jhconning/Jeremy_intervention_plot.ipynb

## Jeremy_intervention_plot.ipynb
{
  "cells": [
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "## Jeremy's LPIS data\n\nLet's read in the dataset as a pandas dataframe"
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "import pandas as pd\nimport matplotlib.pyplot as plt",
      "execution_count": 1,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "df = pd.read_stata(\"./working_data/analytical_file_panel.dta\")",
      "execution_count": 2,
      "outputs": []
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "### Look at some overall means"
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "(df.groupby('flag_LPIS_ever')[['flag_collision', 'collision_count','personsinjured','pedestriansinjured']]\n    .agg(['count', 'mean']).T )",
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 3,
          "data": {
            "text/plain": "flag_LPIS_ever                       0              1\nflag_collision     count  3.659250e+06  159450.000000\n                   mean   4.956098e-02       0.151402\ncollision_count    count  3.659250e+06  159450.000000\n                   mean   6.720803e-02       0.246798\npersonsinjured     count  3.659250e+06  159450.000000\n                   mean   1.881396e-02       0.073572\npedestriansinjured count  3.659250e+06  159450.000000\n                   mean   4.141559e-03       0.022421",
            "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>flag_LPIS_ever</th>\n      <th>0</th>\n      <th>1</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th rowspan=\"2\" valign=\"top\">flag_collision</th>\n      <th>count</th>\n      <td>3.659250e+06</td>\n      <td>159450.000000</td>\n    </tr>\n    <tr>\n      <th>mean</th>\n      <td>4.956098e-02</td>\n      <td>0.151402</td>\n    </tr>\n    <tr>\n      <th rowspan=\"2\" valign=\"top\">collision_count</th>\n      <th>count</th>\n      <td>3.659250e+06</td>\n      <td>159450.000000</td>\n    </tr>\n    <tr>\n      <th>mean</th>\n      <td>6.720803e-02</td>\n      <td>0.246798</td>\n    </tr>\n    <tr>\n      <th rowspan=\"2\" valign=\"top\">personsinjured</th>\n      <th>count</th>\n      <td>3.659250e+06</td>\n      <td>159450.000000</td>\n    </tr>\n    <tr>\n      <th>mean</th>\n      <td>1.881396e-02</td>\n      <td>0.073572</td>\n    </tr>\n    <tr>\n      <th rowspan=\"2\" valign=\"top\">pedestriansinjured</th>\n      <th>count</th>\n      <td>3.659250e+06</td>\n      <td>159450.000000</td>\n    </tr>\n    <tr>\n      <th>mean</th>\n      <td>4.141559e-03</td>\n      <td>0.022421</td>\n    </tr>\n  </tbody>\n</table>\n</div>"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "### Create a `timeafter` LPIS installation variable\n\nMeasured in months.  This will be negative before the intervention.\n\nNote that the `year` and `month` variables are stored as integers but `LPIS_install_date` is in datetime format.  The following formula counts the number of months between the date of the observation and the installation date. \n\nNote that if there is no then there is no timeafter to measure."
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "df['timeafter'] = (df.year - df.LPIS_install_date.dt.year)*12 +(df.month - df.LPIS_install_date.dt.month)",
      "execution_count": 4,
      "outputs": []
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "We only want to see the data from intersections, so let's create a new dataframe with just this data."
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "dflp = df[df.flag_LPIS_ever!=0]\ndflp.shape",
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 5,
          "data": {
            "text/plain": "(159450, 100)"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "Finally let's find the mean number of collisions in each month before and after."
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "dflp.groupby('timeafter')['collision_count'].mean().plot()\nplt.axvline(0)\nplt.xlim(-36,36)\nplt.title('Mean collision count per intersection')\nplt.xlabel('Months before or after LPIS install');",
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": "<Figure size 432x288 with 1 Axes>",
            "image/png": "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\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "## Some notes\n\nNote that we have less observations as more time elapses."
