From b7e7c381d706bebd384be47a49aa7d2e36e911a6 Mon Sep 17 00:00:00 2001 From: rad Date: Tue, 29 Oct 2019 20:54:52 -0400 Subject: [PATCH] #13 add number of trains and observation about stations --- doc/filtering_observed_arrivals.ipynb | 258 +++++++++++++++----------- 1 file changed, 145 insertions(+), 113 deletions(-) diff --git a/doc/filtering_observed_arrivals.ipynb b/doc/filtering_observed_arrivals.ipynb index 2fd817e..c265acd 100644 --- a/doc/filtering_observed_arrivals.ipynb +++ b/doc/filtering_observed_arrivals.ipynb @@ -5,14 +5,14 @@ "metadata": {}, "source": [ "## Filtering Observed Arrivals\n", - "As the [API Exploration Notebook](API_exploration.ipynb) shows, each poll of the scraper produces 3 predicted arrival times for each line direction at a station. We want to transform and reduce these data to only feature observed train arrivals at stations ([per this issue](https://github.com/CivicTechTO/ttc_subway_times/issues/13)).\n", + "As the [API Exploration Notebook](API_exploration.ipynb) shows, each poll of the scraper produces 3 predicted arrival times for each line direction at a station. We want to transform and reduce these data to only feature observed train arrivals at stations ([per this issue](https://github.com/CivicTechTO/ttc_subway_times/issues/13)). \n", "\n", - "This notebook explores how to do this. " + "This notebook explores how to do this. It was [initially developed using a day of data 2017-06-14](https://github.com/CivicTechTO/ttc_subway_times/blob/15c1c17a9de8d867f516222ea1a406abc72bb779/doc/filtering_observed_arrivals.ipynb), but now uses a more recent day of data from the serverless data pipeline in 2019. " ] }, { "cell_type": "code", - "execution_count": 1, + "execution_count": 2, "metadata": {}, "outputs": [], "source": [ @@ -29,7 +29,7 @@ }, { "cell_type": "code", - "execution_count": 8, + "execution_count": 3, "metadata": {}, "outputs": [], "source": [ @@ -38,22 +38,11 @@ }, { "cell_type": "code", - "execution_count": 2, - "metadata": {}, - "outputs": [ - { - "ename": "OperationalError", - "evalue": "FATAL: Peer authentication failed for user \"ryanvilim\"\n", - "output_type": "error", - "traceback": [ - "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[0;31mOperationalError\u001b[0m Traceback (most recent call last)", - "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m\u001b[0m\n\u001b[1;32m 2\u001b[0m \u001b[0mCONFIG\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'../db.cfg'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 3\u001b[0m \u001b[0mdbset\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mCONFIG\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'DBSETTINGS'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 4\u001b[0;31m \u001b[0mcon\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mconnect\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m**\u001b[0m\u001b[0mdbset\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m", - "\u001b[0;32m~/.local/share/virtualenvs/ttc_subway_times-ZmuzQ-JX/lib/python3.5/site-packages/psycopg2/__init__.py\u001b[0m in \u001b[0;36mconnect\u001b[0;34m(dsn, connection_factory, cursor_factory, **kwargs)\u001b[0m\n\u001b[1;32m 128\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 129\u001b[0m \u001b[0mdsn\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_ext\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmake_dsn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdsn\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 130\u001b[0;31m \u001b[0mconn\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_connect\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdsn\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mconnection_factory\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mconnection_factory\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwasync\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 