Skip to content

Instantly share code, notes, and snippets.

@albertovilla
Created February 15, 2018 18:44
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save albertovilla/ca0aebd0c72b1e2aa4cb72d10d097a25 to your computer and use it in GitHub Desktop.
Save albertovilla/ca0aebd0c72b1e2aa4cb72d10d097a25 to your computer and use it in GitHub Desktop.
Display the source blob
Display the rendered blob
Raw
{"nbformat":4,"cells":[{"metadata":{"tags":["context"],"dc":{"key":"13f090f9f0"},"deletable":false,"editable":false,"run_control":{"frozen":true}},"cell_type":"markdown","source":"## 1. Meet Dr. Ignaz Semmelweis\n<p><img style=\"float: left;margin:5px 20px 5px 1px\" src=\"https://s3.amazonaws.com/assets.datacamp.com/production/project_20/img/ignaz_semmelweis_1860.jpeg\"></p>\n<!--\n<img style=\"float: left;margin:5px 20px 5px 1px\" src=\"https://s3.amazonaws.com/assets.datacamp.com/production/project_20/datasets/ignaz_semmelweis_1860.jpeg\">\n-->\n<p>This is Dr. Ignaz Semmelweis, a Hungarian physician born in 1818 and active at the Vienna General Hospital. If Dr. Semmelweis looks troubled it's probably because he's thinking about <em>childbed fever</em>: A deadly disease affecting women that just have given birth. He is thinking about it because in the early 1840s at the Vienna General Hospital as many as 10% of the women giving birth die from it. He is thinking about it because he knows the cause of childbed fever: It's the contaminated hands of the doctors delivering the babies. And they won't listen to him and <em>wash their hands</em>!</p>\n<p>In this notebook, we're going to reanalyze the data that made Semmelweis discover the importance of <em>handwashing</em>. Let's start by looking at the data that made Semmelweis realize that something was wrong with the procedures at Vienna General Hospital.</p>"},{"metadata":{"tags":["sample_code"],"trusted":true,"dc":{"key":"13f090f9f0"}},"execution_count":83,"cell_type":"code","source":"# importing modules\n# ... YOUR CODE FOR TASK 1 ...\nimport pandas as pd\n\n# Read datasets/yearly_deaths_by_clinic.csv into yearly\nyearly = pd.read_csv('datasets/yearly_deaths_by_clinic.csv')\n\n# Print out yearly\n# ... YOUR CODE FOR TASK 1 ...\nprint(yearly)","outputs":[{"name":"stdout","text":" year births deaths clinic\n0 1841 3036 237 clinic 1\n1 1842 3287 518 clinic 1\n2 1843 3060 274 clinic 1\n3 1844 3157 260 clinic 1\n4 1845 3492 241 clinic 1\n5 1846 4010 459 clinic 1\n6 1841 2442 86 clinic 2\n7 1842 2659 202 clinic 2\n8 1843 2739 164 clinic 2\n9 1844 2956 68 clinic 2\n10 1845 3241 66 clinic 2\n11 1846 3754 105 clinic 2\n","output_type":"stream"}]},{"metadata":{"tags":["context"],"dc":{"key":"45ea098e15"},"deletable":false,"editable":false,"run_control":{"frozen":true}},"cell_type":"markdown","source":"## 2. The alarming number of deaths\n<p>The table above shows the number of women giving birth at the two clinics at the Vienna General Hospital for the years 1841 to 1846. You'll notice that giving birth was very dangerous; an <em>alarming</em> number of women died as the result of childbirth, most of them from childbed fever.</p>\n<p>We see this more clearly if we look at the <em>proportion of deaths</em> out of the number of women giving birth. Let's zoom in on the proportion of deaths at Clinic 1.</p>"},{"metadata":{"tags":["sample_code"],"trusted":true,"dc":{"key":"45ea098e15"}},"execution_count":85,"cell_type":"code","source":"# Calculate proportion of deaths per no. births\n# ... YOUR CODE FOR TASK 2 ...\nyearly['proportion_deaths'] = yearly['deaths'] / yearly['births']\n\n# Extract clinic 1 data into yearly1 and clinic 2 data into yearly2\nyearly1 = yearly[yearly['clinic'] == 'clinic 1']\nyearly2 = yearly[yearly['clinic'] == 'clinic 2']\n\n# Print out yearly1\n# ... YOUR CODE FOR TASK 2 ...\nprint(yearly1)","outputs":[{"name":"stdout","text":" year births deaths clinic proportion_deaths\n0 1841 3036 237 clinic 1 0.078063\n1 1842 3287 518 clinic 1 0.157591\n2 1843 3060 274 clinic 1 0.089542\n3 1844 3157 260 clinic 1 0.082357\n4 1845 3492 241 clinic 1 0.069015\n5 1846 4010 459 clinic 1 0.114464\n","output_type":"stream"}]},{"metadata":{"tags":["context"],"dc":{"key":"2bc9206960"},"deletable":false,"editable":false,"run_control":{"frozen":true}},"cell_type":"markdown","source":"## 3. Death at the clinics\n<p>If we now plot the proportion of deaths at both clinic 1 and clinic 2 we'll see a curious pattern...</p>"},{"metadata":{"tags":["sample_code"],"trusted":true,"dc":{"key":"2bc9206960"}},"execution_count":87,"cell_type":"code","source":"# This makes plots appear in the notebook\n%matplotlib inline\n\n# Plot yearly proportion of deaths at the two clinics\n# ... YOUR CODE FOR TASK 3 ...\nax = yearly1.plot(x='year', y='proportion_deaths', label='clinic 1')\nyearly2.plot(x='year', y='proportion_deaths', label='clinic 2', ax=ax)\nax.set_ylabel(\"Proportion deaths\")","outputs":[{"execution_count":87,"data":{"text/plain":"<matplotlib.text.Text at 0x7f213d49ba90>"},"output_type":"execute_result","metadata":{}},{"data":{"text/plain":"<matplotlib.figure.Figure at 0x7f213d3d4b38>","image/png":"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\n"},"metadata":{},"output_type":"display_data"}]},{"metadata":{"tags":["context"],"dc":{"key":"0c9fdbf550"},"deletable":false,"editable":false,"run_control":{"frozen":true}},"cell_type":"markdown","source":"## 4. The handwashing begins\n<p>Why is the proportion of deaths constantly so much higher in Clinic 1? Semmelweis saw the same pattern and was puzzled and distressed. The only difference between the clinics was that many medical students served at Clinic 1, while mostly midwife students served at Clinic 2. While the midwives only tended to the women giving birth, the medical students also spent time in the autopsy rooms examining corpses. </p>\n<p>Semmelweis started to suspect that something on the corpses, spread from the hands of the medical students, caused childbed fever. So in a desperate attempt to stop the high mortality rates, he decreed: <em>Wash your hands!