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "dflp.groupby('timeafter')['collision_count'].agg('count').plot()\nplt.xlim(-36,36);",
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": "<Figure size 432x288 with 1 Axes>",
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYAAAAEKCAYAAAAb7IIBAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMi4zLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvIxREBQAAIABJREFUeJzt3Xl8VPW9//HXJ/tCIAkJEEJkF0QEhMgiqEUroMWqrVpbq9ir5edVu/68la5629tWu9hf9Wdr0Vq1WldccKO1iIILaNihoIRNAoGEfQlk/d4/5sQOEJKQZc5Mzvv5eMxjZr7nzJw3PuK855w5iznnEBGR4InzO4CIiPhDBSAiElAqABGRgFIBiIgElApARCSgVAAiIgGlAhARCSgVgIhIQKkAREQCKsHvAI3Jyclxffr08TuGiEhMWbx48U7nXG5T80V1AfTp04eioiK/Y4iIxBQz29yc+bQJSEQkoFQAIiIBpQIQEQkoFYCISECpAEREAkoFICISUCoAEZGAiurjACQ21NU5jtTUHjdeXes4XFXL4eraT++PVNdSUf+4qpbKmlrqL0p67NVJwy9XeuyFS8PnPX7aiS9zevTrXCPTWva645fnTjifO2q+Y6c173XHThzXP4dx/bueOJBIGBVAB1Bb56g75oOgts5xsLKGA0dqOHCkmgNHajhUWUNVbR3VtXVU1zgqa+uorqkLjdWExiu9aVW1tVTXuLCxuk9fW1VTx8HKWg4cqWb/4WoOVtZQp0tL+8YsdO8cPDB/A698YwKnds/wN5TEBBVABFXW1FK69wjb9h6mZO9hdh6spLL63x+qVfX34Y/Dxqpr66j0Hh8O+yZdVVPXZhmTEuJIio8jKSGOxHjz7sPHQuP5mSl0TskgIyWBzqmJpCUlEGdHv1d8nJGWlEBqUhypifGkJiWE7hPjQ2NJCSTFxx31OrOj3yT82TGTsPCpx0478aSjlnH8tBO8fwPLb06u46c1nOP4accu4wQLD7PzYCWTfzef7z6zjBduHk9ivLbwSuNUAO1kx/4jrCzZx8qtodu/tu1n+/4jDc6bEBf6oK3/8E2MjyO5/nnYWHpyAkkJoWlpSaEP0hTvPiHu2A8ro1NyAhkpCWSkJNI5JeHT1yeGf8CHfbAnxFmzPmgkOuV0Subnl5/BTY8v5r43i/nuhaf6HUminArgJFTW1FK2v5JPdlewadchNu+qYNPOQ2zffyT0bdz7Rl5RVcOR6tC3cjMYkNuJcf270rtrGvmZqeRnpZKfmUq3jBSSE+KIO/ars0gLTRnagy+MzOf+ecVcMLgbwwsy/Y4kUUwFcAJb9x7myUWfsLxkL2X7K9lx4Ah7K6qPmic5IY5TstPomZlKQVYCKfWbNhLjyeuSyhm9ujAkrzPpyfrPLJFzxyWn8/76XXz3mWW8+s1zSEmM9zuSRCl9MoVxzvFu8S4efX8Tc9fsAGBofhd6d01jdN9sundOpltGCgXZafTJSaN7Roq+vUvU6ZKayK+vGM5X/7yIX835iJ9cMsTvSBKlAl8AzjmKyw4yZ9V2Xli2lQ3lh8hOT+Km8/pzzdje5Gem+h1R5KRNGJjDdeN68/C7G+mUksBlI3rSL7eT37EkygSyAPZWVFFcdpA315YxZ/V2NpQfAqCwdxa3XjWAi8/I02qzxLwZFw1m864K7p27jnvnrmNIXmemDs/jkmE9KchO8zueRAFr7KAZADMrAB4DegB1wEzn3O/NLBt4GugDbAKucs7tsdBuJL8HLgYqgOudc0u895oG/Mh76/9xzj3a2LILCwtdW1wQ5s21O3hx6TY27zrEpl0V7Dsc2pYfH2eM7ZfNlKF5TBrSne6dU1q9LJFoU7rvMK+uKOWVFaUs27IXgOG9ujB1WE8+NyyPnlrL7XDMbLFzrrDJ+ZpRAHlAnnNuiZllAIuBy4Drgd3OubvMbAaQ5Zy73cwuBr5BqADGAL93zo3xCqMIKCR0MONiYJRzbs+Jlt0WBfDSsq185+ll5HRKZlCPDHp3TaNP13ROyU7jrD7ZZKUnter9RWLJlt0VvLqylFdWbGPV1v0AjOqdxdfG92HqsJ4+p5O20twCaHITkHOuFCj1Hh8wszVAPnAp8BlvtkeBt4DbvfHHXKhZFppZplcinwHecM7t9gK+AUwBnjypf9lJqP/wH903m4evP4u0pEBu8RL5VEF2Gjed15+bzuvPxp2HeHXFNl5cto1b/7aUhRt28eOpQ0hO0ObPoDipQwXNrA9wJrAI6O6VQ31JdPNmywe2hL2sxBs70Xi70Ie/SOP65qRz6/kDmfOtc5h+bj8eX/gJX/rTQkr3HfY7mkRIswvAzDoBs4BvO+f2NzZrA2OukfFjlzPdzIrMrKi8vLy58Y6iD3+R5kuIj+MHF5/GH64ZybodB5h67zu8V7zT71gSAc0qADNLJPTh/4Rz7nlveIe3aaf+d4Iyb7wEKAh7eS9gWyPjR3HOzXTOFTrnCnNzc0/m38Khyhp+NWetPvxFWuDiM/J46dYJZKUn8dU/L+Ktj8qafpHEtCYLwNur58/AGufcPWGTZgPTvMfTgJfCxq+zkLHAPm8T0d+BSWaWZWZZwCRvrNXq6hzPLylh4m/e4g9vreeyM/P14S/SAgO6deKlW8aTn5XKH+at9zuOtLPmfEKOB64FVprZMm/sB8BdwDNmdgPwCXClN+01QnsAFRPaDfRrAM653Wb2M+BDb76f1v8g3BrLt+zlzpdXs/STvQzv1YUHrh3FyFOyWvu2IoGVnpzAtHF9+J9X17Bq6z6G5nfxO5K0kyZ3A/VTU7uBvrC0hNueXUF2ehK3TxnMF87M16kZRNrA/iPVjPvFXCYP7cE9V43wO46cpObuBhqzJwz/y7sb+c7TyxndJ5u5//c8rhjVSx/+Im2kc0oiV4zqxSvLSyk70PBpzCX2xVwBOOe45x8f8d8v/4vJp3fnL187i84piX7HEulwrh/fl6raOp5Y+InfUaSdxFQB1NY5fvTiKu59s5gvFRZw/1dG6pw9Iu2kb0465w/uxhOLNlPZwDWfJfZF9W4yB45UM3P+ejbtqmDzrkNsKD9E6b4j3HRef26fMkhXrxJpZ18b34dr//wBrywv5YujevkdR9pYVBfApl0V/OK1tWSlJdK7azpj+mZz7qm5fGGk/hBFImHCgBwGduvEw+9u5Asj8/Wlq4OJ6gLo0TmF5T+ZRJc0beMX8YOZ8bXxffnBCyv5cNMeRvfN9juStKGo/g0gNyNZH/4iPrv8zHwy0xJ5+J2NfkeRNhbVBSAi/ktNiucro09hzurt3Dl7NYer9INwRxHVm4BEJDp884KBVFTV8sh7m3j743J+c+VwRvXWEfexTmsAItKklMR47vz86fzt62Ooqqnjygfe4+45a7V7aIxTAYhIs53dP4c53z6HqwoL+ONb6/n6Y4upq4ve08lI41QAInJSMlISueuLw/jppacz/+NyHnt/k9+RpIVUACLSIteO7c35g7vxy9fXUlx2wO840gIqABFpETPjri+eQVpSPN95ejnVtXV+R5KTpAIQkRbrlpHCL79wBiu37uO+uev8jiMnSQUgIq0yZWgeV4zqxf+fV8yST/b4HUdOggpARFrtjkuGkNclle8+vYw9h6r8jiPNpAIQkVbLSEnkt1cNZ8uew0y4+01++doaXUgmBqgARKRNjO3Xlde+eQ4XnNadBxdsYMLd8/jxi6so2VPhdzQ5gZi+JrCIRKdNOw/xwNvrmbWkhLSkBN667TNkpSf5HSswOvw1gUUkevXJSeeuLw7jhZvHs+9wNY+8t8nvSNIAFYCItJuh+V2YNKQ7j7y3iYOVNX7HkWOoAESkXd08cQD7Dlfz5CJdXD7aqABEpF2NKMhkwoAcHlywgSPVOntoNFEBiEi7u3lif8oOVDJrSYnfUSSMCkBE2t24fl0ZUZDJA2+vp0bnDIoaKgARaXdmxi0TB7Bl92FeWVHqdxzxqABEJCIuGNyNQd0z+MNbxbqITJRQAYhIRMTFGTdP7M/HOw7yzzU7/I4jqABEJII+d0YeBdmpPPzuRr+jCCoAEYmghPg4vlRYwMINu9myW+cI8psKQEQi6vKRvTBDu4RGARWAiERUfmYq4/vnMGtJiX4M9pkKQEQi7opRvdiy+zAfbNrtd5RAUwGISMRNPr0HnZITeLZIm4H8pAIQkYhLTYpn6rA8Xl9VyiGdJdQ3KgAR8cWVhb2oqKrltZU6MtgvKgAR8cXIU7Lom5POc4u1GcgvTRaAmT1sZmVmtips7E4z22pmy7zbxWHTvm9mxWb2kZlNDhuf4o0Vm9mMtv+niEgsMTOuGNWLRRt388kuHRPgh+asATwCTGlg/HfOuRHe7TUAMxsCXA2c7r3mD2YWb2bxwP3ARcAQ4MvevCISYJefmY8ZPKdjAnzRZAE45+YDzd1X61LgKedcpXNuI1AMjPZuxc65Dc65KuApb14RCbCemalMGJDDrMU6JsAPrfkN4FYzW+FtIsryxvKBLWHzlHhjJxo/jplNN7MiMysqLy9vRTwRiQVXjOrF1r2HeXNtmd9RAqelBfBHoD8wAigFfuuNWwPzukbGjx90bqZzrtA5V5ibm9vCeCISK6YM7UH/3HTufHk1FVXaJTSSWlQAzrkdzrla51wd8CChTTwQ+mZfEDZrL2BbI+MiEnDJCfH84vIzKNlzmP/3z3V+xwmUFhWAmeWFPb0cqN9DaDZwtZklm1lfYCDwAfAhMNDM+ppZEqEfime3PLaIdCRj+nXly6MLeGjBBlZt3ed3nMBozm6gTwLvA4PMrMTMbgB+ZWYrzWwFMBH4DoBzbjXwDPAvYA5wi7emUAPcCvwdWAM8480rIgLAjCmnkZ2ezPefX6nrBkeIORe9v7wXFha6oqIiv2OISIS8vHwb33hyKT/63GnceE4/v+PELDNb7JwrbGo+HQksIlFj6rA8Jg7K5bf/+FgXjIkAFYCIRA0z42eXDQXgxy+tIpq3UHQEKgARiSq9stK4bfIg3vqoXOcJamcqABGJOtef3Yez+mTx05f/xba9h/2O02GpAEQk6sTHGb+5cjg1dY7bZ63QpqB2ogIQkajUu2s6P7h4MAvW7eRvH3zid5wOSQUgIlHrmjG9GT+gKz9/dY32CmoHKgARiVpxccavrhhOnBm3PbtcZwxtYyoAEYlq+Zmp/HjqaSzauJsnFm32O06HogIQkah3VWEBo/tmc/+89VTV6DQRbUUFICJRz8y4ZeIAtu8/wkvLtvodp8NQAYhITDh3YA6n5XXmT/M36LeANqICEJGYYGbcdF4/issO6uphbUQFICIx43Nn5JGfmcoDb6/3O0qHoAIQkZiREB/H18/pS9HmPRRt2u13nJinAhCRmHLVWQVkpSXywNsb/I4S81QAIhJT0pISuG5cH/65ZgfrdhzwO05MUwGISMyZdnYfUhLjmDlfawGtoQIQkZiTnZ7ElwoLeHHZVorLtBbQUioAEYlJ08/rT+eURK6euZB/bdvvd5yYpAIQkZiUn5nKMzeNIzE+jqtnvs/izXv8jhRzVAAiErP653bi2ZvGkZ2exLV/XsQ763b6HSmmqABEJKb1ykrjmZvGcUp2Gv/xyIfMWVXqd6SYoQIQkZjXLSOFp6aPZUjPztz0+BJ+/OIqDlXW+B0r6qkARKRDyExL4qnpY7lxQl8eX7SZi+9dwIc6WrhRKgAR6TBSEuP50dQhPPX1sdQ5x1V/ep9fvLaGI9W1fkeLSioAEelwxvTrypxvnctXRp/CzPkbGH/Xm9zzxseUHTjid7SoYs5F73m1CwsLXVFRkd8xRCSGfbBxNzPnr2fu2jIS4+K4ZHhPbpjQlyE9O/sdrd2Y2WLnXGFT8yVEIoyIiF9G981mdN9sNu48xF/e3cizRSU8v7SEX18xnCtG9fI7nq+0CUhEAqFvTjo/vXQoC79/AeP753D7rBX8Y/V2v2P5SgUgIoHSJS2RP107iqH5Xbj1yaW8v36X35F8owIQkcBJT07gkevPond2Gl9/rIiVJfv8juQLFYCIBFJWehJ/vWEMXVITmfaXDyguO+h3pIhTAYhIYPXoksLjN44hzuCahxaydnuwziqqAhCRQOubk84TN44F4MoH3mfRhuD8JqACEJHAG9Qjg1n/eTbdMpK59uEPeH1lME4opwIQESF0VtHnbjqboT07c/PflvDXhZv9jtTumiwAM3vYzMrMbFXYWLaZvWFm67z7LG/czOxeMys2sxVmNjLsNdO8+deZ2bT2+eeIiLRcVnoST9w4lvMHdePHL67ixaVb/Y7UrpqzBvAIMOWYsRnAXOfcQGCu9xzgImCgd5sO/BFChQHcAYwBRgN31JeGiEg0SU2K50/XjqJ31zRmL9/md5x21WQBOOfmA8eeU/VS4FHv8aPAZWHjj7mQhUCmmeUBk4E3nHO7nXN7gDc4vlRERKJCQnwc5w7MZeGGXVTV1Pkdp9209DeA7s65UgDvvps3ng9sCZuvxBs70biISFQaPyCHiqpalm3Z63eUdtPWPwJbA2OukfHj38BsupkVmVlReXl5m4YTEWmucf27EmfwzrqO+znU0gLY4W3awbsv88ZLgIKw+XoB2xoZP45zbqZzrtA5V5ibm9vCeCIirdMlNZFhvTJ5p7jjXmi+pQUwG6jfk2ca8FLY+HXe3kBjgX3eJqK/A5PMLMv78XeSNyYiErXOGZjD8pJ97D9S7XeUdtGc3UCfBN4HBplZiZndANwFXGhm64ALvecArwEbgGLgQeBmAOfcbuBnwIfe7afemIhI1Bo/IIfaOsfCDnrG0CYvCOOc+/IJJl3QwLwOuOUE7/Mw8PBJpRMR8dHIU7JITYznneKdTDq9h99x2pyOBBYROYGkhDjG9MvusL8DqABERBoxYUAOG8oPsW3vYb+jtDkVgIhIIyYMzAHokGsBKgARkUYM6p5BTqdk3lmnAhARCRQzY8KArrxbvJO6ugaPX41ZKgARkSaMH5DDrkNVrN1+wO8obUoFICLShPrfAd7tYL8DqABERJqQ1yWV/rnpLFABiIgEzzkDc/lg4y4OVdb4HaXNqABERJrhoqE9qKyp4ysPLqTswBG/47QJFYCISDOM6deVP311FB/vOMjl97/Hxzti/wdhFYCISDNNOr0HT/+fsVTV1vHFP74X88cGqABERE7CsF6ZvHjLeHp2SeX6v3zA80tK/I7UYioAEZGTlJ+ZynP/OY6z+mQzY9ZKissO+h2pRVQAIiItkJGSyL1fPpPUpHhun7UiJo8SVgGIiLRQbkYyP5k6hMWb9/DXhZv9jnPSVAAiIq3whZH5nHdqLnfPWUvJngq/45wUFYCISCuYGT+/fCgGfP/5lYQujBgbVAAiIq3UKyuN2y8azIJ1O5m1ZKvfcZpNBSAi0ga+OqY3hb2z+Nkr/4qZI4VVACIibSAuzrj7imFUVNVw/5vFfsdpFhWAiEgb6Z/biUtH5PNMUQl7K6r8jtMkFYCISBu68Zy+HK6u5YlFn/gdpUkqABGRNjS4R2fOGZjDI+9torKm1u84jVIBiIi0senn9qP8QCWzl23zO0qjVAAiIm1swoAcBvfI4KEFG6P6uAAVgIhIGzMzbjynHx/tOMD8KD5ltApARKQdfH54T7p3TuahBRv8jnJCKgARkXaQlBDHtLP7sGDdTtaU7vc7ToNUACIi7eSa0b1JS4rnwShdC0jwO4CISEfVJS2RqwoLeOS9TSz9ZC+De2QwuEdnBudlcHb/rmSkJPqaTwUgItKObps8iK7pSazetp81pfuZs3o7zsHpPTvz8q0TiIsz37KpAERE2lGn5AS+ccHAT58fqqzhucUl3DF7NS+v2MalI/J9y6bfAEREIig9OYFrx/ZmcI8M7nnjY6pr63zLogIQEYmwuDjjvyYPYvOuCp4p2uJfDt+WLCISYOcP7sao3lncO3cdR6r9OWeQCkBExAdmxvcmD2LH/koefW+TLxlUACIiPhnTryvnnprLH99ez/4j1RFffqsKwMw2mdlKM1tmZkXeWLaZvWFm67z7LG/czOxeMys2sxVmNrIt/gEiIrHse5MHsbeimofmR/5gsbZYA5jonBvhnCv0ns8A5jrnBgJzvecAFwEDvdt04I9tsGwRkZg2NL8Lnzsjj4fe2ci2vYcjuuz22AR0KfCo9/hR4LKw8cdcyEIg08zy2mH5IiIx5TsXnkpNneP8377FnbNXU7ovMkXQ2gJwwD/MbLGZTffGujvnSgG8+27eeD4Qvr9TiTd2FDObbmZFZlZUXl7eyngiItFvQLdOvP6tc5g6rCePL9zMub+ax4xZK9i861C7Lre1BTDeOTeS0OadW8zs3Ebmbeh45+OulOCcm+mcK3TOFebm5rYynohIbOif24nfXDmcebd9hqvPOoXnl27lwt/N5+2P2++LcKsKwDm3zbsvA14ARgM76jftePdl3uwlQEHYy3sB0X29NBGRCCvITuNnlw1lwfcmMiC3E19/rKjdSqDFBWBm6WaWUf8YmASsAmYD07zZpgEveY9nA9d5ewONBfbVbyoSEZGjde+cwhM3jmnXEmjNGkB34B0zWw58ALzqnJsD3AVcaGbrgAu95wCvARuAYuBB4OZWLFtEpMPLSk9q1xKwaL5gcWFhoSsqKvI7hoiIr/YcquKahxZRXH6Q3145nKnD8jA78WmkzWxx2K75J6QjgUVEolz9msCg7hl848mlTL3vHeasKqWurnVf4FUAIiIxICs9iRduPpvfXjmciqpabnp8CRf9fgEvL99GbQuLQJuARERiTG2d45UV27jvzWKKyw7SPzedW88fwCXDepIQH9fsTUAqABGRGFVX53h91Xbue3Mda7cfoE/XNG6eOIAvnXVKswpAl4QUEYlRcXHG54blcdHQHryxZgf3vbmO7z23otmvVwGIiMS4uDhj8uk9mDSkO6+t3M7Uu5v5uvaNJSIikWIWWiNoLhWAiEhAqQBERAJKBSAiElAqABGRgFIBiIgElApARCSgVAAiIgGlAhARCSgVgIhIQKkAREQCSgUgIhJQKgARkYBSAYiIBJQKQEQkoFQAIiIBpQIQEQkoFYCISECpAEREAkoFICISUCoAEZGAUgGIiASUCkBEJKBUACIiAaUCEBEJKBWAiEhAqQBERAJKBSAiElAqABGRgFIBiIgElApARCSgIl4AZjbFzD4ys2IzmxHp5YuISEhEC8DM4oH7gYuAIcCXzWxIJDOIiEhIpNcARgPFzrkNzrkq4Cng0ghnEBERIl8A+cCWsOcl3piIiERYpAvAGhhzR81gNt3MisysqLy8PEKxRESCJ9IFUAIUhD3vBWwLn8E5N9M5V+icK8zNzY1oOBGRIIl0AXwIDDSzvmaWBFwNzI5wBhERARIiuTDnXI2Z3Qr8HYgHHnbOrY5kBhERCYloAQA4514DXov0ckVE5Gg6ElhEJKBUACIiAaUCEBEJKBWAiEhAqQBERALKnHNNz+UTMysHNkdwkTnAzggury3FavZYzQ2xmz1Wc0PsZo907t7OuSaPpI3qAog0MytyzhX6naMlYjV7rOaG2M0eq7khdrNHa25tAhIRCSgVgIhIQKkAjjbT7wCtEKvZYzU3xG72WM0NsZs9KnPrNwARkYDSGoCISECpAAAz+5mZrTCzZWb2DzPr6Y2bmd3rXcB+hZmN9DtrODP7tZmt9bK9YGaZYdO+7+X+yMwm+5mzIWZ2pZmtNrM6Mys8Zlq0Z5/iZSs2sxl+52mMmT1sZmVmtipsLNvM3jCzdd59lp8ZG2JmBWY2z8zWeH8n3/LGYyF7ipl9YGbLvez/7Y33NbNFXvanvVPi+8s5F/gb0Dns8TeBB7zHFwOvE7qS2Vhgkd9Zj8k9CUjwHt8N3O09HgIsB5KBvsB6IN7vvMdkPw0YBLwFFIaNR3V2QqcxXw/0A5K8rEP8ztVI3nOBkcCqsLFfATO8xzPq/26i6QbkASO9xxnAx97fRixkN6CT9zgRWOR9fjwDXO2NPwD8p99ZtQYAOOf2hz1N59+XqbwUeMyFLAQyzSwv4gFPwDn3D+dcjfd0IaErrEEo91POuUrn3EagGBjtR8YTcc6tcc591MCkaM8+Gih2zm1wzlUBTxHKHJWcc/OB3ccMXwo86j1+FLgsoqGawTlX6pxb4j0+AKwhdP3wWMjunHMHvaeJ3s0B5wPPeeNRkV0F4DGzn5vZFuAa4CfecCxdxP4/CK2tQGzlPla0Z4/2fM3R3TlXCqEPWqCbz3kaZWZ9gDMJfZOOiexmFm9my4Ay4A1Ca417w76wRcXfTWAKwMz+aWarGrhdCuCc+6FzrgB4Ari1/mUNvFVEd5tqKrc3zw+BGkLZIQpyQ/OyN/SyBsaiaVe1aM/XoZhZJ2AW8O1j1tSjmnOu1jk3gtBa+WhCmzyPmy2yqY4X8SuC+cU599lmzvo34FXgDppxEfv21lRuM5sGTAUucN7GRaIgN5zUf/NwUZG9EdGerzl2mFmec67U26RZ5neghphZIqEP/yecc897wzGRvZ5zbq+ZvUXoN4BMM0vw1gKi4u8mMGsAjTGzgWFPPw+s9R7PBq7z9gYaC+yrX/2MBmY2Bbgd+LxzriJs0mzgajNLNrO+wEDgAz8ytkC0Z/8QGOjt0ZEEXE0ocyyZDUzzHk8DXvIxS4PMzIA/A2ucc/eETYqF7Ln1e+SZWSrwWUK/YcwDrvBmi47sfv8KHQ03Qt8yVgErgJeBfPfvX/PvJ7T9biVhe6tEw43QD6RbgGXe7YGwaT/0cn8EXOR31gayX07o23QlsAP4ewxlv5jQXinrgR/6naeJrE8CpUC199/7BqArMBdY591n+52zgdwTCG0iWRH2931xjGQfBiz1sq8CfuKN9yP0ZaYYeBZI9jurjgQWEQkobQISEQkoFYCISECpAEREAkoFICISUCoAEZGAUgFIh2ZmmWZ2s/e4p5k919RrWrm8ZO8I6GVm9iUz+7aZpbXnMkVaSruBSofmnUfmFefc0AgtbyyhM1Se5z3fROj4kZ0n8R7xzrnadooo8imtAUhHdxfQ3/tG/mz9efHN7Hoze9HMXjazjWZ2q5l918yWmtlCM8v25utvZnPMbLGZLTCzwd74Jd7PiZDyAAABwUlEQVS53Zd63/i7m1k34HFghLe8bwE9gXlmNs973SQze9/Mlnh5Onnjm8zsJ2b2DnBl5P8zSRCpAKSjmwGsd6ETc/3XMdOGAl8hdLKunwMVzrkzgfeB67x5ZgLfcM6NAm4D/uCNvwOM9eZ/Cviec64MuBFY4Jwb4Zz7PaHzvUx0zk00sxzgR8BnnXMjgSLgu2F5jjjnJjjnnmrL/wAiJxKYk8GJNGCeC51r/oCZ7SN0GhAInfZjmPft/Gzg2dCpaYDQhWogdDKvp70TkiUBG5uxvLGELmryrvd+SYTKpt7Trfi3iJw0FYAEWWXY47qw53WE/t+II3QO9xENvPY+4B7n3Gwz+wxwZzOWZ8Abzrkvn2D6oeaEFmkr2gQkHd0BQpcUPGkudP75jWZ2JXx6jejh3uQuwFbv8bSGXt/A8hcC481sgPd+aWZ2akuyibQFFYB0aM65XYQ2uawCft2Ct7gGuMHMlgOr+fflH+8ktGloAdDYHj4zgdfNbJ5zrhy4HnjSzFYQKoTBLcgk0ia0G6iISEBpDUBEJKBUACIiAaUCEBEJKBWAiEhAqQBERAJKBSAiElAqABGRgFIBiIgE1P8C/zJqvDsnMacAAAAASUVORK5CYII=\n"