131\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mcursor_factory\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 132\u001b[0m \u001b[0mconn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcursor_factory\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcursor_factory\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n", - "\u001b[0;31mOperationalError\u001b[0m: FATAL: Peer authentication failed for user \"ryanvilim\"\n" - ] - } - ], + "execution_count": null, + "metadata": { + "scrolled": true + }, + "outputs": [], "source": [ "CONFIG = configparser.ConfigParser(interpolation=None)\n", "CONFIG.read('../db.cfg')\n", @@ -111,7 +100,7 @@ }, { "cell_type": "code", - "execution_count": 9, + "execution_count": 6, "metadata": {}, "outputs": [], "source": [ @@ -119,10 +108,10 @@ "CREATE MATERIALIZED VIEW test_day AS \n", "SELECT requestid, stationid, lineid, create_date, request_date, station_char, subwayline, system_message_type, \n", " timint, traindirection, trainid, train_message\n", - "FROM requests\n", - "INNER JOIN ntas_data USING (requestid)\n", - "WHERE request_date >= '2017-06-14'::DATE + interval '5 hours' \n", - "AND request_date < '2017-06-14'::DATE + interval '29 hours' \n", + "FROM requests_serverless\n", + "INNER JOIN ntas_data_serverless USING (requestid)\n", + "WHERE request_date >= '2019-07-17'::DATE + interval '5 hours' \n", + "AND request_date < '2019-07-17'::DATE + interval '29 hours' \n", "''' \n", "with con:\n", " with con.cursor() as cur:\n", @@ -131,14 +120,14 @@ }, { "cell_type": "code", - "execution_count": 10, + "execution_count": 7, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "554390\n" + "551408\n" ] } ], @@ -160,14 +149,14 @@ }, { "cell_type": "code", - "execution_count": 22, + "execution_count": 8, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ - "81483\n" + "91665\n" ] } ], @@ -392,11 +381,38 @@ "pandasql.read_sql(sql, con)" ] }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "According to [wikipedia](https://en.wikipedia.org/wiki/Toronto_subway#Rolling_stock) the number of trains for each line is:\n", + "\n", + "|line | number of trains|\n", + "|-----|----------------:|\n", + "|1 | 76 |\n", + "|2 | 62 |\n", + "| 4 | 6 |\n", + "\n", + "So the " + ] + }, { "cell_type": "code", - "execution_count": 4, + "execution_count": 1, "metadata": {}, - "outputs": [], + "outputs": [ + { + "ename": "NameError", + "evalue": "name 'pandasql' is not defined", + "output_type": "error", + "traceback": [ + "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", + "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)", + "\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m\u001b[0m\n\u001b[1;32m 5\u001b[0m \u001b[0mORDER\u001b[0m \u001b[0mBY\u001b[0m \u001b[0mcreate_date\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 6\u001b[0m '''\n\u001b[0;32m----> 7\u001b[0;31m \u001b[0mone_train\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpandasql\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread_sql\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msql\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcon\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m", + "\u001b[0;31mNameError\u001b[0m: name 'pandasql' is not defined" + ] + } + ], "source": [ "sql = ''' SELECT trainid, lineid, traindirection, stationid, station_char, create_date, request_date, timint, train_message\n", " FROM test_day\n", @@ -407,6 +423,20 @@ "one_train = pandasql.read_sql(sql, con)" ] }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + }, { "cell_type": "code", "execution_count": 5, @@ -6842,7 +6872,7 @@ "name": "stdout", "output_type": "stream", "text": [ - "The number of station stops made is 51159\n" + "The number of station stops made is 53958\n" ] } ], @@ -6862,7 +6892,7 @@ }, { "cell_type": "code", - "execution_count": 15, + "execution_count": 12, "metadata": {}, "outputs": [ { @@ -6895,19 +6925,19 @@ " \n", " 0\n", " 1\n", - " 2290\n", - " 738\n", + " 1910\n", + " 747\n", " \n", " \n", " 1\n", " 2\n", - " 2041\n", - " 700\n", + " 1410\n", + " 704\n", " \n", " \n", " 2\n", " 4\n", - " 1306\n", + " 1103\n", " 457\n", " \n", " \n", @@ -6916,12 +6946,12 @@ ], "text/plain": [ " lineid Number of observed trips Number of scheduled trips\n", - "0 1 2290 738\n", - "1 2 2041 700\n", - "2 4 1306 457" + "0 1 1910 747\n", + "1 2 1410 704\n", + "2 4 1103 457" ] }, - "execution_count": 15, + "execution_count": 12, "metadata": {}, "output_type": "execute_result" } @@ -6954,25 +6984,25 @@ }, { "cell_type": "code", - "execution_count": 31, + "execution_count": 13, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", - "\n", "\n", " \n", @@ -6986,62 +7016,62 @@ " \n", " \n", " \n", - " \n", - " \n", + " \n", + " \n", " \n", " \n", " \n", " \n", - " \n", - " \n", + " \n", + " \n", " \n", " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", " \n", - " \n", - " \n", + " \n", + " \n", " \n", " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", " \n", - " \n", - " \n", + " \n", + " \n", " \n", " \n", " \n", " \n", - " \n", - " \n", + " \n", + " \n", " \n", " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", " \n", - " \n", - " \n", + " \n", + " \n", " \n", " \n", " \n", @@ -7050,19 +7080,19 @@ ], "text/plain": [ " lineid trip_id trip_duration\n", - "0 2 3637 0.0\n", - "1 1 1446 0.0\n", - "2 4 5075 0.0\n", - "3 4 4624 0.0\n", - "4 4 4644 0.0\n", - "5 4 4393 0.0\n", - "6 1 249 0.0\n", - "7 1 721 0.0\n", - "8 2 3218 0.0\n", - "9 1 50 0.0" + "0 4 15100 0.0\n", + "1 4 14892 0.0\n", + "2 4 14912 0.0\n", + "3 4 15188 0.0\n", + "4 2 13313 0.0\n", + "5 4 15017 0.0\n", + "6 4 15121 0.0\n", + "7 4 15219 0.0\n", + "8 2 13827 0.0\n", + "9 4 14714 0.0" ] }, - "execution_count": 31, + "execution_count": 13, "metadata": {}, "output_type": "execute_result" } @@ -7393,7 +7423,7 @@ }, { "cell_type": "code", - "execution_count": 17, + "execution_count": 14, "metadata": {}, "outputs": [], "source": [ @@ -7428,17 +7458,19 @@ }, { "cell_type": "code", - "execution_count": 22, + "execution_count": 15, "metadata": {}, "outputs": [ { "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAA6gAAAIpCAYAAACv2hXhAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMi4yLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvhp/UCwAAIABJREFUeJzs3XmYZGV5P/zvrYOsyuaIyGAgERAkLOOwBVBfcEElIBHBBQVDxPiqMWpUkmjERBNM8oJbRImgEKNC3MCEGATjq/iTZUAEcVBGZRlAmaAgqwF5fn/UGSzaGbqnp2rmTM/nc1111TnPWe7nnK7urm8/p05Xay0AAACwqj1iVXcAAAAAEgEVAACAnhBQAQAA6AUBFQAAgF4QUAEAAOgFARUAAIBeEFAB1lBVtW9VfX9V92MqRt3XqvrPqjqymz6qqi4Y4b5fVlXnjmp/y1F376q6pqrurKoXjGB/76iqj4yib6tKVX2yqo5b1f0AYOoEVIAZrqqurapnTmxvrX2jtbbdmGr+TVVdWVX3TxYQquq4qrqvqu7oHj+oqg9V1ebL29duX5+cbL3W2nNba6dN6WAevt5WVdWqatbQvv+1tfbsFd33NPx1kg+11jZorX1xeEEXWpc8Hqiqe4bmX7a0nbXW/qa19sfT6ciqCIZV9UdV9bWVWROA0RNQARiHhUnemuQ/prj+Ga21RyfZJMkhSR6f5NLhkDoKNTBTf/f9VpKrlragC60btNY2SHJ9kt8favvXiesPB24AWJlm6i9pACZRVc+oqkVD89dW1Z9V1RVVdXtVnVFV6wwtP7CqLq+q26rq/1TVTsvad2vttNbafya5Y3n61Fq7r7V2VZLDkyxO8uZl9PVtVXVjN+L6/arav6oOSPIXSQ7vRga/0637tap6T1V9M8ndSX67a/ujh56O+lB33FdX1f4Tzsszh+aHR2m/3j3f1tXca+Ilw1X1e1V1SbfvS6rq94aWfa0bbf5mdyznVtVjl3V+qupVVbWwqn5WVWdX1RO69h8m+e0kX+r6sfbynPeqenf39f50Vd2R5Iiu7RPd8id1I8Wvqqqbuscbl6fGUK0dquq87hiurqoXDi37ZFV9oAaXYN9RVd+qqq2Hlj+3G2G/vao+2J23o6rqd5N8KMm+3fH/z1DJTZa2v6p6RFfrlm5/V1TVDtM5JgBGR0AFYNhhSQ5IsnWSnZIclSRVtWuSU5O8OsmmST6a5OzlDUJT1Vr7VZKzkuw7cVlVbZfkdUl260Zdn5Pk2tbal5P8bQajsRu01nYe2uzlSY5J8ugk1y2l5B5JfpjksUnemeTzVbXJFLr6tO55o67mtyb0dZMMRpE/kMF5OyHJf1TVpkOrvTTJK5M8LsmjkvzZ0gpV1X5J/i6Dr9Hm3XF8Jklaa7+Th46M/nIKfZ/okCSfSrJhkjOWsc7TkjwpyXOTvL2qnrE8BapqgyRfSXJ6Bsf7siQnd1/TJV6a5B0ZjKZfn+Rvum0fl+TMJG/J4Ov04yS7J0lr7coMXhPf6I7/sZPtrzuGPZNsk2TjJC9O8rPlOR4ARk9ABWDYB1prN7XWfpbkS0l26dqPSfLR1tpFrbVfdZ/f/GUGb/DH5aYMQsVEv0qydpIdqmqt1tq1rbUfTrKvT7TWrmqt3d9au28py29J8r5uBPeMJN9P8vwV6v3A85Nc01r7l672p5NcneT3h9b5eGvtB621ezIIYLssbUcZhLlTW2uXdQH0z5PsVVVbjaCfSXJBa+1LrbUHur4szbtaa3e31r6T5LQkL1nOGgcn+UFr7fTufFya5ItJDh1a57Ottfnd1+lf8+vzcWCSy1trZ3XLTkwyPFK6LMva331JHpPkyUnSWvtea+0ny3k8AIyYgArAsOE36Hcn2aCb/q0kb+4u772tqm5LsmWSJ4yxL1tkKSNarbWFSf40yXFJbqmqzyy51PVh3DDJ8htba21o/rqM5tiekN8csb0ug2NbYlnn/GH31Vq7M8mtE/a1IiY7RxPXmc45+q0ke094HR2ewYjwEss6H08Yrt99vRZlckvdX2vt3CQfSXJSkp9W1Ueq6tHLeTwAjJiACsBU3JDkPa21jYYe63UjgiPX3cjo95N8Y2nLW2ufaq3tk0HgaUneu2TRMna5rPYltqiqGpp/YgYjuElyV5L1hpY9fjn2e1PXx2FPTHLjJNtNuq+qWj+Dy4ans6+lmexYksEfJZYYPkdTdUOS8ye8jjZorb1uCtvenGTOkpnu6zUczqfS/4dorb2vtTY3yY5JdkjypuXdBwCjJaACrBnWqqp1hh7Le5fWf07yx1W1Rw2sX1XPX9aIU1WtVYMbLD0iyayu5iMnK1JVs6pq+ySfziAInrCUdbarqv26z7/em+SeJA90i3+aZKta/jv1Pi7Jn3T9flGS7ZOc0y27PMmLu2Xz8tDLURd3tX97Gfs9J8m2VfXS7tgOzyAI/fty9i8ZnJNXVtUu3bH/bZKLWmvXTmNf0/WOqlq3uynRkVn2Z1WTX3/dlzweleTsJE/pzsda3WP3CZ9BXZZ/TzK3qn6/e/2+IcnsoeU/TTKnqtaayoF0dXfv9nVXkv/Nr19HAKwiAirAmuGcDILcksdxy7Nxa21+kldlcKfUn2fwb2SOephN/rmr85Ikf9lNv/xh1j+8qu5McnsGIebWJE9trS1thG7tJMdn8PnDn2QQLv+8W/Zv3fOtVXXZpAf2axdlcLOc/0nyniSHttZu7Za9I8nvZHDc78rgRkJJktba3d363+wuWX3IZ3K7fRyYwd2Ib83gX+8c2FqbymcnH6K1dl7Xl89lMJr4Oxnc2GdluiDJj5Kcm+TvWmtffZh1l3zdlzzOba3dnsFNrY7I4Bh+ksGNnya92VZr7acZXA58Qgbn8neSfDuDz0Ing5svXZPB5bpT+SzpRklOSXJbkmu7/vzGH0QAWLnqoR+5AQB4qKp6UgY3e6pJV15JuhH5mzL4Y8JSLwUHYPVjBBUAWC1U1QFVtVF3ifM7MrgT78WruFsAjJCACgCsLvbJ4BLjxRlcKnzINP/nKwA95RJfAAAAesEIKgAAAL0goAIAANALy/t/8MbisY99bNtqq61WdTcAAAAYg0svvfR/WmuzJ1uvFwF1q622yvz581d1NwAAABiDqrpuKuu5xBcAAIBeEFABAADoBQEVAACAXujFZ1ABAABWpvvuuy+LFi3Kvffeu6q7MqOss846mTNnTtZaa61pbS+gAgAAa5xFixbl0Y9+dLbaaqtU1aruzozQWsutt96aRYsWZeutt57WPlziCwAArHHuvffebLrppsLpCFVVNt100xUalRZQAQCANZJwOnorek4FVAAAgJ76xCc+kde97nXT3v5rX/taDjzwwEnX22CDDZZrv8cdd1z+8R//cbrdWiafQQUAABj1aGpro93fGmJKI6hV9caquqqqvltVn66qdapq66q6qKoWVtUZVfWobt21u/mF3fKtxnkAAAAAq5u77rorz3/+87Pzzjtnxx13zBlnnJFLLrkkv/d7v5edd945u+++e+64444kyU033ZQDDjgg22yzTd761rc+uI9zzz03e+21V+bOnZsXvehFufPOO5MkX/7yl/PkJz85c+fOzec///kH15846rnjjjvm2muv/Y2+/cM//EN222237LTTTnnnO9/5YPt73vOebLvtttlnn33y/e9/f9SnJMkURlCraoskf5Jkh9baPVV1ZpIXJ3lekhNba5+pqo8kOTrJSd3zz1trT6qqFyd5b5LDx9J7AACA1dCXv/zlPOEJT8h//Md/JEluv/327LrrrjnjjDOy22675Re/+EXWXXfdJMnll1+eb3/721l77bWz3Xbb5fWvf33WXXfdvPvd7855552X9ddfP+9973tzwgkn5K1vfWte9apX5atf/Wqe9KQn5fDDly+KnXvuubnmmmty8cUXp7WWgw46KF//+tez/vrr5zOf+Uwuv/zy3H///Zk7d26e+tSnjvy8TPUS31lJ1q2q+5Ksl+TmJPsleWm3/LQkx2UQUA/uppPks0k+VFXVmjFuAACAJPnd3/3dvPnNb87b3va2HHjggdloo42y+eabZ7fddkuSPOYxj3lw3f333z8bbrhhkmSHHXbIddddl9tuuy3f+973svfeeydJ/vd//zd77bVXrr766my99dbZZpttkiRHHHFETj755Cn369xzz825556bXXfdNUly55135pprrskdd9yRQw45JOutt16S5KCDDlrxk7AUkwbU1tqNVfWPSa5Pck+Sc5NcmuS21tr93WqLkmzRTW+R5IZu2/ur6vYkmyb5n+H9VtUxSY5Jkic+8YkrfiQAAACriW233TaXXXZZzjnnnLz97W/Pfvvtt8x111577QenH/nIR+b+++9Pay3Petaz8ulPf/oh615++eXL3M+sWbPywAMPPDi/tH8H01rLn//5n+fVr371Q9rf9773TXpMozDpZ1CrauMMRkW3TvKEJOsnOWBFC7fWTm6tzWutzZs9e/aK7g4AAGC1cdNNN2W99dbLEUcckbe85S256KKLcvPNN+eSSy5Jktxxxx25//77l7n9nnvumW9+85tZuHBhksFnWn/wgx/kyU9+cq699tr88Ic/TJKHBNitttoql112WZLksssuy49//OPf2O9znvOcnHrqqQ9+nvXGG2/MLbfckqc97Wn54he/mHvuuSd33HFHvvSlL43mREwwlUt8n5nkx621xUlSVZ9PsneSjapqVjeKOifJjd36NybZMsmiqpqVZMMkt4685wAAAKupK6+8Mm95y1vyiEc8ImuttVZOOumktNby+te/Pvfcc0/WXXfdnHfeecvcfvbs2fnEJz6Rl7zkJfnlL3+ZJHn3u9+dbbfdNieffHKe//znZ7311su+++774M2WXvjCF+b000/PU57ylOyxxx7Zdtttf2O/z372s7NgwYLstddeSQb/fuaTn/xk5s6dm8MPPzw777xzHve4xz14KfKo1WQfDa2qPZKcmmS3DC7x/USS+UmeluRzQzdJuqK19uGqem2S322t/XF3k6Q/aK0d9nA15s2b1+bPn7/iRwMAADAFCxYsyPbbb7+quzEjLe3cVtWlrbV5k2076SW+rbWLMrjZ0WVJruy2OTnJ25K8qaoWZvAZ01O6TU5JsmnX/qYkx079UAAAAFhTTekuvq21dyZ554TmHyXZfSnr3pvkRSveNQAAANYkk46gAgAAwMogoAIAANALAioAAAC9MKXPoK5KVdPbbpKbEwMAANAzRlABAAB64Nprr82OO+64qrvxG57xjGdkZf1b0N6PoAIAAIzbdK/cXJa+XNF5//33Z9as1Sf2GUEFAABYBU444YTsuOOO2XHHHfO+970vySBQvuxlL8v222+fQw89NHfffXeS5Nhjj80OO+yQnXbaKX/2Z3+WJFm8eHFe+MIXZrfddstuu+2Wb37zm0mS4447Li9/+cuz99575+Uvf3n23HPPXHXVVQ/WXTIietddd+UP//APs/vuu2fXXXfNWWedlSS555578uIXvzjbb799DjnkkNxzzz0r7ZysPlEaAABghrj00kvz8Y9/PBdddFFaa9ljjz3y9Kc/Pd///vdzyimnZO+9984f/uEf5sMf/nBe+cpX5gtf+EKuvvrqVFVuu+22JMkb3vCGvPGNb8w+++yT66+/Ps95