78n7nx5v/MTR0DitbpiNdRRx0VtVqtJ7IAAGTtL6ueTx0BiudK8gAAQDYUFAAAIBsKCgAAkI0PdKFGAIDerN/Oe6SOAMVTUAAAKtpj2ldTR4DiGfECAACyoaAAAFT0p6VN8aelTaljQNGMeAEAVPTeG39IHQGKZwUFAADIhoICAABkQ0EBAACyYQ8KAEBF/XcfljoCFE9BAQCoaPCJX0wdAYpnxAsAAMiGggIAUNHaJd+PtUu+nzoGFM2IFwBARR1/WpU6AhTPCgoAAJANBQUAAMiGggIAAGTDHhQAgIp2GLpf6ghQPAUFAKCi3ac0po4AxTPiBQAAZENBAQCoaM3CWbFm4azUMaBoRrwAACratG5N6ghQPCsoAABANhQUAAAgGwoKAACQDXtQAAAq+tCwA1NHgOIpKAAAFe12zHmpI0DxjHgBAADZUFAAACpqv/e6aL/3utQxoGhGvAAAKtr87p9TR4DiWUEBAACyoaAAAADZUFAAAIBs2IMCAFDRgH0OTR0BiqegAABUtOvHzkodAYpnxAsAAMiGggIAUNHq+d+I1fO/kToGFM2IFwBARbVNf0kdAYpnBQUAAMiGggIAAGRDQQEAALJhDwoAQEUD/2Ni6ghQPAUFAKCiDx/+mdQRoHhGvAAAgGwoKAAAFb3+k8vj9Z9cnjoGFE1BAQAAsqGgAAAA2VBQAACAbCgoAABANhwzDABQ0U4H/p/UEaB4CgoAQEU7j/tU6ghQPCNeAAAVbenYGFs6NqaOAUWzggIAUNEbP/1mRETs9dkb0gaBgllBAQAAsqGgAAAA2VBQAACAbCgoAABANmySBwCoaNDBU1JHgOIpKAAAFSko0P2MeAEAVLR5w9uxecPbqWNA0RQUAICK2v/7+mj/7+tTx4CidVpQzj///Bg6dGiMGTOmJ/IAAAC9WKcF5bzzzoslS5b0RBYAAKCX67SgHH300bH77rv3RBYAAKCXswcFAADIRpcdM9zU1BRNTU0REdHe3t5VL9vl6i+/P3WE7VLrDZ9KHQEAktt57CdTR4DidVlBaWxsjMbGxoiImDBhQle9LABANnYadXTqCFA8I14AABVt+nN7bPpzvpMiUIJOC8pZZ50VRx55ZKxcuTKGDx8eP/jBD3oiFwBAdtYsujHWLLoxdQwoWqcjXnfffXdP5AAAADDiBQAA5ENBAQAAsqGgAAAA2eiyY4YBAEq3y8RTUkeA4ikoAAAV7bj/4akjQPGMeAEAVNSxti061raljgFFU1AAACpa+8ubY+0vb04dA4qmoAAAANlQUAAAgGwoKAAAQDYUFAAAIBuOGQYAqOjDk85MHQGKp6AAAFQ0sL4hdQQonhEvAICK3lv9h3hv9R9Sx4CiKSgAABX9aVlT/GlZU+oYUDQFBQAAyIaCAgAAZENBAQAAsqGgAAAA2XDMMABARbsefW7qCFA8BQUAoKIBw0eljgDFM+IFAFDRxrbnYmPbc6ljQNEUFACAit56+L/irYf/K3UMKJqCAgAAZENBAQAAsqGgAAAA2VBQAACAbDhmGACgot2Pa0wdAYqnoAAAVLTDnvuljgDFM+IFAFDRu60t8W5rS+oYUDQrKAAAFb392LyIiBhY35A4CZTLCgoAAJANBQUAAMiGggIAAGRDQQEAALJhkzwAQEWDT7gkdQQonoICAFBR/8HDU0eA4hnxAgCoaMPvfxMbfv+b1DGgaFZQAAAq+vOKeyMiYsf9D0+cBMplBQUAAMiGggIAAGRDQQEAALKhoAAAANmwSR4AoKI9pl6WOgIUT0EBAKio3y5DUkeA4hnxAgCo6J3nHo53nns4dQwomhUUAICK1j25OCIidhp1dOIkUC4rKAAAQDYUFAAAIBsKCgAAkA0FBQAAyIZN8gAAFQ35v1ekjgDFU1AAACrqu+OHU0eA4hnxAgCoaP3vlsb63y1NHQOKpqAAAFSkoED3U1AAAIBsKCgAAEA2FBQAACAbCgoAAJANxwwDAFQ09PRvpo4AxVNQAAAq6tN/QOoIUDwjXgAAFa377f2x7rf3p44BRVNQAAAqeuf5/413nv/f1DGgaAoKAACQjUoFZcmSJTFy5MjYf//944YbbujuTAAAQC/VaUHZvHlzfOELX4gHHnggnn322bj77rvj2Wef7YlsAABAL9NpQVmxYkXsv//+sd9++8UOO+wQZ555Ztx33309kQ0AAOhl6mq1Wu2fPWHBggWxZMmSuOOOOyIi4q677orf/OY3cfPNN7/veU1NTdHU1BQREc8//3wceOCB3RS5XO3t7TFkyJDUMeglfN7oST5v9CSfN3qaz9y/prW1NdasWbPN/V12HZTGxsZobGzsqpfrlSZMmBDNzc2pY9BL+LzRk3ze6Ek+b/Q0n7mu1emI17Bhw+KVV17ZerutrS2GDRvWraEAAIDeqdOCcthhh8WLL74Yf/zjH+O9996LefPmxcknn9wT2QAAgF6m0xGvfv36xc033xwnnHBCbN68Oc4///wYPXp0T2TrdYzI0ZN83uhJPm/0JJ83eprPXNfqdJM8AABAT3EleQAAIBsKCgAAkA0FBQAAyEaXXQeFD+b555+P++67L1atWhURfz3O+eSTT45Ro0YlTgbw73v++edj1apVcfjhh8egQYO23r9kyZI48cQTEyajN/jc5z4Xd955Z+oY9AKPPPJIrFixIsaMGROf+MQnUscphhWUBL797W/HmWeeGbVaLSZOnBgTJ06MWq0WZ511Vtxwww2p49HL/PCHP0wdgcJ873vfi09/+tPx/e9/P8aMGRP33Xff1seuvPLKhMko0cknn/y+/6ZNmxY///nPt96GrjRx4sSt/7799tvjkksuiXXr1sW3vvUtv8N1Iad4JXDAAQfEM888E/3793/f/e+9916MHj06XnzxxUTJ6I0+8pGPxMsvv5w6BgU5+OCD4/HHH49BgwZFa2trnHbaaXHOOefEl7/85Rg7dmw8+eSTqSNSkHHjxsVBBx0UF1xwQdTV1W39g9+8efMiIuKYY45JnJCS/P3PsMMOOywWL14cQ4YMiXfeeSeOOOKI+N3vfpc4YRmMeCXQp0+fePXVV2OfffZ53/2vvfZa9OljUYuud8ghh/zD+2u1WqxevbqH01C6LVu2bB3rqq+vj+XLl8dpp50WL730UvibGF2tubk5brrppvjP//zP+O53vxsNDQ0xcOBAxYRusWXLlnjzzTdjy5YtUavVYsiQIRERsdNOO0W/fn6t7ir+TyYwe/bsOO644+KjH/1ojBgxIiIiXn755fj9738fN998c+J0lGj16tXxy1/+Mnbbbbf33V+r1WLSpEmJUlGqPffcM1paWqKhoSEiIgYNGhSLFi2K888/318X6XJ9+vSJSy+9NE4//fS49NJLY88994xNmzaljkWh3n777Rg/fnzUarWoq6uL1157Lfbee+9Yv369P8B0IQUlgRNPPDFeeOGFWLFixfs2yR922GHRt2/fxOko0dSpU2P9+vVbf2H8e5MnT+75QBTtzjvv3OYvif369Ys777wzLrzwwkSpKN3w4cPjpz/9adx///2xyy67pI5DoVpbW//h/X369Il77723Z8MUzB4UAAAgGzY8AAAA2VBQAACAbCgoAHSJ1tbWGDNmzDb3X3DBBfHss88mSATA9sgmeQC61R133JE6AgDbESsoAHSZTZs2xdlnnx2jRo2K0047LTZs2BCTJ0+O5ubmiPjrkcNXXXVVHHrooXHEEUe4Dg8A21BQAOgyK1eujIsvvjiee+652GWXXWLOnDnve/xvV1t+6qmn4uijj47bb789UVIAcqWgANBlRowYER/72MciImLGjBnxyCOPvO/xHXbYIaZOnRoREePHj///XlMAgN5LQQGgy9TV1f3T2/379996X9++fV3xG4BtKCgAdJmXX345Hn/88YiI+MlPfhJHHXVU4kQAbG8UFAC6zMiRI+OWW26JUaNGxZtvvhkXXXRR6kgAbGfqarVaLXUIAACACCsoAABARhQUAAAgGwoKAACQDQUFAADIhoICAABkQ0EBAACyoaAAAADZUFAAAIBs/D/7aZDkefu8sgAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 1008x504 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "ax = df.plot.bar(x=\"bin\", y=\"value\", figsize=(14, 7))\n",
    "ax.axvline(weighted_average, color=\"black\", linestyle=\"--\", label=\"Weighted average\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 138,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = df.append({\"bin\": 3, \"value\": 0}, ignore_index=True)\n",
    "df = df.sort_values([\"bin\"]).reset_index(drop=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 139,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>bin</th>\n",