          },
          "metadata": {
            "needs_background": "light"
          }
        }
      ]
    }
  ],
  "metadata": {
    "hide_input": false,
    "kernelspec": {
      "name": "python3",
      "display_name": "Python [default]",
      "language": "python"
    },
    "varInspector": {
      "window_display": true,
      "cols": {
        "lenName": 16,
        "lenType": 16,
        "lenVar": 40
      },
      "kernels_config": {
        "python": {
          "library": "var_list.py",
          "delete_cmd_prefix": "del ",
          "delete_cmd_postfix": "",
          "varRefreshCmd": "print(var_dic_list())"
        },
        "r": {
          "library": "var_list.r",
          "delete_cmd_prefix": "rm(",
          "delete_cmd_postfix": ") ",
          "varRefreshCmd": "cat(var_dic_list()) "
        }
      },
      "types_to_exclude": [
        "module",
        "function",
        "builtin_function_or_method",
        "instance",
        "_Feature"
      ],
      "oldHeight": 122,
      "position": {
        "height": "40px",
        "left": "1408px",
        "right": "20px",
        "top": "120px",
        "width": "250px"
      },
      "varInspector_section_display": "none"
    },
    "language_info": {
      "name": "python",
      "version": "3.6.6",
      "mimetype": "text/x-python",
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "pygments_lexer": "ipython3",
      "nbconvert_exporter": "python",
      "file_extension": ".py"
    },
    "gist": {
      "id": "",
      "data": {
        "description": "Collisions before and after LPIS installation",
        "public": true
      }
    }
  },
  "nbformat": 4,
  "nbformat_minor": 2
}