znOyYMGCJMn3vve9XHDBBVl33XVz4okn5swzz8y73vWu3Hzzzbn55pszb968/MVf/EX222+/nHrqqbntttuy++6755nPfGY++tGPZr311suCBQtyxRVXZO7cuSvtvBhBBQAAWMkuuOCCHHLIIVl//fWzwQYb5A/+4A/yjW98I1tuuWX23nvvJMkRRxyRCy64IBtuuGHWWWedHH300fn85z+f9dZbL0ly3nnn5XWve1122WWXHHTQQfnFL36RO++8M0ly0EEHZd11102SHHbYYfnsZz+bJDnzzDNz6KGHJknOPffcHH/88dlll13yjGc8I/fee2+uv/76fP3rX88RRxyRJNlpp52y0047rbTzYgQVAACgJ2rCh2GrKrNmzcrFF1+c888/P5/97GfzoQ99KF/96lfzwAMP5MILL8w666zzG/tZf/31H5zeYostsummm+aKK67IGWeckY985CNJktZaPve5z2W77bYb70EtByOoAAAAK9m+++6bL37xi7n77rtz11135Qtf+EL23XffXH/99fnWt76VJPnUpz6VffbZJ3feeWduv/32PO95z8uJJ56Y73znO0mSZz/72fngBz/44D4vv/zyZdY7/PDD8/d///e5/fbbHxwRfc5znpMPfvCDad0dnb797W8nSZ72tKflU5/6VJLku9/9bq644orRn4BlEFABAABWsrlz5+aoo47K7rvvnj322CN/9Ed/lI033jjbbbdd/umf/inbb799fv7zn+c1r3lN7rjjjhx44IHZaaedss8+++SEE05IknzgAx/I/Pnzs9NOO2WHHXZ4cGR0aQ499NB85jOfyWGHHfZg2zve8Y7cd9992WmnnfKUpzwl73jHO5Ikr3nNa3LnnXdm++23z1/91V/lqU996nhPxpBqPbj/8bx589qy/q/OdG/33IPDAgAAemrBggXZfvvtV3U3ZqSlnduqurS1Nm+ybY2gAgAA0AsCKgAAAL0goAIAANALAioAALBG6sP9eGaaFT2nAioAALDGWWeddXLrrbcKqSPUWsutt9661P/LOlWzRtgfAACA1cKcOXOyaNGiLF68eFV3ZUZZZ511MmfOnGlvL6ACAABrnLXWWitbb731qu4GE7jEFwAAgF4QUAEAAOgFARUAAIBeEFABAADoBQEVAACAXhBQAQAA6AUBFQAAgF4QUAEAAOgFARUAAIBeEFABAADoBQEVAACAXhBQAQAA6AUBFQAAgF4QUAEAAOgFARUAAIBeEFABAADoBQEVAACAXhBQAQAA6AUBFQAAgF4QUAEAAOgFARUAAIBeEFABAADoBQEVAACAXhBQAQAA6AUBFQAAgF4QUAEAAOgFARUAAIBeEFABAADoBQEVAACAXhBQAQAA6IVJA2pVbVdVlw89flFVf1pVm1TVV6rqmu554279qqoPVNXCqrqiquaO/zAAAABY3U0aUFtr32+t7dJa2yXJU5PcneQLSY5Ncn5rbZsk53fzSfLcJNt0j2OSnDSOjgMAADCzLO8lvvsn+WFr7bokByc5rWs/LckLuumDk5zeBi5MslFVbT6S3gIAADBjLW9AfXGST3fTm7XWbu6mf5Jks256iyQ3DG2zqGsDAACAZZpyQK2qRyU5KMm/TVzWWmtJ2vIUrqpjqmp+Vc1fvHjx8mwKAADADLQ8I6jPTXJZa+2n3fxPl1y62z3f0rXfmGTLoe3mdG0P0Vo7ubU2r7U2b/bs2cvfcwAAAGaU5QmoL8mvL+9NkrOTHNlNH5nkrKH2V3R3890zye1DlwIDAADAUs2aykpVtX6SZyV59VDz8UnOrKqjk1yX5LCu/Zwkz0uyMIM7/r5yZL0FAABgxppSQG2t3ZVk0wltt2ZwV9+J67Ykrx1J7wAAAFhjLO9dfAEAAGAsBFQAAAB6QUAFAACgFwRUAAAAekFABQAAoBcEVAAAAHpBQAUAAKAXBFQAAAB6QUAFAACgFwRUAAAAekFABQAAoBcEVAAAAHpBQAUAAKAXBFQAAAB6QUAFAACgFwRUAAAAekFABQAAoBcEVAAAAHpBQAUAAKAXBFQAAAB6QUAFAACgFwRUAAAAekFABQAAoBcEVAAAAHpBQAUAAKAXBFQAAAB6QUAFAACgFwRUAAAAekFABQAAoBcEVAAAAHpBQAUAAKAXBFQAAAB6QUAFAACgFwRUAAAAekFABQAAoBcEVAAAAHpBQAUAAKAXBFQAAAB6QUAFAACgFwRUAAAAekFABQAAoBcEVAAAAHpBQAUAAKAXBFQAAAB6QUAFAACgFwRUAAAAekFABQAAoBcEVAAAAHpBQAUAAKAXBFQAAAB6YUoBtao2qqrPVtXVVbWgqvaqqk2q6itVdU33vHG3blXVB6pqYVVdUVVzx3sIAAAAzARTHUF9f5Ivt9aenGTnJAuSHJvk/NbaNknO7+aT5LlJtukexyQ5aaQ9BgAAYEaaNKBW1YZJnpbklCRprf1va+22JAcnOa1b7bQkL+imD05yehu4MMlGVbX5yHsOAADAjDKVEdStkyxO8vGq+nZVfayq1k+yWWvt5m6dnyTZrJveIskNQ9sv6toAAABgmaYSUGclmZvkpNbarknuyq8v502StNZakrY8havqmKqaX1XzFy9evDybAgAAMANNJaAuSrKotXZRN//ZDALrT5dcuts939ItvzHJlkPbz+naHqK1dnJrbV5rbd7s2bOn238AAABmiEkDamvtJ0luqKrtuqb9k3wvydlJjuzajkxyVjd9dpJXdHfz3TPJ7UOXAgMAADATVS37MUWzprje65P8a1U9KsmPkrwyg3B7ZlUdneS6JId1656T5HlJFia5u1sXAAAAHtaUAmpr7fIk85ayaP+lrNuSvHYF+wUAAMAaZqr/BxUAAADGSkAFAACgFwRUAAAAekFABQAAoBcEVAAAAHpBQAUAAKAXBFQAAAB6QUAFAACgFwRUAAAAemHWqu7Amq5qetu1Ntp+AAAArGpGUAEAAOgFARUAAIBeEFABAADoBQEVAACAXhBQAQAA6AUBFQAAgF4QUAEAAOgFARUAAIBeEFABAADoBQEVAACAXhBQAQAA6AUBFQAAgF4QUAEAAOgFARUAAIBeEFABAADoBQEVAACAXhBQAQAA6AUBFQAAgF4QUAEAAOgFARUAAIBeEFABAADoBQEVAACAXhBQAQAA6AUBFQAAgF4QUAEAAOgFARUAAIBeEFABAADoBQEVAACAXhBQAQAA6AUBFQAAgF4QUAEAAOgFARUAAIBeEFABAADoBQEVAACAXhBQAQAA6AUBFQAAgF4QUAEAAOgFARUAAIBeEFABAADoBQEVAACAXhBQAQAA6IUpBdSquraqrqyqy6tqfte2SVV9paqu6Z437tqrqj5QVQur6oqqmjvOAwAAAGBmWJ4R1P+ntbZLa21eN39skvNba9skOb+bT5LnJtmmexyT5KRRdRYAAICZa0Uu8T04yWnd9GlJXjDUfnobuDDJRlW1+QrUAQAAYA0w1YDakpxbVZdW1TFd22attZu76Z8k2ayb3iLJDUPbLuraHqKqjqmq+VU1f/HixdPoOgAAADPJrCmut09r7caqelySr1TV1cMLW2utqtryFG6tnZzk5CSZN2/ecm0LAADAzDOlEdTW2o3d8y1JvpBk9yQ/XXLpbvd8S7f6jUm2HNp8TtcGAAAAyzRpQK2q9avq0Uumkzw7yXeTnJ3kyG61I5Oc1U2fneQV3d1890xy+9ClwAAAALBUU7nEd7MkX6iqJet/qrX25aq6JMmZVXV0kuuSHNatf06S5yVZmOTuJK8cea8BAACYcSYNqK21HyXZeSnttybZfyntLclrR9I7AAAA1hgr8m9mAAAAYGQEVAAAAHpBQAUAAKAXBFQAAAB6QUAFAACgFwRUAAAAekFABQAAoBcEVAAAAHpBQAUAAKAXBFQAAAB6QUAFAACgFwRUAAAAekFABQAAoBcEVAAAAHpBQAUAAKAXBFQAAAB6QUAFAACgFwRUAAAAekFABQAAoBcEVAAAAHpBQAUAAKAXBFQAAAB6QUAFAACgFwRUAAAAekFABQAAoBcEVAAAAHpBQAUAAKAXBFQAAAB6QUAFAACgFwRUAAAAekFABQAAoBcEVAAAAHpBQAUAAKAXBFQAAAB6QUAFAACgFwRUAAAAekFABQAAoBcEVAAAAHpBQAUAAKAXBFQAAAB6QUAFAACgFwRUAAAAekFABQAAoBcEVAAAAHpBQAUAAKAXBFQAAAB6QUAFAACgFwRUAAAAekFABQAAoBcEVAAAAHphygG1qh5ZVd+uqn/v5reuqouqamFVnVFVj+ra1+7mF3bLtxpP1wEAAJhJlmcE9Q1JFgzNvzfJia21JyX5eZKju/ajk/y8az+xWw8AAAAe1pQCalXNSfL8JB/r5ivJfkk+261yWpIXdNMHd/Pplu/frQ8AAADLNNUR1PcleWuSB7r5TZPc1lq7v5tflGSLbnqLJDckSbf89m59AAAAWKZJA2pVHZjkltbapaMsXFXHVNX8qpq/ePHiUe4aAACA1dBURlD3TnJQVV2b5DMZXNr7/iQbVdWsbp05SW7spm9MsmWSdMs3THLrxJ221k5urc1rrc2bPXv2Ch0EAAAAq79JA2pr7c9ba3Naa1sleXGSr7bWXpbkv5Mc2q12ZJKzuumzu/l0y7/aWmsj7TUAAAAzzor8H9S3JXlTVS3M4DOmp3TtpyTZtGt/U5JjV6yLAAAArAlmTb7Kr7XWvpbka930j5LsvpR17k3yohH0DQAAgDXIioygAgAAwMgIqAAAAPSCgAoAAEAvCKgAAAD0goAKAABALwioAAAA9IKACgAAQC8IqAAAAPSCgAoAAEAvCKgAAAD0goAKAABALwioAAAA9IKACgAAQC/MWtUdAAAAoD+qprddG0FtI6gAAAD0goAKAABALwioAAAA9IKACgAAQC8IqAAAAPSCgAoAAEAvCKgAAAD0goAKAABALwioAAAA9IKACgAAQC8IqAAAAPSCgAoAAEAvCKgAAAD0goAKAABALwioAAAA9IKACgAAQC8IqAAAAPSCgAoAAEAvCKgAAAD0goAKAABALwioAAAA9IKACgAAQC8IqAAAAPSCgAoAAEAvCKgAAAD0goAKAABALwioAAAA9IKACgAAQC8IqAAAAPSCgAoAAEAvCKgAAAD0goAKAABALwioAAAA9IKACgAAQC8IqAAAAPSCgAoAAEAvTBpQq2qdqrq4qr5TVVdV1bu69q2r6qKqWlhVZ1TVo7r2tbv5hd3yrcZ7CAAAAMwEUxlB/WWS/VprOyfZJckBVbVnkvcmObG19qQkP09ydLf+0Ul+3rWf2K0HAAAAD2vSgNoG7uxm1+oeLcl+ST7btZ+W5AXd9MHdfLrl+1dVjazHAAAAzEhT+gxqVT2yqi5PckuSryTFDH3RAAAW9klEQVT5YZLbWmv3d6ssSrJFN71FkhuSpFt+e5JNR9lpAAAAZp4pBdTW2q9aa7skmZNk9yRPXtHCVXVMVc2vqvmLFy9e0d0BAACwmluuu/i21m5L8t9J9kqyUVXN6hbNSXJjN31jki2TpFu+YZJbl7Kvk1tr81pr82bPnj3N7gMAADBTTOUuvrOraqNuet0kz0qyIIOgemi32pFJzuqmz+7m0y3/amutjbLTAAAAzDyzJl8lmyc5raoemUGgPbO19u9V9b0kn6mqdyf5dpJTuvVPSfIvVbUwyc+SvHgM/QYAAGCGmTSgttauSLLrUtp/lMHnUSe235vkRSPpHQAAAGuM5foMKgAAAIyLgAoAAEAvCKgAAAD0goAKAABALwioAAAA9IKACgAAQC8IqAAAAPSCgAoAAEAvCKgAAAD0goAKAABALwioAAAA9IKACgAAQC8IqAAAAPSCgAoAAEAvCKgAAAD0goAKAABALwioAAAA9IKACgAAQC8IqAAAAPSCgAoAAEAvCKgAAAD0goAKAABALwioAAAA9IKACgAAQC8IqAAAAPSCgAoAAEAvCKgAAAD0goAKAABALwioAAAA9IKACgAAQC8IqAAAAPSCgAoAAEAvCKgAAAD0goAKAABALwioAAAA9IKACgAAQC8IqAAAAPSCgAoAAEAvCKgAAAD0goAKAABALwioAAAA9IKACgAAQC8IqAAAAPSCgAoAAEAvCKgAAAD0goAKAABALwioAAAA9IKACgAAQC8IqAAAAPSCgAoAAEAvCKgAAAD0wqQBtaq2rKr/rqrvVdVVVfWGrn2TqvpKVV3TPW/ctVdVfaCqFlbVFVU1d9wHAQAAwOpvKiOo9yd5c2tthyR7JnltVe2Q5Ngk57fWtklyfjefJM9Nsk33OCbJSSPvNQAAADPOpAG1tXZza+2ybvqOJAuSbJHk4CSndaudluQF3fTBSU5vAxcm2aiqNh95zwEAAJhRluszqFW1VZJdk1yUZLPW2s3dop8k2ayb3iLJDUObLeraJu7rmKqaX1XzFy9evJzdBgAAYKaZckCtqg2SfC7Jn7bWfjG8rLXWkrTlKdxaO7m1Nq+1Nm/27NnLsykAAAAz0JQCalWtlUE4/dfW2ue75p8uuXS3e76la78xyZZDm8/p2gAAAGCZpnIX30pySpIFrbUThhadneTIbvrIJGcNtb+iu5vvnkluH7oUGAAAAJZq1hTW2TvJy5NcWVWXd21/keT4JGdW1dFJrktyWLfsnCTPS7Iwyd1JXjnSHgMAADAjTRpQW2sXJKllLN5/Keu3JK9dwX4BAACwhlmuu/gCAADAuAioAAAA9IKACgAAQC8IqAAAAPSCgAoAAEAvCKgAAAD0goAKAABALwioAAAA9IKACgAAQC8IqAAAAPSCgAoAAEAvCKgAAAD0goAKAABALwioAAAA9IKACgAAQC8IqAAAAPSCgAoAAEAvCKgAAAD0goAKAABALwioAAAA9IKACgAAQC8IqAAAAPSCgAoAAEAvCKgAAAD0goAKAABALwioAAAA9IKACgAAQC8IqAAAAPSCgAoAAEAvCKgAAAD0goAKAABALwioAAAA9IKACgAAQC8IqAAAAPTCrFXdgb6pmt52rY22HwAAAGsaARUAAKDH1qRBNJf4AgAA0AsCKgAAAL0goAIAANALAioAAAC9IKACAADQCwIqAAAAvSCgAgAA0AsCKgAAAL0goAIAANALAioAAAC9IKACAADQCwIqAAAAvSCgAgAA0AsCKgAAAL0waUCtqlOr6paq+u5Q2yZV9ZWquqZ73rhrr6r6QFUtrKorqmruODsPAADAzDGVEdRPJDlgQtuxSc5vrW2T5PxuPkmem2Sb7nFMkpNG000AAABmukkDamvt60l+NqH54CSnddOnJXnBUPvpbeDCJBtV1eaj6iwAAAAz13Q/g7pZa+3mbvonSTbrprdIcsPQeou6NgAAAHhYK3yTpNZaS9KWd7uqOqaq5lfV/MWLF69oNwAAAFjNTTeg/nTJpbvd8y1d+41Jthxab07X9htaaye31ua11ubNnj17mt0AAABgpphuQD07yZHd9JFJzhpqf0V3N989k9w+dCkwAAAALNOsyVaoqk8neUaSx1bVoiTvTHJ8kjOr6ugk1yU5rFv9nCTPS7Iwyd1JXjmGPgMAADADTRpQW2svWcai/Zeybkvy2hXtFAAAAGueFb5JEgAAAIyCgAoAAEAvCKgAAAD0goAKAABALwioAAAA9IKACgAAQC8IqAAAAPTCpP8HFQAAgNVQ1TQ3bCPtxvIwggoAAEAvCKgAAAD0goAKAABALwioAAAA9IKACgAAQC8IqAAAAPSCgAoAAEAvCKgAAAD0goAKAABALwioAAAA9IKACgAAQC8IqAAAAPSCgAoAAEAvCKgAAAD0goAKAABALwioAAAA9IKACgAAQC8IqAAAAPSCgAoAAEAvCKgAAAD0goAKAABALwioAAAA9IKACgAAQC8IqAAAAPSCgAoAAEAvCKgAAAD0goAKAABALwioAAAA9MKsVd0BAACA1UnV9LZrbbT9mIkEVAAAiNABfeASXwAAAHrBCCpMk7+yAgDAaBlBBQAAoBeMoAIAAGum6V4SF5fEjYsRVAAAAHrBCCozis+FAgDA6ssIKgAAAL1gBBUAAFitTfsqutF2Y3I+8zopARUAYERm+kdNZvrxrWzOJ/wml/gCAADQC0ZQGSt/GRwd53K0nE8AGB+/Z5kuARVgBvLGgKma6a8Vx7d0q8vxMTpeK6wuxhJQq+qAJO9P8sgkH2utHT+OOsAUTPM3Uk3zw/jT/UU2039xOr6lW12Oj9HxWmF5eL0sw7ROzEw/KcwUIw+oVfXIJP+U5FlJFiW5pKrObq19b9S1AFgzzeQ3rTP52ABgMuMYQd09ycLW2o+SpKo+k+TgJAIqAKul6YRGgRGYEfxbFFaycQTULZLcMDS/KMkeY6jDNEz/f0T54QRJ/KJm+azMy/C8NkfL+Rwt5xOYolV2k6SqOibJMd3snVX1/dHuP49N8j+j3OcaXS/TrTfNzz/O4PPpazdazudoqTfSWsm0Xi/T/dy41+ZI6zmfo63nfI62np8tI7PSj2/NrvdbU9nHOALqjUm2HJqf07U9RGvt5CQnj6F+kqSq5rfW5o1r/+qptzrUUk899dacejP52NRTT71VV28mH5t6/az3iFF1ZsglSbapqq2r6lFJXpzk7DHUAQAAYAYZ+Qhqa+3+qnpdkv/K4N/MnNpau2rUdQAAAJhZxvIZ1NbaOUnOGce+l8PYLh9WT73VqJZ66qm35tSbycemnnrqrbp6M/nY1OthvWrugw8AAEAPjOMzqAAAALDcBFQAAAB6QUAFAACgFwTUaaqqJ1fV/lW1wYT2A8ZUb/eq2q2b3qGq3lRVzxtHraXUPn1l1Olq7dMd27PHtP89quox3fS6VfWuqvpSVb23qjYcQ70/qaotJ19zZPUeVVWvqKpndvMvraoPVdVrq2qtMdX87ar6s6p6f1WdUFV/vOQcA8DKVlWPW9V9GKeq2nRV9wHGacYH1Kp65Rj2+SdJzkry+iTfraqDhxb/7RjqvTPJB5KcVFV/l+RDSdZPcmxV/eWIa5094fGlJH+wZH6Utbp6Fw9NvyqDY3t0kndW1bGjrpfk1CR3d9PvT7Jhkvd2bR8fQ72/SXJRVX2jqv7fqpo9hhrDPp7k+UneUFX/kuRFSS5KsluSj426WPe98JEk63Q11k6yZZILq+oZo67HzOONJH1QVRtW1fFVdXVV/ayqbq2qBV3bRiu5L/85hn0+pqr+rqr+papeOmHZh8dQ7/FVdVJV/VNVbVpVx1XVlVV1ZlVtPuJam0x4bJrk4qrauKo2GWWtrt4BQ9MbVtUpVXVFVX2qqjYbQ73jq+qx3fS8qvpRBu8rrquqp4+h3mVV9faq+p1R73sZ9eZV1X9X1Serasuq+kpV3V5Vl1TVrmOot0FV/XVVXdXVWVxVF1bVUaOu1dWbVVWvrqovd6+TK6rqP7s/5o9l4OBh+jLyu/lW1SO74/ubqtp7wrK3T3vHrbUZ/Uhy/Rj2eWWSDbrprZLMT/KGbv7bY6r3yCTrJflFksd07esmuWLEtS5L8skkz0jy9O755m766WM4tm8PTV+SZHY3vX6SK8dQb8HwsU5Ydvk4ji+DPwQ9O8kpSRYn+XKSI5M8egz1ruieZyX5aZJHdvM16tdKt98rh2qsl+Rr3fQTx/S9sGGS45NcneRnSW5NsqBr22jU9Sbpy3+OYZ+PSfJ3Sf4lyUsnLPvwGOo9PslJSf4pyaZJjuu+pmcm2XwM9TaZ8Ng0ybVJNk6yyRjqHTDhtXNKkiuSfCrJZmOod3ySx3bT85L8KMnCJNeN6efnZUnenuR3Rr3vpdSal+S/u98PWyb5SpLbu5/bu46h3gZJ/jrJVV2dxUkuTHLUmI7vv5K8Lcnjh9oe37WdO4Z6c5fxeGqSm8dQ73Pd6/MFSc7u5tde8joaQ70vZ/BH/GO777m3da+b1yc5a8S1Hkjy4wmP+7rnH43h2C4bmv5Ykncn+a0kb0zyxTHUu3Jo+r+T7NZNb5tk/hjq/TjJPya5PsnF3XE9YdR1hupdnOS5SV6S5IYkh3bt+yf51hjqnZXkqCRzkrwpyTuSbJPktCR/O4Z6n87g9+yeXc053fRJSc4YQ72Jv2eHf98uGkO9j2XwO/VPk1ya5IShZdP+2TKWF9vKfnQ//Jb2uDLJL8dQ76oJ8xt0P4xPyJhCztKmu/mR1ssgTL0xgzcfu3RtI/8BP1TvOxm8Od104g/aicc6onr/luSV3fTHk8zrprdNcskY6k0MwWslOaj7gbV4DPW+m+RR3Tm9I92b/gxGOBeMod6V+fWbnI2Hv4ZJvjuGet5EjrbeSnsT2dXzRnK09VbaG8nM/DeR35/OshWo96skX+1eJxMf94yh3uUT5v8yyTcz+N07jp8tw+9brn+4voyg1pu7n2W/O9T241Ef09C+h3+uTDyv43gPuCDJrG76wgnLxvGH/OHj2zfJh5P8pHttHrOSXyvjeB/4nQnzl3TPj0hy9Rjq/WA6y1ag3q8y+OPo8O/ZJfP/O4Z6VwxNz8rgf6B+PoMr6qb99RtpJ1fVI4ORol26Nx7Dj62S3DSGel9NF94mfFFOT/KrMdS7KMl63fQjhto3HMcvlm7fczIIcx+a+ANjxHWuHfrG+VG6UZsMQv84ftBvmOQTSX7Yndf7urr/f5Kdx1Bvmd+cS76mI673xu54rkvyJ0nOT/LPGQTJd46h3hsyCDb/nMGo5pLwPzvJ18dQz5vI0dZbaW8iu316Izm+4xvrG8lJXisz4U3kuUnemqGR9SSbZfBHm/PGUO+7SbZZxrIbxlBvQYbeP3RtR2UwQn3dOL9+Sd49Ydk4vheWvGc5IYOPCY3zD+uLMvijyZu737c1tGwcVyq9vnt97pfBVS7vz+Cqtncl+Zcx1PuN3zUZXMV3QJKPj6HetzK4yuxFGbx3eUHX/vSM5w97/yfJPt30QUn+a2jZON5HXNgd2/D790ckOTzJRWOod02SJy5j2Th+tvzGz+Mk78zgvcs1093vrMwM/57BJbeXT1xQVV8bQ71XJLl/uKG1dn+SV1TVR8dQ72mttV92dR4Yal8rg0tFR661tijJi6rq+RlcVjwWrbWtlrHogSSHjKHe7UmO6m7is3UGf1hY1Fr76ahrdQ5/mL7cvaxl09VaO7Gqzuimb6rBDa6emeSfW2sXP/zW06r3/qo6L8n2Sf6/1trVXfviJE8bdb0k11XVW5OctuRr1n3m56gMRnVGbUGSV7fWrpm4oKrGUW/tqnrEku/z1tp7qurGJF/P4I82o/Z/27u7UMvKOo7j39+MV5M1BmYyEhUpWGRFL4ZgryBNFGPQkE5IQSE00ER1U1Q0FV3okbAcxi4E8WIGDLoYC2UIbTIlJL1xxkQHhKFIKgOtjvbq/Lt4nqOn40g4Z639dr4fWMw+a529f/vZs/fZz7Oel7V6HYK1i6FtHjqsqr7X35/X99dvL1BD56xyTpIv04a4vyJJqn97Ms4aDDcCdyS5Bjic5Ae0M8kfBF7w/TSkqroHuCfJHuAy2t+eIecb/SNt8bqtQCX5WFUd6nPgnh0wZ8XTSS6tqnuT7KAN6aeqTibJCHlX0EYS3N3/phTt5PdPgE+MkPctXvw9uGeEvJ/S3od3ruyoqluS/AHYN0LebUnOrKrlqnpuHlqS84FHhw5bVWfZQRsBtmXojFVuojWCofXonw08keRcRvicV9W+JMeA3bTRGGfQRhMcoo0KGdrxUzyHZ2knFw+PkPc5YIlW7/sQsDvJLcDvgatHyNsN3JTkAtoJms8C9DVC9o+QdyVtrZP9SZ7q+86inUi8coS879NGtP32FMeWRsh7IMn2qnruvVFV3+51lx+e7oPm+e9qSZptSV5Jq0ReDqwsrrNSibymqp4cOG8n7Wz/CypUKxX0gfOWaEOV71yzfzuwr6ouGDjvO8BSVS2v2X8+7fXcOWTemowdwNeA11XVuSNl7F2z68aqWqlILlXVp0bIfD//W5H8Ha0ieXM/kTlk1q1VNUYF51RZb+X5SuSXaGX8NL0SWVW/GjjvLbRh2SuVyM9U1fFeidxVVTcMmdczL6T1xN23+jOxtvI1cN55tF6UaeZ9uKrGWJhpYuVbnUU7YfKGqnpoA/zfLUreG4FtE847j8l91t9NO+n1GHAhcAnwcFXdMXRWz7sYqKq6P8mbaL3fj8xV3tBdvW5ubm7T2OjDi82bnzzaQm9vXtTybZS8RSgbbUrEo7STCSeAy1cdG2N4/aTz9ixq3gZ4LTdC+R5Z4Ly9tGG+D9AWQbyLNqf+l8DXJ5D383nMG/RJurm5uU1rY8S50uaZZ95sZI2Vx3RW5zdvzrLMM+808yZyJY5FyluUOaiSNoAkR1/sEG1BE/PMM2+EvEUuW7ep+lC/qjrRh2r/OMlre6Z5s5u3yGUzb/7z/lNtDu8zSR6rqr/27L8nOfl/7rth82ygSponr6YtorB2rmloK/OZZ5554+QtctkA/pjkbdUXW6yq5SQfBW4GLjJvpvMWuWzmzX/ev5JsqbYw5jtWdibZSpvTb94p2ECVNE8mvWK3eeaZN/msaeRNenV+8+YzyzzzXqpJX4ljIfJcxVeSJEmSNBPGuA6cJEmSJEkvmQ1USZIkSdJMsIEqSdIIknwxyZZpPw9JkuaJc1AlSRpBkhPAO6vqz9N+LpIkzQt7UCVJWqckL0tye5IHkzyUZC+wDTiS5Ej/nV1JjvXj166673KS65P8JsldSV7V938hycNJjia5dTolkyRpsuxBlSRpnZJ8HNheVVf3n7cCD9J7UJNsA+6jXSfuSeBnwA1VdShJAVdV1cEk3wTOqarPJ3kceH1V/TPJWVX11FQKJ0nSBNmDKknS+h0DLktybZL3VNVf1hx/F/CLqnqiX3PvIPDefuwk8KN++wBwab99FDiY5CrWXLdPkqRFZQNVkqR1qqrjwNtpDdXv9p7Q0364/u9HgP39ce9Pcsb6nqUkSbPPBqokSevUh/A+U1UHgOtojcq/AS/vv/Jr4H1Jzk6yGdgF3N2PbQJ29tufBO5Nsgl4TVUdAb4CbAXOnEhhJEmaIs/GSpK0fhcB1yU5Cfwb2A1cAhxO8nhVfSDJV4EjQIDbq+q2ft+ngYuTfAP4E3AFsBk40OeyhjZf1TmokqSF5yJJkiRNUZLlqrJ3VJIkHOIrSZIkSZoR9qBKkiRJkmaCPaiSJEmSpJlgA1WSJEmSNBNsoEqSJEmSZoINVEmSJEnSTLCBKkmSJEmaCTZQJUmSJEkz4b/nSeiMphG2/QAAAABJRU5ErkJggg==\n", + "image/png": "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\n", "text/plain": [ "
" ] }, - "metadata": {}, + "metadata": { + "needs_background": "light" + }, "output_type": "display_data" } ], @@ -7461,7 +7493,7 @@ }, { "cell_type": "code", - "execution_count": 14, + "execution_count": 16, "metadata": {}, "outputs": [ { @@ -7492,53 +7524,53 @@ "
\n", " \n", " \n", - " \n", - " \n", + " \n", + " \n", " \n", " \n", " \n", - " \n", - " \n", + " \n", + " \n", " \n", " \n", " \n", - " \n", - " \n", + " \n", + " \n", " \n", " \n", " \n", - " \n", + " \n", " \n", " \n", " \n", " \n", - " \n", - " \n", + " \n", + " \n", " \n", " \n", " \n", - " \n", - " \n", + " \n", + " \n", " \n", " \n", " \n", - " \n", - " \n", + " \n", + " \n", " \n", " \n", " \n", - " \n", - " \n", + " \n", + " \n", " \n", " \n", " \n", - " \n", - " \n", + " \n", + " \n", " \n", " \n", " \n", - " \n", - " \n", + " \n", + " \n", " \n", " \n", "
0236374151000.0
1114464148920.0
245075149120.0
344624151880.0
4446442133130.0
544393150170.0
612494151210.0
717214152190.0
823218138270.0
91504147140.0
0[BSP1, SGL1, YNG1]295[YNG2, SGL2, BSP2]343
1[YNG2, SGL2, BSP2]265[BSP1, SGL1, YNG1]334
2[SGL2, BSP2]64[YIE1, YIE2]65
3[BSP1, SGL1][YIE2, YIE1]22
4[YNG2, BSP2]17[VMC1, VMC2]16
5[SGL1, YNG1]11[VMC2, VMC1]13
6[BSP1, YNG1]10[STA1, UNI1]7
7[LAW2, EGL2, DAV2]6[FIN2, FIN1]7
8[YNG2, SGL2]5[FIN1, FIN2]7
9[SGL2, BSP2, YNG2]2[EGL2, DAV2]5
\n", @@ -7546,19 +7578,19 @@ ], "text/plain": [ " stops count\n", - "0 [BSP1, SGL1, YNG1] 295\n", - "1 [YNG2, SGL2, BSP2] 265\n", - "2 [SGL2, BSP2] 64\n", - "3 [BSP1, SGL1] 22\n", - "4 [YNG2, BSP2] 17\n", - "5 [SGL1, YNG1] 11\n", - "6 [BSP1, YNG1] 10\n", - "7 [LAW2, EGL2, DAV2] 6\n", - "8 [YNG2, SGL2] 5\n", - "9 [SGL2, BSP2, YNG2] 2" + "0 [YNG2, SGL2, BSP2] 343\n", + "1 [BSP1, SGL1, YNG1] 334\n", + "2 [YIE1, YIE2] 65\n", + "3 [YIE2, YIE1] 22\n", + "4 [VMC1, VMC2] 16\n", + "5 [VMC2, VMC1] 13\n", + "6 [STA1, UNI1] 7\n", + "7 [FIN2, FIN1] 7\n", + "8 [FIN1, FIN2] 7\n", + "9 [EGL2, DAV2] 5" ] }, - "execution_count": 14, + "execution_count": 16, "metadata": {}, "output_type": "execute_result" } @@ -7584,7 +7616,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "The top \"trips\" are from Bloor-Spadina to Yonge via St. George and vice-versa." + "The top \"trips\" are from Bloor-Spadina to Yonge via St. George and vice-versa, but these are the stations on line 2..." ] }, {