</em> This was an unorthodox and controversial request, nobody in Vienna knew about bacteria at this point in time. </p>\n<p>Let's load in monthly data from Clinic 1 to see if the handwashing had any effect.</p>"},{"metadata":{"tags":["sample_code"],"trusted":true,"dc":{"key":"0c9fdbf550"}},"execution_count":89,"cell_type":"code","source":"# Read datasets/monthly_deaths.csv into monthly\nmonthly = pd.read_csv('datasets/monthly_deaths.csv', parse_dates=['date'])\n\n# Calculate proportion of deaths per no. births\n# ... YOUR CODE FOR TASK 4 ...\nmonthly['proportion_deaths'] = monthly['deaths'] / monthly['births']\n\n# Print out the first rows in monthly\n# ... YOUR CODE FOR TASK 4 ...\nprint(monthly.head())","outputs":[{"name":"stdout","text":" date births deaths proportion_deaths\n0 1841-01-01 254 37 0.145669\n1 1841-02-01 239 18 0.075314\n2 1841-03-01 277 12 0.043321\n3 1841-04-01 255 4 0.015686\n4 1841-05-01 255 2 0.007843\n","output_type":"stream"}]},{"metadata":{"tags":["context"],"dc":{"key":"2da2a84119"},"deletable":false,"editable":false,"run_control":{"frozen":true}},"cell_type":"markdown","source":"## 5. The effect of handwashing\n<p>With the data loaded we can now look at the proportion of deaths over time. In the plot below we haven't marked where obligatory handwashing started, but it reduced the proportion of deaths to such a degree that you should be able to spot it!</p>"},{"metadata":{"tags":["sample_code"],"trusted":true,"dc":{"key":"2da2a84119"}},"execution_count":91,"cell_type":"code","source":"# Plot monthly proportion of deaths\n# ... YOUR CODE FOR TASK 5 ...\nax = monthly.plot(x='date', y='proportion_deaths')\nax.set_ylabel('Proportion deaths')","outputs":[{"execution_count":91,"data":{"text/plain":"<matplotlib.text.Text at 0x7f213cf51898>"},"output_type":"execute_result","metadata":{}},{"data":{"text/plain":"<matplotlib.figure.Figure at 0x7f213d744400>","image/png":"iVBORw0KGgoAAAANSUhEUgAAAYsAAAEACAYAAABCl1qQAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAIABJREFUeJzsnXmYXGWd7z9v7V3VVb13OvtONpIQQHYQGBdGx6CMCowLiDNeRdF7vaPiONcFR8flzqJXUHBAhEdFBHSQwVGURRCQhBBCEsgeku50kt6X2pf3/nGWrq6u5VR1nep09/t5nnq66tQ5VW93V53f+W3fn5BSolAoFApFMRxTvQCFQqFQnPooY6FQKBSKkihjoVAoFIqSKGOhUCgUipIoY6FQKBSKkihjoVAoFIqSKGOhUCgUipIoY6FQKBSKkihjoVAoFIqSKGOhUCgUipK4pnoB1aK1tVUuWbJkqpehUCgU04oXX3yxV0rZVmq/GWMslixZwtatW6d6GQqFQjGtEEK8bmU/FYZSKBQKRUmUsVAoFApFSZSxUCgUCkVJZkzOQqFQWCOZTNLZ2UksFpvqpShqiM/nY8GCBbjd7oqOV8ZCoZhldHZ2EgwGWbJkCUKIqV6OogZIKenr66Ozs5OlS5dW9BoqDKUoSiyZJpZMT/UyFFUkFovR0tKiDMUsQghBS0vLpLxJZSwURfmHh17hxp9sm+plKKqMMhSzj8n+z1UYSlGUQ31hwvHUVC9DoVBMMcqzUBRlOJokklBhKMXMYvv27Tz66KPm44cffphvfOMbtr3f9ddfzwMPPFDRsb/61a/YvXu3+fjSSy+dkgZkZSwURRmKppSxUEwJ6bQ9n7tUKjXBWGzevJmbb77ZlvebLLnGYqqwNQwlhLgC+A7gBP5DSvmNnOc/CnwcSAOjwEeklLv15z4PfFh/7pNSyt/auVZFfoZjSVR0e+bylV/vYvex4aq+5tp5Ib70jnVF9zl8+DBXXHEFZ511Ftu2bWPdunXcc889rF27lquvvprHHnuMz372s6xevZqPfvSjRCIRli9fzl133UVTUxOXXnopGzdu5KmnniKVSnHXXXdxzjnn0N/fzw033MDBgwfx+/3ccccdbNiwgS9/+cscOHCAgwcPsmjRIv70pz8RjUZ55pln+PznP080GmXr1q1873vf4/Dhw9xwww309vbS1tbGj370IxYtWsT1119PKBRi69atHD9+nG9961u8+93vzvv7SSm56aabeOyxx1i4cCEej8d87sUXX+TTn/40o6OjtLa2cvfddzN37lx++MMfcscdd5BIJFixYgX33nsv27dv5+GHH+app57in/7pn3jwwQcB+MUvfsGNN97I4OAgd955JxdffDG7du3iQx/6EIlEgkwmw4MPPsjKlSur9n+1zbMQQjiBW4G/BNYC1woh1ubs9lMp5Xop5RnAt4B/1Y9dC1wDrAOuAG7TX09RQ2LJNIlUhngqQzojp3o5ihnGnj17uPHGG3n11VcJhULcdtttALS0tLBt2zauueYaPvjBD/LNb36THTt2sH79er7yla+Yx0ciEbZv385tt93GDTfcAMCXvvQlNm3axI4dO/j617/OBz/4QXP/3bt38/vf/56f/exn3HLLLVx99dVs376dq6++ety6brrpJq677jp27NjB+973Pj75yU+az3V3d/PMM8/wyCOPFPVEfvnLX7Jnzx52797NPffcw7PPPgtoPS433XQTDzzwAC+++CI33HADX/jCFwC46qqr2LJlCy+//DJr1qzhzjvv5IILLmDz5s18+9vfZvv27SxfvhzQvKMXXniBf//3fzf/Jj/4wQ/41Kc+xfbt29m6dSsLFiyo+H+TDzs9i3OA/VLKgwBCiPuAKwHTn5JSZl/SBADjjHQlcJ+UMg4cEkLs11/vORvXq8hhOJo070cSKYK+ypp5FKcupTwAO1m4cCEXXnghAO9///v57ne/C2CevIeGhhgcHOSNb3wjANdddx3vec97zOOvvfZaAC655BKGh4cZHBzkmWeeMa++L7/8cvr6+hge1k4zmzdvpq6uruS6nnvuOR566CEAPvCBD/DZz37WfO6d73wnDoeDtWvXcuLEiYKv8cc//pFrr70Wp9PJvHnzuPzyywHNQO7cuZM3v/nNgBZqmzt3LgA7d+7kH//xHxkcHGR0dJS3vvWtBV//qquuAuCss87i8OHDAJx//vl87Wtfo7Ozk6uuuqqqXgXYayzmA0ezHncC5+buJIT4OPBpwANcnnXs8znHzrdnmYpCDMeyjUVaGQtFVckt5TQeBwKBSR1fCKuvWwyv12vel7J8b1tKybp163juuYnXvddffz2/+tWv2LhxI3fffTdPPvlkyXU4nU5SKa1a8W/+5m8499xz+a//+i/e9ra3cfvtt5tGqhpMeYJbSnmrlHI58DngH8s5VgjxESHEViHE1p6eHnsWOIsZio43FgpFNTly5Ih50vzpT3/KRRddNO75hoYGmpqaePrppwG49957TS8D4Oc//zkAzzzzDA0NDTQ0NHDxxRfzk5/8BIAnn3yS1tZWQqHQhPcOBoOMjIzkXdcFF1zAfffdB8BPfvITLr744rJ/t0suuYSf//znpNNpuru7eeKJJwBYtWoVPT095u+dTCbZtWsXACMjI8ydO5dkMmn+DqXWms3BgwdZtmwZn/zkJ7nyyivZsWNH2esuhp3GogtYmPV4gb6tEPcB7yznWCnlHVLKs6WUZ7e1lZzdoSiT4ehYf4XqtVBUm1WrVnHrrbeyZs0aBgYG+NjHPjZhnx//+Md85jOfYcOGDWzfvp0vfvGL5nM+n49Nmzbx0Y9+lDvvvBOAL3/5y7z44ots2LCBm2++mR//+Md53/uyyy5j9+7dnHHGGabRMfh//+//8aMf/YgNGzZw77338p3vfKfs3+1d73oXK1euZO3atXzwgx/k/PPPB8Dj8fDAAw/wuc99jo0bN3LGGWeY+YyvfvWrnHvuuVx44YWsXr3afK1rrrmGb3/722zatIkDBw4UfM/777+f008/nTPOOIOdO3eOy9dUBSmlLTe0ENdBYClaiOllYF3OPiuz7r8D2KrfX6fv79WPPwg4i73fWWedJRXV5ZfbOuXizz0iF3/uEfnng31TvRxFldi9e/dUL0EeOnRIrlu3ruLj3/jGN8otW7ZUcUWzg3z/e+O8W+pmW85CSpkSQnwC+C1a6exdUspdQohb9MU9DHxCCPEmIAkMANfpx+4SQtyPlgxPAR+XUqo4iI386qUu1s0LsXJO0Nw2PmehPAuFYjZja5+FlPJR4NGcbV/Muv+pIsd+DfiafatTZHPzQzv46zMX8LV3rTe3DauchcImlixZws6dOys+vljyt5a88sorfOADHxi3zev18uc//3mKVmQfShtKQSqdIZbM0DeaGLc9O8GtchYKxUTWr1/P9u3bp3oZNWHKq6EUU09Y9xp6R+Pjtg9HU3ic2kckqmTKZxSygrJPxfRmsv9zZSwUZj6iLzzRs5jToNVzh+PKWMwUfD4ffX19ymDMIqQ+/Mjn81X8GioMpTBDTBM8i1iS9qCPzoGoSnDPIBYsWEBnZyeqN2l2YYxVrRRlLBSM6l7DSCxFLJnG59ZkuAxjEfC4VIJ7BuF2uyseramYvagwlIJIVvK6PysUNRRN0lDnps7jVJ6FQjHLUcZCwWiWscgORQ1HU4R8LgIep8pZKBSzHGUsFONCTEb5bCYjGY5pnoVfhaEUilmPMhaKcZ5Fj+5ZjCZSSAmhOjd+FYZSKGY9ylgoxjXcGZ7FUERryAv53Pi9yrNQKGY7ylgozKY8n9th5iwMXahQnZuA8iwUilmPKp1VEI6n8HuctNR76DOMhS5PHqpzUacS3ArFrEd5FgoiiRQBr4vWeq/ZxW3oQjXUuQl4XEruQ6GY5ShjoWA0nibgcdIS8NIzkhOG8rnxe51KSFChmOUoY6EgHNc8i7agx/QsDHnyBr8bv9tFPJUhnVFaQgrFbEUZC4VpLFoCXvrDCa3HIppECKj3uAh4NfkPleRWKGYvylgoCCdSWhiq3kM6IxmMJhmKJgl6XTgcAr9Hq4NQ5bMKxexFGQsFkXjaTHCDJvkxHEvR4HcD4PdonoXKWygUsxdlLBSMxlPUe1201HsA3VhEk4R8442F8iwUitmLMhYKvc/CRZvuWfSNJkzFWYCAV4WhFIrZjq3GQghxhRBijxBivxDi5jzPf1oIsVsIsUMI8QchxOKs59JCiO367WE71zlbSGcktz6x3yyLBU0wMJJMU+910jIuDDXmWdQZYSiV4FYoZi22GQshhBO4FfhLYC1wrRBibc5uLwFnSyk3AA8A38p6LiqlPEO/bbZrnbOJlzsH+fZv9/CHV0+Y26LJNFKC3+uisc6N0yEmehZ6gjuqPAuFYtZip2dxDrBfSnlQSpkA7gOuzN5BSvmElDKiP3weqHzmn6IkXQNRAPrDY56FkbQO6JVPzQGPnrNIEarTjIRKcCsUCjuNxXzgaNbjTn1bIT4M/CbrsU8IsVUI8bwQ4p12LHC2cWxQMxYDWdPwDBHBer2XoiXgoXsoRjSZVgluhUJhckoICQoh3g+cDbwxa/NiKWWXEGIZ8LgQ4hUp5YGc4z4CfARg0aJFNVvvdKVLNxb9kSxjoXsLRi9FW9DLwd5RALN0ViW4FQqFnZ5FF7Aw6/ECfds4hBBvAr4AbJZSmjM9pZRd+s+DwJPAptxjpZR3SCnPllKe3dbWVt3Vz0AMz6J/dKKxqNcNQkvAQ6cerjI8C6/LgRCqg1uhmM3YaSy2ACuFEEuFEB7gGmBcVZMQYhNwO5qhOJm1vUkI4dXvtwIXArttXOuswDAC4zyLxFjOAqCl3ovUJaCMBLcQgoDHpWTKFYpZjG1hKCllSgjxCeC3gBO4S0q5SwhxC7BVSvkw8G2gHviFEALgiF75tAa4XQiRQTNo35BSKmMxSfLlLEZ1AxDQ8xJGFzdgJrhBy1tEk8qzUChmK7bmLKSUjwKP5mz7Ytb9NxU47llgvZ1rm22MxJIMx7ST/UCWZxGJ53oWHvM5w7MAzVgoz0KhmL2oDu5ZwrHBGABLWvwMRJJkdLnxUcNYGAnubM/Cl20sXCpnoVDMYpSxmCUYIajT5zeQzkizi9uocDJkyLM9i1CWZxHwOlU1lEIxi1HGYpbQqRuL9fMbAOjX8xbheAqvy4HLqX0UDMkPj8uBz+00j6/zuMyeDIVCMftQxmKWcGwwitspOK0jCIzlLUb1wUcGLQHNs8gOQYGWAI+qMJRCMWspaSyEEAEhhEO/f5oQYrMQwl3qOMWpRddAlLkNdbQGNM/BkPyIJNJmCArA53YS9LpoqBtf++BXpbMKxazGimfxRzTpjfnA74APAHfbuShF9Tk2GGVeo4+mgGbnjfLZ0XjKTG4btAa94/IVoFVDqQS3QjF7sWIshC72dxVwm5TyPcA6e5elqDZdg1HmN/pp1sNMfbqxiCTGh6EANixoYO3c0LhtfpXgVihmNVb6LIQQ4nzgfWhif6A12SmqQDKdwe20N3WUTGc4MRxjfqOPOrcTr8uRlbNIj+unAPjONROUVfC7XcRTGVLpjJkMVygUswcr3/pPAZ8Hfql3YC8DnrB3WbODRCrDuV//A7c9ud/W9zk+FCMjYX5THUJoMuTZ1VBG93YxjLxGJKm8C4ViNlLSWEgp/yil3Cyl/Kb++KCU8pP2L23mMxRN0h9O8G+P7WXfiRHb3sfosZjXWAdAc8Bj5iwi8YlhqHz41QAkhWJWY6Ua6jQhxB1CiN8JIR43brVY3EzHSBgn05LPPbiDtN5VXW0MafL5WcaiP6t0tt6SsVADkBSK2YyVnMUvgB8A/wGoy8oqYpSivnXdHH676wT3PneY6y9cWvX3yfUsmvwejvZHkFISSaRNQ1AMNQBJoZjdWDEWKSnl921fySzEkAd/37mLiSYzfOu3e3jT2jksaPJX9X26BqO01nvMjuzmgIe+cEJLWGekpTCUGoCkUMxuCoahhBDNQohm4NdCiBuFEHONbfp2xSTJnn/99XedDsA//monUlY3HNU1GDO9CtA8i5FYiqGo1phnJcFdZ4ShVK+FQjErKXZJ+SIgAaE//kzWcxJYZteiZgvZIn4Lmvx85q2r+Mqvd/Of24/xzk3FxpWXR9dAhNPmBM3HzXpjnjEMyZJnoSe4I6qLW6GYlRT0LKSUS6WUy4A1+n3zBqyt3RJnLrny4B88fwmbFjXylV/vom80XuxQy0gpOZbjWTTrkh+dAxGAshLcqotboZidWOmzeNbiNkWZ5A4ecjoE3/zrDYzGU9zySHUGAw5EkkSTabMSCjAlPwzPwl+WsVCehUIxGymWs+gQQpwF1AkhNgkhztRvlwLVzcDOUgzJ7+xqpNPmBLnx0hX85/ZjPPHayUKHWia3EgowJT+O9huehZWmPJe+ZuVZKBSzkWKXlG8FrgcWAP+atX0E+Acb1zRrCMdTuBwCr2u8zb7xsuX8YutRfvrCES5b3T6p98jtsQBo9mvG4ohuLKzkLLwuBw6hmvIUitlKsZzFj6WUlwHXSykvy7ptllI+ZOXFhRBXCCH2CCH2CyFuzvP8p4UQu4UQO4QQfxBCLM567johxD79dl1Fv90pjtHjIIQYt93rcrKoxc9g1qzsShnV526HsiTHG3VjYSa4PaWNhRBCyZQrFLOYkmcJKeWDQoi3oynN+rK231LsOCGEE7gVeDPQCWwRQjwspcwOxr8EnC2ljAghPgZ8C7haL839EnA2WuXVi/qxA+X9eqc2xbqnG+rcHO6NTPo9orqWU13W1DuPy0HQ6zJDVFY8C1Ay5QrFbMaK3McPgKuBm9DKaN8DLC56kMY5wH5dSyoB3Adcmb2DlPIJXf4c4Hm0kBdoIbDHpJT9uoF4DLjCwntOKyKJVMHkckOd2+yDmAwx3Vj4cnopmgIeUrq8iJUObmM/leBWKGYnVqqhLpBSfhAYkFJ+BTgfOM3CcfOBo1mPO/Vthfgw8JsKj52WhOPpgg1xIZ+b4Vj1jEW2ZwFjSe58OZNC+D0u5VkoFLMUK/GHqP4zIoSYB/QBc6u5CCHE+9FCTm8s87iPAB8BWLRoUTWXVBPCRRRfG+rcRBLpSc+7iCbTOB1iwmsYxiLgdU3ImRQioAYgKRSzFitnoUeEEI3At4FtwGHgZxaO6wIWZj1eoG8bhxDiTcAXgM1Syng5x0op75BSni2lPLutrc3Ckk4twom0Kf2dizHWdHiSoahYMjPBqwBN8gOsSX0Y1HlcZrmvQqGYXViZZ/FVKeWglPJBtFzFainl/7Hw2luAlUKIpUIID3AN8HD2DkKITcDtaIYiu6ngt8BbhBBNQogm4C36thlFOJ4q2ONgTK+bbN4imkybAoLZGJIfVpPboBmWiJIoVyhmJVYS3H4hxP8RQvxQv/JvF0L8VanjpJQp4BNoJ/lXgfv1SXu3CCE267t9G6gHfiGE2C6EeFg/th/4KprB2QLcom+bURRLcBulrpM1FrFEmjrPxH9zkx6GstK9baDlLJRnoVDMRqycKX6EJip4vv64C23GxSOlDpRSPgo8mrPti1n331Tk2LuAuyysb9pSLMFteBbDscldyUeTaXyuPJ6FHoay0r1toEpnFYrZi5WcxXIp5beAJIBe6motI6ooSDojiSbTBcNAIV91wlCxZNqUF8/GTHBbaMgzaKn3MBhNqi7uGcwrnUN8/qEdZGya2qiYvlgxFgkhRB1acxxCiOVAdSRRZzHGFXqhk3VDlRLchXMWY9VQVlk1J4iUsO+kffPCFVPLf27v4mcvHKW3SqrHipmDFWPxJeC/gYVCiJ8AfwA+a+uqZgFG7N9fIAwUqlqCu0A1lGksrIehVs8NAfDacWUsZioHekYBODmijIViPFbkPh4TQmwDzkMLP31KStlr+8pmOMYsi0JyHz63E4/LMenGvFgijS/knbDdyFmU41ksavbjczt4rVsZi5nKgZ4wACdHYkDD1C5GcUpRTKLckCQ/E61kths4BizStykmgTFxrlCfBWihqEn3WaTSeT2Lhjo3y1oDrMqaoFcKp0Nw2pwge04MT2pNilOTWDLNUX0g1snhU8eziCRSfPyn2zg+FJvqpcxqil1W/ov+04fWXf0ymmexAdjKWHWUogLMKXlFwkAhn4vh6CSroRL5E9wOh+Dxv7+07Ndb3RHk8SrM2VBMLduPDvLQtk6+snmd2cF/qDeMMf69nDDU/VuPct7SFha12DPmZu+JUf5rRzd/sbqdq85cUPoAhS0Ukyi/TJco7wbO1DulzwI2kaebWlEepRLcUB0xwUIJ7kpZ1RGidzRBj4ppT2seefkY9zz3Okf7o+Y2I18BRhiqNOF4is8+sIO7nz1c7SWaGNV3Kuk+tVhJcK+SUr5iPJBS7gTW2Lek2YEhm1HUs6iCsYhV2Vis7tDCVntUkntac2xIMxK7u4fMbftPjiIELG7xWw5DdeuhoYO9oyX2rBxDDLN3dPLzXRSVY8VY7BBC/IcQ4lL99kNgh90Lm+mEc+Zv56OhbnLKs6l0hmRa5s1ZVIphLF47bn/e4rt/2Mff/+Jl299nNtKlD77adWzs/3igJ8zCJj8Lm/yWw1DdutE5qCfG7cA0FsqbnVKsGIsPAbuAT+m33fo2xSQwjEWxBHfINznPIpbKABPlySdDS72X1npvTcpnXzoywAuHJq/yIqVkR+egmSdSQNeg5hHszjYWJ0dZ3hagPei1HGbs1l+ncyBCPGVPs6YxwKs3rDyLqcRK6WwM+Df9pqgSRp9FMdVXoxpKSmlZRjwbI9abO/hosqzuCNYkDBVLZiZ1gpdS8sSek/z77/exo3OIz7x1FR+/bEUVVzg9iSXTZvzf8CwyGcnB3lEuXNGCwyHoGYlb+twZ4ayMhNf7IpxWRnWdVaLKszglqHxQgmJShOMpvC4HriKzKkJ1LjKSik+Y5pQ8i8ONrLK6I8jeEyOkbZaEiKXS5gzxso9Nprn69ue54e6t9IcTeJwO+lTMGxjLM6zuCHJ8OEbfaJyuwSixZIblbfW0B30k0hkGI6W92uxy1oM99uQtVIL71EAZiykinCg8+MhgsmKC5pS8KnsWqzqCxFMZDvfZF6cGzbNIpDMVhTf2HB/hhcP93HT5Cp74+0tpCriVCKKOMXv9zWvnALC7e9ishFreXk97UGvitJK3ODYUY1lbABhr6Ks2cT2c2hdOKM2qKUQZiykiHE+XlNowZ1pYuMLLR7TASNXJsrpDk/2wOxQV19cfjpdvLIyr0L9YMwe300FADW4yMZLbhrHYdWyY/Sd1Y9GWbSxKl892D0ZZ0VbPnJDXtiS34VmkM5LBKsylV1SGlXkWpwkhfiiE+J0Q4nHjVovFzWTC8VRJxVdDebbSiijjS1ZtY7FyTj0OAa9121sRZXhGlYSijARta70xt0MNbjLoGowihGb05zfWsfvYMAd6wjQHPDQHPLSHfIC1Lu7uoRjzGutY1lpvW/mscdEDKhQ1lVgRBvoF8APgh4C6NKsSkURheXKDyYoJGl8yb5WNhc/tZElrwPaKKKOaq5KcjXFSaa3XrpL9HhdhFYYCNGPRHvTicTlYMzfErmNDtAS8LNfDSVbDUMOxJKPxFHMbfCTTGR7Z0V1xMUYxxhmLkbgtSXRFaawYi5SU8vu2r2SWMRpPEfRZzFlUaCxiyeqXzhqs7giys6tGnkVFxiJB0OsyGxIDHid9qvQS0HIW8xrrAFg3L8QfXjvByZE4b18/F9B6fwIeZ8kwlJHcnttYh8vpYCiapD+coKV+onDlZIhlGYse5VlMGVZyFr8WQtwohJgrhGg2bravbIYTSVgIQ03Ss7ArwQ1aCONIf8TsF6k2UsosY1H+798zGqctOHbS8ntdtq11unFsMMp83VisnRdCShiJpVjRXm/u0x7ylfQsjET5vAafmeQ+2Fv9vEUsmTY9RNXFPXVYMRbXAZ8BnkUbr/oimpCgYhJoCe7ixiLodSFE5Z6F4b773NWvY1ipn1gO2XByAEimJUbhy2gFCe6ekbh5ggHNs1Dzw7V+imODMdNYrJsXMp9b3jZmLNqCXnpK5CyMEtyOBh/LW7Vj7SifjSbSdDR4cTmEyllMIVaa8pbWYiGzDa10tvgVv8MhCHpdFZfO2pXgBljcol1JHu4Lc/r86s89iGWVy1aS4O4djZvSJKCFVpRnAb3hOIl0hvlNmrGY31hnClZmG4v2oJedXUOFXgbQKqGEgDkhHw4h8LgctlRERZNp/G4XLfUe1Zg3hViphnILIT4phHhAv31CCOG28uJCiCuEEHuEEPuFEDfnef4SIcQ2IURKCPHunOfSQojt+u1h67/S9CBiwbOAyYkJGifcagoJGizW5ahf74tU/bVhfJy6kjBU7wTPwkUkkUbK2V2nf0yX55jXoBkLIQRr54bwuhymAQFoD5YOQ3UPxWgPenE7HTgdgiUtflt6LWLJDD6Pk9Z6r/IsphArCe7vA27gNv3xB/Rtf1vsICGEE7gVeDPQCWwRQjwspdydtdsR4Hrg7/O8RFRKeYaF9U07Eimt2ayY1IfBZAYgxRJphABvlTu4QbtSbw96OWxTGCquJ+ehdBhqKJo0iwEA4qk0w7EUbfXZOQsnqYwknsrYYjynC0aPhZHgBnjfeYs4c3EjTsdYFVN7yEskkWY0nio4zbF7KMbchrHXWdZaz14b5rPHkmnmhLy6sVA5i6nCylnkDVLK66SUj+u3DwFvsHDcOcB+KeVBKWUCuA+4MnsHKeVhKeUOIJPvBWYqRidxMRFBg8nMtIgm0/hczqqXMhosaQnUxrMoEoZ6+eggm275HftOjJ2kjBNKa3C8ZwHM+ryFkZTO9iL+asM8PvPW1eP2M8tnhwtXRB0bijKv0Wc+XtYW4EhfhFRa+zpXy4szZrIoz2JqsWIs0kKI5cYDIcQyrPVbzAeOZj3u1LdZxSeE2CqEeF4I8c4yjjvlMTqJC12xZRPyVS5THk3mn5JXLRa3+G2T/IiN8ywK//6HesNkJOw8NhZf7x0Z32MB4Nf/DjM1b7H72LCZoypG12CUeq+LUImy7fag3phXIBQlpaR7MEZHaMzoLG0NkMoOIcKCAAAgAElEQVRIjg5EGY2nuPr25/nCL1/Je3w5RBPaaODWoIe+0cSsDyVOFVaMxWeAJ4QQTwohngIeB/63vcsCYLGU8mzgb4B/zzZYBkKIj+gGZWtPT08NllQdTHnyEglumJxnEUtmbEluGyxpDXByJG7LCTg7wV1M7qNf75043Dvm4Yw15HnMbUZ+aCZ6FiOxJFfe+gz3Pn+45L5detlsKW+zPVS8MW8omiSaTOd4FlqCfPexYT589xZeONzPn6sgMW8M8Gqr95JIZyou+FBMjpLGQkr5B2Al8EngJrTJeU9YeO0uYGHW4wWUMY5VStml/zwIPIk2zjV3nzv0ca9nt7W1WX3pcfSOxrnqtj/xm1e6Kzq+EszBRxbCUKG6yudwa+67ffJfdia5s8NQI0WM0UBENxZZHo5hLMb1WRiexQzs4j7aHyWZluw9UbpsVWvI85Xcr1QYyiibzc5ZGB3gNz+4gxcO97Nmboij/ZFJi//Fkhnq9AQ3KMmPqaLgmUQIcbn+8yrg7cAK/fZ2fVsptgArhRBLhRAe4BrAUlWTEKJJCOHV77cCF6INXao6dW4n244M8nq/PbH3fJizLCyEoRrq3ESTaRKp8tM6sUR1R6rmskQvn33dhlCUEYYK+VyMFgnDjXkWY2voyROGMj2LCno2TnU6B7TPrpVig66s7u1iNNS58bgcBYcgGRPy5mYZnka/pi01Ek/x9Xet52/OWUg8lZlU13UqrRWD+FxZxkKVz04Jxc5Wb0QLOb0jz3MSeKjYC0spU0KITwC/BZzAXVLKXUKIW4CtUsqHhRBvAH4JNAHvEEJ8RUq5Dm3G9+1CiAyaQftGThVV1fB7nHhcDgZqKAUxak7JK30iz+7izr5StkI0mbY1DGV4Fodt9Cxag96iYSjDszjUGzZ1iXKlPmBmexadeoVTqfxROJ5iMJIcl9wuhBCCtnpvwTBUbgmuwY2XLifkc/PeNyzkyT0nATjSH2FOqLQ3kw9z2qPHQWtQCyuqiqipoaCxkFJ+Sb97i5TyUPZzQghLjXpSykeBR3O2fTHr/ha08FTucc8C6628x2QRQtAS8JhXqLXAqIaykuAem2lRvrGIJa31clRK0Oemtd5jk2ehG4t6r1numQ9joNFwLMVAJElzwEPPaHxcJRRkV0PNXGPRO5pgJJYk6MvfBmVWQlnwLEDLWxTSh+oeiuJ0iAmfyb+9eJl5f7HpeUZ4w5LKFIJiWTL7Kgw1tVgJaD+YZ9sD1V7IVNLkr62xMPoGrCS4DZnySpLc0aT9PQWLWwK2SH4YV5St9R5GioShBiIJ03syrqx7RuLjeixg7G9dyWyMUx0jDAXF80dd5RqLoLegTHn3UIw5Qe+43oxctES65llUijka2O2kye/BIZSxmCqK5SxWCyH+GmgQQlyVdbseqMynPEVpDnjoj9TQsygrwV258qxRRWIndvVaxLM8i3CRzuv+cJINCzS5ESNm3zsaN0MWBjPZszg6MCYMWMxwm6Ejy8aicBd392CMuSVex+NyMK+hjqOTMBbmaGC3E6dD0BxQvRZTRTHPYhXwV0AjWt7CuJ0J/J39S6sdzQFPTXMWYb2z2ko+oaFOO8lV5Fkk0tTZWA0FsKTFz/HhmKUa/3LIDkOlM3Jc34WBlJKBSIKNCxtxiCxjkSP1AWN/65nqWVywvAUoXmzQNRjB6RBmpVMp2oNehqLJcZVpBt1DUeY2lL5mXNhcNznPImfaY2u9h54RlbOYCorlLP5TCPEI8Dkp5ddruKaa0xzw1HTWQTiewu924ijiwhuEJjGHO5ayN8ENsLhVi0sf6Y+wqqN6Q2liyQxCQJNf+/1H4skJDYbDsRTpjKQ96GV+Ux2H+iKm1EeusXA4BH6Pc8Z5FkPRJCOxFKfNCTIn5OVQb+ETc+dAlI6QD5fT2gVEh24Mjg1GzR4K0BvyhmK8ZV1HyddY1OzniT2V90CZM1k8hrFQnsVUUfRTI6VMAzOqezofTX4PI7EUyXRtVEciiZTlxLM5WrVCz8JnYwc3aJ4FlK7EKZeYLlViJGvzeQSGN9gc8LCkJcDh3rBZKZOvGMA/A+dwG/mKhc112t+gyP/h1e7hsgz6Sn0i3b6T4/s3+sMJ4qkMHRYqnBY1++kZiVfseUazwlCgeRbKWEwNVi4x/iSE+J4Q4mIhxJnGzfaV1ZBmvdN3oEZ5CyuzLAx8bidel6NsY5ExRPNc9ie4wVqNfznEUlpDofF3yqcPZeSZmgIelrZqJ8p8Uh8GgRk4h9uohFrQ5Gdpa6BgGCqaSLP/5Oi4+RWlMGaW7M0Zn2uElRZYKMFd2KxdTBwdqCwUNZbg1k5VhmehJD9qj5UzlqH8ekvWNglcXv3lTA3Nfs1Y9IcTpiaOnYTjKUs9FgaVSH7EU+Pdd7toqHPTHPBUvdcipldyGeXFI3n0oUzPwq95FiOxFHt1QcFsqQ+DmehZHM06cS9uCRQsn33t+DAZCevmWZ89EvC6WNBUx94cz+LVbu1vvLqjtOFZpBuLI32RimZnx3JzFkEvsWSGcCJtqfRcUT2sDD+6rBYLmUqaAtoXq1bls+EywlCg5S3KFRPMTQzayeIWf9V7LYxKLmNOeb4wVH92GKpVOyltOaxpEeX1LGZgzqJzQBMGbKhzs1T/GxzujbB+wXijsOuYNi+9HM8C4LQ5wXGKvqCFs+p1Q1IKs9eiwiR37mjg7C5uZSxqi5XhRw1CiH81BPuEEP8ihKj+aLQppCWgfQAHwpUJ9pVLOJ62NMvCoBLPopbGYklLgIM94UlrAGUTS2bwurLCUPk8i8j4nAXA1sMDQIGchdc146qhOgeiLGjShAGzpxfmsuvYMA11bksn+GxWzqnnQM/ouHzeq93DrO4IWirQaPK7qfe6Ki6fzVcNBarXYiqwkrO4CxgB3qvfhoEf2bmoWmN6FrXKWZTrWfhc5RsLPdzitbl0FuDcpc0cH47xiZ9ty1tmWQnxVHpcGCpvziKcxONy4Pc4Wdjsx+kQHOwNT5D6MJiZnkWEBU2aR7GkSP5o97Eh1s4NlT3bZNWcIMm0ND3HTEby2vER1sy15qEIIVjY7K+4fHZigtvo4lbls7XGyplkuZTyS/oQo4NSyq8Ay0oeNY1oMnIWNfoARuJpSw15BnNCPjoHomVduefGeu3k6jcs5AtvW8Nvdh7n6jueLyg+Vw4xXTHXNBZ5w1Bxmv0ehBC4nQ7zqjlX6sPA75lZnoWU0vQsQAvVdIR8HMrxLFLpDK8dHyk7BAWYeQZD0bZTn1Vh1VgALJpEr0XMuOjRpz02B2pbjKIYw4qxiAohLjIeCCEuBAqL9UxD3E4HIZ+rhtVQKUtSHwZnL2lmMJJkzwnrIytzY712IoTg7y5Zxg/efxZ7j49w1ff/NOkmPSPB7XNr853zhaH6w0maAmOJbOPKOl9yG7RqqJkkJDgUTTIaT40LLWn5o/En5gM9YeKpDOvml28slrfVIwTs0SuiXj2u5T7WzLWerF7U7K9YqjyW0mayGB6RkcMqNj1RYQ9WjMXHgFuFEIeFEK8D3wP+h73Lqj3NNRITlFISThSea5yP8/Xu3OcP9lk+ppY5C4O3ruvga+86naP9UQ70lJ6tUAyjz0IIQb3XlffkMBBJ0BwYq/oxej4KCS76Pa4ZJVGeXTZrsLQ1MCEMtUufInh6GZVQBnUeJ4ub/ezTZ2u/2j2MEJTVr7Go2V+xVHk0MX7aY8DjQojiM04U9mBl+NF2KeVGYAOwXkq5SZ+bPaNoqpGxiCUzZKS1+dsG8xvrWNTs57kDZRiLxPhYb61Yond0TzYUZfRZgKbOmy8MNRBOmCHE7PfOVwkFWs4ikc5UNBvkVMRoyMv2LJa0BugLJ8ZVz+3sGsbndozrwi6HlXOCZhjq1e5hlrYEyvr8Gr0WlYSitDnyY6cph0NQ78l/8aCwFyvVUC1CiO+iTat7QgjxHSFEi+0rqzG1kik3wiCBMsJQAOcta+bPh/otu/KGamutjYWh9jqZgTcwFoYCw1jkCUNFEmYMGywYC92bq7aO1VRheBYLszwLw7t6PUv2Y9exIVZ3hIoqxBbjtDn1HOoNE0+lebXbenLbIFuqvFyiyYkqBPU+V1ElYoU9WAlD3Qf0AH8NvFu//3M7FzUVNPk9NclZGGGQchLcoIWihqJJdncPW9rfSAzWImeRjXGinrRnkaWYW+9zmQOjDFLpDEPR5DjPYmW7Fl8vJMFtGOiZkrc42h8h6HPR4M8KxekG00hySynZ3T1cUXLb4LQ5QdIZyc6uIY70R8rKV8DkpMrjeQZ4aRcPM+N/OJ2wYizmSim/KqU8pN/+CZhj98JqjSEmaLeMgPEhL9ezOH9ZK2A9bzEVOQvQjFPQ65q0sYgnM2bZbyBPGGoomkRKxnkWC5r8/OrGC3nHxnl5X9NfZZnyVDrDPz2ym1ctGvBqo1VC+cdtW9ysX8XreYuj/VFGYqmyOrdzMSqiHt5+DLDWuZ3NZKTK8017zHfxoLAfK8bid0KIa4QQDv32XrRRqTOK5oCHRCpjzse2i7EwVHmeRUeDj6WtgXHGQkpZUPxwrD7d/j6LXNqCk1MGTWekOXcZIOidOId7IEsXKpuNCxvxuPL/zoEqD0A60BPmP545xHt+8Bx/3Fu5smqlZJfNGtR5nCxq9nP/i0c50DNqJrcn41ksawvgdAge2dENwJoKXqtSqfJonjnyQZ+bEZWzqDlWziR/B/wUSOi3+4D/IYQYEUJMzSWVDRgnHbvzFoYgYKHRl8Uw8hbpjGQ4luTaHz7Pe29/Lu++5tAYm4UE89Fa752UZxFPjU/O5ws79Ovd9s3+/GWy+TA8i2qFoQyD5XIKbrh7C/dvPVqV17WC1mMRyduR/W9Xn0EknuZdt/6Jn205itMhJiUf73U5WdLipy+cIORzMc/CHItcFjb5K/QsJk57DHpVzmIqsFINFZRSOqSULv3m0LcFpZRFLzGEEFcIIfYIIfYLIW7O8/wlQohtQoiUEOLdOc9dJ4TYp9+uK/9XKw/jpGN33sK4Igr5yte1OW9ZCyOxFH/c28M1tz/P8wf7OXAyf4lqNJnG63JYkmSoNm1B76QS3MYMA19WGCrXGzCMelPAutE1p+VVybMYjGgnrNvffxbnL2/hsw/s4A+vnqjKa1t573AinTc/c9biJn718QvpaPDxx709rGyvn3ShgxGKWlNBFzhonnHvaJx0mb0W8WR6Qt5N5SymBksxCiHEZiHE/9Vvf2XxGCdwK/CXwFrgWiHE2pzdjgDXo3ku2cc2A18CzgXOAb4khGiy8r6VYsiU2z0EybgiqsSzOH+ZVoT2d/ds5WDvKBcsb2E4liKVJxQVS0z8ktWKtuDkPItYjsSDEaPOrgQzjLqh62UFf5UT3ENRbQ0Lmv3ced0bCHicPL2vtyqvXQojzDenwEyJhc1+HvzYBVx15nyuecPCSb9ftrGohPaQj4yEvjIvIrScxfjTVL1Plc5OBVZKZ78BfArYrd8+JYT4ZwuvfQ6wX5cIMcJXV2bvIKU8rPds5J7t3go8JqXsl1IOAI8BV1h4z4oxPQu7w1D6hzxYgWfRHvKxak4Qv8fJT/72XN6yds6418wmqje1TQWt9dowqUp1omI5+Zagd2L4yPAsGv0VeBZVyksZnkWT343H5WDN3JCZI7CbvizF3UIEfW7+9b1ncP2FSyf9foaxWFupsdAbJU8Ml28sJuYsNKn5cr0UxeSwcsZ6G3CGlDIDIIT4MfAS8PkSx80HsoO4nWieghXyHTvf4rEVUaucxUgshcfpqDgscNeH3oDLIZgT8nG0X6uzH8zpNwAtlDOVngVoV7+51TpWMMNQurEzigHC8bTpkfWHEwQ8zrL+jqZnUaUQxkAkicfpMKt11s4L8dC2LjIZaXv4b8CCsagmF65o4e3r53LZ6vaKjjc8oBPDMdZjvTJLmyM/MQwFWmVhQ135HrqiMqyWyjRm3T9l5MmFEB8xpNN7eiZXjRLyuXA5RA2MRbIir8JgfmOd+cUzrqoHIhOTffmuyGqFYSwqDUXFjAS3ZywMBeNlygfCiQmVUKXw63+PankWQ9EEDX63GcNfOzfEaDxV8VS4crDiWVSTRr+HW993ZkEplVIYnsXJMj4T5rTHPJ4FoPIWNcaKsfhn4CUhxN26V/Ei8DULx3UB2cHSBfo2K1g6Vkp5h5TybCnl2W1tbRZfOj9CCJoC9jfmjcRSkzIW2TTqoTMjdp5NLE+st1ZMVkY6t5LLCENll0vmdm9bweV04HU5qpazGIwkacoKgxm9DMagITsxPIumMqrBppI2MwwVs3xMvIAKgeFdqrxFbSl6NhHaJdMzwHnAQ8CDwPlSSisd3FuAlUKIpUIID3AN8LDFdf0WeIsQoklPbL+FGvR2NPvtl/zIN/KyUhp1F3wwn2eRpz69VkzWs4jnqYaC8f0RubpQVgl4qycmOBBJ0FiX1UE+px6nQ7C7BsaiL5wg6HUV7Ck51XA7HbTWe8ryLMYaS3MS3ObFgyqfrSVFP2lSa2d+VErZLaV8WL8dt/LCUsoU8Am0k/yrwP1Syl1CiFuEEJsBhBBvEEJ0Au8BbhdC7NKP7Qe+imZwtgC36NtspSngtr/PooqeRZNZ7jvxSxNLTYz11gqjQqniMFRuNVSeaXmVeBYAfk/1ZMoHI8lxUhs+t5MVbfWWJVkmw0AkYVbwTRfagj5OluFZRAvI7BthSaU8W1usnLW2CSHeIKXcUu6LSykfBR7N2fbFrPtb0EJM+Y69C21KX81oCXh57bi9X/SRWJK21srUP3MJ+lw4BAzlCZ1FExMF2GqFx+Wgye+uuIs7ltOUZxjX7DDUQDhZmWdRRZnyoWiSDTnVWOvmhXi2DHXgSumv0LOaSuaEvGV5FrkXDQbBItMTFfZhxYc9F3heCHFACLFDCPGKEGLGSZSD5lnku0qvJtXMWTgcgoa6/GuOJTNT5lnA5Lq48zXlwVgVUzyVZjSeGjfLwir+Kg5AGogkzLyRwdp5IY4Px8ruJyiX/nCClholt6tFe9BbVs6ikMy+mbNQnkVNsXLWeqvtqzhFaNaVZ9MZWbGccyk0Y1G9cr9Gv4fBPPO5o8n0lOhCGUymizs3wW1oOhknB7O/oYKTZcDjqko1VCyZJpbMTCjdNPoQdncPc/HKyRVdFKM/nKi4QW6qmBMa6+K28v0qNBrYDEOpnEVNKXg2EUL4hBD/E/gMWkNcl5TydeNWsxXWkOaABym18IIdpDOS0Xj1PAuAhjo3g3nCULE8ap21ZDJd3GOehbZ+r8uJx+UwY9RGXqkcXSgDv8dZlT4L4zOSGwpaq4vs2ZnkllJOW8+inC7uQjkLv9uJECoMVWuKXXr+GDgbeAVNsuNfarKiKWSyjXn3vXCET9+/veDzxpVxNY1Fk989oRpKSplX2rmWtNZXrjxrXFF6syp96r0u8yRvlo1W4ll4XVUJQxkl1rkd5I1+D/Mb62wtn40k0sRTmYp+/6mk3WzMs/a5MC4acj/HxrQ8leCuLcXOWmullOsBhBB3Ai/UZklTh1FdU2mvxaM7j/Pi4X54b/7nDbc5VOUw1P6cedfxVAYpmbIEN2ieRSSRJhxPlS3HHkul8eSIIGbP4e6PVN6Q5vc4q5LgNgx0Y54O4jVzQ7ZWRPXXuCGvWhjNpCdHYljp7S0msx9U+lA1p5hnYV6u6mWwMx7jy9dXYTPZgZOjhBPpgppIw9HqexZaGGq8ZzGV8uQGbZOYmBdPZsbNXQZjAJL29zOuTCvts6iGZ2EaizxrWDsvxMGeUdvGt04mDDeVlKsPFSsyR14brTorTkunDMWMxUYhxLB+GwE2GPdn0hyLbCbjWUQSKboGo0WPn4zibCGa/JpoX7byrOm+T6Fn0ZqlD1UusXzicbqxiCXT3PXMIVbNCdJaQZ+B3+MklsxMWoRusEAYCrTy2YzEtjJs01hMuz4LQ/LDWkVUsWmPSqa89hQ0FlJKp5QypN+C+iwL4/70KsOwiHGlWknO4mBP2Lxf6HhzlkVd9TwL42SVnZSfqpGq2UzGs8hnLAyZ8u8/eYCuwShf3ryuorkKgSqNVjUq0PIZi+yKKDuYrp6F2+mgJeApI2dReI58vc+tchY1ZnpoBdQIn9tJwOOsKAx1ICtvMBDOX001Eq++Z5FPTHCsPn1qS2eBispnY8nMhLUHvC6O9kf5/lMHeMfGeZy/vKWidRnKs5Mtnx2MJPG4HHkN8oKmOkI+l21J7unqWYCW5LbaxR0tEk4N+tS0vFqjjEUO85vqKlINzZ5Y118wDFX9nEU+McFogc7XWtIc8OAQFXoWqTyehdfFUDSJyyH4h7etrnhdhmcx2fLZwUiCxjp3Xu9GCMG6eQ32GYtIArdTmJ3M04n2oPUu7mhyYqGDQdCrEty1RhmLHJa31Y/zEqxyoCdsNmgVGqBki7HIIyYYPwXCUE6HoDlQWflsLM/gJuNvdtPlK5nbMHGUqFX8nup5FsUGL50+P8Sr3cMk80wxLMXuY8P822N70aTZJtI/qkl9VBKGm2rmhKx3ccfyzLIwUDmL2qOMRQ7L2+p5vS9CIlXel3z/yVE2LWpEiMKjWYdjWujCW8UqpXxigoWamWpNpY15sWQGb04Y6qIVrbxtfQcfvmhyU9/qvVXyLKITpT6yOX1+A4lUhv0FZqQX497nX+c7f9jHb3fl1+ysVETxVCC7i7sUxSRrgj43ETUtr6YoY5HD8vYA6YzkSH+49M466YzkUG+YVXOCmlZTEc8iVEWvAjBVT7O7uE+FMBRMxlhMDENdclobt73vrElLcvu91RmtOhhJ5u2xMDh9vtZHsLOr/DGrr3QNAvB/f7c373z1/vD0NRbldHEXk6wxB2KpUFTNUMYihxVt2qzh/SetG4uj/RES6QzL2+tpDngK5iyGo9WbZWEQ9GrKs4N5EtxTGYYCbRZ3JQOQ8k1HqxYB3duabK9FqTDU0pYAAY+z7LxFPJVmz/ERVncE2X9ylIdemjgvbGA6GwuzMc+qsSjgWRgzLeIqyV0rlLHIYVlbAKCsvIWx7/K2ek2MsIhnUc18BWjSB5qY4Nh7GmGw0BTPJzY8i0Kx90JoOQt7PpqmZzHJLu7BaHGJcIdDsHZeqGzPYs/xEZJpyU2Xr2Tjgga+8/t9E5o8+6azsShjYl4smS4YSq1Xo1VrjjIWOQS8LuY2+MZVN5XCMBYr2uppChSetjfZ+duFaMzp4t53YpT2oHfKh9m31XtJpDNm57pV8oWhqoVVz+JnLxzhqtv+lPc5U3G2iGcB2pjV3d3DZcXVd3RqxmXDggY+e8Vqugaj/OTPR8znU+kMQ9HktDUWc8rQhyomhhlUYaiao4xFHla0l1cRtf/kKK31Xhr87qKjWbWcRfVP4A05YoL7T46wck51BixNhnI7dg3y9VlUC7/HWs7i/q1H2XZkMG8t/5guVPET9unzG4gk0hzqtR7SfKVziCa/mwVNdVy4opWLVrRy6xP7iesDoYxChulqLIz57FY+E8XCUPV55rIr7EUZizxo5bNhy+GTAz1hluvhq+Z6bSZGvmPtCEOBVhFlhKEyGcm+k6OsbA9W/X3KZXmbZrCMq2UrSCnz9llUC4/LgdspilZD9YcTbD+qJZnzhUuMv3VTCc/i9PlaJ3c5oagdXUOsX9BolsW+/7zF9IcT7OzSch8DkxBRPBXwuKx3cUeLlM4G1WjVmqOMRR6WtwUYjacsfaCllOw/Ocrydu3E2Oz3kEzLvLFULQxVfc8iOwx1bChKJJE+JTyLtXNDtAQ8/HFfj+VjEmldMdfG5Hy915V3YJTB0/t6MGx999BEY2F06JcKQ61oq8frclg2FrFkmr0nRtgwf0yR9cxFjQC8dGQAGBO5nG5SH9m0h3z0WPAsNA+zkGehT8tTnkXNsNVYCCGuEELsEULsF0LcnOd5rxDi5/rzfxZCLNG3LxFCRIUQ2/XbD+xcZy7GFbGVUFRfOMFQNMkK/RhjxkCu5EcqnSGcSNuTs/B7TGOx74S25tPmTL1n4XAILl7ZyjP7eslYjNsbIohemxLcoP1/958o/L99ck8Pbqd2ZZ/PWBjd8qXCUC6ngzVzQ+w8Zs1YGPmN9QvGjEV7yMf8xjpe0j0d07OYhlIfBtp4VYs5C0/+z0FQTcurObZ9I4UQTuBWtMFJa4FrhRBrc3b7MDAgpVwB/BvwzaznDkgpz9BvH7VrnflYoXsJVhqqjES46Vnoc6H7wuO/DGODj2zwLPxuRuMpkukM+06OALCyfeo9C4CLV7bRF05YFtWL16BHZFVHkNeOD+cNFWYykqf29vCWtR0AHM9jLMbGupb+X54+P8SurmFLxvKVrOR2NmcubuKl13XPYpqKCGYzJ+S1nrMo0MDq9+jT8lQYqmbY6VmcA+yXUh6UUiaA+4Arc/a5Em0iH8ADwF+IU0DDoC3oJeh1WfIsjMFDhoEZ66gen+S2Q+rDoNE/Jvmx98QobUFv0e7iWnLxaa0APLXXWigqd6SqHazuCDIcS+X1GnZ0DdEfTvDmtXNorffkD0NZTHADnD6vgZF4ypLe2I7OIVrrvXToFUMGmxY2cmwoxvGh2KSmBJ4qLG4JcGI4XrQxz5z2WKB0VghBvVfNtKgldhqL+cDRrMed+ra8++gDloYAQ050qRDiJSHEU0KIi21c5wSEECyzWBF14GSYOreTufoXvCWgVXv054Shhs0pefaEoUALj2jJ7VPDqwBoD/pYMzfEH60ai5T9irmrOrTE857jIxOee3LPSYTQOsY7GnwcH4pO2GcwmsDjclha41gnd2nPamfXEBsWNEzQfNqk5y22Hx2gP5wg6HPhdk7fdON5y7Sv+PMH+wvuY057LHLREPK5lWeB5v0WGrhWTU7VT1w3sEhKuQn4NPBTIcSEGRpCiI8IIbYKIbb29FhPolphRVs9Byx0cR/qHWVJa8BUxjRCE7mNeWOehfvEqs4AAB35SURBVD0JbtCuePefGDkl8hXZXHJaKy++PmDpi12LKX+rOrS/z2t5jUUPGxc00hzw0BGqy5+ziCRp8udXnM1l5Zx63E7BKyWS3JFEin0nR1g/f+K40bXzQnicDrYdGaQ/nKBlGnsVABsXNFDvdfHsgd6C+8QLzN/ORvMsVM7iH375Cu+8NX9PUDWx01h0AQuzHi/Qt+XdRwjhQhvM2yeljEsp+wCklC8CB4DTct9ASnmHlPJsKeXZbW1tVV388vYAx4djJT+MR/ojLG72m4/rvS7cTjFB8sMcfGRTzgLg1e5hwom0GRI7VXjjyjZSGclzB/pK7luLMFRDnZt5Db4Jk+z6wwle7hzk0lXaZ2lug4/j+UpnI0lLISgAr8vJ6o4Qv3ypk8d2nyhYjr372DAZOTFfYbzG6fNDvHRE8yymcwgKtMT/OUubi34erOibGQOxSpHJSNtG3E418VSa5w70cc7SZtvfy05jsQVYKYRYKoTwANcAD+fs8zBwnX7/3cDjUkophGjTE+QIIZYBK4GDNq51AkZFVPYEvFwyGcnRgSiLWsaMhRCCJr+H/tFcY2EMPrKnzwLghUOaW3+qeRZnLWmizu20FIoyPQubBzet6ghOCEP9ca9WMnvpqnYAOhp8DEaSE040A5FEybLZbG65ch1Bn5u/u2crH7zrBXZ0Dk7Yx+hFyedZAGxa1MSOziFOjsSmvWcBcMHyFg72hunOE+aDbOXkwp+DeoszLf7993u56JuPT2iO7B2N8+CLnZYr9U5Ftr0+SDSZ5uKV1b1Yzodt30g9B/EJ4LfAq8D9UspdQohbhBCb9d3uBFqEEPvRwk1Gee0lwA4hxHa0xPdHpZSFA5w2YBiLYhVRPaNxEqkMC7M8CyCvmKCdCW7jxLXlsPYnOpVyFqBdGZ+3rJmnLfRbxGqkmLuqI8SBntFx8yae3HOS5oDH7HOY26DloXK9i6FosmRDXjabFjXxm09dzBf/ai3bjw6y+Xt/4u3ffZp7n3+d/955nM8+8DLffXwfcxt8ptDexNdoJJ7KsPfEaFFNqumCMenw2f35vYuYhZksQZ/LUlPeswf66Asn+NCPXjDVFY72R3j395/lf//iZZ7ce7Lc5Z8yPL2vB5dDcN4y+z0LW0dtSSkfBR7N2fbFrPsx4D15jnsQeNDOtZVicYsfj8vBq0VKPo/0axUui/IYi4k5i+qPVDUIel04HYITw3Fa6z2nZJjiktPaeGJPD0f6IuM8sVxiKSMMZa9nsWZukGRacrAnzKqOIIlUhsdfO8mb13aY+acO3Vh0D0VZ2howjx2MJNm4oLy/sdvp4IaLlvLusxfwny918dMXjvJ/frUT0E56l65q50MXLil4/KZFTeb96dxjYbCmI0ST382zB/r467MWTHjeShhKG61a3Fik0hl2HhvivGXNbDsyyEfu2cqX3rGOv71nC1G97+k/tx/j8tVzJvcLTRFP7+vlzEVNtpxXcpl+cxlrhNvpYO3cUNHE5JG+/MaiKeCZYGSGYym8Lsek5zHkQwhBY52bvnDilJD5yMfFK7US2ucP9RU3FvpJopoDovIxluQeZlVHkOcP9jEcS/GXp3eY+xgT+XJ7LQYiiaLy5MUI+dx84PwlvP+8xezsGiaSSHHm4qaS1U3zGnz6lLn4tO6xMHA4BOcvb+G5A71IKScUC8QSFnIWFsJQe0+MEktmuPacRXzgvCV8/KfbeMf3nqE96OX+j57PPc+9zq9e6iKSSJm6YdOFvtE4O48N8ek3TUjn2sKpWg11SrBhQQM7u4YKxjSP9EcQAuY3jh/zmU+m3C6pDwMjFHUqyHzkY2mrVhVUqhy5Fk15AMta63E5hFkR9d+7juP3OLlIN2qA2e+QXREVS6aJpzKT7mMRQrB+QQPnLmuxVAYrhGDTQs27mK66ULmcv7yVY0MxXu+b2IMStRCGqve6iSbTeQdEGRj5oQ0LGnn7hrl8+R1rOXNRIw9+7AJWd4TYvHEekUSa3786/UJRfzrQh5Rw8Wn25ytAGYuirJ/fQDiR5mAB1dCj/RHmNdRN8BaaAh4Go8lx0tTDNkzJG/ee+slr5SmW3DZwOgSLWwJFCwYguxrK3o+mx+VgeVs9e46PkM5IfrfrBJetah9npOo8Thr97nGehak4W6FnMRmMfouZYiwu1PMWf8pTQmt8DoqNBg5amGnxcucQIZ+LJbo3e/2FS3noxgvNPOM5S5rpCPl4ePv4Qs3e0fgpn/h+em8PjX53waKIaqOMRREMjZ5CQnBH+iMsaKqbsL0l4EHK8aNO7VKcNTB6LU615HY2y1oDHCzhWdQqwQ2wem6Q17qHeenIAL2jcd6aFYIy6Aj5xnkWRmd+sZGqdnHZ6nZa672nXLVbpSxtDdAR8vFsnhLafSdHEEKbiVKIel9pmfIdnYNsyFLxzcXhEGw+Yx5P7e0xv6+P7DjGOV/7PQ+/fKycX6emSCl5el8vF65oxemojeiFMhZFWNFWj8/tKCixfaQ/MiFfAVliguOMRW3CUKfyiWRZWz1H+iNFwwaxVBqnQ9SkQ3lVR5BjQzHu33oUj9PBZasmuvNar8VYeeeYZ1H7q/vT5gTZ+o9vmlB9N10RQnDB8haeP9A34Sr+8ddOsmlhY9FiDWO0aiHPIpbURtRuXFj8ynvzxnkk05Lf7DzOU3t7+F8/305GwtbXa1qAWRb7T45yfDjGJVlhU7tRxqIILqeDdfMaeKVrYl18LJnm5Eg8r7EwEpDZkh8jsRShOvs8i3XzGlgzN3RKhyiWtQVIpiWdA/lr60GXpbZRcTab1XqS+6FtXVy4oiWvMe9oqKN7cMyzONKvhdHaQ4WveBXWufi0VvrCCV44PHZiPjEcY0fnEH+xpniFkvH/KmQsdh0bJpWRbFjQWPR11s0LsawtwA+fPshH732RFe1BPV9Z3vz0WmJorV1Ug/4KA2UsSrB+fgO7jk0cjdmpC8Plq+wxJD+yJ+aNxJIEvfZ5Fh++aCm/+VRNJbTKxhgQdbC3cCjKzpGquRgaUamM5Io8ISjQPIu+cMIMjz29r5f2oJdlWaW0isq5Yt1cGv1u7v7TYXPbE69pyea/WNNe9Nj6EjLlRnJ7YwljIYRg88Z5HOwJMyfk5Z4bzuGcJc282j1c1Au2g3RGcuczh9h/cqIUjcFAOMEPnjrAGQsbJxTX2IkyFiVYr4/GzI21Gz0W+UICxtV9trEYjtqbs5gOLGst3RVfbOBNtZnX4CPoc+EQ8KYCV7FGr8XJYS3h+eyBPi5a2WpJF0pRmjqPk2vPWcTvdh83L8B+/+pJ5jfWsapESLXUaNUdnUO0B73m/7AY7zt3Mdees5B7P3wubUEvp89vIJ7KcKBEQUY1SWckn/nFy3z1kd184zevFdzvlkd2MxhJ8vV3ra/Z2kAZi5IYWj25eYtCPRYwUaY8mc4QTaZr0jhzKtMU8NDkdxf9AsZSabw2V0IZCCE4e3ETl5zWRkuBROrcrMa83d3D9IcTZs+Iojp84LzFCCG497nXiSXTPLO/hzetaS9pkEtVQ73cOcjGhcW9CoO2oJd/vmqDefFnjMQtJQBZLdIZyWcf2MFDL3WxrDXAU3t7GIpM9Jgef+0Ev3ypixsvW8HaeRO0VW1FGYsSLGurx+9xTvjQHOmP4vc48+r0+NxOAh6n6VmM2ij1Md1Y1lZftCIqXmTgjR18//1n8YP3n1Xw+WzJj6f3aSWeF65QxqKazGus44p1HfzshSP84dWTxJIZLi+Rr4AsY5HHsxiOJTnYE2ZjHmFGKyxtrafO7SxrfnqlSCn5/EM7eHBbJ//zTSv5zjWbSKYl/72re9x+w7Ek//DQTlbNCfKJy1bYvq5clLEogdMhWDdvYie3UQlV6OqnKUvyw05dqOnG0tZAwb6VdEbSNRjDX6S2vtr43M6iYa8OvYu7eyjGM/t7WN0RpD1YOqyhKI/rL1zCcCzFl3+9i4DHaUnrqM7txCGYoMMGsNOcOmjNs8jF6RCsnRdil8WRuJPhuQN93L+1kxsvXc7/fNNpnD4/xJIWP79+ebyx+OdHX+PkSIxvvXuDLUoQpVDGwgLr5zey69jQuGTX0f4IC5oKlzA2BzzmCMxhG3WhphvL2gL0jMTzJiX/7bG9vNo9zHvOnqgVNFXUe10EvS4O94bZcniAi5RXYQtnL27i9PkhekbiXLyyzZLcixCCc5Y289C2rgnKwNvNzu3KG9ZOnxdi1zFrI3Enw31bjtJQ5+aTf7ES0H6vd2ycx7MHes3xs1sO9/OzF47w4YuWWg6tVRtlLCywfkGIWDJjjlCVUhbssTBoDnjMnMVRPRluZwf3dKFQkvt3u47zvSf2c/XZC3nv2QvzHTpldDT4+O9dx0mkMuPkQBTVQwjB9RcsBeDyElVQ2fzvt6yiZyTOj587bG6TUvLMvl4Wt/gn1Q+zTi9uOdRnX5J7IJzgv3ce512b5o/zcDdvnEdGwm9e0T53//DQK8xvrON/vbk2OlD5UMbCAuvna5b8Fd217R1NEE2mWdRcuGyt2e+hP5zguQN9/P0vXmZhcx2nT+IqZ6aQr3z2QM8on77/ZTYsaOArV6475SqNjLkWHqeDc5e2lD5AURHv2jSf71zz/9s78yipqjuPf77d7NCAbM1iEJBFdkZAVESNBBo0HDHRARUnGhTct2CiMjMxGsdknDlKGOJ2jJjMEDXEGNwGR42KUUFQXEDcUEEEVKKo7E3/5o/7GotOd1c1XVXvlfw+59SRevdV+elX793fu79777tDmDik6urLNTO8WxuO6d2eW59+d08L/o5Fq3nu3U2cPqJrvXwGdqn9CQ7Z4IHl69i5u4JJw/e+QepVWsIhHUtY8MpH3LFoNW9//BXXntg/1ocderDIgB7tmtOicQOeejNMhFlbyxyLSg5o3ogNm7dz5l1L6NS6KX+YfmROVskrNLq2bUaRvm5ZlO+u4IL/eYlGDYq4ZcrQvA2brQuVndxDDzqg1mcVOfWjuEicOKRLnfPxM8b24fOtu7hz0Xs889Yn/OLRVZwwsBPnjOpRL5+eHVrQqEFRzoKFmXHPkrUMPjBMqK3KhMGdWfbBZ8x64m2OH9gx7STFXOPBIgOKisSZR3bj4dfWs3DFhj1ppXRpqPIKo1dpC+6bfkRGY733Bxo3KOZbbZrt6eSev+xDVm34kusnDsjrBKO6UPmock9BJZOBB7ZiXP+O3Pnse1z0+5fpXVrCjacMqncLtWFxEX07luRsJvfytZ/z5sYvmXxY9S2gCYM6A9CouIifTuifE4e64En0DLl4dC+eXPUxV9//GhMGhx+xtg7uMf1K2fjFdmaU9fEWRRXCAwW3sG3nbm56/C0O7dq6xhnUSaDyYZFH5/HRCk7duHxsbxau3EDLJg25/YxhWUvX9O/Sigdf+ajaNTeqY+MX23lsxQYaFBdxag1BoJJ7X1xLs0bFe+qTqnRt24zpx/RgUJfWlNawgmI+8WCRIY0aFHHTpCFMmP0sc597n9KWjWtNmfQuLeHaEwfk0bBw6NG+Bc+v3sRv/voeG7/YwexTD01cP0UqEwZ3pn1J4z1PIXaSR+/SEuacdihd2zSrNT1cVwZ0bsW8xWtY+7dtNX5v+e4K7l26lvnLPuTlNV8/R65N80aU9a/+JuirHeUseOUjvjuo056Z6NVx1fi+9fsDsoinoepAn44lzCgLoxFqS0E5tdO9XXO276pg1hNv852+HTise+7XD64PTRoWc2yfzEfoOPFw/MBODMjy2g6VM7lfr2a+hZnx5KqNjJu1iJl/ep3tuyqYMbY3j14yioFdWnHlH1/l4yrrt1dy61PvsnXnbqYcflBWfXOJB4s6MvWoHpwwqFONzxJy0tMjGhFVvruCH487JGYbx6mZ3qUlNCwWj7+xca/t5bsruHDey/xw7lJ2Vxi3nzGURy4+iguP60XfTi25adIQtu3azYz5r/7dPI01m7Zy+6LVnPQPXfZ50mAc5DRYSBon6U1J70i6spryxpLujcoXS+qWUnZVtP1NSWW59KwLxUVizmmHMv2Yg+NWKVh6Rgs0nTz0wESvv+E4TRoW88OR3bn/pXV7LYZ03UMrefi19fxoTG8WXno0Y/t33CuV2rNDC2ae0I9n3vqEuc+9v9d3Xv/IShoUiZ8U2I1SzvosJBUDc4AxwIfAi5IWmNnKlN2mAp+ZWU9Jk4FfApMk9QMmA/2BzsDjknqb2d7TNJ2CpENJE+adPSK2maiOUxdmlPVh2QefcdUfX6V/55YseusT7n7+A6Yd3YOLolnX1TFlRFeeWvUx1z28kvWbt/GjseF7Fq7YyBVlfQpuhKTMcjOVXdIRwDVmVha9vwrAzG5I2WdhtM/zkhoAG4D2wJWp+6buV9P/b9iwYbZ06dKc/C2O4+zfrN+8jRN+9SxNGxazfvM2Rvct5dYpQ9MuabplRznXP/IG8xav2bMGyq6KCv7vsmMSM6dI0jIzG5Zuv1ymoboAa1Pefxhtq3YfMysHNgNtM/ys4zhOXujUqik3TxrCR5u30bdTS2ZNHpLR2tfNGzfg304ayH9PHcGO8gpWf7qFmcf3TUygqAsFPXRW0jRgGkDXrvWb2u84jlMbR/duzwPnj6Rbu+Z1nsdxVK92LLzsaFas25z40X81kcuWxTog9YEnB0bbqt0nSkO1AjZl+FnM7HYzG2Zmw9q39wlTjuPklsHfak2rpvs2ybZF4waM6NE20XOKaiOXweJFoJek7pIaETqsF1TZZwHwg+jfJwNPWuhEWQBMjkZLdQd6AUty6Oo4juPUQs7SUGZWLulCYCFQDPzGzFZIuhZYamYLgDuB30l6B/gbIaAQ7XcfsBIoBy7wkVCO4zjxkbPRUPnGR0M5juPUnSSMhnIcx3G+IXiwcBzHcdLiwcJxHMdJiwcLx3EcJy3fmA5uSZ8AH9TjK9oBn2ZJJ1u4U2Yk0QmS6eVOmZNEr1w4HWRmaSeqfWOCRX2RtDSTEQH5xJ0yI4lOkEwvd8qcJHrF6eRpKMdxHCctHiwcx3GctHiw+Jrb4xaoBnfKjCQ6QTK93ClzkugVm5P3WTiO4zhp8ZaF4ziOkxYPFk5BoQQ+31mSX0cZIGnfnu2dY5J4TiWR/eIkl9Q6+m9i/l5J3SSVxu1RFUk9JR0ct0cqkgZLGgNgCcmbShoq6XwAM6uI2wdA0uGSbpTUIm6XVCQNk3QXcEjcLpVI6i/p25Coc6q7pI5xe9REYirPXCCptaTfAg9J6mpmFXEHDEkHSLoN+DMwT9LUOH0qkdRG0hzgfuDXlRVh3ES/1yPADEl9U7bF5dNW0mzgFmBLtC32O9Po0f+3Edax3ykp9nU7o3NqNjCbsG5NEn6/ZpLuAO4Brpb0U0mN4/Kp4vRn4BZJkyU1jcpiP7cq+UYHC+BSoAPwAnABxHsXGN3x3QTsNLPBwL8D0yW1issp8moI3AyUm9kg4FrgkgRcRMWENdmfBp4HToPwG8Z4Ed0LjDGzw8zs7sgn1jvTaJXJtsDxZvafZrYz7vVfojvkO4FdZnYEcCYwCmJviZ0EtDSzgcBFwDgg7gp5ItAiuvZ+DowHTpVUHPe5lco3LlhIGi6pcur6LOAcYB7QT9LIaJ+8/t2SDpPU2sy+An4NXAxgZguBr4guonwTebUxs13ApWZ2SVTUm1A5943BabikNgBRhbcdaAq8CbSXdERUlreLKHLqEL29GmgebS+TNE1S3n+/1OMEdAaOMrN1ksZLukPSP8WRTozOqZbARuAsM7s8KmoLbI32yff1N1xSu+jtTr5esnkwoSU2SlKTGJ0aEeoBzGwZoV4+BRiZT6d0fKOCRZSDXAyMldTIzD4zs7WEiuYvwDTI751N5PQCcEJ0p7zUzExSsaTmhNUKl+fLpxqv8ZIamtnfJBVJmgz8DFgF3Crp+5VN4jw5LY6cGkWbOwHvmdnvgZeB8yT9s6QD8uw0RlJTM1sCLJZUAVwGHADclZo6yKPTeElNzGxN5PRb4CzgGWA0cLmkA/PhlOL1AjABaGhmn6d0ar8KfA9iuf4WA2XR9fcssFzSY4TW9F+AmcDFktrG4CTgY2BXdOPRnlAvryUsS52YOjoxIlmiG/AScDApnWlmtgV4FGgiaRLsabrn22lAlQvFgG3A53lyqcmrH+y5iB80s65m9gvgv4DTY3KqbNV8CjSM7sJGE9Zq72Jmn+XpQqrO6SxgppmNM7NfAtdEXvlK/aQ69Yq2PQWMAO4ws98RUpzFKeX59joEIGq1QqiUV0s6Lo8+qU49gX5mtp7Qsl8HjDKzXxFSPwOBNjV9SY6cekWvJwj102jgAeB/CUH32JhTrntR0MFCUscqFcZHwHzCjzGyykH+ALgbOFnSvwJTc5GTT+N0ZKVTlGIZCawxs68kXSBpYq5OjAy8iiKvLSn7LQBaAjlpoqdxOiLadiDhQl8OfAlcARRL6pKLO9Q0TiMkNTCzL83shpT9HgJaA82y7ZOBU2UK7HFgKSF9gZmtIKRb1uXCKQOvqtdfh6g8pwG1FqeDgKOi36+ccFwOi/Z5gnCebc2zU1fgO4Q+zAeBs4GxUbB/jtDaKEpKv0VBBgtJoyUtAuYQ+gAqGUlIOd1MuFM4T9LRkmRmWwkn7PGETq1nzGxHXE5R2eFAN0kPEzq5Xsv2iVEHr3MljYoupgpJZcCDwBJCJZ1vp8GSzgY6Eu6ay8xsKvAYsIzQl5Fvp4HAtOg4qcpxWkw8x2mgpHMJrZ6rgUGSfibpeeAT4ONs34Ds4/W3ASgldN5mnTo4nS1pNKE1P0XSTwhpu7eAzdk8Vhk6DQDOV+j32hLdrE0E5gKLkzIsGwAzK6gXofN1MaHZ34EwrHJMVDaJcKfVA3gb+IIQqSGkWl4ETk6A0/FR2c3A+8C4hByrMYQ+lOmECvnEmJ22AN+u8vmiJBynqOwMQj9K3MfpS2B8VNaVUCFPTMg5VZby2WMqr8eYz6mjCJ3K3yVU5N9LwHGqrKeOBN4ATsrF71efV77y9vUiJUVSAQwBlpjZfIVRF1sIB5eo7ErC6JnHCaNWdkZNuZXA8IQ4bYnKZpvZpdlyyoLXTjMrl3S/md2WECeL7kwt5TvidtoZlT1oIWWQFerptC06TmuANdlyyoLXjsrfz8yeToBTC0JfTrmZPURIIcbtlFpPPUcMoxAzIfFpKElnAR8C10WbXgWGKkxieY3QtL1R0s2EOQxLCB1X5wGro/KsTm7JglOn6AJ6N1tOWfQqMrNPEuRUSpbHwWfxOGVtYEISj1NSverp9C4htZm0OiHr9VTWibtpk6Yp14IwOuASwuiBPtH29oSOzvOi902ATcDwKp9vvD84JdXLnQrXKale7hTfK9EtCwuT2C42s1mEjs1roqJNhKF5r0f7bSdMvKuMzpXNwax1YCfZKale7lS4Tkn1cqcYiTta1SF6dyQ03So78q4i5AD7EEaBLAe67+9OSfVyp8J1SqqXO+X3VVCLH0maDkwxs1HR+/8gzPAtAn5sYbb2fu+UVC93KlynpHq5U/4omGARdShWSJpPmB6/FbiPMDdhmzsl28udCtcpqV7ulF8S3WeRSvQDNCOMWf5HwsznJXH+AEl0SqqXOxWuU1K93Cm/FMQ8ixTOJ4w2GGPJ6RRKohMk08udMiOJTpBML3fKEwWThoKvm3hxe6SSRCdIppc7ZUYSnSCZXu6UPwoqWDiO4zjxUDB9Fo7jOE58eLBwHMdx0uLBwnEcx0mLBwvHcRwnLR4sHCdLSLpG0oxayidK6pdPJ8fJFh4sHCd/TCRa79xxCg0fOus49UDSTOAHhEc7rCWsMLgZmEZYje0dwop6QwgL7WyOXt+PvmIO4VHWW4FzzGxVPv0dJ1M8WDjOPiJpKGGt5BGEpyG8BNwK3GVmm6J9fg5sNLPZkuYCD5nZ/KjsCeBcM3tb0gjgBjM7Lv9/ieOkp9Ae9+E4SWIU8Ccz2wogaUG0fUAUJFoTFsZZWPWDkloQ1lv+Q8riaI1zbuw4+4gHC8fJPnOBiWb2iqQzgWOr2acI+NzMhuTRy3H2Ge/gdpx95xlgoqSmkkqACdH2EmC9pIbA6Sn7fxmVYWZfAO9JOgXC2suSBudP3XHqhgcLx9lHzOwl4F7gFeBR4MWo6F+AxcBfgdQO63uAKyS9LOlgQiCZKukVYAVwYr7cHaeueAe34ziOkxZvWTiO4zhp8WDhOI7jpMWDheM4jpMWDxaO4zhOWjxYOI7jOGnxYOE4juOkxYOF4ziOkxYPFo7jOE5a/h87BmMxIyBOJwAAAABJRU5ErkJggg==\n"},"metadata":{},"output_type":"display_data"}]},{"metadata":{"tags":["context"],"dc":{"key":"518e95acc5"},"deletable":false,"editable":false,"run_control":{"frozen":true}},"cell_type":"markdown","source":"## 6. The effect of handwashing highlighted\n<p>Starting from the summer of 1847 the proportion of deaths is drastically reduced and, yes, this was when Semmelweis made handwashing obligatory. </p>\n<p>The effect of handwashing is made even more clear if we highlight this in the graph.