       "      <th>value</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>5</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   bin  value\n",
       "0    0      1\n",
       "1    1      2\n",
       "2    2      3\n",
       "3    3      0\n",
       "4    4      2\n",
       "5    5      5"
      ]
     },
     "execution_count": 139,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.lines.Line2D at 0x120d2ff28>"
      ]
     },
     "execution_count": 52,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1008x504 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "ax = df.plot.bar(x=\"bin\", y=\"value\", figsize=(14, 7))\n",
    "ax.axvline(weighted_average, color=\"black\", linestyle=\"--\", label=\"Weighted average\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 140,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_train = pd.DataFrame({\"feat\": np.random.rand(1000)})\n",
    "df_test = pd.DataFrame({\"feat\": np.random.rand(1000)})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 141,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>feat</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.266349</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.890336</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.172578</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.729294</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.248798</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>995</th>\n",
       "      <td>0.129390</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>996</th>\n",
       "      <td>0.547107</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>997</th>\n",
       "      <td>0.746495</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>998</th>\n",
       "      <td>0.636268</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>999</th>\n",
       "      <td>0.872947</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1000 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "         feat\n",
       "0    0.266349\n",
       "1    0.890336\n",
       "2    0.172578\n",
       "3    0.729294\n",
       "4    0.248798\n",
       "..        ...\n",
       "995  0.129390\n",
       "996  0.547107\n",
       "997  0.746495\n",
       "998  0.636268\n",
       "999  0.872947\n",
       "\n",
       "[1000 rows x 1 columns]"
      ]
     },
     "execution_count": 141,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 142,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>feat</th>\n",
       "      <th>feat_bin</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.266349</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.890336</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.172578</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.729294</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.248798</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>995</th>\n",
       "      <td>0.129390</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>996</th>\n",
       "      <td>0.547107</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>997</th>\n",
       "      <td>0.746495</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>998</th>\n",
       "      <td>0.636268</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>999</th>\n",
       "      <td>0.872947</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1000 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "         feat  feat_bin\n",
       "0    0.266349         2\n",
       "1    0.890336         8\n",
       "2    0.172578         1\n",
       "3    0.729294         7\n",
       "4    0.248798         2\n",
       "..        ...       ...\n",
       "995  0.129390         1\n",
       "996  0.547107         5\n",
       "997  0.746495         7\n",
       "998  0.636268         6\n",
       "999  0.872947         8\n",
       "\n",
       "[1000 rows x 2 columns]"
      ]
     },
     "execution_count": 142,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train.loc[:, \"feat_bin\"] = pd.qcut(df_train.feat, 10, labels=False)\n",
    "df_train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 143,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>feat</th>\n",
       "      <th>feat_bin</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.294102</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.571480</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.753343</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.030228</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.699942</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>995</th>\n",
       "      <td>0.029048</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>996</th>\n",
       "      <td>0.867419</td>\n",
       "      <td>8</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>997</th>\n",
       "      <td>0.147510</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>998</th>\n",
       "      <td>0.093708</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>999</th>\n",
       "      <td>0.921401</td>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1000 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "         feat  feat_bin\n",
       "0    0.294102         2\n",
       "1    0.571480         5\n",
       "2    0.753343         7\n",
       "3    0.030228         0\n",
       "4    0.699942         7\n",
       "..        ...       ...\n",
       "995  0.029048         0\n",
       "996  0.867419         8\n",
       "997  0.147510         1\n",
       "998  0.093708         0\n",
       "999  0.921401         9\n",
       "\n",
       "[1000 rows x 2 columns]"
      ]
     },
     "execution_count": 143,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_test.loc[:, \"feat_bin\"] = pd.qcut(df_test.feat, 10, labels=False)\n",
    "df_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>feat</th>\n",
       "      <th>feat_bin</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.479995</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.031599</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.269777</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.548331</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.207935</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>995</th>\n",
       "      <td>0.939967</td>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>996</th>\n",
       "      <td>0.436288</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>997</th>\n",
       "      <td>0.894522</td>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>998</th>\n",
       "      <td>0.898392</td>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>999</th>\n",
       "      <td>0.797771</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1000 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "         feat  feat_bin\n",
       "0    0.479995         4\n",
       "1    0.031599         0\n",
       "2    0.269777         2\n",
       "3    0.548331         5\n",
       "4    0.207935         2\n",
       "..        ...       ...\n",
       "995  0.939967         9\n",
       "996  0.436288         4\n",
       "997  0.894522         9\n",
       "998  0.898392         9\n",
       "999  0.797771         7\n",
       "\n",
       "[1000 rows x 2 columns]"
      ]
     },
     "execution_count": 69,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_train.loc[:, \"feat_bin\"], feat_bins = pd.qcut(df_train[\"feat\"], 10, labels=False, retbins=True)\n",
    "df_train"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([8.00296009e-04, 8.27041149e-02, 1.83487678e-01, 2.89539672e-01,\n",
       "       3.89987164e-01, 4.98902517e-01, 6.15882594e-01, 7.02465079e-01,\n",
       "       8.04221493e-01, 8.91121321e-01, 9.99799581e-01])"
      ]
     },
     "execution_count": 71,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "feat_bins"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([      -inf, 0.08270411, 0.18348768, 0.28953967, 0.38998716,\n",
       "       0.49890252, 0.61588259, 0.70246508, 0.80422149, 0.89112132,\n",
       "              inf])"
      ]
     },
     "execution_count": 73,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "feat_bins = np.concatenate(([-np.inf], feat_bins[1:-1], [np.inf]))\n",
    "feat_bins"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>feat</th>\n",
       "      <th>feat_bin</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.485560</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.307222</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.608054</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.530871</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.012206</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>995</th>\n",
       "      <td>0.975463</td>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>996</th>\n",
       "      <td>0.734652</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>997</th>\n",
       "      <td>0.708907</td>\n",
       "      <td>7</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>998</th>\n",
       "      <td>0.355773</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>999</th>\n",
       "      <td>0.961182</td>\n",
       "      <td>9</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1000 rows × 2 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "         feat  feat_bin\n",
       "0    0.485560         4\n",
       "1    0.307222         3\n",
       "2    0.608054         5\n",
       "3    0.530871         5\n",
       "4    0.012206         0\n",
       "..        ...       ...\n",
       "995  0.975463         9\n",
       "996  0.734652         7\n",
       "997  0.708907         7\n",
       "998  0.355773         3\n",
       "999  0.961182         9\n",
       "\n",
       "[1000 rows x 2 columns]"
      ]
     },
     "execution_count": 75,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_test.loc[:, \"feat_bin\"] = pd.cut(df_test.feat, feat_bins, labels=False)\n",
    "df_test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 162,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_db = pd.DataFrame({\"key\": [1, 2, 3, None], \"value\": [2, 2, 3, 1]})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 163,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_ot = pd.DataFrame({\"key\": [\"3\", \"4\", \"5\", \"Null\"], \"value\": [1, 2, 1, 0]})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 164,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>key</th>\n",
       "      <th>value</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2.0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3.0</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   key  value\n",
       "0  1.0      2\n",
       "1  2.0      2\n",
       "2  3.0      3\n",
       "3  NaN      1"
      ]
     },
     "execution_count": 164,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_db"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 173,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>key</th>\n",
       "      <th>value</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Null</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    key  value\n",
       "0     3      1\n",
       "1     4      2\n",
       "2     5      1\n",
       "3  Null      0"
      ]
     },
     "execution_count": 173,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df_ot"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 166,
   "metadata": {},
   "outputs": [],
   "source": [
    "df = pd.concat((df_db, df_ot))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 167,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>key</th>\n",
       "      <th>value</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>NaN</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Null</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    key  value\n",
       "0     1      2\n",
       "1     2      2\n",
       "2     3      3\n",
       "3   NaN      1\n",
       "0     3      1\n",
       "1     4      2\n",
       "2     5      1\n",
       "3  Null      0"
      ]
     },
     "execution_count": 167,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 168,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>key</th>\n",
       "      <th>value</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Empty DataFrame\n",
       "Columns: [key, value]\n",
       "Index: []"
      ]
     },
     "execution_count": 168,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[df.key.duplicated()]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 170,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>key</th>\n",
       "      <th>value</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>4</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>5</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  key  value\n",
       "0   1      2\n",
       "1   2      2\n",
       "2   3      3\n",
       "0   3      1\n",
       "1   4      2\n",
       "2   5      1"
      ]
     },
     "execution_count": 170,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = df[df.key != \"Null\"]\n",
    "df = df[df.key.notnull()]\n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 171,
   "metadata": {},
   "outputs": [],
   "source": [
    "df.key = df.key.astype(int)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 172,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>key</th>\n",
       "      <th>value</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   key  value\n",
       "0    3      1"
      ]
     },
     "execution_count": 172,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df[df.key.duplicated()]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}