{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Read in the data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy\n",
    "import re\n",
    "\n",
    "data_files = [\n",
    "    \"ap_2010.csv\",\n",
    "    \"class_size.csv\",\n",
    "    \"demographics.csv\",\n",
    "    \"graduation.csv\",\n",
    "    \"hs_directory.csv\",\n",
    "    \"sat_results.csv\"\n",
    "]\n",
    "\n",
    "data = {}\n",
    "\n",
    "for f in data_files:\n",
    "    d = pd.read_csv(\"schools/{0}\".format(f))\n",
    "    data[f.replace(\".csv\", \"\")] = d"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Read in the surveys"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [],
   "source": [
    "all_survey = pd.read_csv(\"schools/survey_all.txt\", delimiter=\"\\t\", encoding='windows-1252')\n",
    "d75_survey = pd.read_csv(\"schools/survey_d75.txt\", delimiter=\"\\t\", encoding='windows-1252')\n",
    "survey = pd.concat([all_survey, d75_survey], axis=0)\n",
    "\n",
    "survey[\"DBN\"] = survey[\"dbn\"]\n",
    "\n",
    "survey_fields = [\n",
    "    \"DBN\", \n",
    "    \"rr_s\", \n",
    "    \"rr_t\", \n",
    "    \"rr_p\", \n",
    "    \"N_s\", \n",
    "    \"N_t\", \n",
    "    \"N_p\", \n",
    "    \"saf_p_11\", \n",
    "    \"com_p_11\", \n",
    "    \"eng_p_11\", \n",
    "    \"aca_p_11\", \n",
    "    \"saf_t_11\", \n",
    "    \"com_t_11\", \n",
    "    \"eng_t_11\", \n",
    "    \"aca_t_11\", \n",
    "    \"saf_s_11\", \n",
    "    \"com_s_11\", \n",
    "    \"eng_s_11\", \n",
    "    \"aca_s_11\", \n",
    "    \"saf_tot_11\", \n",
    "    \"com_tot_11\", \n",
    "    \"eng_tot_11\", \n",
    "    \"aca_tot_11\",\n",
    "]\n",
    "survey = survey[survey_fields]\n",
    "data[\"survey\"] = survey"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Add DBN columns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {},
   "outputs": [],
   "source": [
    "data[\"hs_directory\"][\"DBN\"] = data[\"hs_directory\"][\"dbn\"]\n",
    "\n",
    "def pad_csd(num):\n",
    "    string_representation = str(num)\n",
    "    if len(string_representation) > 1:\n",
    "        return string_representation\n",
    "    else:\n",
    "        return \"0\" + string_representation\n",
    "    \n",
    "data[\"class_size\"][\"padded_csd\"] = data[\"class_size\"][\"CSD\"].apply(pad_csd)\n",
    "data[\"class_size\"][\"DBN\"] = data[\"class_size\"][\"padded_csd\"] + data[\"class_size\"][\"SCHOOL CODE\"]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Convert columns to numeric"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = ['SAT Math Avg. Score', 'SAT Critical Reading Avg. Score', 'SAT Writing Avg. Score']\n",
    "for c in cols:\n",
    "    data[\"sat_results\"][c] = pd.to_numeric(data[\"sat_results\"][c], errors=\"coerce\")\n",
    "\n",
    "data['sat_results']['sat_score'] = data['sat_results'][cols[0]] + data['sat_results'][cols[1]] + data['sat_results'][cols[2]]\n",
    "\n",
    "def find_lat(loc):\n",
    "    coords = re.findall(\"\\(.+, .+\\)\", loc)\n",
    "    lat = coords[0].split(\",\")[0].replace(\"(\", \"\")\n",
    "    return lat\n",
    "\n",
    "def find_lon(loc):\n",
    "    coords = re.findall(\"\\(.+, .+\\)\", loc)\n",
    "    lon = coords[0].split(\",\")[1].replace(\")\", \"\").strip()\n",
    "    return lon\n",
    "\n",
    "data[\"hs_directory\"][\"lat\"] = data[\"hs_directory\"][\"Location 1\"].apply(find_lat)\n",
    "data[\"hs_directory\"][\"lon\"] = data[\"hs_directory\"][\"Location 1\"].apply(find_lon)\n",
    "\n",
    "data[\"hs_directory\"][\"lat\"] = pd.to_numeric(data[\"hs_directory\"][\"lat\"], errors=\"coerce\")\n",
    "data[\"hs_directory\"][\"lon\"] = pd.to_numeric(data[\"hs_directory\"][\"lon\"], errors=\"coerce\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Condense datasets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {},
   "outputs": [],
   "source": [
    "class_size = data[\"class_size\"]\n",
    "class_size = class_size[class_size[\"GRADE \"] == \"09-12\"]\n",
    "class_size = class_size[class_size[\"PROGRAM TYPE\"] == \"GEN ED\"]\n",
    "\n",
    "class_size = class_size.groupby(\"DBN\").agg(numpy.mean)\n",
    "class_size.reset_index(inplace=True)\n",
    "data[\"class_size\"] = class_size\n",
    "\n",
    "data[\"demographics\"] = data[\"demographics\"][data[\"demographics\"][\"schoolyear\"] == 20112012]\n",
    "\n",
    "data[\"graduation\"] = data[\"graduation\"][data[\"graduation\"][\"Cohort\"] == \"2006\"]\n",
    "data[\"graduation\"] = data[\"graduation\"][data[\"graduation\"][\"Demographic\"] == \"Total Cohort\"]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Convert AP scores to numeric"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = ['AP Test Takers ', 'Total Exams Taken', 'Number of Exams with scores 3 4 or 5']\n",
    "\n",
    "for col in cols:\n",
    "    data[\"ap_2010\"][col] = pd.to_numeric(data[\"ap_2010\"][col], errors=\"coerce\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Combine the datasets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "metadata": {},
   "outputs": [],
   "source": [
    "combined = data[\"sat_results\"]\n",
    "\n",
    "combined = combined.merge(data[\"ap_2010\"], on=\"DBN\", how=\"left\")\n",
    "combined = combined.merge(data[\"graduation\"], on=\"DBN\", how=\"left\")\n",
    "\n",
    "to_merge = [\"class_size\", \"demographics\", \"survey\", \"hs_directory\"]\n",
    "\n",
    "for m in to_merge:\n",
    "    combined = combined.merge(data[m], on=\"DBN\", how=\"inner\")\n",
    "\n",
    "combined = combined.fillna(combined.mean())\n",
    "combined = combined.fillna(0)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Add a school district column for mapping"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 73,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_first_two_chars(dbn):\n",
    "    return dbn[0:2]\n",
    "\n",
    "combined[\"school_dist\"] = combined[\"DBN\"].apply(get_first_two_chars)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Find correlations"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 74,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "SAT Critical Reading Avg. Score         0.986820\n",
      "SAT Math Avg. Score                     0.972643\n",
      "SAT Writing Avg. Score                  0.987771\n",
      "sat_score                               1.000000\n",
      "AP Test Takers                          0.523140\n",
      "Total Exams Taken                       0.514333\n",
      "Number of Exams with scores 3 4 or 5    0.463245\n",
      "Total Cohort                            0.325144\n",
      "CSD                                     0.042948\n",
      "NUMBER OF STUDENTS / SEATS FILLED       0.394626\n",
      "NUMBER OF SECTIONS                      0.362673\n",
      "AVERAGE CLASS SIZE                      0.381014\n",
      "SIZE OF SMALLEST CLASS                  0.249949\n",
      "SIZE OF LARGEST CLASS                   0.314434\n",
      "SCHOOLWIDE PUPIL-TEACHER RATIO               NaN\n",
      "schoolyear                                   NaN\n",
      "fl_percent                                   NaN\n",
      "frl_percent                            -0.722225\n",
      "total_enrollment                        0.367857\n",
      "ell_num                                -0.153778\n",
      "ell_percent                            -0.398750\n",
      "sped_num                                0.034933\n",
      "sped_percent                           -0.448170\n",
      "asian_num                               0.475445\n",
      "asian_per                               0.570730\n",
      "black_num                               0.027979\n",
      "black_per                              -0.284139\n",
      "hispanic_num                            0.025744\n",
      "hispanic_per                           -0.396985\n",
      "white_num                               0.449559\n",
      "                                          ...   \n",
      "rr_p                                    0.047925\n",
      "N_s                                     0.423463\n",
      "N_t                                     0.291463\n",
      "N_p                                     0.421530\n",
      "saf_p_11                                0.122913\n",
      "com_p_11                               -0.115073\n",
      "eng_p_11                                0.020254\n",
      "aca_p_11                                0.035155\n",
      "saf_t_11                                0.313810\n",
      "com_t_11                                0.082419\n",
      "eng_t_11                                0.036906\n",
      "aca_t_11                                0.132348\n",
      "saf_s_11                                0.337639\n",
      "com_s_11                                0.187370\n",
      "eng_s_11                                0.213822\n",
      "aca_s_11                                0.339435\n",
      "saf_tot_11                              0.318753\n",
      "com_tot_11                              0.077310\n",
      "eng_tot_11                              0.100102\n",
      "aca_tot_11                              0.190966\n",
      "grade_span_max                               NaN\n",
      "expgrade_span_max                            NaN\n",
      "zip                                    -0.063977\n",
      "total_students                          0.407827\n",
      "number_programs                         0.117012\n",
      "priority08                                   NaN\n",
      "priority09                                   NaN\n",
      "priority10                                   NaN\n",
      "lat                                    -0.121029\n",
      "lon                                    -0.132222\n",
      "Name: sat_score, Length: 67, dtype: float64\n"
     ]
    }
   ],
   "source": [
    "correlations = combined.corr()\n",
    "correlations = correlations[\"sat_score\"]\n",
    "print(correlations)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Plotting survey correlations"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 75,
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "# Remove DBN since it's a unique identifier, not a useful numerical value for correlation.\n",
    "survey_fields.remove(\"DBN\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 76,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x11f8abf28>"
      ]
     },
     "execution_count": 76,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX8AAAErCAYAAAA2W4OGAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nCuTkb2ZWICd/M7MC/X8QODddNXWDHQAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "%matplotlib inline\n",
    "combined.corr()[\"sat_score\"][survey_fields].plot.bar()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "There are high correlations between `N_s`, `N_t`, `N_p` and `sat_score`.  Since these columns are correlated with `total_enrollment`, it makes sense that they would be high.  \n",
    "\n",
    "It is more interesting that `rr_s`, the student response rate, or the percentage of students that completed the survey, correlates with `sat_score`.  This might make sense because students who are more likely to fill out surveys may be more likely to also be doing well academically.\n",
    "\n",
    "How students and teachers percieved safety (`saf_t_11` and `saf_s_11`) correlate with `sat_score`.  This make sense, as it's hard to teach or learn in an unsafe environment.\n",
    "\n",
    "The last interesting correlation is the `aca_s_11`, which indicates how the student perceives academic standards, correlates with `sat_score`, but this is not true for `aca_t_11`, how teachers perceive academic standards, or `aca_p_11`, how parents perceive academic standards."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Exploring safety"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 77,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x10c282eb8>"
      ]
     },
     "execution_count": 77,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAY8AAAELCAYAAAAhuwopAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMi4wLCBo\ndHRwOi8vbWF0cGxvdGxpYi5vcmcvFvnyVgAAIABJREFUeJztnXucXXV16L9rnhkSIMMkBJJJCBCg\nDUIijjxEKZqKqJS0glR7K+jVS221BQqCtr1yxXrLQ+lV6dWLlUqqBRJQiV4sItaiXgJMMAkEUII8\nMgmvTIbAhMlkHuv+sfeeOedkv87ZZ5+9zznr+/lMMue3H2edPfv81l7Pn6gqhmEYhlEOLVkLYBiG\nYdQfpjwMwzCMsjHlYRiGYZSNKQ/DMAyjbEx5GIZhGGVjysMwDMMoG1MehmEYRtmY8jAMwzDKxpSH\nYRiGUTZtWQuQFnPmzNHFixdnLYZhGEZdsX79+h2qOjdqv4ZVHosXL6a/vz9rMQzDMOoKEXk2zn7m\ntjIMwzDKxpSHYRiGUTamPAzDMIyyMeVhGIZhlI0pD8MwDKNsTHkYhhHJ4PAoG7e+wuDwaNaiGDmh\nYVN1DcOoDndu2MYVd2yivaWFsclJrj3neM5eviBrsYyMMcvDMIxABodHueKOTewZm+S10XH2jE1y\n+R2bzAIxTHkYhhHMwNAI7S3F00R7SwsDQyMZSWTkBVMehmEE0tvdxdjkZNHY2OQkvd1dGUlk5AVT\nHoZhBNIzq5NrzzmeGe0t7N/Zxoz2Fq4953h6ZnVmLZqRMRYwNwwjlLOXL+DUJXMYGBqht7vLFIcB\nmPIwDCMGPbM6TWkYRZjbyjAMwygbUx6GYRhG2ZjyMAzDMMrGlIdhGIZRNqY8DMMwjLIx5WEYhmGU\njSkPwzAMo2xSUx4islBE/kNEHheRzSJykTt+kIjcIyJPuv93u+MiIl8RkS0isklETig41wXu/k+K\nyAVpyWwYhmHEI03LYxy4VFV/FzgZ+ISILAU+DdyrqkcB97qvAd4NHOX+XAh8DRxlA1wJnAScCFzp\nKRzDMAwjG1JTHqr6vKo+7P7+GvA4sABYCdzs7nYz8Ifu7yuBVeqwDpgtIocC7wLuUdWdqjoE3AOc\nmZbchmEYRjQ1iXmIyGLgjcADwDxVfR4cBQMc7O62ANhacNiAOxY0bhiGYWRE6spDRGYBdwAXq+qr\nYbv6jGnIuN97XSgi/SLS//LLL5cvrGEYhhGLVJWHiLTjKI7vqOp33eEXXXcU7v8vueMDwMKCw3uB\n7SHj+6CqN6pqn6r2zZ07t3ofxDAMwygizWwrAb4JPK6q1xdsWgt4GVMXAHcWjJ/vZl2dDOxy3Vp3\nA2eISLcbKD/DHTOMXDI4PMrGra/YUq1GQ5NmS/ZTgQ8Bj4jIBnfsb4CrgdUi8lHgOeD97ra7gPcA\nW4DXgY8AqOpOEfk88JC731WqujNFuQ2jYu7csI0r7thEe0sLY5OTXHvO8Zy93EJ0RuMhqr7hg7qn\nr69P+/v7sxbDaCIGh0c59ZqfsmdsetnWGe0t/PKKd9haGEbdICLrVbUvaj+rMDeMKjEwNEJ7S/FX\nqr2lhYGhkYwkMsIw92IybCVBw6gSvd1djE1OFo2NTU7S292VkURGEOZeTI5ZHoZRJXpmdXLtOccz\no72F/TvbmNHewrXnHG8uq5wxODzKFXdsYs/YJK+NjrNnbJLL79hkFkiZmOVhGFXk7OULOHXJHAaG\nRujt7jLFkUM89+Iepq1Ez71of6/4mPIwjCrTM6vTJqEcY+7F6mBuK8MwGpKggLi5F6uDWR6GYTQc\nUQFxcy8mxywPwzAypdops3ED4j2zOlm2cLYpjgoxy8MwjMxII2XWAuK1wSwPwzAyIa2UWQuI1wZT\nHoZhZEJaFfkWEK8N5rYyDCMT0rQQLCCePmZ5GIaRCWlbCBYQTxezPAzDyAyzEOoXUx6G0SAMDo/W\n5SRsFfn1iSkPw2gArEusUWss5mEYdY51ia0+ttZHNGZ5GEadU+9FcXlzt5kVFw9THoZR59RzUVze\nJupCK85TxpffsYlTl8zJhWLLE+a2MowcUYm7pF6L4vLobrOlhONjlodh5IQkT+H1mPKaR3dbPVtx\ntcYsD8PIAdV4Cq+3org8TtT1asVlgVkehpED8vgUnjbeRH15ibWV9eetRysuC0x5GEYOyONTeC3I\n60RthYvRpOq2EpGbROQlEXm0YGy5iKwTkQ0i0i8iJ7rjIiJfEZEtIrJJRE4oOOYCEXnS/bkgTZkN\nIwua2V1Sb+42wyFty+NbwA3AqoKxa4HPqeqPROQ97uvTgXcDR7k/JwFfA04SkYOAK4E+QIH1IrJW\nVYdSlt0wakpen8INw49UlYeq3icii0uHgQPc3w8Etru/rwRWqaoC60RktogciqNY7lHVnQAicg9w\nJnBLmrIbRhaYu8SoF7KIeVwM3C0iX8Rxm73FHV8AbC3Yb8AdCxo3DMMwMiKLVN0/By5R1YXAJcA3\n3XHx2VdDxvdBRC504yj9L7/8clWENQzDMPYlC+VxAfBd9/c1wInu7wPAwoL9enFcWkHj+6CqN6pq\nn6r2zZ07t6pCG4ZhGNNkoTy2A7/n/v4O4En397XA+W7W1cnALlV9HrgbOENEukWkGzjDHTMMwzAy\nItWYh4jcghPwniMiAzhZU/8N+LKItAF7gAvd3e8C3gNsAV4HPgKgqjtF5PPAQ+5+V3nBc8MwDCMb\nxEluajz6+vq0v78/azEMw8iIvLV6rxdEZL2q9kXtZxXmhmE0HHlr9d6IWGNEwzAypdqr9uWx1Xsj\nYpaHYRiRpOUCSsNCaMYmk1lgysMwjFDScgGltWpfszaZrDXmtjIMI5A0XUBprdrXzE0ma4lZHoZh\nBJKmCyhNC8GaTKaPWR6GYQSS5gSftoVgrd7TxSwPw6gTsqhbSHu1P7MQ6hdTHoZRB2RZt5D2BG9t\n6OsTUx6GkXPSykoqB5vgjVIs5mEYOSetrCTDSIIpD8PIOVa3YOQRUx6GkXPyULdQ7RYiRv1jMQ/D\nqAOyzEqyJoOGH2Z5GEadkEXdQtZNBs3iyS9meRiGEUiWTQbN4sk3ZnkYhhFIVsH6rC0eIxpTHoZh\nBJJVsN7Sk/OPua0Mwwgli2C9pSfnH7M8DMOIpNbB+rgWjwXUs8MsD8MwEpFWw8Yoi8cC6tliysMw\nmoQ0Jvm0J/Cgnlp56PfV7JjyMIwmIOkk76d4spzAbZ3y7DHlYRgNTtJJPkjxZDmBW0A9eyID5iKy\nn4j8dxH5hvv6KBE5K87JReQmEXlJRB4tGf9LEfm1iGwWkWsLxj8jIlvcbe8qGD/THdsiIp+O//EM\nw0iS9hpWb5HlBJ6Hfl/NThzL41+A9cAp7usBYA3wwxjHfgu4AVjlDYjI24GVwPGqOioiB7vjS4EP\nAMcC84GfiMjR7mH/BLzTfe+HRGStqj4W4/0No+lJMsmHWRfLFs5OdZXBKGwVwmyJozyOVNU/FpEP\nAqjqiIhInJOr6n0isrhk+M+Bq1V11N3nJXd8JXCrO/60iGwBTnS3bVHV3wKIyK3uvqY8DCMGSZaS\njVI8WU/gtkhVdsRRHntFpAtQABE5EkiSVH008DYR+QKwB7hMVR8CFgDrCvYbcMcAtpaMn+R3YhG5\nELgQYNGiRQlENIzGotJJPo7isQm8OYmjPK4E/h1YKCLfAU4FPpzwPbuBk4E3A6tF5AjAz5pR/OMy\n6ndiVb0RuBGgr6/Pdx/DaFYqneTTti7SqhMx0iVUebjuqSeA9+FM9gJcpKo7ErznAPBdVVXgQRGZ\nBOa44wsL9usFtru/B40bhlED0rIurNCvfgnNtnIn+O+r6qCq/l9V/WFCxQHwfeAdAG5AvAPYAawF\nPiAinSJyOHAU8CDwEHCUiBwuIh04QfW1CWUwDCNjrHNufROnt9U6EXlzJScXkVuA+4FjRGRARD4K\n3AQc4abv3gpcoA6bgdU4gfB/Bz6hqhOqOg58ErgbeBxY7e5rGEYdY51z65s4MY+3A38mIs8Cu3Fc\nV6qqx0cdqKofDNj0pwH7fwH4gs/4XcBdMWQ1DKNOsEK/+iaO8nh36lIYhtF0JEkhNrInUnmo6rMi\nsgx4mzv0c1XdmK5YhmE0A1nXiRiVE6c9yUXAd4CD3Z9vi8hfpi2YYTQitv7EvtR6rRCjOsRxW30U\nOElVdwOIyDU4QfCvpimYYTQalpZaPlYDkl/iKA8BJgpeT+Bf0GcYRgDVaF/ebBOpKdt8E7cx4gMi\n8j339R8C30xPJMNIn1pPxEnblzfbRGqLPeWfOAHz60XkZ8BbcSyOj6jqr9IWzDDSIouJOElaajNO\npLbYU/6JEzA/GXhSVb+iql8GtoiIb2NCw8g7WVU1J1l/ohmL6awGJP/EcVt9DTih4PVunzHDqAuy\nfKKtNC21GSdSqwHJP7EC5m6PKwBUdVJEbPlaoy7JeiKOajDoF4tp1onUakDyTRwl8FsR+SscawPg\nL4DfpieSYaRHnifisFhMs06ktlZIfpECo8J/B2eZ2K/gdMJV4F7g4oIVAHNJX1+f9vf3Zy2GkVPy\nlvY6ODzKqdf8lD1j01bRjPYWfnnFO3Ihn9E8iMh6Ve2L2i9OttVLOG3QDcNICcsuMuKQp4eeSOUh\nItcCfw+M4LRKX4ZjeXw7ZdkMIxXSTtWt5AuedSzGyD95q/WJs57HGar6KnAWzmp/RwOfSlUqw0iJ\ntFN179ywjVOv+Sl/+s8PcOo1P2Xthm2xjkuSyms0PnlcOCtOwLzd/f89wC2qutNZndYw6o803UNJ\ni/maNShuRJNHt2Yc5fEDEXkCx231FyIyF9iTrliGkQ5puoeq8QUPyy7Kk7/bqC15dGtGuq1U9dPA\nKUCfqo4BrwMrve0i8s70xDOM6pKmeyjOF7zSluyVusMKsXbw9Use3ZqRqbqRJxB5WFVzV21uqbrx\nacYn2rQ+89oN2/apIfGCmpUGPKuRxpu3YGshzXj/VUotrlXVUnXjvFcVzmFkRJ4nlTSppNI7DkFx\ni7jxEL/3TeoOy3NjxWa9/yolT0WT1VAeyUwXIzPyPKlkyZ0btnH57ZtobREmJpXrzi2e0KIUi98X\nPI4CCJpIk/q78xhsBbv/6p04qbpGg9KM3VqjGBwe5bI1Gxkdn+T1vROMjk9y6ZqNU3GCSmMPUQog\nLBXT83d3tArtrUJHq5Tl785jsBXs/qt34rRk3+cOLRl7ppoCGbUjr5NKlmzevouxiWJjemxC2bx9\nV6Jc+6iAZ9REurp/K3snlLEJZe+EsqZ/a+zPlMdgK9j9V+/EcVvdz77t16fGVPV9QQeKyE04xYUv\nqeobSrZdBlwHzFXVHeIUj3wZp57kdeDDqvqwu+8FwN+5h/69qt4cQ24jgjw3CcyOoBCeJHb/hNVx\n9HZ3sWd8omj/PeMT9HZ30f/0IL/YMli07edbBul/epC+w3tifao81pDY/VffBCoPETkEWAB0icgb\nmf5WHQDsF/P83wJuAFaVnHsh8E7guYLhdwNHuT8n4XTxPUlEDgKuBPpw4ivrRWStqg7FlMEIIY+T\nSpYcO/8A2lpgvOCBuK3FGQcCJ/i4hAU8SzMfvdf3PbnDd//7ntwRW3lEvXdW2P1Xv4S5rd4FfBHo\nBa4HvuT+/DXwN3FOrqr3ATt9Nv0jcDnFwfaVwCp1WAfMFpFDXTnuUdWdrsK4Bzgzzvsb8eiZ1cmy\nhbPti4tzLa4/bzmdbcJ+7a10tgnXn7d86toETfBJGRgaoau9+Fmuq72NgaERTjtqju8xQeP1ht1/\n9Umg5eG6hm4WkXNU9Y5qvaGInA1sU9WNJW1OFgCFjtwBdyxo3DBS4ezlC1h66AFs2PoKyxfOZsm8\n/YHpCf610fGpfb0JPunE19vdxcjYeNHYyNj41NP40fNm8psXd09tO2bezLKsDsOoNnFast8hIu8F\njgVmFIxfVe6bich+wN8CZ/ht9nv7kHG/818IXAiwaNGicsUzDCA8ZTZogq8GzsOUlrx2MrGe21mc\ngfTszpGpTCzDyII42VZfB/4Y+Eucifz9wGEVvt+RwOHARhF5Bscl9rAbXxkAFhbs2wtsDxnfB1W9\nUVX7VLVv7ty5FYrYfFjbimmiMqpKm4JWq0nowNAIM9pai8ZmtLUyMDRiKa1GLomTbfUWVT1eRDap\n6udE5EvAdyt5M1V9BDjYe+0qkD4322ot8EkRuRUnYL5LVZ8XkbuB/yki3e5hZwCfqeT9jX2xCt9i\ngiZkb3xGWytjE9PWhzfBV8NtFZa2mueUVmsv0pzEKRL0Oui+LiLzgXEc6yESEbkFJ633GBEZEJGP\nhux+F87a6FuAb+CslY6q7gQ+Dzzk/lzljhkJyeMaAVkzs6O1qIcUwJ6xSWZ2tIam08YlyMoLq8XI\na50GVKdho1GfxG3JPhunJuNhHKfsN+KcXFU/GLF9ccHvCnwiYL+bgJvivKcRn7y2rciS3Xsn6GwV\nRgsKBTtbhd17J+iemSzbKsrKC0tbzWNKq7UXaW7iKI8ngAk3cL4Upzjw++mKZdSCRq7wjXKlBG3v\n7e5iokQhTKjS292VKNsq7kQbVouRZZ1GGg0bjfomjvL476q6RkTeilPY9yXcAr5UJTNSp1ErfKOe\n8KO2B2U9JVG2A0Mj6GSJ1TKpVZ1o04o9pNWw0ahv4igPz8n7XuDrqnqniPyP9EQyakke3SFJiHrC\nj9o+MDSyTyCwBWfyX7ZwdsXKdmZHa5ErDGB0QpnZ0RpwRHmklfgQdb0a8eHDiEcc5bFNRP4P8PvA\nNW5TROvG20AkcYfkLdMmypUStT1qkq9U2e7eO8GM9pZ9FnTavXci5Kh4pBl7iLpejfbwYcQnjvI4\nD6cdyBdV9RW3Zcin0hXLqAfymOYb5UqJ2h5nkq9E2Qa5csrN1PKbpNOMPcRxTeWxZ5aRPnHWMH9d\nVb+rqk+6r59X1R+nL5qRZ/Ka5huV1hq1vRqTfCVyeQSl8oalxKZZ+d4zq5M3H9ZdNPbmw7pNWRhV\nWUnQaEJqkWlT7aVgC7f79a6CeEkEackVZMnFcUsFBfmTsuXF1/i5Tzv4LS++VnTdjHxQSzeyKQ+j\nIqqVaRN0syd1iYW5UuLUWwQpl7TkClMQceI4aVW+b9j6SuC4KY98UWs3sgW+jYpI6oaBYFdMmi6x\nOOe+c8M2zrrhF3zuB49x1g2/qIlcYf2rksZxkrB84eyyxo1syMKNbMrDqJizly/gl1e8g29/7CR+\necU79nnKCfPTh93saTYCjOpdlZVcYQqgZ1Yn5/X1Fm07r683dhwnCUvm7c/5pxR3qD7/lEVmdeSM\nLJpnmtvKSEQlbpiolNlqPEkHucPCeldBeCwnrlyV+J3DYi2Dw6Os7h8o2n91/wAXrTh66vxppsxe\ntfI4zj95sa8bz8gHWRRsmvIwElFp+mjUk3aS4rMw329Y7yoIX0s8jlxJ/M5BCiBuckKaKbNL5u1v\nSiPHZFGwacqjhuStoC4pYRNl1JOQd7N/6vaNtEoLE1p8s1f6JB1l8fR2dyEtAgXKQ1qk6AktrPlh\nmFzVKNbzUwBpJycYjUGtCzYt5lEjGq11dVSALo4f3pmSxV0rct/U0krWth4YGmF8oniiHZ+YnPL9\nenIVrlFeKFfYWuJx3jup39kvwaAaMY0833+2GFn1qOV68GZ51IBGbF0dx5US5yl9dHz6+HKvid+T\n9Nj4BOPFuoPxSWfcw1Nak7rvKse93V0MjxYX3A2PThfcJbG2gmT2CDt3kqfKPN9/eexSYMTDLI8a\n0IjLiMZ1pQQ9CSW9JkFP0o9uf9V3f298cHiUy9ZsZHR8kj3jk4yOT3Lpmo1TT71Du/dSukKHuuNJ\nra1Ks8+Sktf7L69dCox4mOVRAxqxdfV0zGLT1Fg5rpQk1yTsSXrOrA7fY7zxzdt3MVbS+HBsQtm8\nfRenHX0wv9iyw/f4X2zZwRsXdceytvwKDJNkn/XM6uTODdu4vCA+dN25y2I/oef1/mvk9UCaIb5k\nlkcNiMrTr1f6n9nJqPv0Pjo+Sf+z8VcHTuLHD3uS/p1DDvA9Zno8qG2HM97Z5v+V6GxriTUJBxUY\nRj39h2V5DQ6PcunqDYyOK6+PTTA6rvz16g2xn9B7ZnVy3pvyd//lVaklJc/xpWpiyqMGBOXpV9M8\nTxJ0rOTYLS++xqp1zxWNrbr/Oba8+Frsc0QVGQYRNul4XXELKeyKO//AGb7n9MYXdO/nu31B934F\nwfYW9utopbOtWOGFuWHiTJRBWV6bt7/qG8fZHOCiK2VweJTV69O9/yohzeLGrGgmV5y5rWpA2uZ5\nkqBjpcfG7XmUhvkelebrR2HL9bYWiibjthamlMux8w/w3X7sfMdyUe9fLW5ECM7feaxklh8bn4y1\nkFTYErel7zNNvPXTw6rqs56oG209kEZ2xZViyqMGpGmeJ8mkSXJsnJ5HSZeDDaMozVenXVFRxVIz\nO1p9n+K9CvOeWZ1cf97yIsV03bnLpiq9nQwxxVtgs/B6jY1PUBJOYUKnM73CJsqweyRotcH5B8a7\nf6Kq6o3q0aiuOD/MbeVDtfPO0zTP42bS+H2mJMd2z+ygpSR80CLOuHdMmPkex7zf8uJr3N6/dR9X\nWGGa7+t7JxgdLz727OULuPqP3sBJRxzE1X/0hiKFFOXW8o6/5n3H8ZYlPVzzvuOmjo+6Xs8Mvo4f\nheMbnhvi3x54lg3PDRXt490jHa1CZ1sLHa3T9SdeVXwhhVXxUSQ9HoL/FhD9fQk7Ns34QBb1I43o\nigvCLI8S0so7T8s8jxvE/dSaDQgtKJN88f3LOXv5gtjH+l2PgaERZnYUu1lmdrQVtQkPcuHEyS76\n7PcfKYqpnH/KIq5aeRwQ7YY54x9/xm9e3A3ATx5/ia/951Pcfcnp09fLJ9uq8DMHHR8W1IZoa6zw\nvLf1D3DMvJlTcoGTgLB3QvHsqv5nd079nSZK4iETqrGfZnu7uygxtpgk/gJXYX+LqO9L2LFp1p9k\nWT/SaK64IMzyKCDtYFca1Z9RTzqDw6NcfOsG9k7A6MQkeyfgoludTJ04x1YaAN7x2h5fF86O1/YA\n4UovKhgf5oa597EXpiZoj1+/uJt7H3sBcOo1JiZLJuJJZWj3XoDI48NalyyZtz9vW9JTtP1tS3pY\nMm//yPNGfebSxZ3KXewpTO4wwuSK+r5Efaa06k/yELSuZaV3VqSqPETkJhF5SUQeLRi7TkSeEJFN\nIvI9EZldsO0zIrJFRH4tIu8qGD/THdsiIp9OS968FlNBuAl+9vIF/PCTb+XKP1jKDz/51qInrPuf\nGvQterv/qcGpY4MynsKuR5Ti+Y9fv+z7ObzxsOPDgvEQ7ob58WMv+h7rjUedO+z4gaERWksm7VaR\nonbu654uTlde9/ROBodHE8nlLfZUiLfYUxyStFyJkivs+xJ1rdOKD+T5e9xIpO22+hZwA7CqYOwe\n4DOqOi4i1wCfAa4QkaXAB4BjgfnAT0TkaPeYfwLeCQwAD4nIWlV9rNrC5jXYlSTwvGN4j+85g8YL\niboeYeZ5R6v/k3HheFBB3eIe/3RZbzysueEpRxzEbSVp0QCnHHEQEMO1tHSe7/FnLJ3HzI7Wom68\nAKMTOhV4DitADDtvlFzdMzsStYJPcl8nkSvqWqfVCTav3+NGI1XLQ1XvA3aWjP1YVT1H+TrAq15a\nCdyqqqOq+jSwBTjR/dmiqr9V1b3Are6+VSfrYJefdZE08PzWJXN938sbDwtYxrkeQeb5CYcd5Pu+\nheNBBXXtba2+wfj2tumMqKCit7ZW/wwib7x7Zsc+ZYLCdKB/xdJDOPSA4ir1Qw/oYMXSQ9i9d4L2\nEqXYXhB4fnWkuCeWx6sj46xYegjHzJtZNH7MvJmsWHoIEO7yivN3SPp3DCJsMaio88ZZSKrSWp8w\nsv4eNwtZB8z/K3Cb+/sCHGXiMeCOAWwtGT8pLYGyCnaFBaaj1q8O2+59gVfdXxy0XDJv/1gBy0qv\nxylH9lBaCSHuOIQHS2d2tFISlmBSp9Npg4reLlpxNM8OFscVPLzxgaERZnUWB/pndU4H+geHR3l5\neG/RsS8PO32tZna0+loWnlwHdPl/nbzxuy85nXsfe4EfP/YiZyydN6U4vM90/28Hi467/7eDU7Gp\npK3gk9zXYYtBRZ33TYcdxK0PbkVEUFX6fB4q0liHpFmC1lmSmfIQkb8FxoHveEM+uyn+1pFvtE9E\nLgQuBFi0aJHfLrFI42YOI+zLH2f96t17i594d+8dLzLRnS/wc1PZVt4XOM1FhnpmdfKhEqX1oVMW\nFRXF+TEwNMLWnf4K4IkXXmXJvP1D5T5opn9vK2886nqGVXMf2NUeupDUsfMPpEUoUnwt4ox7rFh6\nSJHS8Ah739OOdqzEoL/DwNAIWqJtdVKrWpgWthhUkFzefV2YQVbLbr61/h43G5lkW4nIBcBZwH/R\n6bSPAWBhwW69wPaQ8X1Q1RtVtU9V++bO9XfXJCWN3PEkgemh3Xt9n9K97KHpL/B0tlU5LTMqJaol\nS1jG1I6SJ38PbzxM7gUBsnvj0X2egqu546TMtpb420pfB1N5FXlULAYcy/YtV9/LB29cx1uuvrfs\neopK7nsLXDc2NVceInImcAVwtqoWVlWtBT4gIp0icjhwFPAg8BBwlIgcLiIdOEH1tbWWG9IraOrt\n7mJkrNh6GBkbLwpMB/mFozJakigmj7CJI2hbmGUBsH2X//btu0Z465I5vtu88ekeU/su6HTs/AN9\n4xLe039Un6egqm1vPCxlNklW1LHzD/RVPIVWSxBPvODfT8wbT9pYsdL73gLXjU2qbisRuQU4HZgj\nIgPAlTjZVZ3APe4Xb52qflxVN4vIauAxHHfWJ1R1wj3PJ4G7gVbgJlXdnKbcfqS9oI5zLbTk9TRB\nJnhURkuSjCkIz+QK2xbVEmNbwIS6bWgk0P3TXeCSCmtP8qX3LytqFX/ducU9pMJcdV4FeqHsXgX6\n7r0jtLZIUdyjtUVircseh0prMXYEKAFvPI5LLIgk931a2VRGPkg72+qDqnqoqraraq+qflNVl6jq\nQlVd7v58vGD/L6jqkap6jKr+qGD8LlU92t32hTRlDiJNEzzJE2tURkuSdvBhmVxRWV7bd/mnAnvj\nO3f7u6Z27t47Vb1eiFe9Xig4Q7jTAAATM0lEQVRXUHsSBVQnnf6FWjxrxokh+eH1mApTiHEsuSBL\nbfP2Xb7ux83bd/nKU0iUpfbqyJjv9sLxMAsyyX2fRjZVvdMoy+5mnW1VN6Rpgic991Urj+P3jpob\nmMXjF3u4aMXRU4sMBVkPYU/pQXhP4a+O+CsHb/ywgFqOw3r2i7weYa1PAC5dvcF90nb2+evVG6ae\nlL0J/rI1G6cygAoneE/ZFgb6PWXrFAkWlZfQKuzTFyvIkguv1wlfZySMsIw6gAO62n2P88aTLq0b\nhQWup2mkZXetPUlMqpE7HvTEkfTcn/3+I3x01Xpu6x/go6vW89k7H5naFpaJE2U9RHV6TdKp9ZQj\n5/jWcpxy5JzI6xHWvTbO2hdeD6nR8Un2TmjRIlaDw6Pc8uDWouNveXDrVKqu3/uWfma/2peoa+21\ngi+ksBV8FFetPI6fXHIaXzz3eH5yyWlT/aOizp10aV0jPnlom1JNzPIogyS541FPHJWeO6h/0Pkn\nL2bJvP1DM3GiUjzDfNZBCxFt37WHJfP2Z3iPf8GcN94zq5P/9cfLuXT1BhABVb503vJYdQlh3Wtn\ntPsrL89FE3W9wqrED+zqCIyHRBHVzLFnVnAr+LgEpdOGnXvj1ldiLa1rNRPJabS1Pkx5lEklJnjc\noGMl545alCksABwnxTOohUhUaunWIf8JvnBcgZaWFlpbZJ9mhVBZkkBQrMVz0URdr7Aq8aDMpzgu\nnDiWWvC1Tk6QAojrljLXU3IaLfvM3FY1IM1ge5w+UH7EWbIVgluIRKW0RhEV9Pb28XPzhbXyiFpm\nNio7LaxKfDpF2H8Z2jC546ypceeGbbz3q7/gs2s3896v/mKflNikgVY/d1pY2rNRXRrNBWiWRw1I\n84mjva3Vd9nUwj5Q5aZLenKFWUzeZBhUbf27h/o/pXvjUSZ8mJtvcHiUh54tXkzpoWeHGBweDbW0\nYLq3VWnbFC8NOEophi1DC8HuybBmjt5numzNxiKX2aVrNk5Zp3du2MblJW6nagVag9KejerTSC5A\nszxqQJpPHL3dXbS1Fv8Z21pbihRTULpklFxhWU1Tk2EBhZOh18OqFG88TKFGBRbDLLkwS8s7trTj\nb0frdFv1MGuscBlar9gubpPKqMr2sFhL0iK/MOJYgGnTKKmrcfGzAOsRszzKJKjtdRRxnjgqOben\nAAqDoeUopjC5wrKavMmwMPgct37Ek3vRQV1FCyQddlDXVBDXj8JivKCK/Ci5ouI8YconSZNKILCZ\noyNbcKpukiK/KLIO4jZS6mqzYZZHGSRtTxL2xJHk3EVuB59JqNJzh2U1DQ6PcstD/imtML3YVCne\neP/Tg74r6/U/PRgruBzUJiRKrqg4T5g1FqfAMGh7VNwrLJ02TpFfpWQZxG201NVmw5RHTNK80ZOc\nO8rtEHXuMMUSFlwOc7MAka3R73tyh+/2+57cERlcDqvIj5Krt7vLdxnaUjef38qMUdX6Ya6pqP5l\nPbM6+ZMTizsF/MlJThfiqCK/JGQZxLXGifWNua1ikqZ5H1UDkESuKFdKWApxd0B78+6ZHYEpsZ7l\nc1jPTN+t3viyXv+A+rLeAyO714a1od8V+DQ+rYyiekgFuVKiqvXD1hkB0JJQvRbIFHasZ5WUJkXE\nLSCMIqsgbqOlrjYbZnnEJM0bPUm1dpqulPuf8rcO7n9qR2RFtLcYVCGFi0G1lx7svb87riVHF74O\na0M/Nu5fsOeNR63nHWapRV2vsKLLzdt3+Vo8nkUU1f04yCqpFmkGcdPqrGBkiymPmKTZniRODUCl\nciXx4Yetq+FVLRfWB1xfUCHeM6uTD51cPOEVLgYVHiAOn2jDCv3WPb3Td5s3HuU+CrMCo65XeDA+\nvHdVVPbZvz1YXBX/bw88t899lFXWUtj7RsXbrHFi/WJuqzJIqz1JVA1AUrmCtkfVgER1a41aGjUs\nu2i/dv/nlv3aW3jhVX+XmBcgDovFjE1M+m47Ys60Gy2s/X2YFRh1vcLWKDl2/oG+9SWepRbWkPG+\n37wcmW2VVdZSVD1O0s4KlWY3GuljyqNM0mhPUkkhX7lyBW0Pa4kR1a017LxRsZhHA3pjPbr9VY6Y\nO8t32wFdHbHlKuXNi6eX3p3R1srYxLT14QXbe2Z1RhY/hivqcOuirbV4LZC21pKYR0A8JaoVTDXW\nmqlkko5636RxwjgK0ZRLdpjyqAFxvkRZBS2jvqBXrTyO809eXHa/pSgXT2dAzKOzrSVWgDhIrqgK\n8zgxoigrMEhhhskdpbTC7hFvdcRCxVO4OmItJmk/ot43SZwwjkK0GpFssZhHDSin+VwtK0/jpggv\nmbc/5/YtLKtRX1QsJmyt8ah4Sphcvd1djJe4rsYnpq913BhRJb2ePLk7WqGztYWOVqbkTpLY0DPL\nWR2xsKfWl94/3XG3t7uLPSWJAnvGJ8qepMtNE4/6TEnihFHJCVYjkj1medSAariloqjEfE+7ujjM\nmop6mk5iifllYpXKFda9NkmvJwVEvE7B05Nf1D0QFvOIJXOFS9gmuQfi3NeV/h3jLAjWSO3N6xFT\nHjUiTbdUpeZ7LfLsg1w83tP0p27fNNWSvXCt8bBjPfwU5v1PDfoqj/ufGuSsZfOBeEHe0QLfU6m7\nJEhRRx0bmWCQYMXHrvY2Xhuddol56cdR91lU9lkUce7rSuKEUYrJakSyx5RHDankSxRFkmBpLSyi\nMNLIXtsR4LbwxuMEef2I0+03ztNwJQkGEF7MmXQiDcs+i0PS+zpIGYfdH1nfu4Ypj7onqfmedYvo\namevRaUXR62eGJaqG6V4kkzicYo5g/7GSSbSqEB+HJJkPEVZzWH3R9b3brNjyqNOCPqCJnU7QP2t\nEhc2mS5bODs0jTeqq+7uvRO0Fidb0SrO+O696U3iUcdGKaW0YgtRJMl4qkaKcb3du42EKY86IOoL\nmtTtUG9ETXhh6cVRqbwzO1p929DP7Gile2ZHapN42LFxlVIasYUw4k7+QQ8+FvSub0x55Jw4Pvqk\nbod6I86Et2Te/r6pxVGLRYUplyXz0pvEo45N00VT6bnjTP5RnRUs6F2/pKo8ROQm4CzgJVV9gzt2\nEHAbsBh4BjhPVYfEeVz+MvAe4HXgw6r6sHvMBcDfuaf9e1W9OU2580SahVj1TKUTXpwsHj+88Sz9\n7Gm6aCo5d9S9V4vOCkZ2pG15fAu4AVhVMPZp4F5VvVpEPu2+vgJ4N3CU+3MS8DXgJFfZXAn04fhm\n1ovIWlUtXsS6QYlbiNWMX8BKJ9OkWTzmZ3eIulZ57qxgJCdV5aGq94nI4pLhlcDp7u83Az/DUR4r\ngVXqVDetE5HZInKou+89qroTQETuAc4EbklT9ryQZiFWM2NZPNUh7FqV01nBrnH9kUXMY56qPg+g\nqs+LyMHu+AKgcP3QAXcsaLxpSKsQywjGrmd8wgpBm9UqbgbyFDD3SxHSkPF9TyByIXAhwKJFi/x2\nqVtsMjPqkaRWnHXNzS9ZKI8XReRQ1+o4FHjJHR8AFhbs1wtsd8dPLxn/md+JVfVG4EaAvr6+eM19\nDKPK2IRXTKUPPtY1N99k0VV3LXCB+/sFwJ0F4+eLw8nALte9dTdwhoh0i0g3cIY7Zhi5I2rlvCiy\nWg0wb1jX3PyTdqruLThWwxwRGcDJmroaWC0iHwWeA97v7n4XTpruFpxU3Y8AqOpOEfk88JC731Ve\n8NyofxrpKT1O0VzY57Un7WmsgDD/pJ1t9cGATSt89lXgEwHnuQm4qYqiGTmg0SbLqAmvGku2NgvN\nWr9UT9hiUEYmNKJbImzCi/q8UYsfVYMkLrFau9O8TK1KFpIyakOesq2MJqIR3RJhqakbt76SaaeA\nOzds4/KStVPiWnlZWYhWb5NvTHkYmdCobomgCS/LTgGDw6NctmZj0aqNl67ZWNYCV2m608LiQJai\nnl9MeRiZ0MgFZH4TXpadAjZv31WkOADGJpTN23dx2tEHJ17gKgmNFvdqJkx5GJnRbG6J7DoFBLXo\nl1QXuIrCkgTqGwuYG5nSM6uTZQtnN81kkcXnPXb+AbSVfNPbWpzxqEB9moHrWiQJGOlhlodhNDg9\nszq5/rzlfOr2jbRKCxM6yXXnLkt9lcIoGjXu1SyY8jCMJiBslcLz3tTLqnXTy/ae19dbk8B1I8e9\nmgFTHobRJPgpgMHhUVavHygaW90/wEUrjq7JJN5sca9GwpSHYTQxeai3sXTc+sQC5oZRJ6RR5W1x\nB6NSzPIwjDogrXoIizsYlWLKwzByTtr1EBZ3MCrBlIdh5JxaxCUs7mCUi8U8DCPnWFzCyCOmPAwj\n51h7ciOPmNvKMOoAi0sYecOUh2HUCRaXMPKEua0MwzCMsjHlYRiGYZSNKQ/DMAyjbEx5GIZhGGVj\nysMwDMMoG1HV6L3qEBF5GXg2pdPPAXakdO4kmFzlYXKVh8lVHvUq12GqOjfqJA2rPNJERPpVtS9r\nOUoxucrD5CoPk6s8Gl0uc1sZhmEYZWPKwzAMwygbUx6VcWPWAgRgcpWHyVUeJld5NLRcFvMwDMMw\nysYsD8MwDKNsTHmEICLPiMgjIrJBRPp9touIfEVEtojIJhE5ISdynS4iu9ztG0TkszWSa7aI3C4i\nT4jI4yJySsn2rK5XlFw1v14ickzB+20QkVdF5OKSfWp+vWLKlcX1ukRENovIoyJyi4jMKNneKSK3\nudfqARFZnLZMMeX6sIi8XHCtPlYjuS5yZdpc+vdztye/t1TVfgJ+gGeAOSHb3wP8CBDgZOCBnMh1\nOvDDDK7XzcDH3N87gNk5uV5RcmVyvQrevxV4ASe/PvPrFUOuml4vYAHwNNDlvl4NfLhkn78Avu7+\n/gHgtpzI9WHghhr/3d4APArsh9M5/SfAUdW+t8zySMZKYJU6rANmi8ihWQuVBSJyAHAa8E0AVd2r\nqq+U7Fbz6xVTrqxZATylqqVFrVnfX0FyZUEb0CUibTiT4vaS7StxHhIAbgdWiIjkQK4s+F1gnaq+\nrqrjwH8Cf1SyT+J7y5RHOAr8WETWi8iFPtsXAFsLXg+4Y1nLBXCKiGwUkR+JyLE1kOkI4GXgX0Tk\nVyLyzyIys2SfLK5XHLmg9terkA8At/iMZ3V/eQTJBTW8Xqq6Dfgi8BzwPLBLVX9cstvUtXInzF1A\nTw7kAjjHdQ3dLiIL05TJ5VHgNBHpEZH9cKyM0vdNfG+Z8gjnVFU9AXg38AkROa1ku9+TTS3S16Lk\nehjH1bAM+Crw/RrI1AacAHxNVd8I7AY+XbJPFtcrjlxZXC8ARKQDOBtY47fZZ6wm6ZERctX0eolI\nN86T8uHAfGCmiPxp6W4+h6Z6rWLK9QNgsaoej+M+upmUUdXHgWuAe4B/BzYC4yW7Jb5epjxCUNXt\n7v8vAd8DTizZZYBijd5LDczWKLlU9VVVHXZ/vwtoF5E5KYs1AAyo6gPu69txJu3SfWp9vSLlyuh6\nebwbeFhVX/TZlsn95RIoVwbX6/eBp1X1ZVUdA74LvKVkn6lr5bqQDgR2pihTLLlUdVBVR92X3wDe\nlLJM3vt+U1VPUNXTcK7DkyW7JL63THkEICIzRWR/73fgDBxzsJC1wPlu5sLJOGbr81nLJSKHeP5e\nETkR5+88mKZcqvoCsFVEjnGHVgCPlexW8+sVR64srlcBHyTYNVTz6xVHrgyu13PAySKyn/u+K4DH\nS/ZZC1zg/n4u8FN1I8NZylUSRzi7dHtaiMjB7v+LgPex798y+b1VyyyAevrB8ZVvdH82A3/rjn8c\n+Lj7uwD/BDwFPAL05USuT7rbNgLrgLfU6JotB/qBTTiujO6sr1dMubK6XvvhTLoHFozl4XpFyVXz\n6wV8DngC50HpX4FO4CrgbHf7DBwX2xbgQeCIGl2rKLn+oeBa/QfwOzWS6+c4D0kbgRVp3FtWYW4Y\nhmGUjbmtDMMwjLIx5WEYhmGUjSkPwzAMo2xMeRiGYRhlY8rDMAzDKBtTHoZhGEbZmPIwjCohIr/j\ntt3+lYgcmfBcn3TbZWth9bb7HveLyKiIXJZcasOoDFMehlE9/hC4U1XfqKpPJTzXL3HaX5R2tN0J\n/BVOQz7DyIy2rAUwjDzjtoBZjdP7pxX4PHAM8AdAF/D/gD/D6QV1MTAhIqep6tvjnEtVb/N7X1X9\nlXtM6fhLwEsi8t5qfD7DqBRTHoYRzpnAdlV9L4CIHAjco6pXua//FThLVX8gIl8HhlU1yCrwO5dh\n1CXmtjKMcB4Bfl9ErhGRt6nqLuDt4ix1+gjwDiDuehZ+5zKMusSUh2GEoKq/wWmj/QjwD+Ks1/2/\ngXNV9TicNtszQk4RdS7DqEvMbWUYIYjIfGCnqn5bRIZx1qQG2CEis3Daf9+e8FyGUXeY8jCMcI4D\nrhORSWAM+HOcrKpHgGeAhxKeyxcR+SvgcuAQYJOI3KWqHxORQ3Dayx8ATIrIxcBSVX217E9mGAmw\nluyGYRhG2VjMwzAMwygbc1sZRpURkR7gXp9NK1R1sGTf7wGHl+x3harenZZ8hlENzG1lGIZhlI25\nrQzDMIyyMeVhGIZhlI0pD8MwDKNsTHkYhmEYZWPKwzAMwyib/w8r/PcB0lu+gwAAAABJRU5ErkJg\ngg==\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "combined.plot.scatter(\"saf_s_11\", \"sat_score\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "There appears to be a correlation between SAT scores and safety, although it isn't thatstrong.  It looks like there are a few schools with extremely high SAT scores and high safety scores.  There are a few schools with low safety scores and low SAT scores.  No school with a safety score lower than `6.5` has an average SAT score higher than 1500 or so."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Plotting safety"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 78,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/srinify/anaconda/envs/dq/lib/python3.6/site-packages/mpl_toolkits/basemap/__init__.py:1698: MatplotlibDeprecationWarning: The axesPatch function was deprecated in version 2.1. Use Axes.patch instead.\n",
      "  limb = ax.axesPatch\n",
      "/Users/srinify/anaconda/envs/dq/lib/python3.6/site-packages/mpl_toolkits/basemap/__init__.py:3222: MatplotlibDeprecationWarning: The ishold function was deprecated in version 2.0.\n",
      "  b = ax.ishold()\n",
      "/Users/srinify/anaconda/envs/dq/lib/python3.6/site-packages/mpl_toolkits/basemap/__init__.py:3231: MatplotlibDeprecationWarning: axes.hold is deprecated.\n",
      "    See the API Changes document (http://matplotlib.org/api/api_changes.html)\n",
      "    for more details.\n",
      "  ax.hold(b)\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAO8AAADuCAYAAADRLFAcAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMi4wLCBo\ndHRwOi8vbWF0cGxvdGxpYi5vcmcvFvnyVgAAIABJREFUeJztvdeTHEee5/nxEBkpSmstoAgQilo3\nye5mT0/3TvfIHS12b/ce1uz+g3u+tzO7x7N7uD07s7setXszO6J7W5BNBRIgSIIECIIACZTWOitV\nZES430NWFSpRmVVZlbKq4mNGAysjwt0LyG+4+89/Qiil8PHxOXxo1R6Aj4/PwfDF6+NzSPHF6+Nz\nSPHF6+NzSPHF6+NzSPHF6+NzSPHF6+NzSPHF6+NzSPHF6+NzSDH2c7MQwnfH8vGpAEopsdc9+xIv\nwP/yk7sHG42PzyEnMXGFUN9LCLGnrorif/7Txwq6z182+/gUiNADKC9d7WFs4YvXx6dAhBFCuclq\nD2MLX7w+PgWimb54fXwOJcIIId1UtYexhS9eH58C0YwgyvFnXh+fQ4ezPoUWqKv2MLbwxevjUwD2\nwm2EZmA2DlR7KFv44vXx2YPUwm0QGlbbuWoPJQtfvD4+u5Ca/wJRg8IFX7w+PnlJzd9CaEZNChcO\n4B7p43McSM3fQugBrNbCXBWrgT/z+vg8Qmr+Zs0LF3zx+vhkkZq7idCDNS9c8MXr47NFau5zhBHE\naj1T7aEUhC9eHx82hRs6NMIF32DlU6O4yiaq5tExaRCdZY2hTc19jjDDWC2ny9ZHOfDF61NTKKX4\n2nuPCXkDgQYodAJcMH5AqzZY8v5Ss5+hBSJoVgOrn/1nGi78CZoRKnk/5cAXr0+J8TDqb2M0fI4Q\nabxUP87qsyi3uaCn73sfMCFvIHG3tejwmfuPPGf8KfVae8lGmpq9gTDDuPF5tHQcs/nkoREu+OL1\nKSkewe6/R7PmEFpGfMJcw6j7itTM7yPt3t2fVg7j8pMs4W4i8RjxrnJJ+1FJRpqc/RSZXIHkMqHe\n51HShdXRkrRdKXyDlU/JMOpvZwkXQAiF0Bysjp8Cu+cvjKtlIN/eVrGqpkoyzsTkh6RmbmA09BMZ\n/i5aoA574Uus9sdL0n6l8Gden5JhNHyeJdztCD2JCCyi0vmXvaYIopB5r+sEih5jcvo6XmKBpkt/\ngdAftqekk/XzYcAXr0/JEGKX5GxKIIS969wbEo2EaCLO4o5rGgZ92uWix2h1XCDU82zWZ876FEZ9\nT9Ft50M6SYQRLLnF3BevT8nwUv0Ic42c6b2FRO4y625y0fgB192/ReJuzcIaBnWijT69ePHmMkil\nl+8THnil6LZzoTyH2IOfY4RaH44h2ITZOIhuNRTVti9en5LhrD6LUfcVCCfrcyUNnOglUNaebdRr\nHbxo/hVj3icsyVF0YdKrXaRXO48mSv91VUqCACHKY/6xF+8QGXgVPdSy0Z9CplZxVkew7ejWfXqk\nA7OhH80MF9y2L16fkqHcZlIzv4/V8VOEngQlQEic6CWc5dcKbickGjhrfLs0Y5IuQsv/NU8vf11W\n5wwvtUKw89LWz0II9FAzeujh0ZlSEi+xiL3w5b6yU/ri9Skp0u4lOfEfEYFFhLAzS+UCZtxyEbv/\nc6y2cwSaT+S87sZmyxaEIJ0kmhHc8z4hNIxIB0akY1/t++L1KQMClW7f42CoMujBJtzYNHowe7YD\nkK5dVguzvfAFVvuFsrXvn/P6HHlCfS+RnLm+o1SJvXgbq/182fqVTgItEClb+/7M65OXgJnkRN8t\nutpGcRyL+5OXmF0cIr8jRW0ihEZ44FXiY+8QGX5j68hG2utFW3zz4aVWy9b2Jr54fXJSH1nijef/\nBl13MfSM40VX2xgzi0N88NmPOGwC1owgwc7LJKc/Itz7PJ4dRbPqy9afvfAloZ5nytY++Mtmnzy8\ndPlfMY3UlnABTMOhu22Uwe6vqjiyg2NEOtCDTdhL97AXviBYxv1oJTy2fPH67KAuvEJ9ZAUtx7fD\nNBxOD35a+UGVCKv1MbzkIjIdK5u43MQCeritLG1vx182++zACiSQUgM99/VgIFHZAZWYUO+LKKd8\nv4NuNWEv3ilb+5v4M6/PDtbjLeial/OalILltc4Kj6i0CCHKagUWuommB5Hp9bL1Ab54fXKQdkKM\nzZzF9XYuzKTSuTPyfM7nND2ObkTZK/TvOBDsfpLkzI2y9uEvm31y8vGXb2AaaXraH+BJPWNbFopr\nt77PSjR75jWDszR1/wLTWkYhUJ7F2tyrJKOHKz62lAjNRDMys68WKI9V2xevT06kNLjy2Y+JhNZo\nbZrGdQPMLg0iZfZXxggs0Tb4d2h6JhhBAGguTT2/BDjWAg52P0li8kMiA6+WpX1fvD67Ek82Ek82\n5r1e3/5BzgB8TXNp7HyXZPQcuuZxduAefa3TxO0wt0bOsxbP3+ZhwY0vINPref2mhfZw75tv9s0E\nJSzhxmfwEkuE+l4suH9fvD5FEawbyx2/CwjdprVpkj97/V8wDQfLdHA9jRfPfcQ7N1/ho7vldWIo\nN258FuWliY++Rajn+ZxGsM3ZN9z/Cl5qBTc2i0ytbLtDoIfbNuJ7m/Di8wX374vXpyiUynOeBAgk\nv//SLwhbSTQtI3BDzwTYv3bpChMLvcwsd1dknGVBSazWMwgjRHLqI4RhEex6Mis2WGgmRqSL5OSH\n6MFmzLoetLbH82TV0HBWHxTcvW9t9imKxOpZlMz9NWo06mkIx7eEux1d83j2scPr7AGgpAdCR2gG\n4f6XMJuGiI+8iRPNTpRntZ4h3P8yVvvj6KHmvOlwtEAdMh0ruH9fvD5FEVt6HumFsgSsVMbgJRIX\nkSrPF1VTtNRnlo8Kj7h+jwXrZywEfkFSn0AdhuMmlRHvJkaolboT30Paq8TH3kG6qX01t98cV/6y\n2acopBdm/sFfUt92jVDjHYTwsOMDRBdewrEEmnY153OeFMyvtuORYib017jaOko4oCBufkXQ66cz\n9dsbVRNqE6UkIocPqdV+HtO1SU5fQ7easDoulqVciy9en6KRXpi1uW+zNpedumbRhsW1Vjqb59Ef\nWTpLqXP97lMsWW/iaKsgNlK+ClA4pPRxouYNGp2nix6fUrI8Oapk9sy7Hc2wiAy8ihubJT7yK4Kd\nl/edKWMvave15lNRPFI4rJd8ufpf3vsdVmON2I6JlIK0a+C4Bj+9/gZza03Eja8fCncbSrhEzdx7\nYqUU0rUL6t9qf5zk5IdF/Q75UXu+FIy6LiLDb+CuT5EYf29HQoBi8GfeY44tlpk2fklSTAMaGiYd\n7su0yNxpVpubv6G//wrh8BKeZzI/f57JyZfxvNx5qmLJOv6Pf/0fGO4ao7tljqQd5KuJMyTTIaSI\nIhB5XxeeyB084KyN46yNEhncO6mdHmzGiHRgL36F1XZ2z/vLgRCCYNeTSCdB7MEvqTv1g/yi38cK\nwRfvMcZhnQfmT5DYG65REg+XWeNtpOfQ5mWfw3Z0fM7Q0NvoGzG+hpGmq+smTU1j3Lr150hp5ulJ\nMDI7xMjsUNanugqzW1C/IZtyfu5Gx/e1DA60nCYx+SFuYhGjAqF6+dDMMMGOizhrYwSahnPeowdz\n/8452yvVwHwOH0v6J0icHfpRwmVB/yCr4JemOQwNvbMl3Iefe1hWlLa2L/fdv8Cg3rmEUDvnEKEM\nmpwXcj6nULBPA1Co9wVSs5+WdNl6EIyGfpzoRN7rvnh9CmJdu59zv5lBkBILWz/V10+h8hz76LpL\ne/v+xQvQkv4WIXc4I2Clb/3ZkH6GOndnStZMbqiMa6VShe/PhRCZPFbj7+7ruVIjhACVf+x6pPBw\nS3/ZfIzZ/RhGZV3P5wL58Hr+AmG7j0Gn0/4x6fQyKWMMlE7YO4mhcsfbppfuYnVexll5gEytbFUi\nKATNCBLsuEhq5uMd9YoqiVHXhRefw6jr2nFtP9sBf+Y9xjTK84g87o0Ck6B6eLQRjfbmFajnGSwu\nFpe4PKBaaHCepMG9lFe4ANKz0YwgRn03zvr0vvsxIp1oZpj06kgxwy2KQPNJ0ivf5Ly2n2W9L95j\nTIv3BKaqR6htXwOV2W/2ur+B2LYZljLA1NTzeI8E6EspcN0gCwsXyz5e5TlbpUs0qwlprx6oHav9\nPE50Am9braBKIjQdJXO/CBP7ONbyxXuM0QlwwvkzWryn0FUIoUwiqp8h5w+olyd33D819Tyjo98m\nnY4gpYaUGsvLp7l168/zHhWVkvTKNwSaM3WFivVYCve/QnLyw4x/chXQg414WdFF4ESn9pW4zt/z\nHnN0gnR5r9HlFVIITDA/f4n5+Yvouo2UZt6oIukmQSmEHti10Nd+cBMLWG3nStKWEBrh/pdJTLxf\n0HlxqQm0niU1d4Nwb8airpTEXvySuhPfK7gNX7w+B0DgefkLaHl2NBMCF25HeTaogxmzQGTEv/Ef\nj1hotWAziYkrOR7T0IwgQrcQhpX5M+v/AxtJ6OoINA2Tmr9JsOPSznbKiGZYKPfh/jY1/fG+k7T7\n4vUpKUpJklNXiZz4XtH+xEpJlJfe+s9sGsq6HsxTZ0hJN/OMa6O8FNJNI50VlGej3BTKc9ieJE+m\nY1Bh8QJoZgjpJLaMVHqweY8nsvHF61NSkpMfEOp9oSSBAEJoCCMIBZTJzHpOMzJL9X0Uqq4GVts5\n7MU7eKkVIkPf2ffzvnh9tmhpGufU4DXqwsuk0nWMTDzNzPxjFFqXyF66hxHpKnuBraOCFqgjvXSP\n8OCrB3rZ+eL1AWCw91MeO/neVm2iYDDGxbM/p7V5nC/u/gYAXnI5r1OEl1rDSywQ7n+5YmMulsyy\n3Mksp7eW5w//P9A0VLa0rZvUn/0dNCN0oGd98fpgmgnOnnwXXc8+NjF0l57OO0xMX2JhIkVy+hqN\nj//RjueV9EhOXyMy/EZZxifd1Mb+NbfIDu6vLBC6+dCIpQcQuoVm1iH0AMnp6wdazu6HgwoXfPH6\nAJ1t91FKA3aeeWrCo6fzC6ZvCsz6vpzPJyavEOp9sTwB70Ds3j8TaDv7UGRGEM1q3CY4syx9G5Eu\nnPVpzPqekrddCnwnDR8M3cnr+qhpCs2ZJtjzDEIP7MjLZC9+hVnfC0qSGH+vPOOr7yHYcRGr9QyB\npiHM+h6McCu6VY9mWGV7aQTazpGuQMGwg+KL14fl1V5UHqOU45rMTTejW40YkU68+NzWNS+5gpda\nxqjvIzl1FbPpBMmZTyo17LIjhMBsPkl6+etqDyUnvniPJIpI/QN6Bv+ZvhP/labWG2ha/n1hNNbJ\narQbz8v2lpJSkE7CkvN9IBOu5m6IN7PP/Yhgz3Mkxt4mPPg6ZkMvmhEivXK/fL9ahQk0DeGsjVc1\njDAfvniPHJLe4X+gZ+hfaGi+R13DKB0973Li3H/GMPM74n9y83eZWzyFJ3UcN4Dn6SwttvD+ld9A\nkSlCrRnWhoMDJCbeJ9z/Msnx9wj1vYBmZHybrfbHcePzuInFgkfsJZdze0rVCFbHReyFW9Uexg58\ng9URo7H1FpG6CbRtGS803QXh0T3wMybu77QWA3jS5LMvfwvTSBIKRkklTVbuf05kaGfeJ3vxDmbj\nAPbiHQKtj20Fx28S6n2B+MivCA+8sqc11VmfJr38NWZDP/bSXazW4kILy4ER6cBeuI2SHkLLXyGi\n0vgz7xGjpf3TLOFuommKUGQG3Yjv+rzjhjLL6JHbhHp31uFVbgovtYpybTSrIaclVghBZPB1EmPv\nonbxa06vPMCNThAZfI1A84lMHZ8cFetzGcoqTbD7aVKztbWf98V7xNCNZN5rSum7Xt/Ejc+jBerR\ncrgXBrufwmjoQ6Zju86SQjcJ9b2Y1wJtL9xGpmNZL4hw30s507RqViOySrG3m+hWA8q1C045Wwl8\n8R4x7GT7o8E3WwghcdK7uy4qpUjNfY7VmTv1K2g4Kw8KioDRrQYCzSdIzWZXiE/OfAKaSbAzOxhA\n6CaBltPYC7d3tCPttT37KzfBnmdIzVyv9jC28MV7xFicfQGVIxuj9AxWly6iZGDX5+2N8Lhcwe7S\ntUlOXSU88K2Cx2M29INmkF4dQSlFYuJ9jEgHVuuZ3Pc3DuAll7MKbmlWQ9WyXmxHM0KgmXj2erWH\nAvjiPXIk4/3MTnwH6Rl4XgDPM5FSZ33tFPNTuwedSyeJtKMYdTszGColSYy9TWTo2/t2igh2XMRd\nnyL+4BcEWs9mBL0Lob6XSEx+uHU8I4wQqsp73k1CNbT39a3NR5DoykXW1x4jUj+Gpjkk47046b0r\n0SenruYNLEiMvUOo78VMUPwBCPW9jPLSW0dKuyE0Hav9fGYV0Hm5LEW6DorQDHSrCTexsPfNZcaf\neY8oSgaIrZ0muvJ4QcJ11sYx6rpyijM5/dHGkdDBQ/2EEAUJdxOzvgfpxPFqYK/7KFbnJey5m9Ue\nhi9en438Scv3cuaHshfvoFlNVXHOD/W+QHLqWs15NwmhYTT0Z1L8VBFfvDVOeuVB2ftIzXxMqHtn\nKU0nOol0EnmNS+VGCI1g5xM7rNW1gNV6hlBv7nIslcIXbw2jpEdy5uOy9uHZUZT0duRP8lKrpFfu\n5xR1JTEiHSCdHWlSa4Fc5+AV7b+qvfvsipdYKHthrNT0dUI9z2V9Jl2b5PRHG0dCCiuQxDSqV6Ar\n2PMsTnQSJZ2qjaEW8a3NNYyzPoWxj8JT+8Ve/hqz+USWv+72I6Hhnvu8dPEd6oLrIGBuuZv3PnuD\n5fXKlskUQqPp4l/krUJ/XPFn3hpGOYmyLc2UdHCjEzvqxG4eCZ3sH+GNZ35KY2QNXZfomqS7dYrf\nfe2vaYhUfgmrBSJlC7o/rPh/G8eU5NRHhHqyAw+S0x8RaDuLbtXzyqVfYxrZAQ5CZLJuPPPY1UoO\n1ScP/rK5limTc4KbWEQYIbTAw2p8W0dCdd3Uh1cJmLmPQTRNMdBVfgt4baIIR2apbxhFKY3o6klS\nqcpuIbbji7dGkel1NDOSM0SuGJRSpGZvZGV6zBwJJQl1P7Vxj7bre0Op47dgE8Jl+NQ/EqmbQtM8\nlIKu7qusrJxhYvQ3KTS3dSnxxVujOOvTGPW9Jc+fZC98gdVxYcvl0EutkF65n1VsK5asJ5aoo6l+\nZwlNz9P4ZrL2Aua309www9kTH9DcOIPnmYxNXeDr8WfxvIO5dgJ0975PXd3UVqx05q/Ppan5Hol4\nF0sLT5Zm8Pvg+L1CDwleYnFf5R4LQbopvOQKZl33xs82yenrOaKEBO989j0c18gKL/SkwHaCfHpv\nZ5B+rdDZ+oCXn/47OlpHCZg2oWCMU0PXee3Zn6BrBz1qkrS238yZ5EDXXTq7qhMm6Iu3ZlElt64m\np65lBb8nJ68QGXw9Zz/TiwP80/t/yNRCP56nk3ZM7o2f5+9//Rck7Yd75UgwxqXhW1w+cZPGSLX9\nkBVPPv5zDN3NWvYbukc4uMZAz8HyUOm6nTc1LoAZiOW9Vk78ZfMhp6v9a84Of0hdZIW0E2Rk4gm+\nGX9mR93czcLNm8EBSnoIPbhrlND8Sjf/fOUP81xVvHbpPZ597FOkFCBAE4rbo+f42fXfoBp7wKb6\nOXQ99+xqGC5DvV8wMvnUvtv1ZCBvUnoAx4nk/Lzc+DNvDaKkU5BDwsmB6zx94ac0Niyg6y6hYIwz\nJ67y0pP/BcieKdIr32SVxHSi45iNu8fV7saFods8feYGhu4RMF0Chouhe5wb/IoXz107cLvFoGku\nqPwvDU3buewtCKWztHgBKXf+m3iewfzs/urqlgpfvDWIG5vDqOva9R7TSHHu5JWtwmCbGLpLU8Mc\nXW3ZxzmPVqd3NwxiB+Xl81cJGDvFEDBcnjv7Mdvr31aKtfVOhMjdr+fpzC6cPHDbM5OvEo/14Hkm\nSoFSAukZRFdPsjhfeWMV+MvmmsSNTWN1bOSQElrOlKMdraNIpaHnWMoZhkNf95fMLp7K34mSRe2p\nGyP509KYhotl2tjO/urqFosnTe6NPseZ4WtZLzWlQEqD+xP7XzI/bMPg/r1/S6RuivrGB6A01lZO\nk0yWz311L3zx1iDbM04IzUBJd4d4NS33/msTfZfrSnpQpDEslQ4SDubORKmUwHHNoto/KPdGn8fz\nDB47cRVNSIQmWYt28OmX3ydlF1uuUxCP9RGP5S64Vml88dY4QjNBukB2FoqF5QG0PBZQ1zWZnj+9\n9bN0bYT+UExOdHLPPFJ78cnXT/DCues7XChdT+f22DmkqlYQgeD+xDM8mHyKUDCK6wZIO9UN3SsX\n/p63xtiRNUIzcobCpex6JmYfx/Wy379SatjpMFNzDx0pZDqKtq2qgbs+WdR+F+DqneeYWe7Edh6+\nFGzHZHm9mbdu7J7orhIopZFINh1Z4YI/89Yc0l7LEprQzbxxrJ/feYNUqo6Tg58ghESgmF08wc2v\n3kDKh6KS9np2hXcliy7b4UmDn7z1R5zoHuXcwFdoQnJv8jRfT52s4qx7vPDFW2M461OZercbCM3Y\nWDbnQuPuyEvcG30eK5DAcYJ4cudeU9prBCIdQCZet9j97kMED2aGeTAzvPetPiXHXzbXGDK1grYt\nJY3QTFRe8WZQSidl1+cULoB0EoiNuGA3WvyS2ac28MVbg2TlKdaMrbKahaGwgsuEwnMI8fC5zWOh\nUhirfGoDf9mcBze+QHr5Lm58noazv1e1cQjNQO4x824SiUwzeOJnmGYMlAZCMTf7DA8mthnBVG2V\nqfQ5OL54t+GlVrEXv0R5Lka4jWDnk6TmK5dcW3lphJbta/zwqGh3rOAypx77e/RHPK46u67jnO1i\nKV7q/a5PtTn24pXpWKbcpGujBxsJdT+z5ayfmLpKsPOJio3FWZ/BqO/O/jDPUdGjdHZfQ4idjhm6\n7tJ3Zprlzxyc6BxGXXeOp30OI8dWvG5iAXv+CzSrAavz0o4K7kpJlJtCM3ev7F7SMcVnCHVl50kW\nurGnwQqgoX4cTcvt16uUIBhaJj4xviPN68YdBEJzmNYyXrqBVKKXakQF+eyP4yve2AzB7qfz1t9J\nL90jsEvx6LIg3SxPKCjM2gxknes+ihAqc116OwIUdDNK19A/YJgPY3GlF2R29Pdw7OrlZyo1mh5D\nGAmk04iShddMqmWOrXiRuzvmu/FZIm1nKzigPAi9oD3vwsIlenqv7NjzAqRTFqlkY46Edoru4b/D\nMKOIbbO20By6T/wtE3f/xz3r+dY6mrFOfdfPMEPTKKUjhEcqepbY/HdBVcf/ulQcW+uFIr/xxk0s\noYdaKjseJcm1VC20vOXiwmXsVDPeNndJpQSeq3P/y+c2wgyz97uhujF0I5El3EyfIIRHXeOd/f8i\ntYRwaBr4CWZoCqF5aHoaoXkEG76ioedfqj26ojm24kXmF6+9cBur7XzOa+XCSy4X9cJQ0uTuV3/C\n9NTLJJMtpO16Fhce49OfnyBpn8JZG8NsHMh6JhCcR+QJUNd0h0B49sDjqQWs+rsIzUZo2QEcQvMI\nhMfRA0tVGllpOL7LZnIvmzPHNXrFz0Ld9SnMpuLcDJU0mZ99mqm7bThrowjdIthxKZOfWbqZY6dt\neG4YJQ1EjtQxSmp4Tl1R46k2gcgDtDxpcRRghibx0q2VHVQJObbiVUrlTGqemvucYOelio9HpmNF\nFa+WToLU/E2Ua2M2DhAeeG1ryZ3vd41HT9Pa+2bO9hQasZULBx5PLaCkRZ5fHZRAHfI977EVL8rb\nkSdKKYVMx7IjcCqAm1jkIGljlFI4K/dx1qfQjBDBzss7jrwgY3zTcxQsU9JiYeKHtPf/FEEmcF1K\nAegsz3wL12nc8cxhwo6ex2q4m+UmuokQknTsRBVGVTqOsXgVjxqInNUHBJoPnufoILjxBezFLwkP\nvFrwMzK9TmruFko6BJpPZCVM30R5aezFO3ipNYQRINT9bM62EtHTTH39VzS03iAQXMCxm4guP4mT\nat91DMHgEnX1E0hpsrZ6As+r3Hl4oTjJXtKxkwTq7qNty9mspEFs/jWUrGyanlJzfMXLTkuuE50g\nMvh6xfp34/PYi3cID7y6p1VZKUl66R5ufA7NjBDsfnorVc7WPZ6DvXQHL7mK0E2stnMEO5v2Hke6\nieWZbxc0ZiFcTpz6J+rrJzJ9IhgY+iWTE6+yOH/wHFHlQbA+80OshjuEmj9GM+J4dhuJpedxkgN7\nP17jHGvxbsdLraEVsefcL258DnvpbkHC9VKrJMbfI9B6ZsfZs5Iu9tJdvMQSQjewWs8S7LiEo88R\nC3yMFHFMr5dw+gKaKn6m6R98k/qG8R05tHr73sNOtbIeHSy6j9IisKOPY0cfr/ZASs6xFa904lk/\n2/M3CfW9WJG+3dgs6eWvCfd/q6Bz3PrT/2bHZ9K1SU5+gNADBFrPZuVkjgbfJWHdADwQCluNEreu\n0hL7I0y5+3J4NzTNpqX1Ts7kd7ru0tV9rQbFe3Q5due8Mh0nNvIrrLaHb+JN98NHXQcPgmevERv5\nVSZDYw6c2AzplW8IDxQm3FwopUiMv0uo70XC/S9jhB8ed6T1CZLWDRAubOYwFi5K2KxE/hF1QMPY\nmrOOZ8yjciQe3yQYOtznpoeNYzXz2gu38ZLLmfo824Rqz9/C6rhYkj7Si18R7LxMfORXhHqfQ9+W\nFcNZn8ZZHSHc/0pRfSSnrhLsehLN2LkMjls3UORwvBCgtCSOPkvAKzyy6Fb0Lj9dfJuEl6TRUvxf\nFyT55Futsh/HlWMhXukkSE5+SKD1DFb7Ts8pz14jGNzbsFNQX56NEW4ncuJ7JCevoodasNrO4qxP\n4ayNEe5/uaj27aW76OE2jDwVBD0tmj8gSAmkFstXcmcHt6J3+a9z/x1HZV4GSyn4Yh4udoLxyJrN\n8zIOIseFFXeBr1KfEpXLNGptnA09RZNeWYePIy9ee/EObmKB8OCrOzyMAJy18ZKlhcnkR8448guh\nEe5/ifTKfWL3f45mNRDue6mo9t34HDK1mlXp71FMrwtXn3+4ZN6GEhLDKyxSSCnFzxbf2RLuJv/r\nh/C/fR8aAwLLVBvVCEzWVk+yvHT0jEK5uJf6jE8S7yDxUCgWmWEk/SXPh7/HiWDl/g6OrHilkyQ5\n+QFm8ykiu5yhplcfEB4oTZ6439WYAAAfOklEQVTh9PI9rJbsMMJA80nMxsGi99PSSZKav0Vk6Lu7\n3hexnyIZuA2PLp2Vhul2Y8jmnM89StSNEfd2VkRYTsJ//Cf4zpDGX545hfQCLC09Tjx2PGKA43Kd\nTxLv4G37+1UoPFyuJX5BT2CIoFaZXNFHUrz20l3c2GzmGEbP7wIn0zE0M3Jgw9GjeKkVgjn2zsUK\nVylJYvxdIsPf2XOshmyhKf5brEX+FRSojRnY8NpoTvyo4D4Noec1bjkS3h01edX4rcJ/iSPCiP3l\nLkY/wVj6Lo8FK1N47EiJV7qpzGzbNJzT6+hRUnOfE+rJ7Xm0X5SSiDLNPImJ9wn1vZBz2Z+LoHsS\na+0/YZsjSJHE9Lowvf0VxIoYYToCLczYCzuuaWhcqj9YogJH2SRVFEtEsMThq2aQkglkHqOBh4ut\nctdvKgdHSrzxB7+g7uRv7lowehMlvY0C06UJNnfWxjEbS3/GmZq7SaBxEN3K7WeslGJWfsWId52U\nWickGhnWn6NTO03QOVNU37/d8T3+z8m/w1Xu1lyjoRHWg3y7dX9n4p5yuJV+kynvKzR0JB6tWh9P\nWD8gKA6PlbrV6MKwTVx2+ksbmDTrHRUby5E65w12Xia9/E1B99qLt7HaS2dccKMTGA2lrR7nRCdA\nyV1fCnfct7jt/pJ1tYBDiqia4wv3Z9xz3yu6//5QN/9p4M84FzmFpQUIaUGebbzI/zT4l9Qb+xPc\ndfufmPLuIvFwSSPxWJTjvJ/6CZ46YNHrKjAQOI0hdq6ABAJLC9FrVi7Y4UjNvGbjIImJK3h2dM/w\nOi+xRLCjdKF/ClVUvdtH8ewo6ZX7u/pax+QiU/IL5CPGKQ+Xcfkp/eoyYVFcZFCn1caf9f52UW1E\n5QLLcnLHOBWKtEoy431Nn3GuqD4qhS4Mvt/wx7y1/g8kZYyMkU4R0Rv4dt3voVUwte6REi9AqPcF\n4qNvEhn+Xl7jjhub2bPyfC4yGSVtlJdCuTZy4/+lvYYRKu0ZnxubQd+jzZmNmSznWFHMefcYNkqz\np8+HUgqJg0BHE7ndN5a8ybxGHg+HeW/k0IgXoF5v5seN/54lb5aYt0a93kyL3lEyw2ehHDnxCk0n\n2PUkqdlPCXXndhrYDAgohOjdfwTPwajvASEQuoUwgmi6hTAsNLMFo6675DHAVutj2Et3Sc3eINiV\n23opccgXB6w2FqjlZE7eZowrOGT8xFvVKU6I7xB4ZA+rCwOBRj7vEIPDl+ROCEGb0U2bUb082Edq\nz7uJEc4437vx+R3XpJPMCLDA5U39md/G6riA8mys9guEup8m2H6eQMspzIZ+jEg7utVQlreu1foY\nWrCJxNS1nNdb9EF0clugdUxatfLVJJqU17nPr0izjkKikCzyNZ+p/wdXpbLu7dRPZhL+5Rlnn3E8\nnDtKzZEUL0Cw6ylSc59tZGV8SGr+c4JdhVdBEEJgtZ0jPPAa6aWvSExcQXnpUg83L4GmYcyGfuLj\n7+4ovN0mhgiLJsQj3sYCnTrRRpMoTzVATzmM88GOPSwoXFLMqltZn1oizFnzW+iPLPR0TLr0UzRr\nfhWHg3BkxeusjiB0i+1eP5t71lypYh7l0aggoemEep4j2PUkickPSc3e2PFiKBdmfQ9W2+MkRt/K\n6lMIwbPmH9GhnUBDRyeAhk6XdppnzD8o2x5snemNZfBOJC4LfLXj85Pm0zxr/TYtWh8BQjSIdi4G\n3uDJwA8qvlc8Khy5Pa9SiuT0NfRAww5HjfTSXawCqyCs3fy/MZtPIISOMEKYjYPo4TY0M0xk8DXc\nxAKJ0V9jNg0TaC7/8YARbkP0PEt85FdEhr6z5bVlCosnzB/jqBS2imOJOkyxd0WAVXeFz+MfM5Oe\nJqSFuRh5gmHrVIFC2v2efM4q7foQ7fpQAe37FMKREq90kyTG3yPY9eTWvnc7bnwOq60wq2bD+T8m\nOfkhoaHXUG4SZ22M9NLDGUUPtxPqewk3Nk185E2szst5I31KhW41EO5/hfiDXxI5+f2sfbspgpii\nsEwZk/Y4P13+B7wNx3qAOWeGYeskbzT9cE8BN9CT13qsYdCBv4etBEdGvM76NPbil5lY3RxeU25i\ncc+jl+1oZhir4yLJ6Y8I9z6fJXqlFF5iAXvhNspNgm6yfue/YNT3EBn+XlmLkwnNAE3noEEAUkl+\nsfLPuI/sV13lMGLfZ9weYTC4+0pCEwbD6jVGeDtr3yvQCBChUxzulLGHhSMh3tTc5yjpUjf8Rt57\n7IXbhAe+ta92jUgH0l7DXryTJV4hBEakAyPy0BUu3PsCTnQCNzZdtgyUmQwa7xWU9yofM+lJvDyW\nX1c5fJH4fE/xAnRrlwmoCKPqfZIsoWHSweMMipfRxeE7+jmMHGrxKulkErO1nN41Jle6NkIzDuQB\nFWg5TXL6Y5z1acz6nrz3CT1Q9rSxqdlPsdrP58ygUXAb0t7jeuGO9a3iFK3iFEop3+hUBQ6ttdlL\nLhMf/TWh3hf2DKa35z8n2Hn5wH2Fep4hvXQXz14/cBvF4qyNIfTAgTzDttNhdiJVbmcJDZ3ewP5T\novrCrQ6HUrz20l3spa+IDL+BZu4eVqaUQjoJtEBxdXfCA6+SnPygoCr1pUamY6RXR3LGCu+XeqOB\nQWt4x5krgC50LkYKPwP3qS6HSrxKSRIT7yOETrjvpYKWwc7K/ZIsZ4WmEx74FvHRt3c4S5STzO98\nhXD//vbru/FG8w8ZCp7InAyLAKYwqdMb+O2Wf0tEP9zFxY4Th2bPK9MxEhNXCPW+gB4sPFLGiU4Q\nGSqsGkDOfp0kzvokXnweUAhNR7lJxB4zfqlITlzZCMQvXdVCQ5h8v/lHxL0YS+4iQRGk3eysueWv\nkh6JiffRAvUEOy6ULPb6qHAoxJteHcNZGyUy/Ma+vsReahV9H1khpZPAiU7iJRbYdPgXehCzoY9A\n80mE0JCujZdcIr38DTK9Dkru24pdKPbClxj1vXkD8YslotcVNdN6yiGuljFEgLAoLDdWoSgvTXz0\n14T7X0Epj+TMxyjPwWzow2w6UXMvmmpQ0+JVSpGa+RhhBAtKa/Mo9vytvFUQZDqemVETD9O8CCOU\nEUukE5lcwksuoTyb9Mp9WLmfuUcPoIdaMZuG0AL1mSp90YmSZaDcxE0s4KXXCZcwYUCpUEpx3/uA\ncfkJIFBIgjRw0fghDdr+0u3kQropEmNvEx58fcuyHu57CaUU7vokifH3EEIQaH+85KGYh4maFa90\nbRLj7xLsvJx1nloom4YloRkZoUbH8RKLmWsolJRohoXa5syn3BTOyn20QD16uBWr49KOYl6PYjaf\nJDH+TknFq7w0qdnPiOxybl1NvvHeZ1x+muWgkWCZj92/5UXzrwgVkQBApuMkJt7PuIA+skwWQmA2\n9GM29GdqNC3ewZ7/As2MYHVcyHmEJnFIml+RMkYRKkDEOU/A6y1bvrFKUpPidWNzpOZvEh54dU/x\n5MNevIuzPs3a7b8BFFqwGc2sQwiBEBpGpAU91IYebCpqPymEQOgBpGsfeKzbUUoRH3unKEeMcuKq\n9A7hbiLxGPWuc8442EvHs6Mkp64SGf7unhk3hWZsWd9lOpaJIHNtjLpuAi2nEELDFVHmIz9BiTRK\nOKAgad4l5JymOfWbh17ANSfe1PwtlGtn9re7fHkzhbCjeIlFvMTSjiMcoQcI9T6XcejfEG25CHZc\nxp7/nFDPc0W3lZr5hGABM361iKkFNLScPloKyZIcO1C7XnKZ1OyNjX/3/R2CaIE6wr0vABk32cT4\n+yAgdmYMKRLbajaBwiFpfk3QHSLsHp7sHbmoGfEq6Wa8pZpPYHYMbn3mJZczAk2t8mjWCM1qQA+1\nEux6oqqWSC0QQTqJottJr44hDAujrvh9Y7nQMXctVmbkSQ6wG258PuO+OrR3Xuq9MOt7MOt7cNUq\nK8YneSpHOKwHPvHFWwq81ArJqY8QRggnOokTncxcEBp6qBWjrotA29mSJngrNWZ9X1GGK5lez1jU\nD2CYqyR1oh2DIF6O1KcaBr3a/pL6OetTOCsPCA++XtLVkdRTCGGgyJ04wdPiOT8/TFRdvPby13jx\neUL9L5Feupc371StU4zhKuOI8UHNGqi2I4TggvEDbrj/30byu8zMpmFQJ9ro0QuPKEqvjuHGZ8py\n1GbIRlS+imoKtLi2kYjw8GbxqKp4Uwu3EZpBuP9l7KW7JT9uqSTFGK4yFRFe3NNw1hRZpa99Gsc1\neTAzhOPtf4laClq0fp43/5wR9yorahKDAL3aJfr0y+iisK9UevkbPHtta69aajRChJwzJM17IB7J\nioJBk/g+nh3FXrqHMCyC7RfRAsUlf3eik5glzt29G1UVr0ytbpW89BILBFpOV3M4RXMQw5W98CVm\nfd+ueaZ1zeXHL/6U070P8GRm6yCE4mcffY/bY9U5B64TrVw0/82BnrUX76CkU/ZVVnPqe0iRJG1M\noshk+FAoGlOvE5QD0JpJ8ifdJPb8F0gngdk4QKBpeF/9SDdJfOQtEOL4iDfLAKVKm7S8GuzXcOXG\nF5DpdUJ7OGL8xtNvcapnBEP3MPSHs8gPn/slq7EmppbyhyrWGqn5mwjNLGnC+3xomLQnfx9HW8TW\npxCYhJwTaGSfB2tGiFDPsyglSU5c2Zd40ysPcKLjaEaQUJFF0/fL4VZLDbJpuNoL5aVJzX1GcI9Z\n2jJtLgx9iWnsPFfVNZeXzl898FgrTXLmEzQjVHAqolJhyjbqnMtEnMd3CHc7zuooZoHC3TwdUdLB\najuPHmqp+PFe1cS7vRC1dJOIIgLMawmz+WTGnXIX9uOI0Vy/gidz74U1Dbqad1bxq0USU1fRQ601\nvTVy1icx6vdOl+vGZomP/ppg11NYrY+Rmv8cq7PyoZRVWzZ7iXn0cOY8041OlbxIV7UoxHC1H0eM\neCqMruWxmm5cPyhN9Us8//i79HeOIoDJhQGu3X6V5ejO5H0HRSlFcuJ9zOYTmAUIo9rs5RiUmrmO\n0MwtJyJ76R5Wy+mqeMNVbeZ14/NbPstufA4jXLnSiOVm03CVD7NpGHvxy4LigtcTDcytdiDlzi9H\n2jG5fu+pA42xuX6R3331/2Wg6wG6JtE0SX/HKL/z6l/T2riz0sRBSU5eIdD6WM0L100s7hrk4KXW\niI/8ErP5JMGuJxFCoKSHG50oS2nXQqiaeJWbfJhlUcmSxqtWm70MV0a4lWDnZRJjvy4ocfs/ffBD\nkukgaTezUFIqI9wHs4PcGjmYtfmFC+9gGA7atneCEGAaDi9eePtAbeZCKXmgwJJKk16+R6Aldz3j\n1Pwt7MXbRIbfyBJ4avYTgt3PVGqIO6i6k8ZRZS+PKz3UQrDzSRKjvyY89O1dLe2r8Sb+93/+D1wa\nvs3JnhFSjsXNBxcYmR3kYClgFX3tY1nC3U536ySa8JCq+Beq0EyUl675QHrluQg9+9xcukmSEx8Q\naD2zIwWRTMdRnrOvxBClpuriVV4aavwf9iAU4nGlh5oJdj9NfPStTAjcLgJOuxYff/0UH399sGXy\nDnbTfAm3b4Hmk6RXHmC1nS1doyVGuskd4YTplQc4a2OEB76V88WTnP6IcBmOhpz16YLvrcqyeftS\n0Vmf2jWl6mFFbJQDlW5q1/v0YBOhnmeJj7xZsdpHIJhdzL8HnV/pKsmsC5nKEtsTHtQi6cW7BNoy\nZXCUdDNF3aRDZOjbuRP4x2bRw607ZupiUV4ae/HLgu+vinhlag0tmEmbctj9S3cj2HEJe/7mnvfp\nViOh3uczApb5Lcul5MMvXsdxdy68HNfg6q3XS9ZPLcYkP4qXjqJbjVtHQKGup3etaZVa+AKrvfhM\nno+SmHgfTS/8rLgq4nUT8w+ty9LbM/D6sLIfjyvdaiDU+wLx0coIeHGtk3+58ofMLncjpUBKwfxK\nF//6wR8wt1LalZAww8h0bUbxKCURCJJTH+HGZogMv4GzPpmztjNkXDut1rMlfynZC7dxY3OYTUMF\nP1MV1XiJJQLNp6rRdcXZT6igbtUT7nuJ+OibRIa+W3YL/PxKN//t3T/F0DPhfW6ZAh0CLadIr3xT\nVOL7cuGsjuKsjRMeeh0nOkFi/F0CLaex529hDH83614lXdzYLJGh0nqIealVYg9+TuP5P9tXLHeV\njooyR0NKOnBEZ91NCvG42o4WqCPc9zLxkV+h5E6XyHLgembZhAuZbYG0o2VrvyiEjlHfgxOdINhx\nmcjga5j1PQRaz2AvZtcZTs58XPKjIaUksfv/naZL/27fSRiq6tvsxmaP7H53k0INV9vRApFMgveR\nN6tSoeGoo6RHau4m8bG3UW6S8OBrhHtfyKruaDb0465PbRkRM2l+FbpVX/Lx1J/5MXqoZd/PVVW8\nexXvKgtaEqxRCExBnmp5paZQw9V2NDO8IeC3UN7hF7AWbMJLLld1DJ69TmLiComJKxj1vUQGX8fa\nJUOL1fUEqbnPAEhOf0yo59mSj0kIbc+SPfmo+JpVeWmEtrFEq+jhvYSmt6HuJigdUKAMWP4hpIbK\n2rOXXEIL7P+NnRHwqw/3wPs4mpCkcbUVNBXEUNVzJNgk0HIqk0c7VHySvv2glMJZyyTt1wL1hHqe\nLfg7Z4Rasee/IL06hhHprDnDasVH48YX0KvhLtf4HkRuIYS3LbOCg2r9bzD/J+CUZ0xKSezle7vW\nDt4NzQwRHnx9w5Ej97ljVn9I1qx3iQc+R6ChkBiymZbkDzFl24HGUAo0I4Rydy8vWkqU55Cav4lM\nr2M2DhIeeO1AFuJQ9zPE7v+M+rO/X4ZRFkfFl81uIhOEoKQHlQq+F2mo+wyh5TAACQ/qr5Wt69T0\ndUJFGjk0I7glYOXlTqi2yZr1JonA5yBclEiDcHG1BRYif4Mnqn9cU+4ibV5ymfjYuySnrxFoOU1k\n8HUCTcMHPtrRAhEazv1BTZ5XV1y8ykmgBSKZSKIia80WjLFCvl9VCAVW4S5p+8FLrQHsq15SPjTD\nIjz4beKjbyHzzGCeSBAP3EaJR15SAhQucfOzosdRDEZdF258tuTtKqWwl+4SH3sbJzpJuP9lwv2v\n7Jpa6ChQtUW8uz6JVYFUKABIi12NU6o8GRCSM9eJDH2nZO1phkVk6DvER9/KquOziaPPItBzZ00U\nHinzAQ3pl0s2nv1iNg2RnL6OWaITBukmSc19jnJTBFrOEBnM7xVVSyglM0ZImUZ5Dko6WX8WStXE\nq1w7Z22ZsuA1gduEMhd5dPWjpAGx0jsP2It3sFrOlDwvl9ADGwL+NeHBV9GMh8cbQu1u0BJlekkV\nitBMKIH3mBubwV66izCCBDsuZx3xFItSCi+xiHKTG2JKZ4mrFOMHgdBNhGZmjJAbfwotgGYWnsGy\nouLN2u9Ueg+x/EPo+BsULkJkZmElDUh3Qqy0KwDlpTc8cQ5eF3g3Hgr4rUw9p40vb8DrBaXljAoS\nyiSSLr0/7r4RGkp6+/YeU9LDXryNl1zGiHRupBAq3YtRpuOk5m+iPBsj0olmRhBmGM1qzBaaMGpm\n/1tR8Uo7imY1bhx8V/gvwGmH2X8HdZ+igqOgAhnRJs4CpXVDTExdJVSmfMSbCN0kMvwd4iNvER74\nFpoZRqDRnPpNVkL/gsLd+isWysD0ugi55VtWKiXxEos4a+Po4TYCeXx0zcYBnOh4wRkaPXsde/4m\nSnlYbedLmnVSKUl6+Wvc2AyaGSHY9WTlVoMloKLideNzGJEOvMQCerh0eZIKxquHtdcy/5UJe+HL\njTd36ZZy+cjkUvou8ZE3Cfe/ghaIEHJPosf/mHXrGml9Bk1ZRNJPEHEuIkpon/RSazjRMeSGUQ6h\noYfbsNofx43PER97e6Oi/aWs82mjvreg9KqZguojaGbdvs5mCxp7cgV74QuUkgRazxDZJYKolqmo\neL3kIoHmk6TmPqt4+s9KYC/eQaEIVvDLIDSDyPAbxEd+Rbj/ZbRAHQHZSWvyxyXrQzrJjfrGC5kc\nPEKgWQ2YDYPoHTsdQAJNwwSahjMlO6evoZQk2H4RPdSMEFreQmWlOpvN2bZ0sRdu46VWMzHUfS/W\nnNPFfqns6DdyVSkncWCXsFrFXrqHku6OdCmlbH+3oHZhhoiP/pr6Mz8qqh/lOZmQuPUZUB4IgTBC\nmA39BFrO7EtMutVAuP+VzH51/hapuc8w6nt3ZNf0ksukFr5ACA2r41JJj3gyxq17mbbbz9dkZNNB\nOdyvnhrBXv4a5SbL+sVQTgKr7dyBHNjztqkkbmwWNzqJ8uyMEVEzMOt7CfU+X7KQRKHpBLsyeY2d\n6CTp5a/x4nM4bhI3NoMebCHc93LJ+pNuCnv+FtKJY0S6MqlsDnk1jlxU3re5zB42lSa9ch+VjhHs\nerKs/VgdF0lMvH/gEqBKKbzUMu7aODIdy3woNIy6LqzOyxXL9q+HW9HDbaRXRzY8oEqzxcj4MI/i\nrI0hdCuTF7vIwmG1TsXEqzwHNBMvuYy+S37cw0R6dQQvtUaou0RJ4XZBaDrCCCIL3HJk6v2OZ0Xy\nZCoWnDpQkESxlOtsVqbXSc3fQnkOZuNQSffJtU7FxOsmFjDCbZkk1c0nKtVt2UivjuIllgj1VC5v\nb7DzCVIzH29VVtxEujZudAI3Pgcb8adaoA6jcYBA2+NV+zKX62xWKUl68SvcxMLGEc/TFa8TVAtU\nTLxefI5AyylS69OH3ufUWRvHS8zvq5RnKdAMC5TMhLitT8NGpg2hWxgNfRkLag3s7cp1Nusmlkhv\nVJqwWh/D2qO64lGnYuKVThxh1lWqu7LhRCdxYjOEe5+vSv/B7mdw47OEup8peerRYinH2azyHOyF\nL/DsKHqohVDfS0equkYx+NbmfeCsT+NEJwj3vVi1MWhmaN/Fn8tJuc5mnfUp0stfIzQDq/0CwRJE\nZh01KidepZD2Gtoh/UdwYzM4qyM79pvHlXKczUoniT1/E+kmMep6Su6/fNSoiHg3j4cyKVAPXylP\nNz5HevkbwgPfqvZQqo6zPkV66R56qDRns0opnNUHONEJhBEi2HHxyDnwlIuKiDcTkNCATK2itV+o\nRJclw40vYC9+RXjg1WoPpeooJUkv3S1JjLJnR7Hnb6GkS6D5BJHB14sf4DGjbOJ9GLExi9AMgt1P\nk5q+fqjO4NzEEvbi7WN1drgbqdkbBDsP7oySOTq6s5WQr9QBB8eNkor3Yaa+MYTQCLScwmp9DCUd\nUjM30A7REZGXXMaev0l48HVfuGRilGU6hh5q3vezmdXLHRBgtZ4j2HG4Vl+1SknE68ZmsZfvgVIb\nXi6vZiqHew6JqWso1ybY9WRZElaXAy+1Qmr2BuGh7/jC3SA588m+EukpL01q/hYyvY4ebifcXzrf\nZZ8MBxavl1zOhMBJF6Oui3D/K1uWQeWlScx+inLThLqfQgscnvNdL7VGcuaTjXq5vnCBTLE0pQry\nFXaiE6RX7iM0E6vj4qF3yKll9i3e5NQ1pGujh5oI9TyX5SigvDTJmU9Q0iHU9fShcwzPxJ9+RGT4\nu/4RxTaS0x8T7sufGUQ6iUwKGdfGbOjzbQQVYt/itTovZSU9g4xvbWr2E5Aewa6nDp1oIePgnpy6\nSmT4DV+42/BSq5kUO48YljIGyW8yKWSMUMkTwfnszb7Fu1240rVJzXwCyiPY/fShPZ+T6TiJiQ98\n4eYgNfsp4YGHYYheajWTQkZ6BFpOHThE0ad4DrTnlW6K1MyngMrMtIfkjas8Z4c/sHQSmTjZ4Td8\ng8ojuLHZrVxjqfmbeMkVdKuRUM/zNedXfRw5kHiTU1cJ9T6/Y/lcqyilSM3dIDXzKU1P/Iet/Zh0\nkiTG38vscX3h7iAx8T56uJ3k5AcE2h8vaeZGn+I5kHiFZh4a4TrrU9gLXxLsegJpxx4K102RGH9n\nQ7h+fEYurI5LBFpO+VuJGuXI/qtIJ0l87G1kapXI8BsoL71VC1i6NomxtzPHQZq//MuH1Vr6ig8+\npePITTlKKey5z5DpGOG+l7aspM7KA0L9L2fOoMd+nRGu75rnc4g5UuJ11qexF24T7HwCI5Kd1F2h\nQLobRbr2rnPr41PrHAnxSjdJcuoj9FDrxnFPtoOAE5vBCLVtq653/PId+Rw9DrV4s5fIL+adTdNL\nd5FOgsjgtw9VLRofn904tOJ9uES+jBHp2PVeNzZH/ZkfHZrzaB+fQjh04n24RG7JuUTOReP5P6rA\nyHx8KsuhEa9SKpPfyI7uukT28TkuHArxOrEZ7PkvMkvkI1QoysenGGpavNJNkZy6tq8lso/PcaEm\nxbu5RPbsNUK9L/hHOz4+Oag58bqxGVLzXxDsvHSkaqn6+JSamhGvdG2SU1f9JbKPT4FUXbyZJfIt\nPHvVXyL7+OyDqorXjc2Rmr9JsOMSwU4/VtTHZz9URbyZJfI19FCTv0T28TkgFRXv1hI5tbqRicNf\nIvv4HJSKiffhEvmiv0T28SkBZRfv1hI56C+RfXxKSRkLjalMRfPkCqHe5/xQPB+fElMW8brx+cwS\nuf08wY6L5ejCx+fYU1LxStcmNf0RmtVAZOi7/hLZx6eMlES8D5fIyxtWZH+J7ONTbg4mXk0nMXFl\n60flpQm0nfWXyD4+FUQopQq/WYjCb/bx8TkwSqk995z7Eq+Pj0/t4KfD9/E5pPji9fE5pPji9fE5\npPji9fE5pPji9fE5pPji9fE5pPji9fE5pPji9fE5pPji9fE5pPz/dX6pJCB35TQAAAAASUVORK5C\nYII=\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "from mpl_toolkits.basemap import Basemap\n",
    "\n",
    "districts = combined.groupby(\"school_dist\").agg(numpy.mean)\n",
    "districts.reset_index(inplace=True)\n",
    "\n",
    "m = Basemap(\n",
    "    projection='merc', \n",
    "    llcrnrlat=40.496044, \n",
    "    urcrnrlat=40.915256, \n",
    "    llcrnrlon=-74.255735, \n",
    "    urcrnrlon=-73.700272,\n",
    "    resolution='i'\n",
    ")\n",
    "\n",
    "m.drawmapboundary(fill_color='#85A6D9')\n",
    "m.drawcoastlines(color='#6D5F47', linewidth=.4)\n",
    "m.drawrivers(color='#6D5F47', linewidth=.4)\n",
    "# Temporary bug: if you run the following line of code in the Jupyter Guided Project interface on Dataquest, you'll get an error. \n",
    "# We're working on a fix, thanks for your patience! This should work fine locally on your own computer though.\n",
    "# m.fillcontinents(color='white',lake_color='#85A6D9')\n",
    "\n",
    "longitudes = districts[\"lon\"].tolist()\n",
    "latitudes = districts[\"lat\"].tolist()\n",
    "m.scatter(longitudes, latitudes, s=50, zorder=2, latlon=True, c=districts[\"saf_s_11\"], cmap=\"summer\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "It looks like Upper Manhattan and parts of Queens and the Bronx tend to have lower safety scores, whereas Brooklyn has high safety scores."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Racial differences in SAT scores"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 79,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x11f61ccc0>"
      ]
     },
     "execution_count": 79,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX8AAAExCAYAAACUFqJ7AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nS1KDDH9JapDhL0kNMvwlqUH/H16yZIExE7kvAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "race_fields = [\"white_per\", \"asian_per\", \"black_per\", \"hispanic_per\"]\n",
    "combined.corr()[\"sat_score\"][race_fields].plot.bar()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "It looks like a higher percentage of white or asian students at a school correlates positively with sat score, whereas a higher percentage of black or hispanic students correlates negatively with sat score.  This may be due to a lack of funding for schools in certain areas, which are more likely to have a higher percentage of black or hispanic students."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 80,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x10c2856a0>"
      ]
     },
     "execution_count": 80,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAY8AAAELCAYAAAAhuwopAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nYRiGYdTM/wf2TZ+UntQWnAAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "combined.plot.scatter(\"hispanic_per\", \"sat_score\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "44                         MANHATTAN BRIDGES HIGH SCHOOL\n",
      "82      WASHINGTON HEIGHTS EXPEDITIONARY LEARNING SCHOOL\n",
      "89     GREGORIO LUPERON HIGH SCHOOL FOR SCIENCE AND M...\n",
      "125                  ACADEMY FOR LANGUAGE AND TECHNOLOGY\n",
      "141                INTERNATIONAL SCHOOL FOR LIBERAL ARTS\n",
      "176     PAN AMERICAN INTERNATIONAL HIGH SCHOOL AT MONROE\n",
      "253                            MULTICULTURAL HIGH SCHOOL\n",
      "286               PAN AMERICAN INTERNATIONAL HIGH SCHOOL\n",
      "Name: SCHOOL NAME, dtype: object\n"
     ]
    }
   ],
   "source": [
    "print(combined[combined[\"hispanic_per\"] > 95][\"SCHOOL NAME\"])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The schools listed above appear to primarily be geared towards recent immigrants to the US.  These schools have a lot of students who are learning English, which would explain the lower SAT scores."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "37                                STUYVESANT HIGH SCHOOL\n",
      "151                         BRONX HIGH SCHOOL OF SCIENCE\n",
      "187                       BROOKLYN TECHNICAL HIGH SCHOOL\n",
      "327    QUEENS HIGH SCHOOL FOR THE SCIENCES AT YORK CO...\n",
      "356                  STATEN ISLAND TECHNICAL HIGH SCHOOL\n",
      "Name: SCHOOL NAME, dtype: object\n"
     ]
    }
   ],
   "source": [
    "print(combined[(combined[\"hispanic_per\"] < 10) & (combined[\"sat_score\"] > 1800)][\"SCHOOL NAME\"])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Many of the schools above appear to be specialized science and technology schools that receive extra funding, and only admit students who pass an entrance exam.  This doesn't explain the low `hispanic_per`, but it does explain why their students tend to do better on the SAT -- they are students from all over New York City who did well on a standardized test."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Gender differences in SAT scores"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 83,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x11f10e0b8>"
      ]
     },
     "execution_count": 83,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYYAAAEqCAYAAAARXvdwAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n/wPje2leCg22KAAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "gender_fields = [\"male_per\", \"female_per\"]\n",
    "combined.corr()[\"sat_score\"][gender_fields].plot.bar()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In the plot above, we can see that a high percentage of females at a school positively correlates with SAT score, whereas a high percentage of males at a school negatively correlates with SAT score.  Neither correlation is extremely strong."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 84,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x11f1ea208>"
      ]
     },
     "execution_count": 84,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAY8AAAELCAYAAAAhuwopAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "combined.plot.scatter(\"female_per\", \"sat_score\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Based on the scatterplot, there doesn't seem to be any real correlation between `sat_score` and `female_per`.  However, there is a cluster of schools with a high percentage of females (`60` to `80`), and high SAT scores."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 85,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "5                         BARD HIGH SCHOOL EARLY COLLEGE\n",
      "26                         ELEANOR ROOSEVELT HIGH SCHOOL\n",
      "60                                    BEACON HIGH SCHOOL\n",
      "61     FIORELLO H. LAGUARDIA HIGH SCHOOL OF MUSIC & A...\n",
      "302                          TOWNSEND HARRIS HIGH SCHOOL\n",
      "Name: SCHOOL NAME, dtype: object\n"
     ]
    }
   ],
   "source": [
    "print(combined[(combined[\"female_per\"] > 60) & (combined[\"sat_score\"] > 1700)][\"SCHOOL NAME\"])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "These schools appears to be very selective liberal arts schools that have high academic standards."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# AP Exam Scores vs SAT Scores"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 86,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x11f463048>"
      ]
     },
     "execution_count": 86,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAY8AAAEKCAYAAADq59mMAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nhmEYRmhMeBiGYRihMeFhGIZhhOb/A5CW4qe1YQ+lAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "combined[\"ap_per\"] = combined[\"AP Test Takers \"] / combined[\"total_enrollment\"]\n",
    "\n",
    "combined.plot.scatter(x='ap_per', y='sat_score')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "It looks like there is a relationship between the percentage of students in a school who take the AP exam, and their average SAT scores.  It's not an extremely strong correlation, though."
   ]
  }
 ],
 "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": "3.6.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}