</p>"},{"metadata":{"tags":["sample_code"],"trusted":true,"dc":{"key":"518e95acc5"}},"execution_count":93,"cell_type":"code","source":"# Date when handwashing was made mandatory\nimport pandas as pd\nhandwashing_start = pd.to_datetime('1847-06-01')\n\n# Split monthly into before and after handwashing_start\nbefore_washing = monthly[monthly['date'] < handwashing_start]\nafter_washing = monthly[monthly['date'] >= handwashing_start]\n\n# Plot monthly proportion of deaths before and after handwashing\n# ... YOUR CODE FOR TASK 6 ...\nax = before_washing.plot(x='date', y='proportion_deaths', label='before')\nafter_washing.plot(x='date', y='proportion_deaths', label='after', ax=ax)\nax.set_ylabel('Proportion deaths')","outputs":[{"execution_count":93,"data":{"text/plain":"<matplotlib.text.Text at 0x7f213d261160>"},"output_type":"execute_result","metadata":{}},{"data":{"text/plain":"<matplotlib.figure.Figure at 0x7f213d72b3c8>","image/png":"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\n"},"metadata":{},"output_type":"display_data"}]},{"metadata":{"tags":["context"],"dc":{"key":"586a9f9803"},"deletable":false,"editable":false,"run_control":{"frozen":true}},"cell_type":"markdown","source":"## 7. More handwashing, fewer deaths?\n<p>Again, the graph shows that handwashing had a huge effect. How much did it reduce the monthly proportion of deaths on average?</p>"},{"metadata":{"tags":["sample_code"],"trusted":true,"dc":{"key":"586a9f9803"}},"execution_count":95,"cell_type":"code","source":"# Difference in mean monthly proportion of deaths due to handwashing\nbefore_proportion = before_washing['proportion_deaths']\nafter_proportion = after_washing['proportion_deaths']\nmean_diff = after_proportion.mean() - before_proportion.mean()\nmean_diff","outputs":[{"execution_count":95,"data":{"text/plain":"-0.083956607511833356"},"output_type":"execute_result","metadata":{}}]},{"metadata":{"tags":["context"],"dc":{"key":"d8ff65292a"},"deletable":false,"editable":false,"run_control":{"frozen":true}},"cell_type":"markdown","source":"## 8. A Bootstrap analysis of Semmelweis handwashing data\n<p>It reduced the proportion of deaths by around 8 percentage points! From 10% on average to just 2% (which is still a high number by modern standards). </p>\n<p>To get a feeling for the uncertainty around how much handwashing reduces mortalities we could look at a confidence interval (here calculated using the bootstrap method).</p>"},{"metadata":{"tags":["sample_code"],"trusted":true,"dc":{"key":"d8ff65292a"}},"execution_count":97,"cell_type":"code","source":"# A bootstrap analysis of the reduction of deaths due to handwashing\nboot_mean_diff = []\nfor i in range(3000):\n boot_before = before_proportion.sample(frac=1, replace=True)\n boot_after = after_proportion.sample(frac=1, replace=True)\n boot_mean_diff.append(boot_after.mean() - boot_before.mean())\n\n# Calculating a 95% confidence interval from boot_mean_diff \nconfidence_interval = pd.Series(boot_mean_diff).quantile([0.025, 0.975])\nconfidence_interval\n","outputs":[{"execution_count":97,"data":{"text/plain":"0.025 -0.100637\n0.975 -0.067834\ndtype: float64"},"output_type":"execute_result","metadata":{}}]},{"metadata":{"tags":["context"],"dc":{"key":"0645423069"},"deletable":false,"editable":false,"run_control":{"frozen":true}},"cell_type":"markdown","source":"## 9. The fate of Dr. Semmelweis\n<p>So handwashing reduced the proportion of deaths by between 6.7 and 10 percentage points, according to a 95% confidence interval. All in all, it would seem that Semmelweis had solid evidence that handwashing was a simple but highly effective procedure that could save many lives.</p>\n<p>The tragedy is that, despite the evidence, Semmelweis' theory — that childbed fever was caused by some \"substance\" (what we today know as <em>bacteria</em>) from autopsy room corpses — was ridiculed by contemporary scientists. The medical community largely rejected his discovery and in 1849 he was forced to leave the Vienna General Hospital for good.</p>\n<p>One reason for this was that statistics and statistical arguments were uncommon in medical science in the 1800s. Semmelweis only published his data as long tables of raw data, but he didn't show any graphs nor confidence intervals. If he would have had access to the analysis we've just put together he might have been more successful in getting the Viennese doctors to wash their hands.</p>"},{"metadata":{"tags":["sample_code"],"trusted":true,"collapsed":true,"dc":{"key":"0645423069"}},"execution_count":99,"cell_type":"code","source":"# The data Semmelweis collected points to that:\ndoctors_should_wash_their_hands = False","outputs":[]}],"metadata":{"language_info":{"codemirror_mode":{"version":3,"name":"ipython"},"file_extension":".py","nbconvert_exporter":"python","mimetype":"text/x-python","version":"3.5.2","name":"python","pygments_lexer":"ipython3"},"kernelspec":{"name":"python3","display_name":"Python 3","language":"python"}},"nbformat_minor":2}
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment