Commit 1427d1ba authored by Prince Joseph Erneszer Javier's avatar Prince Joseph Erneszer Javier
Browse files

added narratives

parent b4f52eb9
......@@ -33,7 +33,7 @@
"</p>\n",
"\n",
"<p style=\"text-align:justify; font-family: Times New Roman, Times, serif\">\n",
"In performing data analysis, a common task is to search the most appropriate algorithm(s) to best resemble a given system. In this report, we demonstrate the suitability of using a neural network in predicting the potential number of users using combined historical rental and weather information. The idea is to augment previous machine learning models and discover the possibility of getting better test accuracy. We used K-Nearest Neighbor, Linear Regression, Ridge Regression, Lasso Regression, Linear Support Vector Machine, Decision Trees, Random Forest, and Gradient Boosting Method as baseline models for machine learning. We used a 3 layer fully-connected feed-forward network with 56 hidden nodes. This report shows that such configuration works well the most with 74.6% accuracy compared to GBM and RF with 73.4% and 72.7% respectively. \n",
"In performing data analysis, a common task is to search the most appropriate algorithm(s) to best resemble a given system. In this report, we demonstrate the suitability of using a neural network in predicting the potential number of bicycle-sharing users using combined historical rental and weather information. The idea is to augment previous machine learning models and discover the possibility of getting better test accuracy. We used K-Nearest Neighbor, Linear Regression, Ridge Regression, Lasso Regression, Linear Support Vector Machine, Decision Trees, Random Forest, and Gradient Boosting Method as baseline machine learning models. We used a 3 layer fully-connected feed-forward network with 55 hidden nodes. This report shows that such configuration works well the most with 72.4% $r^2$ and 65.6% MAPE. In comparison, RF could predict with 67.4% $r^2$ and 78.9% MAPE while GBM could predict with 65.5% $r^2$ and 66.4% MAPE. \n",
"</p>\n",
"</div>"
]
......@@ -200,7 +200,7 @@
"</p>\n",
"\n",
"<p style=\"text-align:justify; font-family: Times New Roman, Times, serif\">\n",
"Features selected were year, holiday, temp, hum, windspeed, season, weathersit, mnth, hr, and weekday. The target variable was cnt. One-hot encoding was then applied on season, weathersit, mnth, hr, and weekday. The features data contained 56 features. The features were then scaled using min-max scaling given by:\n",
"Features selected were year, holiday, temp, hum, windspeed, season, weathersit, mnth, hr, and weekday. The target variable was cnt. One-hot encoding was applied on season, weathersit, mnth, hr, and weekday. The resulting features data contained 55 features. The features were then scaled using min-max scaling given by:\n",
"</p>\n",
"\n",
"\\begin{equation}\n",
......@@ -208,7 +208,7 @@
"\\end{equation}\n",
"\n",
"<p style=\"text-align:justify; font-family: Times New Roman, Times, serif\">\n",
"where X is the feature matrix. Since the maximum value of cnt was found to be 977, cnt was divided by 1000 to scale it to values between 0 and 1. The last 20 days were set for testing set. In the remaining dataset, the last 60 days were set as the validation set. Finally, the remaining dataset was used as training set. The training set was used to train the machine learning models. The validation set was used to evaluate the model during training, and finally, the testing set was used to test the accuracy of the model after training using the best parameters.\n",
"where X is the feature matrix. Since the maximum value of cnt was found to be 977, cnt was divided by 1000 to scale it to values between 0 and 1. The last 20 days were set for testing set. In the remaining dataset, the last 60 days were set as the validation set. The remaining dataset was used to train the machine learning models. The validation set was used to evaluate the model during training while the testing set was used to test the accuracy of the model after training using the best parameters.\n",
"</p>\n",
"\n",
"\n",
......@@ -218,7 +218,7 @@
"\n",
"\n",
"<p style=\"text-align:justify; font-family: Times New Roman, Times, serif\">\n",
"A feed-forward neural network having 56 input nodes, 56 nodes in one hidden layer, and 1 output node was developed. The learning rate from input to hidden and hidden to output were 0.001 and 0.0001 respectively. The loss function used is given by:\n",
"A feed-forward neural network having 55 input nodes, 50 nodes in one hidden layer, and 1 output node was developed. The learning rate from input to hidden and hidden to output were 0.01 and 0.001 respectively. The loss function used is given by:\n",
"</p>\n",
"\n",
"\\begin{equation}\n",
......@@ -226,7 +226,19 @@
"\\end{equation}\n",
"\n",
"<p style=\"text-align:justify; font-family: Times New Roman, Times, serif\">\n",
"where $\\Psi_{NN}$ is the predicted value and $\\Psi_{true}$ is the true value. The input, hidden, and output activation functions were linear, sine, and sigmoid respectively. The neural network was trained and validated using the training and validation sets over 12,000 iterations. The testing set was used to evaluate the predictive accuracy of the model. The accuracy metric used was the coefficient of determination, $r^2$.\n",
"where $\\Psi_{NN}$ is the predicted value and $\\Psi_{true}$ is the true value. The input, hidden, and output activation functions were linear, sine, and sigmoid respectively. The neural network was trained and validated using the training and validation sets over 20,000 iterations. The testing set was used to evaluate the predictive accuracy of the model using the coefficient of determination ($r^2$) and mean absolute percentage error (MAPE). The equations are shown below.\n",
"</p>\n",
"\n",
"\\begin{equation}\n",
"r^2 = \\frac{\\sum_i(\\hat y_i-\\bar y)}{\\sum_i(y_i-\\bar y)}\n",
"\\end{equation}\n",
"\n",
"\\begin{equation}\n",
"MAPE = \\frac{100\\%}{n}\\sum_i{\\left | \\frac{y_i - \\hat y_i}{y_i}\\right |}\n",
"\\end{equation}\n",
"\n",
"<p style=\"text-align:justify; font-family: Times New Roman, Times, serif\">\n",
"where $\\hat y_i$ is the predicted value, $y_i$ is the true value, $\\bar y$ is the mean of true values, and $n$ is the number of samples.\n",
"</p>\n",
"\n",
"</div>"
......@@ -242,24 +254,25 @@
"Machine Learning Models\n",
"</p>\n",
"\n",
"\n",
"Eight more regression models were trained on the same training dataset, namely k nearest neighbors (kNN), linear regression, lasso regression, ridge regression, linear support vector machines (LSVM), decision tree, random forest, and gradient boosting machines (GBM).\n",
"\n",
"Using the optimal parameter, the target values were predicted using the test set. The accuracy was measured as the $r^2$ between the true values and predicted values. The table below shows the optimal parameter of each model.\n",
"Using the optimal parameter, the target values were predicted using the test set. The accuracy was measured as the $r^2$ and MAPE between the true values and predicted values. The table below shows the hyperparameter tweaked for each model.\n",
"\n",
"|Model|Parameters|\n",
"|:-|:-|\n",
"|Feed-forward NN|no. of nodes<br>no. of hidden layers<br>activation functions<br>learning rates\n",
"|kNN|no. of nearest neighbors|\n",
"|Linear regression|-|\n",
"|Lasso regression|alpha|\n",
"|Ridge regression|alpha|\n",
"|LSVM|C|\n",
"|Lasso regression|regularization: alpha|\n",
"|Ridge regression|regularization: alpha|\n",
"|LSVM|regularization: C|\n",
"|Decision tree|max depth|\n",
"|Random forest|max depth|\n",
"|GBM|max depth|\n",
"\n",
"</div>"
"</div>\n",
"\n",
"Each model was trained and tested on a range of parameters. The parameters that gave the highest $r^2$ on the test set were identified as the optimal parameters."
]
},
{
......@@ -273,19 +286,19 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"The feed forward neural network was able to predict bike-sharing counts on the test set with 74.2% accuracy, higher than the eight other machine learning models trained. The table below summarizes the predictive accuracies and corresponding parameters of all models evaluated\n",
"\n",
"|Model|Parameters|Values|Max Training Accuracy|Max Validation Accuracy|Test Accuracy|\n",
"|:-|:-|:-:|:-|||\n",
"|Feed-forward NN|no. of nodes<br>no. of hidden layers<br>activation functions<br>learning rates|(56, 56, 1) <br>1 <br>(linear, sine, sigmoid) <br>(0.001, 0.0001)|-|-|74.2%|\n",
"|GBM|max depth|19|-|-|73.4%|\n",
"|Random forest|max depth|31|-|-|72.7%|\n",
"|kNN|no. of nearest neighbors|4|-|-|68.5%\n",
"|Decision tree|max depth|27|-|-|50.5%\n",
"|Lasso regression|alpha|0.0001|-|-|44.8%\n",
"|Ridge regression|alpha|10|-|-|41.9%\n",
"|Linear regression|-|-|-|-|41.3%\n",
"|LSVM|C|0.1|-|-|33.0%\n",
"The feed forward neural network was able to predict bike-sharing counts on the test set with 72.4% accuracy, higher than the eight other machine learning models. The MAPE obtained was the lowest at 65.6%. The table below summarizes the predictive accuracies and corresponding parameters of all models evaluated\n",
"\n",
"|Model|Parameters|Values|$r^2$ test accuracy|test MAPE|Top Predictor|\n",
"|:-|:-|:-|:-|:-|:-|\n",
"|Feed-forward NN|no. of nodes<br>no. of hidden layers<br>activation functions<br>learning rates|(55, 50, 1) <br>1 <br>(linear, sine, sigmoid) <br>(0.01, 0.001)|72.4%|65.6%|-\n",
"|Random forest|max depth|32|67.4%|78.9%|holiday|\n",
"|GBM|max depth|23|65.4%|66.4%|temp\n",
"|kNN|no. of nearest neighbors|2|62.9%|134.9%|-\n",
"|Decision tree|max depth|23|48.8%|83.3%|temp\n",
"|Lasso regression|alpha|0.0001|48.1%|382.5%|temp\n",
"|Ridge regression|alpha|10|48.0%|399.4%|temp\n",
"|Linear regression|-|-|47.1%|418.1%|holiday|\n",
"|LSVM|C|1|46.9%|302.8%|temp\n",
"\n",
"\n"
]
......@@ -301,7 +314,9 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"Bike sharing data were taken from XXXX. Hourly counts of bike shares were predicted most accurately using a feed-forward neural network, followed by GBM and random forest."
"We demonstrated that a fully-connected feed-forward neural network could predict hourly bike rentals with the highet $r^2$ and minimum MAPE of 72.4% and 65.6% respectively. The neural network was followed by the forest regressor could predict with 67.4% $r^2$ and 78.9% error. And finally, GBM could predict with 65.4% $r^2$ and 66.4% MAPE.\n",
"\n",
"Further research can include using recurrent neural networks and ARIMA, which are specifically made for sequential data."
]
},
{
......@@ -310,7 +325,7 @@
"source": [
"## References\n",
"\n",
"https://archive.ics.uci.edu/ml/datasets/bike+sharing+dataset"
"Fanaee-T, Hadi, and Gama, Joao, 'Event labeling combining ensemble detectors and background knowledge', Progress in Artificial Intelligence (2013): pp. 1-15, Springer Berlin Heidelberg, https://archive.ics.uci.edu/ml/datasets/bike+sharing+dataset"
]
},
{
......@@ -327,25 +342,13 @@
"## Loading the Dataset"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### About the Dataset\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": []
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"ExecuteTime": {
"end_time": "2018-10-24T17:48:03.081737Z",
"start_time": "2018-10-24T17:48:02.716900Z"
"end_time": "2018-10-25T13:47:45.277833Z",
"start_time": "2018-10-25T13:47:44.796679Z"
}
},
"outputs": [
......@@ -353,7 +356,6 @@
"name": "stdout",
"output_type": "stream",
"text": [
"The history saving thread hit an unexpected error (OperationalError('disk I/O error',)).History will not be written to the database.\n",
"> Dataset loaded.\n",
"> (17379, 17) rows and columns.\n",
"> Converted datetime values to datetime.\n"
......@@ -384,8 +386,8 @@
"execution_count": 2,
"metadata": {
"ExecuteTime": {
"end_time": "2018-10-24T17:48:03.104535Z",
"start_time": "2018-10-24T17:48:03.083679Z"
"end_time": "2018-10-25T13:47:45.498702Z",
"start_time": "2018-10-25T13:47:45.457933Z"
}
},
"outputs": [
......@@ -565,8 +567,8 @@
"execution_count": 3,
"metadata": {
"ExecuteTime": {
"end_time": "2018-10-24T17:48:03.112129Z",
"start_time": "2018-10-24T17:48:03.106581Z"
"end_time": "2018-10-25T13:47:46.075293Z",
"start_time": "2018-10-25T13:47:46.057124Z"
}
},
"outputs": [
......@@ -592,8 +594,8 @@
"execution_count": 4,
"metadata": {
"ExecuteTime": {
"end_time": "2018-10-24T17:48:03.137065Z",
"start_time": "2018-10-24T17:48:03.114025Z"
"end_time": "2018-10-25T13:47:46.614292Z",
"start_time": "2018-10-25T13:47:46.594462Z"
}
},
"outputs": [
......@@ -643,8 +645,8 @@
"execution_count": 5,
"metadata": {
"ExecuteTime": {
"end_time": "2018-10-24T17:48:03.244729Z",
"start_time": "2018-10-24T17:48:03.139832Z"
"end_time": "2018-10-25T13:47:47.802151Z",
"start_time": "2018-10-25T13:47:47.580682Z"
}
},
"outputs": [
......@@ -889,6 +891,13 @@
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"The history saving thread hit an unexpected error (OperationalError('disk I/O error',)).History will not be written to the database.\n"
]
}
],
"source": [
......@@ -898,22 +907,24 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 30,
"metadata": {
"ExecuteTime": {
"end_time": "2018-10-24T17:48:05.127465Z",
"start_time": "2018-10-24T17:48:03.247079Z"
"end_time": "2018-10-25T15:08:46.807741Z",
"start_time": "2018-10-25T15:08:46.551111Z"
}
},
"outputs": [
{
"data": {
"image/png": "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\n",
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAagAAAEYCAYAAAAJeGK1AAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMi4yLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvhp/UCwAAIABJREFUeJzsvXmcJddd2Put7W69z0zPIo12W0fyildhWyI2NnjBOBgcEgjk2cALIayPsOQTICzvAeEF8iAQCC9hCQmYxCbGcvDzhrEsyZskW7ZlWUcaSTPS7N3T2+271XbeH6eqbtW9dbtvz3T39IzPV5/56HYtp05V9z2/+u2WUgqDwWAwGPYa9uWegMFgMBgMZRgBZTAYDIY9iRFQBoPBYNiTGAFlMBgMhj2JEVAGg8Fg2JMYAWUwGAyGPYl7uSdgMAghFPAkEKBfmp4CflhK+ZQQ4pXA/ymlfKMQ4k+BY1LK/2ubr/9LwFEp5Q9c4jiPAX9PSnluWya2CwghDgF3SCnvvtxzSRFCHAWelVJal3suhsuLEVCGvcJrpZQnAYQQvw78DvCtUsrPAW+8rDMbEynlbZd7DhfB64A3AHtGQBkMKUZAGfYiHwfeBiCEeC3wn6WUz8kfIIR4MfAB4PXACeA3gTcBFeD/lVL+2uCgQogXAP8JmE6O+x0p5e8lu6tCiHcDXw+cA75DSnlKCCGAPwL2Ax7wC1LKdyfjKeBfAe8EngeEwHXAc4BfBz4BfBtQA94ppbxHCLEP+HNAAA8Bq8BJKeUvDcy1DvwhcBfQBX5VSvnfhBA14LfRgiUGPgj8jJQySuZzXU7Qq43mAzSB3wNcIcQk8D3AHwDfADjAl5J5rw3M7Tjw+8A/BOaBP5FS/mKy723ArwITwDHgu6WUi4mWei3wYuAvpJS/PTDm9wG/CKwlzyfdbgO/ixaiFeA+4PvQLy3/Rkr5gtyxDwG/IqV8P4arAuODMuwphBAV9EI58o1eCDEPvAf4XinlE8CPoQXEC4HnA+8QQry15NRfBP6jlPL5wKuANwghqsm+NwD/Ukp5E7CAXgRBC77/JaW8Pdn2R0IILzemJaUUUspo4FovAT6TnPf7wM8n2/8VsCalvBn4DeC7RtzmvwAqyXy+CfhdIcQ1wE+ghc7zgZeiBdioMTacj5Ty82gB9V4p5T9CL/o3A7cBzwW+kjynMl4FvBJ4OfCjQogXCyGuA/4U+K7k/v4O+I+5c94CvKVEOM0B/x54k5TyhcA1ud1vT+7xBcDtwMvQgvHDwBEhxIuSMa4DbgE+NMazMFwhGAFl2Ct8IvHhnEMvfH8y4jgP+Cvg16SU9yTbvhP4IyllT0rZAv4M+PaSc88D3yGEeClwQUr5bVLKXrLvXinlieTzw8DR5PPfB/5t8vk+tPZxJDfm/xoxz2buTf7zwPXJ57uAdwNIKR8EPjvi/LcAf5kcdxKtGZ0GvgWtIYZSyg5a2/jmEWOMM588C2hB/3agIaX8BSnlh0eM92dSykhKeR64F3g18K3AA1LKR5Jj/gB4mxDCSX7+rJRysWSsO4AnpJRfTX7+L+kOKeVfAS+XUgZSyi7wAHCzlDIA3ktfOL8deH/u92m4CjACyrBXeK2U8jYp5Rzwg8A9QogjJcf9GPot+mRu2yzwb4QQjyVC7sfRJqZBfhZ4BPgfwLNCiH+e25c3Y0VoExdoreKTQojHgUcBi+L3ZmnE/ayOGG8OWM7tOzXi/APASvqDlHI9+Tg/cP4ycHDEGOPMJyPx9/1o8u+sEOIvhBCzI8bL3/cy+r5mgTtyv4fPJNfdX3JOnn0D88vuL9GW/0wI8Xgy5t+n//zfTV9AfRvw30eMb7hCMT4ow55DSvlJIcQJtBlpcFF7P3ph+iMhxIuklKvAaeA3pZSjtJl03HW0ie1fCSFeAXxICPGxUccnprz3AN8ppfxgYg7sXPSNadbQPrCUI+gIxkEW0UIqnctR9LM4R3/BJ/mcRg3GJIInMZttGSnle4H3Jr6yPwZ+Gvi5kkMP5D7vS+bWBT4mpXzH4MHalTeSZWAm9/N87vOvoqM7Xyil7Akh/jy375No/9lb0SbAj250EcOVh9GgDHsOIcSt6CCCL5fsPpaYnT6CDhYA7a/6ASGEI4SwhBA/L4R4U8m4HxBCPD/58RH0W3u8wVQmkn+fT37+ccAHprZ6Tzk+B3xHMp+vQ5szy7gb+CfJ/RwGvoBeuP8G+P7kXieA7022AZxBByGA9pdtdG8pAVrzQQjxLiHELwBIKZeAx4BR7Q7+oRDCTsLU70Sb+T4C3CWEuDkZ75VCiN8ZYw4P6sPFc5Of/7fcvoPAI4lwejHwGpLnL6WM0VrT7wF3J2Y/w1WEEVCGvcIncqah9wA/mARAjOIngdcJIb4VvUCdQDv1H0M70+8rOed3gb8QQnwVLXR+X0p5bNQFpJQrwP8NfFkI8QW0pvPXaM2rzIQ4Dr8K3CqEOIYOhHg/5ULg/0H7zE6go+9+KvGR/XvgWfS9Poj2gb0nOefngD8QQjwMtCiaLUfxEeAbhRAPJHN5mRDiieQZPQ/4dyPO+wpa2D6Ijob8SuIj+9+B9yXn/x5jmN2klAvoZ/G3QohHAJnb/VvADwkhngB+ODnuB4UQ/yDZ/27ghnGuY7jysEw/KINhdxFCWFJKlXx+D3CflHIcTWNPkISZf4+UsuwlYFdJNLjPA9eXRFIarnCMBmUw7CJCiB8B7k7MYweB1wKfvryzuqL5ZeAPjHC6OjFBEgbD7vKnaKH0BNpH9FtJ9JxhCySa06fRycT/x2WejmGHMCY+g8FgMOxJjInPYDAYDHuSq8rEt7DQVABzcw2Wl9uXezobciXMEcw8txszz+3FzHP7uJxznJ+fKq1cf1VqUK47lCS/57gS5ghmntuNmef2Yua5fezFOV6VAspgMBgMVz5GQBkMBoNhT2IElMFgMBj2JEZAGQwGg2FPYgSUwWAwGPYkRkAZDAaDYU9iBJTBYDAY9iRGQBkMBsNl4OTCOsdOrW5+4NcwV1UlCYPBYLhSaLYDeoEpwr4RRoMyGAyGy0AQxsSxKda9EUZAGQwGw2VgIwH12InlXZ7N3sQIKIPBYLgMBFFEGMel+x55emmXZ7M3MQLKYDAYLgMbaVB+aHxTYASUwWAwXBbCMCZKBJRSiuVmr7DPYASUwWC4SB49bsxQl0Jeg1rvBNzz8KnCPoMRUAaD4SL56i458tvdcFeus9sEUV9Ara77dP2+Wc83AgowAspgMFwk0S6FSH/wMyd25Tq7TZAz8a20eoWcKKNBaYyAMhgMF8Vu5fB0/atLg7rvS2eAoolvdd0v+J0CEyQBGAFlMBgukijaHQHV6V2+xfoheX7bxzy1uA6AAiKVCKiWz1Sjkh2TalBRHLO40tn2OVwp7FipIyHEJPBnwD6gAvwycBb4A/Tv5ktSyh9Kjv1p4B8k239ZSvlBIcQM8BfADLAOfLeU0nhlDYY9QjQih2e7GaVBraz3aIeKhmvtyHXDKObJ02u8TBzc1nF7gX5ujm1lGpQfRFQ8rS8opQgifUyzHfCpR87ytjtvGhpHJcLNsnbm/vcCO6lBvROQUsrXAu8Afgf4beDHpZSvAfYLId4shLgJ+EfAncBbgd8RQjjATwCfkFLeCdwN/OwOztVgMGyRcJc0qK4fZYtxnpX1HsfPrO3YdXeqFFEvCYZwbKtUC42VyraHYcyFtW7pOMfPNq/6ihM7KaAWgf3J5zlgCbhJSvlAsu39wBuA1wH/n5TSl1IuAMeB5wGvB943cKzBYNgj7JYG5QcRcYmAUmpn/VN+GG+7GVMpVUjCLbuvKFKZ6S+IYpZGCKggjOld5cEUO2bik1L+pRDinUKIY2gB9a3Af8gdchY4AlwAFkq2H85tT7dtyNxcA9d1AJifn7rUW9hxroQ5gpnndnO1zNPz3F25lxiY2zdJ1XMK25c7IaeXl3ZsDrHTplLdvnucn58iihWWbTM/P8XERDXbnv/c7gbYtsX8/BTrQUyrF5XO4exaD7sdbOv977W/zZ30QX0P8IyU8k1CiBcD70X7klIstM9p0IBatj3dtiHLy21AP+SFhebFT34XuBLmCGae283VNM9Wx9+Ve2l3Q86dW6NeLS5XS8stun64Y3M4s9ii1e5ty/jp8wyjmFZbP7dWS1eOGPy83gnw/YiFhSYLi+sopUrnsLzcptUJtu3+L+ff5ijBuJMmvtcAHwaQUn4RmAQO5fZfC5wBTqG1pY22p9sMBsMeYbei+MIwKs25Ugq6vZ0z8QVhNPY9KqU4P0a0XRoAsVGjwiiKM9NfEMZ4TvkyHStVKDYbRlefuW8nBdQx4A4AIcQNQBN4RAhxZ7L/24EPAR8HvkUIURFCXIMWRo8CH0FH9gF8R3KswWC4jDx6fIlm2wd2L1E3iFT5tRR0dlBA+UGc+YI2IwhjPvPI2U2Pi5U+9n2ffIqJmlfY59gWYaSTd1O5E0YxrlMepaeUyoI4Or2Qjzzw7FhzvZLYSQH1h8CNQoh70OHi/wwdmffrQoj7gSellB+TUj4D/Cfgk8BfAT8kpYyBfw+8XAhxLzqQ4t/u4FwNBsMYXFjtZkJht4IkbEtrFYPEShXKA203fhiNHcUXRHHmgxgV1AA6ubnnR9x4eIqX31YMX696Dn4QEcaKNHI8jBTuCA1Kqb4W2/XLtcwrnZ0MklgHvrNk110lx/4u8Lsl53/bzszOYDBcDAqtBcDumfgc2x65+KZRfA8fW+T2G+ayQAql1CXnB/nB+FF8YRhnofDvv+9p3vWW2wEtrPZN17LjlFJcWOsyP1dnbqpamGO14nD6QpultS6OrbdrDWqUgOpH+3V6YWko/pWOqSRhMBjGJs6ZlXbjjT2KYypeuYBSStFNqkw8/swKK+s60KDZ9vmTDz52ydf2wwhnhHltkCCMM8F9cqGFUgqlFD/3nz9b0MJSE9/MRL9qRKcXUqu4VCsOx06ucvxsEycRSmEU47r6871fPF24ZpxoUA/JBRZWOmOEkV15GAFlMBjGR/Vzd3bDxOcHMfWqW2riU4qswOpqq8daS/vGnjy9xmry+VIIgpiK62x+IDpnKtVgmm2ftXZAGCkqrl3I1Uqf3XQioJRSnFpscc2BCWqey+kLLZotP9OgdJCE/vzAY8WyS6kP6plzTc4ttUtzqq50jIAyGAxjk3fM74aJr9n2mZmolGtQgJ2YyPwwZnVdC6VWJ2Cy7g0dv1X8MMbz+kvk0xtUrfire57MPjdqLktrXYIwYmaiWmgXohRUPLugQZ290Obw/gbVisPiSof1TpAJqGfOrWcmvqVmryB4ldJa7Gqrx+Jal6tQPhkBZTAYxidWZAvhbpj41toBs1PVkSa+1IUzPVHJFu/tE1ARFbe/ROYbCj7+7Er2uRdEnFpsESdmvTTYIQhjZiYrtHORhnGsqFdcpnOFYcNYh5JXPYeOHxFGMY5joZTiow8+m5n4PNdmaa1LGMV8+pGzxLEiimPWOyEXVrtXo4XPCCiDwbA1UlNSOKaAuhTnfbPls2+UgIJMQE3WPFqdAIB2L6Re7Zvmxrn+Rz73DH5QjAgcNPEtrPSj8+55+FT2HJptn/V2kJkc61WXWGkNbGaiUgiF/9hDz/K2O2+i4uXnp++jWnE4OFsnihWObWcCx7X1Mj1V92i2A3pBxH/6X4/ygU8dJ4oVtYrDhbWuCZIwGAxf2+SDJOIxfVAfuP/4lq9zbklXhTlxrsnsZHWED0phJQVnLCtJXI3iodDzD33uGRZWOjx7fn1ojJSPPniycJ5SijinoQEsrvYTcVfWfdYTgdhsB1pLUro1yGTdI45VJqDyJr7FlS6uXQy8SCMOJ2sut984RxgrHNvKBI6bVGufrGshHMcKcd0ss5NV4lglJsXeVVnV3Agog8EwNuoiTHwX1rpbrgr+icScdvf9x0ea+Eg0jyiOsZNF/9nz60MJq8trPRZWOnzpycVs2ydzEXE9X7e6yGtQn398gfPLfYEUxTHLTT8TGq1ukAVlrLV8JmousVJ0eiGNmksUK8JUQOU0KD+Isrlmt5Hcx8xkldd+3bXcenSWI/sb2XNONajJukezExAruPnaaaJYJ/XWKy6H9zewrz75ZASUwWDYAolmAeO32wgjVVikx6HV0ce/7TU3UvWcIQHVCyJOLrSwLIueH1HzHCzLwrEtvvXVNxaO7fghfhhz4lxfgzq92Mo+L651ufbARKHluh/ErHeD/hi9iJkJL9OyGlU3E1DNdsCB2TpK6WtN1lINKmJ6smji88OYQUVHa4J93vHaW5hu9AND0uPrVZdOLySOFZ5j66rnkcK2Ld7x924Z46leeRgBZTAYxiZW5KL4xjPxRXFMK1nsnzw9ugZdnlZOOJT1TVpp9nji5Aq2bdHuhdSSQrJKwY2Hi4VHo0hrNion5PKh3xdWOxzZP5E1EoThKhXtXsiBmTqtbkCsFLOT1UxA9YKI2YlKlpc1UfeIlTbx1StuQZB3/SiLPEzRvrTiNiu557e95sb+NqsfRek4Ojes44dUPJtbr5vd8HleqRgBZTAYtkQ/D2oLGlTih3ngq5u3UFdK0er2KyM4tjWUc9X1dRmiqufQbAfUKk7Ob1Rc7KNY0eoEeLmIvLzwWW35HJyrFzQopfqNBQE63ZBr5ye4sNql1dGRhX7Si8kPIqYmKii04GvUXOJYEYQxtYpTyE/yw2hofkoxZJ5L77laGc7DipTCdfT+ViegXtmxgkCXHSOgDAbD2KiciW9cv1IUxf0Iu+7mpr4gjAnCKMtzSrWFPL0gIlY68i0VUHp+YNtFoRYrxfqAgPKDfsXwKFJM1LyCD0olQiBludnjZbfOc+zUqg59TwIUQJvtphoeFtoUOJH4oIJwOMm455f5oIa7DtmWRRj1g0AKx8cKNyn/tN4JqFXHSya+EjECymAwjI2O4kvako8poCqeQysRTOP4otLCp2mekxY2ZQJKJQLKp1ZxsSwri4jzXIcg0XDiWGtkeQGVb6URRjGNmlvUoKAQYv7swjq3XDujfVNtn9nJvo9IKcWRfRNUPCfRoBITXxBRrTiF4/wwHhI5aZBEHjsRsGWBD1GscF0toFpdXSbpasUIKIPBsCXyoebjUK042eLfzvmWRtH1w6zlhGVZ2LY1dL1ezsS31vapek4hNNxz7aKA6gQFgaNbeOj9YaRoVIsCKlaqUEUiDGMqnoNlMaRBAdz5oiO4jkXX1xpUHOu+T/lr/t0XThGG8bAGhRoWUJbW7FJzYGrunKh5NNt+5pfr+iH1EjPg1YIRUAaDYWxipU1McayGFtpRpMJCKTWWia/rR1hobci2LWwYqjOX+aAqDgsrXaYaunKE9udYRQGlYL0bUPHsTKgEYZxpNlGsNSg/FySBKmpQeQGy1vKZmayU1r4LE6EUxYogiAtam3xmhTAuRvHZlha+g34p27YKbTeiJDeqXnVpdcPMB9X1o6FOw1cTRkAZDIaxSbWUKFZD0Wij8Bw7Ewi9YPP+TZ2kEkSqDdm2NVRnLjXxzUxUWe8EWUuL1MTnOhZBlGpQMb1kIU+vXxBQkUoEVNEHVfHKl8dWJ2C6UcmEXZlwSf1eE7U0ulCxsNIhDIvPrVpxksg+hsaIojgbO43cq1UcOr0Q19HCNo5Voa7f1YYRUAaDYXxUEmquFPaYq4fr2IRRTBDGWeTbRqRaQaoNpb6lPKmAeuFzDvDPv+0F2fY4iYjT11TZ9f0gzoQBaE0n9UHFSlHxnMLcYgUvumV/6fxipfDc0T2qnJxJMhUw6x1dbWIwyrCaCJyyIAn9EqB/Tl8IqhWHdiKgwljPe6phBJTBYDBk/qd4CxqU6+hW5kEUE26QO5Wa5Lp+lIVnW5aV5P8Uj9UmvuHggvQc27KyvKeKp31gtYqT5T9pDao/F3tACCqleMFN+2l1Q46dHM7dSv1iYRQPCU+7JKhjpdnLNLS8YK95Dp1eNHQfafv3VJilJr6q59BJTXyRYt9UdWxT65WIEVAGg2FslOpH8LmOPbJA6WMnloe2heHo7rCxUtx9/9OADpLQQQ9aGyrToMIo1r6bofmpTOtKfUT7pqu68aHrZH4m2y7P40qvk0bWObbFI09fyPbrSuWx9h0pxRePLfLU6WIbjr5fqb9treVn917QoBLhOSigZqeqXFjtZtu1ic+ilmhQustwzP6ZGpvR6gacX25vetxexAgog8EwNgqyQqgVzx7Z4uELTywObQsi3VaijCCMs+64nV5SETzua1CDsiStqlCW9Kr9VnDfl87Q6gZUPYfrDk5p01uW/GsPVadYa/n88p88kIyjc5D+0eufWzgmr4UBQ+HremxrKICiF0RZl9y85mnZ5UESNxya4ukzzYIGZdt9E5++Brz6BYdLn2ee04stnjw9upfVXsYIKIPBMDa6lTkEQaRbRgwIjrQIa1k4eRBqP1CZmc8PoiyAoRdEWdi4bVuZ+e3hY4vc/+UzAFhYQ9XGgSy60LYs1tp+JvS+5VU3FPKpHGfYDOeH/ZJMcS43SX+2kvPsQpuRdjfkba+5qTBOWVh8GPaFc94iZ1ta+AxqgpN1j3Y36EfxRTGObVGruHS6YRI4osYqcdTqhkOtRK4UjIAyGAxjk5r4/FCbzNSAhErNXa2BcPK00vdEzc18TXn8IM4EVJqgmwqJ1AcVhjEPJm3PrXRhH6lBaR+NH+oxbzoynQkOpVRp+aQwivGS0HJF38cW5BoXpua7lK4fcv2hycI4ZebDIIypVR0siia+fHLxIGklDSsJmHBsi5qnNag0snGcFhutTlAMob+CMALKYDCMjUKHmQdhTNWzh4IX2j39tt4a0KCOnVzli8cuUK+OEFBhNPSWn/mTkpyoNHoOKAiwlJV1n09/5SwWWoMKoriwMKcaVBip0grpQc5Hlq/u4Dp21mDQcYa1o6Ewc2v4mCCKqXkOnmcXTXzW6IaK6XYL3RzSti08z6brh8lzYaxAlVY3zAT1lYYRUAaDYWxUkqjrh1GhK2xKGMYsNXtDi38quBqjBFROg0pJAw1SYZSa78IozqL08rXqHpLneer0amLi02ax/LVSDaoXREzUvCEfVBDpxNo0Mi8VPM89Oks1FVAlEXr5Z2MlGs/wc4moVV08x8bKrbo6mKN0uEyDIrkX19bCLYq0NmXZ1pCJs4xOLyx95mWcyrUh2QtsKqCEEG8WQnxP8vnPhRBPCCG+feenZjAY9hxJHpRuhz4cxRdGMRdWu0OLuG1Z+GGE5w2bBUFrUHnfjm1ZRIkGZVsWCh05WPUc/sfHjwEM+aB+8V2vYG6qlpn4wpyJD/rh393E1BjFilML61xY1a3ctZ/I4u77jxc0qOffNMfLxHw2r1FlnlLfWRlpZXPPLWpQNhtpUKmJU99LGk6eJTAnz2YzttIK/p6kUeReYRwN6l8DHxJCvBlwgJcAP7ajszIYDHuSNA8qiHRtusG1L4xiFlc7WQ5SujhqzUS/+ZeF/vlBMcLPti1dty6XBxXHipeJeVzXzsbOayuTdS/LHbIsizAuJganCbRdX/dsiuKYhZUuZ5MQ7DDS1Rra3SAzL+rz7Kyc0EYaVC8pDqvnVjS/jRJQ2gdV/qzT+7Modg2OFZmWOGYq2tistzevlbibjCOg2lLKReBbgP8qpVwHrkyDpsFguCSyIIkgEVAD+yuewyNPL2XmvzRfyk1aZji2VRqa7odF7cNxknYTdj+QIFaK6w5OZQELutFff4x89QUt4FTBr5XuTwu6RpEe00kHSYrMdnphaYVxKE/CTYmT+4NEy7EHBZSL5zqFcTfyQeWDRMJI4drFpF3bLjcnXgprbX9bx7tUxqkyWBNC/DTwJuCnhBDPBWZ2dloGg2EvYtskQRJJZNvA2jo/W+f5N+3j+BkdzRdGMY6ji7dGqe+oZNzPP75QqH3nWH1f06APKkUpCj6ovH/KTs4PBjUopSuAaw2q350WwE0qNbS6YWmXW0iDJMr9OXmTY15YgfZv1SsOnjOsQY3yDuWTjqOor0HZiXkvP/52sda68jSofwpcC7xLStkF3gj87I7OymAw7ElSH4wfphpUUdxM1Fy+7jkHCgmmrm0zP1vPkk0HbVpKKT7zlXN4OZ/WoLBRSfWKwUW5oEEloeVpom4YFU18aY8lrUElAkqpLHLPTYqxNjcwczlWX4Nq93Tvp5R8+adYFUtBRZGum+e59pDWt6kPCvrm0WSetm3hjFsMcQs095gGNc4dfq+U8ieklPcCSCl/D/iunZ2WwWDYa5xbbieVunVSa1mYeUq66Gq/jsUbXn40EVBFpavTC2l1QywLjuyfYCEJWHAcmyCKC3lQca54KgwHSaQmPCvToBRBzsSX+qA6fshE3SWK40RA9Rf+asVhveOPFBr5JNy1ls/0RF9AqcQ3BGSmxhTL0jUJPdcuaIHWsLwuPEMrkVBhFBcEqe40vL0alG6AuLc0qJEmPiHE24FvB94ghLgmt6sOvHqnJ2YwGPYWf33v08zP1nU/KKXwxujkGiULa2amsopBEh/8zAle/YLDvPmOG3jprfM8/swKkBRLDfsmLu2DYtjEN5ioSz/yz3EsekMalMo0qNV1H9uy+LrnHtDXTGrdrXdG96xybJsokSitbshkPadB5bQmFRfnClqwaA1qOFG3jL4GZRVytFIht90mvk5XN3Uc1P4uJxv9hX0IOA+8HPjb3PYY+PmdnJTBYNh7nFpoMVX3aNTSVhhFB/+nHjkzdE6YOvStfj259IyH5Hl6QcRay+e262eZm6rS7GgTU+pDyheXjeK4uCiPKHVkWSQ5Qloopji2nUXx7Z+p8fATixycqyOunwNSE59LpxeOzE2yc1GIg2HlUc5HFqnhho6pL25Qsxp1rXw19yCKM03Pc6wdMfG1e1rgRlGM7e6NLr0jBZSUsgPcL4R4iZSyK4SwGGxaYjAYvmawbTi/0uG6g5NJAmlf2MSx4pGnlzg4Wy+cEyVBErZlZcJKKcWHPvsMzY6PH0SstQOO7GvguXZW+SFtN5EPnBgKkqAYJAF9rWpQeOr5a/NcFMVMJZpP3myYBkkAI9uCpNFz6b3lBZQO2iifK8DtN+zj9GKroEFt5oOyEx9UUYNysC22XYOKIpXUSlR4e6RJ7zismKUYAAAgAElEQVTT+BEhxM8DU8nPFvpvY1MRK4T4x8DPACHwC8CXgf+anHsG7d/qJcf9BFo7+0Mp5R8LITzgT4Eb0GHt75JSPrWFezMYDNuI6+hIvA9/7lle88LDTNa9zH/y0OMLLK12SwSUDpKwkgoI6aJ9YbWLZev8p3Y3oFFzC4u141j0/KiwmMcDuUVloeBZgdmSgq35HKZ+lfRcvlMSJOEkOVhlODnTmp0TaFAUSoNmMqVgZqJCreKWlDoqvVTOB2Vl0ZCgfVmOvRM+KC1wgyimvvnhu8I4OuL3Ay+SUjrJP1tKOY5w2g/8InAn8Fbg24BfAf6DlPIu4DjwfUKICXQy8BuA1wI/I4TYB3w3sCKlvBP4DeDXt3pzBoNh+7CTsjyNqsNLb50v2FO+8PgCS83e0DlR0sdIm/iSMHOlzUlhpMsO6QaF/XflNNE2yi3yrW7IynqvILDKiqymuUNlmklZFYi8X6viaR9Rvepm7eKHnkEu98ixrEK5p7xQGgwzz8+hmAe1kQalsii+QR+UtQNh5lGs29wPloC6nIwjoJ6QUj5zEWO/AfiYlLIppTwjpfynaAF0d7L//ckxdwAPSClXE7PivcBrgNcD70uO/TBa0BmuIMp8EoYrk1QziWPFvukaL7x5vzalKF0dfGmtm4WF5wmjGCfVoHI+qK4fEgS6QGzaQTePRd+fBHDmQovjZ5qAXqCDMM60oEHSIInBKg2ObWUBDin50PAj+xpJ1Qjn4jQopbJuuflxXccmSEou5U2EsJkPqq/p5QWU69iFeWzEYIv5DY+NFRW3vB3K5WIcE9+XhRB/AXwCbaoDQEr5x5ucdyNgCSH+O3AN8EvAhJQyfc06CxwBDgMLufOGtkspIyFELISoSClHBurPzTVwE+fe/PzUqMP2DFfCHOHi57ncemZX7/Fqf567TX6eXT9kerJKuxtwcKrG/PwUU1M19u+fpOI5dMMYccM+ZmbqzM9PMTFRZX5+ivNNn3ojTsaymJmqMTfX0P4r2yLGotGocOjQNACTE1UAZmfrBEp/p+fnp3AcB2WFzM9PcWh+ihNn1nAcLYTy8/Rcm/n5KXp+iOc51BsVXEdvC8KIer2C48bZHBsNj/n5KaYnKnznG2/nc4+eZapRxXad0t9TZNvUavqcWtXj6DUzWaKv5zrMzU4wPz+FV3GzZ3FofpKnTq0yPz/F/n0NDh2cZnqiAkAnMXuWXcvzHOZmG6z3InqR4vChaepVl+mpGgcPTlNP5pGSPvPPPXqWVz5PNzLs9kLmZur0gmjTv7vVkytMT1aZmq7vmb/RcQTUNUAPeNXA9s0ElAUcBd6O9iP9HcUUiNSXNSjeN9s+kuWkptb8/BQLC81Npnd5uRLmCJc2z9W17tC5ay2fasUZWVTzYvlaeJ67yeA819o+jgU9P+TAdI2FhSatVo/FxXVipWi2fF79/MPUHCvbd/zZJRYW13Edi6UlBz8Iabd9lpZarLd9giCi1fFptXrZtVpJomhzrcvqWpe1CY+FhSa9XkCvF+rjwoheL0iqmTP0PJcurOsEXaVYX+9RqzgsLDSJY8Vas0scq2yOKoxYXlqn19ZBE61mF9exWM/NKc/qWpcwiFhYaGKhWFrqV//u9kLWmh0WFpp0cvcVB1F2zZfcvI9eu8dCW7+nr6y0CcK49FphGLG62mF9vcdqs8vKcot1xybwQ5YurBNFxfPS6939iWPcND+hn2Pbx+8FtDrBpn93cayI45iFxXVqu9znYpRA3FRASSnfdZHXPAd8SkoZAk8KIZpAKISoJ6a8a9GBEqfQPqqUa4HPJNsPA19MAiYsKeXeyiIzbEiZHf/R40sc2tfgpiPTlzT25756jlfefuiSxjCMT8+PqFcc4hhuv0GHZadvjF0/ot0N2T9d5WXiYHbOfV86Q6Pqcs2BiX6dvCRMuxdEWfJtWObzsIrmqVj1I+sm6l4WeDFovUoLqKblgKqeTbunDT+WRakPKm8CcxybRtUtVKAojJ8zraUFZFPyBWbziboTNZe56Voyh8FKGKN9UHYSjWhbxUoStYqu5zfKxHd2uUOrGzBR8wiSih90Nl8641hRvdJMfEKIZynRXKSU129y6keAPxVC/AawD5hE+5K+A/hvyf8/BHwW+M9CiFm0CfE16Ii+aeAfJOd8K1oDM1xBlPWg6fjDjekuhqdOrxkBtYv0At3PKFaKO56XPPdkce36uiFePmcJdJUIx7aSRF0d0ZfW4vODWL+xq/K/k7zPCpL6f4kgm6x7iXmvpFmgrf1PaTCDuH6Ov773qWzMQeKBfCXHtqhWHLrr5cm6eR/SoIBKw9uhWFWiUfPYN1W+6Fsl4fD58dIovnxAyFtffaMOknDK1Zya53B+ucNNRzz8MM6aPG5GGiRxRQkoisEJFXTwQmOzk6SUp4QQ7wU+nhz/o8ADwJ8JIX4QOAH8FyllIIT4l2hBpIBfllKuJr6rbxJC3Ic2Mb5z/NsyXAx/+9BJXv+yo9s2XtlbaNcfv3naKJRSQ83tDDtLL4ioV92sjQYkGpSCbk9XZnBzC6FlWbQ6AZ5rJ4m6Sah0kgflhxFhpBNXyzTttOFgKlOiXMDEZN3TDfuswSyofov0tJjqc4/O8GPveNHI+8oHM4AOb6969sieT3kBNT8QUp8XmK7T79V0ZH+DG47OQkmR2Y3abaTaYPqcU9IXgVEaVLXiZC+BfhBRGTPpNo51vcBRASKXg3FMfCcGNj0hhPgw8O/GOPcPgT8c2PxNJce9F3jvwLYIuFjzouEiWFjpbOt4ZX/onV400nwyLlGsLlnIGbaG7+tuuIUouGR97PoRUw2v2M/JglY3oFZ1s2AG3YJC71cKemGEY1tZhJverjLNoVg6qG/imqx7HNrXyCpG5NGaU2IeS1p11DYoyZSPvANwbd3efVRLjVRDA/jmV1xX2GdZfeHl5mru1asu8/snSn1AG+k2fQ0KytzvZQIqTrSg9Puhi/qOq0HpY4M9FGY+jonvGwc2XQfcsjPTMVxOtlsryXczTUnNQZeCEVC7Ty/QDffiIQ1K0Q1CphqVginJti3WOyFTjQjHsbFtklblusCsY1usd7TQq3nFHKh07GhEdXDPtXnV8w/zP+95aliDSjScvD8oz+nFFgdm6tmxYVQ87uBcnVuPznLs5Grpc9govDsVjNCvOL4Zo0Ll0/mlY5bJy7J5dP2Iqbr2PZ1cWKfrh1n/LID7v3yG17zwyNB5URwTx2j/2x6yToxj4vuF3GcFrAH/bGemY7ic9Pzt/cMsEyJ+EBEEl6hBRWpP2cm/FugGYanPBbQ/aaLmFnxQWkAF9IIIN62LlwQOKHSLizDxj8zP1rLzChpUzqyX90f1r1/ig0rMfpZlDWlXAI89s8ILb+6byPwgLoxRr7rMz9ZHmvi0ACx/RqnWBgz1fRpF2T30x8tVzigTUCU+qK6vXxaCKObBx85zcK7Okf06ok8pxf/85FO88vaDLDd7HJzre2o+cP9xXvDceSbrHq3u6GK5u804Jr7X7cZEDJeXeAe0krLxHMfeBhNfbDSoXcYPYmYalWKZHrSpzg90C/WCBmVZ9IKIXqA1qLxGFEWKimuj0JrGgdnhwjqWNahBDWsMg1UZQPt+rERQOCULv2Nb2TzLyiGlxwwm9OavuVGR1rwGNU4ibZkfrbAv9UGNaeLrJObWINR9r1rdMLvfTi/Ec2yOnVzl6bNN3vL1N2TnNTsB7aQ6+8JKl6W1Lvuma5xdanP8zBpf//zDm97LTjCOie824PfRVc0VOgT8h6WUx3Z4boZdJIjikXb3SxlzkIprb4uJz2hQu0vPj6jX3GJ2ogXHz67x1Jk1ZieqWbVtSMxTyXmp0EgDG2KlskXzpmumuS2pJp6SalFR3G+brmKFPeBLKdM+Uq1iVL+kI/sbWXkix7IISwIXRgkufU1rZFRcWsECwHWtsTSojdq262eYSaghygSUH0RZeHnXj2h1gszEt9rymZuq8sz5dboD1pJ2N6TVDZidq9P1Qz7++VO847W38KUnLxDHihNnmzi2xdGDk5ve03Yyjvfs94DfQld3uBb4j8Af7OSkDLtPFMWlX9aL4QOfOg6Ua1Cea2+LiW9UrbRL4W8fOmk0sxH0goh6xS1UD7ewWFrrcW6pTaPmDgRJaF+QH/ZbZDhJae447nexbVRdGrXh92SLYqXx0h5FJdqHm1u0B8PeAQ7ONXj7XTfrOW6gQY0SUKPGTaaTCVRvbB/UcMHblH5O1wgf1IhisVXPSQRUSKsTZgL5bx86yb7pKqcXW0Oh7e1uSLsbZr+rrh/ylaeXWGn28IOI5fUe57c5iGocxhFQlpTyb6SULSnlupTyfYxRydxwZRFEatuKRD7+7AqdXnk4uZ28QV8Kl2LiG5VzAvD5xxfo+HvH/r6XCKO4tJdRN6mld/M10wUflW1bTNY97YNKw6IdKzP1pVrI4N9CGnY9aOKzLWtIMNgli3veL1OmYbzy9oPZPEcJIrts4BwvvHnfyH1Z644kMGQz0rD4Miwrr4WNGcWXaKdBlGhQvb4Gdd+Xz3Bgpk4QxkPntpNqE6lQ7fkRj55YYqnZJVa6Rcn6GMm+2804AqoihHhp+oMQ4hWMF1xhuIKIttHE1+mFnF1qF5rFbSfRqOoDY/CQXODUYqt03+Jqh27PCKg83ZzATjWgPGmx1+fduK9Q2duxLaYaHr4fZYueLhpb1KDUwJ+I6+hE3sEgCcuCerX4Xly2uOc1qDJT3PNu7AsXx7FL/+bTBoujEAMmyfx88pGG4wdJlO9LfWyWVV7j7VVlfiHVL6arTXwhXpIH9aZXXs91BydH5J1ZdHph9rvqBro6SPoiGEaKZntkGdQdYxwB9VPAXwghloQQS+geTT+5o7My7DphFBONMPGdXFjf0lizk1XOXmhnX/7tfvOKIrVp58xTI+Ycxrr/0CBKKeoVl05v74TY7gU++JlnMn+fNeAvsazRkZ+WpfOVwpwWpN/atQbtujauM6xNO7adaUZ5DcqyLOqV8ijCwvkFDWrj5a2s/QZs7BfaiLyJb+ww8+S/0vnZuVyoEgmVRuflUZAlQzu2RbsXFHyDjmOVWkqqnkOrE+Akvr8g1JU+5qZ08d4wiml1dv/lbVMBJaX8LPA84CZ0hfKvk1I+uMPzMmwjDzx2fkPTFmgT3yi7+2/+5cNjmdS+enyJMIqZmaxkpgGAD332GeJYbTqHcYlG9NrJ88kvlrf6UIohBzFoH8vsVJWO0aAK5Ct/pLXhUix0pF6ZpmJbVtY+PCUtTxTFCs8ZNtmlx6TBFLp6RCqgoDaoQZWsXvnF2N2kod+oaL00/2ir5EsdbYcGlY/iG9csrnJtfSuJvzcvbF1nuJTReidgZqJCu6s1qCCMiZViZrLKK27TtRXDKM5qGu4mmwooIcQ7gA8k/ZrWgHuTbYYrhONn1kaWU0kZZeLrBTrbfxzfzD1fPE2zHTA7WWWtFWTXjGNF14+SrPZLd1+GcbxpN9Fmp9wcoWvHlSUQR8wZATVEz4+yBU0vuEUNKgh1DtQg2sRXKfxNOUlkXxzrBbxsEU81j9QUmGohtmUNFRguEwB5rcndpAbdRkESo4O/R5NP1NXdczf/Wy8Llc/vs7NKEuOh5VPfzDhoznNta0hAfenJRV5x+0Ha3SALbFFJgEpqzgwjte0dfMdhHBPfT1IsOfTNwL/YmekYdoL0jWjDY6JhxylAqxOwf7o25Jsp04ZOnFtnZb3HZM0livvjhXGsO6f2QupjfGk3ot0N8YO4sBCVZf03W6MEFNm9nDjbLz3T6YVaQCWC+P4vm2aLoF9QUn+fbVP0zSSWp+lGZeg8O/FB5bUrx7azKuWuowWUNbACpXX7UvNb3gc16HMpM6HlF1F3ExOfY5ebuwY1xXHJlzp68XMOsG+6tskZaa29ESa+TIMaXa+vfFD9wjU9Ucna2qTBJ45jEw4I5XY3ZP9MnVaiQXmOPRQ1GEbxps9zJxg3iu98+kOiRZlY3CuIIIo3DJuFpAxNicllve2zf6Y25Jv5m0+fKLyJ6Xbe0GwHVDyn0PJaa1DhUGvvi+GRpy9w8vx6QZh+7KFnh47r+FGhxluKUnofwKe/cjbb3vUj5iar2X1++akLlzTPq4WuH2Vv4YNBCXrhVExNDAuoQ3MNDu9rFAqV6ig+KwuScEuqLaQ5U6BfbPI+qEGBVCag8mbDzUx8tm2NDJK4WB/UOGa94jmjNSitsFojgyTKUEphA+eW2hw9OMlkQ/e5ylfwGBTKcaxoVF063QDbsmjU3KEX0DCKcd3d16DGWS0eTCqLfwIt0N4EPLSTkzJsL+EYGlQYxYU8lpRWJ2T/dG3I9LXc7LGy3uPshTYvuHk/a62AAzN1Wp2AqucQxlrgxUoRJSa+Mj/CVokilbR26LcgOL3Y5mOfe4YX39SPropjRasbMjtZvF7aHgJ0MdOUbqJBHU+0qqVmjyCMsgior1V6fpQV/bUHovgsSwv8/SWawg2Hp2h1A6peMezbsvqh0J5rDyfa2nZWkHVQgxpc/MuEQT6KbzNzsmOXpzwM3ue4WJQLzQ3PsTYodWRb2CT7x/ZB6UGP7J/ghkNTPPHsanIdizhOqqznvuZhYtqvVRzaSXuURtUt0aDUntWgfgz4ADpQQgB/ju7XZLhCCKJ407/vMCr366x3Eg1qwAe13glYWOlyckGHbC83exyaq7PeCah4NipW2lQQ9wVUz48uuZNuGOkcKM91ssXFcSw+9+jZwnGxUrRKogfTBntAISqp60dMNrxMK4wixYW13iXN9Uriq8eXSrd3g6IPanDBUMDbXnNj6bmObQ2EnttZAq7n2Em9uuI5uk0FpT6o4VJHJdfM/Q2/9dU3DB8wML8yDcreJMx8FBtpQ6PYzAeVlkIa18SXtiL/zm98DkfnJ5lKNahEGDvJc0/54rFFTpxr4ibf1VSDGhpXqS3f23YwTi0+hW4w+N92fjqGnWAcH1QYqREaVMD+6WphMf/K8SVOX2ix2uplmtVys8uhfQ1WWz7XuZNggefpPJM4VrrkjWtdsoCKYoUf6KRRbUaEF9+yn0ajWjiu4jmlRS/jXJBEQYPyo0IYs+NYrK73OLxv09ZnVwUPPr7A7UmOUN50a1v9iiCWVdQQ0m6wozQA17GLAsrRkieOFVMNj5uvmR7SOFINKovio2/iG7zMZia+TcPMRyXqWhvX2xvFxZn4Nori6+8b2wWlVC7U3eKuF1+TjYXS2/LPKEq+m46jGzXatsX0RIVGdW+kuu6+zmbYddKcho3QGpRNqxvwmZw20uoE7JuuZSGmJxfWefTpJU4ttFhd93MCSmtQrY72QdU8N9OgUh9UsIXunhvN0w+jREAV9+XvcbLmlWtQiux1tJ0TYOvdoPDmWPMcepdYkulKIQijggn3bz59Ivuc/k3UKm5WTy/Fgg1XTse2CiY+N4nii5SiVnW55ZqZ4UTbpNFfqmmlcsJxhv1CZQJqMNJvI0ZpUOk8torFePX3CueUJBunpIJ6o4Kyg6RJzunY1x7QuVJp6am0w3F2vNLfKduyqFZcbBteePN+rj+0uzX3RmEE1NcAWoPa/BjPsWh1Q84stvvbo5jpiUrmt3nmXJNTiy0sYHXdz74M652AualqZuKrVhw8187aSHeTaLAyLW0jlFKcW+7PJ4qVDldPxk6duZYFH/zMiSwwYqLmsj4iITebc25/qxMwWfeyn2sV52uma+96JywI93zOm+fYrLWCzHdo5zSLzZz3lmUVyh+lPiiV+JaswahASHpH6ePCXB6UWyKMyoTBS2+d3/BeC+fb1sjk9FHt1DdCa5hbPq206roer2/uLGsdUsbo7rxaQLmOXQi/V4mPGKBecbYsYHeacaqZ31yyOQROJV1vDXucsii+WOkKxekbZ6en+/30/Khg+grCmFpSfFIfp0ugvPGV17PeDdg31TetVTxHCyi3L6DSNtI9P6Li2pvmpqQJga1OwJH9Eyw3e9zz8Gm+83XPAVITX0R9opoFYLiOboLX7oY6CRSYqHulme/9Om8x3YHIxPybbLXiFMr8XM00235Bk8gv2p5r0+mFTNT79ev6WJsmX+dDrdNFv1Bjb8jEl5b3sQrFYssExqUuphtVLS8TiJuxkTa02TxKt1v9dhzjTkdR7iuyLDLtKa8dKkUWdt6oeRc1/51kHHn/N8DjwBfQ0XsSuAc4L4T4jh2cm2GbCMJ4aCFZWu3y8BOL2c/tVEAFUaE0USoAltZ6PPzEIu2eDhe/dn4iC1f96AM6zLvi2okG5VDzHCqukxUGzYIbNnkzvfv+pzmz2Mqi6U6cbRZax/eDJLTw84OIiudgWdDxw8zsVysRMLHS5kYLi54fZ2+7T55e5exSu3BszXO3vYHjXmW9ExQW6nwYsutoAZVGM+aDEMZZy958x/XZ5367jX4S6qDxKg09T4Mk0gWzLEdvqxFzg9Q2KG01qmL5RtjWxc1ptIDqC+uxx80l6g5eo8zEl34ngIKJW7/IXX5hNc5v4T3At0gpZ6SUc8Bb0JF8zwN+ZicnZ9geynxQ77/v6UKWeZq31PVD2r2QD332GY6dXM0iqZaaXS6sden0QvwgytpqAzyb1L3ra1AO1YqDmwgR17YJI13gdTMfVLsb0mwHWdvph48tUs0l9+ow8zgzH/aCmIpnU6+6rK77hWCQZ8+v84H7n+Z8YiJ87MQy8tmVxHwUZ1/UsxfaQ4KzWtFBFttVnmkv08q1WQAybSpOzLMdP8zeugd9UJs9nvwil8+LSxfdMg0qHySRbwA4yCXKJw7M1Fhc7Zbuu5iqCcXq4+MzsoV8mo+1heCLWJW/OKT+Q3cgii/1QQFM1Pombt3eZAs3sUOMI6BeK6X8cPqDlPKjwKuklOeA3a+/btgyYdSP4lta69Js+yyv9wqaCWgzSrsb4to2X37qAu1ev1xRuxvqDql+hEIVHMxrSdUGL9OgbGoVB8+xiZLwVKV0AcrN3kw7vZD1bkAviPGDiINzdRzbYrXl8/ATi1lViopno5TOiaq6Do2ap+v/5QSxbVkEkeJjD57Mxg4jXZssivqJxO1uyD98/XML83Adi/ff9zQnzjW52gnCYj291MQXRnGmZaSLWmExtcavEQdayKR5ULZVXrGhVtXad2qGTRfbndCgqp4zsvHlRWlQFzmfUcJHP6Mkv2pswdevxTc8lm7iWAyS6LfZadQHBNQekFDjxBLaQogfAf4O7RN9NbBfCPHqHZ2ZYduwrX6plM9+9RxH9k3Q6oSldbra3ZDpCY+DczMFZ3nV0yYzz9Whw/m+TivNHvaRaVzH5uj8BK5jU/UcKp6daUKgfWFlGlSnF2alb7p+RLOlgy8urHXZn7SdvrDa5QOfOs5zj85os57rsLDSoVHzqHg2s5MVFla6BV/KD739Bbzvk0+xmgjQrh9lyZ9h1BeWHT8cauWQkla+OL/SYWGlw/NvHN0L6EoljFQhrDpdsMJIJ3AurXX7PZ3yQRJbjFpLa9ylnXIthhf1Q3MNDs01OL/SKZiZyjSa7VhAb7+hvHXGxUTxjdPivYyNTXz9lhvjoEaZ+BINyrYs5qaqmflb0deY86HlKr50H992MM5rwvcCdwB/iTb3vQn4HqAHfP/OTc2wXVi5jPkTZ5ssr/dodYOhCuUVz2Gt5fP2u27mpbfOE4T9N9h61SWKdMBDxXUKdcy6QcRE8vb1fW+5HYBbrp3hzV9/A5999Fw2fpTU+0vzZ1I+/vmTPHlKZ7z7YZwlhy6udjkwUwe0EKlVHKKob9b7uy+c0sEXnpNVIs+Pa1u6MOZaTkClZqMg1GH1KrHBj8p7Scdba/msre9+P5zdQPsZh018YRxTqzh0elEW3FIQFFv0uaQVGtJCpBu1tRg0H5Yt/hdT0HWQn/6ul5Ruv5govostpjrqGT73utms2sa4zzkpJDGElWhPAG/K+QV1Ir1eB974qn5ic5yLdtVJvmNdftsZJ1H3abSQMlyh2FYxR2i52aOVNCPLaxL1qsOphXUqnkMYqYIAm5msZNrPZN3LMtNBv3GnGevXzk9mx0zWPepVl5VmL3PAWpaF61iJP0p/AY6fbXJwTifE+oHWcnD0PI/cqLd3ujqIQ3fT1Sapnh+x3tWtAuamdLTYYF5LFKmcBqWj/GpVh3Y3xHPsDcOkD+9rZF/MXhDtSJv5nSSOFV968gJf99wDGx6X5sBlP8f936s28YWlJr6tBgU4jp21jki1g1Gn6xD2YrDG0Hg7aIK6mLI+F61BjTjtOdfOAFsz8Y2q+GDb5b+rfNrFNQcmWVjQJu28D8qxdVsV+yKE9qUyTruN7xJCfEEIcUII8Uz6bzcmZ7h00sKcsdJ/jI2qy3Kzm/lj7r7/eHZsveqysu5T9XSIuJ8TUK97ybXZ56mGV/BB1SoOUzn7dZ6pujfU3sKx7UKB16lGJdNy/LDf9qPZ9plKKmV3kkrosUr7Qen5tToBEzWX2alqaQvvKFa0uwH3ful0ZuKrV91+SaYNfChv/4abs/35thOXk/PL7bGjC584uTJW0dsoGtCgor4Pql7VNdpSDaq4yG2tJFDakTft85T6RcrIm6WzcweP2cH18mK0oTtuP3Rx19rsIW4hSGJUFJ9lWaX5VrEqv76K+7lXjm1vmui/U4zzK/5l4MeBbwDuyv0zXAH0gohaRVcXb3YCDs41WG72qFd1blM+56lRdWklPWHSttEp1x+ayj5PNbwsh8SyLG67YY6br5kpvX7FG0549Vyb42f6wQeTdZdWJ+Cp02t9DQodfZiWRur4EfWqi+Ok+TEWfhISP1n3qHgOz79pX6bVpW+FUax7UD16fDkz8TWqLs2OrzWoDb53ec2zF0SbNm0Mo5gvPL6w4TGXyqPHl1lqlkeeDXL6QnusEjm6NUqx/A0kBYRdW2usyYLtDiTqbkVrSH1QWZDERia+ATNwmQl2J9d/R0EAACAASURBVH0kF+ODSq0HW2UzLdTCGmpLMopRv297wEyYPt+08+4gqZabzi815+92VOs4QRJPSCk/ueMzMewIfqAX9vu/fIbF1S53vegIn/5KwHSjosPKcyVuahU303bSZmdOSe28N91xA2cvtDLfRVo5oowyLeVlYp6V9X4h1jTg4uOfP4kflDdO7PZCalWXbi9EKf323AviLMEY4M4XHsnOTa8ZRrpt9YmzTZ5z7UymQZ1f7uC5G2tQ+bf4cTQoP4h44uQqL9lCNYOt0vWj0h5GZegePpsvtGFUXKSinIkvTRHIgiTyeVBsTUikHXXTFxvtWxl9fP5XUyYwxq2ucDF840uP7tjYg2z2DK0taFBpIvrQNWwLR+UFlD5Wf5fKTX92pkHpzsOOYw/5K3eacQTUp4QQv4Zut5GtZlLKj+/UpAzbwxceX8BxdMj3V44vccs1M3ieTdcPmZms4nlOIVGxXnOzSB4dBFFeBX1mosLCcgfHtvBcB2eDmnUVzxlyOM9OVkvf2k4vtojicgGVf+t2k7bgaYRgvvZYmYlvbqrKiXNNusEkURxTr+h8Lc8dbsyWx0oEZ7sb8tgzy5sWjg3CeGQn3+0i9aONg+7ho599uxvQ9aPSJnp5v0W7G/ZNfEmuWL4CyFS+OeFWfVCJNIrj/qK7UYh1QYMqWRRHlQjaDmYnq5sftE1spoWWRTuOYlTx3sEx0r9trUENvyUM+qD0y0ry/13sQDOOgHpD8v9X5bYpwAioPc7yeg/btrJCn1HSAO72G+aI435LilQzaFS1Lwc2zyK3bR0V5Ll2Zv4po+r163vl19X0C5Lui2LF+eVOFi04ijSPw7YseuGgb2u4v08UxRyYrWdjRrGiXnMzAVWmQaXbbFu/YX7xyUUekgu85etvGDo2TxDFpeWVtpNOb2NN7q/ueZK333Uztm0lmo9+vqcX26y1/YKACqO4kAYQxTE/8tuf5NajM8l+fX41yWkD+OZXXJcdb7GFCgfAW77+es4utbPkb8se/XeWVpxIuetF1wwdsxfydLaDTTXBLSYAlx1p2xZW7nnaiQY1ygeVTzrW+9PcxxjYPQk1ThTf63ZjIobtp9UJwLKoVx0s9IJjWxbvfPPtvPtjT+CHEVEU4wc6ebVWcZibKr45jvpeOLaFa+u6XhvV16u4dhZQkf8iVDy74GPyg5iDc3Va3WBk8mdaGsdNCor6A5qbbZMJ3rzg2zdVzSIQldKmzFYnoFZxSjVEpfo5KK1uwFePL3Ngtr7pghhG6rJrUI88vcQLb97PrdfNZr46AD+MhrTLJ0+tZhGOoIXfRM3Nmfh0WkCt4pYnrm5Rg6pV3MwHlS6Ao84fzP2Zn60PHbMX8nS2g800QW05GG8sBSMSdS1yFr6+D4ryhNx8aHtaZLasXfxOM1JACSF+R0r540KIeynxvUkpv2FHZ2a4ZFpdXaU6zVEKozj7o0t9Q1GsaPeCrE/Mt39DWW1gTd5endb18lx7w6z7qufgOBZnl9qFKKeKq4MnUgEVhBF3vugIUaR44uRK6ViOY6EC7Q9xbGtIk0gDN+JYFd5KD8zWedMd1/PMuXVipZNP1zsBUw2vVIOKkjd827J48vQqr3rBYVrdYFMHcRDGO16/r+NHmQmujFuumebEuSa3Xjdb2F7m2zu/0imUvYmSlIO0h1damqpWcUr9DjYXJyTSXLSyShIp45QNGjdwYK8zjpAfN+drpIlvwI+V+qDiuDxIIh9hmVot8rmPu8VGGtQfJ///+d2YiGH7ePT4Evumaxw7tcr8bJ39MzWw+hoU6PDvtBp4q9MvBrqRsLGsvrM6M/E5Dp4zelGueLoJmkXxLTitMpEu+rqFhkN9whmpIXiOdthXPXsoygv0FyqK42IV7MRnVfV0JKNKBVQ30LUCBy6VjpG2fHj2/Drf+NKjiOvnaOciHuUzy9x63SyWZfE/P/kk3/4NtwzlE+0EvSQScRST9fI+WH4YFTTTTi9kYaXDobm+Xy016WnTj07grDsuU/URVa6t4S63m5GWOrIsOHpwYqRfb5zqCVeLBrVpFN9WEnXLKx1lf8/ZmKQ+KEqru1hWP3LQsW2cxO87qj3JTjFSQEkpv5h8fLuU8qJavAsh6sBXgF8B/hb4r2gD5hnge6WUPSHEP0a3kI+BP5RS/rEQwgP+FLgBiIB3SSmfupg5fC3yoFzgpiNTnFtqU/UcakmEXV6D+qZXXMfd9x8ninW/pXEaCVYrThZm7Ni66+jmGpR+83Jdm/nZWm67k73VpxUdKp6daWZlaBODDht3bGvIPOckGe/5OmKOY+PYdpILpr+QVS9J1C3xQVmJ7yZ9w+8Fuk3IN7/iOv763v6f4McePMm185NM1j3u+9IZ3vqqG7elIeNmWMmLxjgopbWgzzx6ljAsJnC+/76naffCwktDKmDT6hqpwJpslOe4bTWKLyU1PTq2jVMpP2Yc/9ZOJuruJuPcx7i3umG7jdyONAglfWEbvl7RB+U5WkiNG6CzXYzzbYqEEN8ohKgJIez035jj/zyQZgr+CvAfpJR3AceB7xNCTAD/Gh2I8VrgZ4QQ+4DvBlaklHcCvwH8+th3ZGCl2WNprcdN10zTbAfUq27ig+q3mMjKmFgWf/7Rx0vbYAwKgFqSwAt5DcraMOw0FSaH5xo0ctWS0/yotAVHmhzcFyb9OVaT5oGeaxMmfiu7RED1TXz9L6NjW5kWlTY4TKP9yvKgbCtZqJM3zigqt9GfW+6w0tQlow7M1jm71MYPoi03ZNwq6Vtsz4/4ytNLmx7f6YWcX+oM+aCWm72sa21KWlUkTipcpwLrm15+XcnIwy3gxyENjtlMrlnW5matb3nVjVu69l5l04CkLWhQqPLxphuVQgRmGoSilP4uDs+p//Khv+s2Fdch2OUu0+N8m34A+CjQRoeZh4xRxVwIcRu6JcffJJteC9ydfH4/WijdATwgpVyVUnaAe4HXAK8H3pcc+2HgzjHmaUhYbfVQSvHON93GyrouM6R7MqnCG69SCs+zabaD0jf/wXelWsXNjnMsCzcJM99Ig3Jsi33TNd52502F7VVXm/jSArL5Gn+Oo8euJO3CJ2pe1hJCH2snOUrDJr5YKb0A5nI48jb0dD2ealSoeE7pGKmmaeU+54mVYmaywkcefJbFlS5H9jWIYsV7PvHkRVXB3gppLko3iHj2/PrI43p+hGVZdP2IMFZaW83d6/J6byhSLkxCiUHx7o/IrMJEWWh6ylarOaRCcXOz1uZj77S2ulvkIyNLscbXVEeZ+K4/NMXRg/1E4rRdTqxU5gfOkxeKbvKCV5Z0v9Ns+htO+kA5Uko7/QfcNsbYvwX8ZO7nCSllmp15FjgCHAbyqfdD25OuvbEQYoQxwJBHKcVKUtR0bqpKHCsm655ufRHFhT9017FxLCvrfjvIzESF1VxCbf649K3q4Fyd6w6NzqC3LKv0DbziOfhhTBj2BZSXRPw5dl9ggW7f7iaRRI2am/m1BgWonUQL5qPXHMfGTWzoFbdfsmVuqqqfSVx0KqetONJeRfmxUrq9iCP7G3z20XOcWWoxN1UlisY3lV4Kuo6h9rNtVBvw7k89DZCVfxrUoNZafmbKSwnj1MQHy2u9JNF3I5/kRfQ/soqNCDcaey80zNsNJkeUCUuxGL95oBrRbmNoTKtvIUlfBAv77b4PMI3iq3r2rguocVq+O8AbgbTiZBX4OeDGDc75J8CnpZRPCyHSzfn1xEp+HnyUm23fkLm5Bm6yqM3PT21y9OVnJ+bY7uq8pomJKgcPTnP94Sn275tkolGhE3TYv38iu+7cbJ1D+ye49tAUB3LbU97++ltZWG5n2w8vd+kFEfPzU3i1ClOTVW65cf9FzbMVKk4trDM1U2ffXIPYsjg0P0UviJiarLJ/X4OK6zA/P8U1q11OLXXYv6+BHwN2mwP7JwCoNyrZ/PbvmyC2beb2TTAzXWN+forJiQoHDkziK5ieamJZa8zPT3H4wARzcw2mZxrZsQBTUzWmZurMTHfYN9fAce1s38RElfn5Kc4vtbntpv28WBzi0acvcPTgJPWJCn4QM5mbTxnHTq7wnKOzI/dvxkSjQqNRZW5ugkrVHbrWxIROE1ha6zLRqOBHimrVxXUsGo1qdnyrE1CtejQaFeI0cGaqzv/f3plHW3ZXdf5zhju9+b2qV0OqkqokJD8zmARjQkhMGMIgEEBFRGlpGqVbAVHbblwozi7becC2tR3o1Yh2N93aghLEMAgJIHRADEPgl5CQOVX1quqNdzpj//E759xz5/veu+N7v89aWXl177nn7nvuuWefvX97f3chb+MFAZslh/xUlsOHZllsE0Gd2XSYnS1t6zwu+SGZrN3yfEvjuD6Z6PvvxiT81mHndq6WPeY2ql1fPz2dY3Y2z4GlGZYPTnfcdm42z9LSNNPTOa6+9ECy7/j/M9M5FhemWF6e5cBGlZIbcOTwHGfXykM93r006v4FsAhcC3wSuAn4+S6veRlwiRDiDuA4ajRHUQhRiFJ5x1CFEk8Cd6Redwz4TPT4EeC+qGDCkFJ2TSuuRpNTl5dnE1XecWVQNq5tVTENg2KxysrKJsvzedbXSgS+WrdYWytRiNaMqhUXy4RLjsxQ3Kq2tOf4oZqd0xmDnGmxsrLJVtmlWnV3/BmKm2XOnttiyjYolxxcx2Nrq0LF8XAdD6fiEto+KyubuBUX3/UpblUJfZ/AC1hfL6v9FB31OZdn2Vgvs7paYqVgUyqpx13HY2O9RLFYJYjWVVZWNrniwgU2i1VOndmgUq59jlKpysrKFsVilfX1MlXHT56Lj+kTZ7YIXJ+jy9P8zSPnOX5gilNRus33/Y7H5O/ueZjvf8FlbZ/vhuv4rK2XOXt2k42NStN7FYsq4j23WiJvm7iuh+t6GBhYYcjKymZSnl+uOKxvVJLZQGfPbREGIa4bsFFyOL9aYmO9jFdt/dPbWC9TKTvbOgdWV0uUyy5rqyVyHe701RTooOu+J+G3Druzc22tRKnY+veZplisspExWV0tYoed14q2ilX+5mMP4AchR+fzyW8ofo9y2WVzU51fmxsVymWH0laFlbNbAzne7ZxeL/mI41LKbweklPLVqPWgGzq9QEr5GinlDVLKm4A/A34Z+AjwqmiTVwEfAj4L3CCEWBBCzKDWn+4B7gJeHW37ctSwRE0PNFaSffuzLsKIQvTGnoeMZWJicOzgDEuz3aVd5mdyqmSdWhXfTlH57CCasmswP51lKmcnRQ25jJXkxqfydjJCfipnc9u1R1NVTbXAOp57lV6Et0wzKZLIpqr2rrvsIIZhNB2veA0qHu4WtqhaKlc9Cnmb2akMZ1bLkWK7usi3K5L40GcfIwhCHtvlhF4rTvGFnVN8xUrNnnhIY8XxWVkr47i+Gn8S1ssJeX6oes3CkK2So0r/W6R/EraxNpJ6Sd0aYdvtdlCAsZfp9VgEYdhTx5RpGDx9rtTh+eY+qNw4rkGlsIUQeSnlo8BVO3ivnwdeHzX+LgHvjqKpt6MKIT4C/KKUch14L2AJIT4JvAX4qR28374kVqCOOXpgGtMgufDUrUHZam3mxJFZDnfRmWsk1sTbKVnbour4FCtKjfzGKw6zOJuLei5UIURcXbQwk+PaSw+wMJPj0GKBQ4tTyQ+2cSRD0LgGFZfDRz+w+vUmosGF9eW3XrRWp3p2mm0vVTymcjYZ28IPAqbyaqSIaagfcquG3vMbFTZKDhtFh3u/dmbHDb22aUbViO3LzS3LZKOk1pjUDCbl9L/yyHn+x4cfoOoqm0Pq52f50ZpTGKp1tlhJoh0GO6niixp1u2wXq4Zo4p6w3qv4elqDgrpxOs3vWWuituI1qKy6qRwmvaT4PiaE+EngfcA/CyGeZhuOTUr5C6l/vrDF838F/FXDYz7whl7fQ6N4+lyRiuM3VZKZ0UU6aFAuzkSVbTshY5m7Gn+ez1o4rs/6lsNlKdWD2PFdcWIpiYJsy2waZRA7oLQvMKOLX/pzWlEZfOz00h/XNAwcz68fIRH3QcURVMPS56OnNilXPY4eUA794HwB2zKoOB6z02rsR6trRMXxWduqMlPI8PiZTcRFC4kC/NpWlaxtMpXP8MDja00qEDFhGCbl8kEY4rW5wGRtM2nWfcaxeb7+5DphqCr5Zgqqt2sqZydVXDFeoJQj/CBM7pQ7Xhh3EEFBr0USvff+7HWMbczdCulNdcKIzv12mKkI9vihGY4emMIwDKrOYLUmm+zotoGU8ueB35ZS/haq5PwPUEUTmjHjvq+f49x6pamSzDRUqXV6jDOoMt3djKm+9FjrGVC9vj4IQzaKDvOp/gy7RwklK1KnqBvxHqf4UqlMK6o2jMtk6yIoU0VQtp2OoIxaBGU2q6N/Tp6hFKX4AA4tFLAsVd10gzjUdghixfE4s1rm2PIMmyW3TjLmvq+f5e8+/QgA937tTNvP7Ach2YyFH1XxtRONzUYtBYZhcM2lB5J0jeP5ylZHpfhiqZv4c7ueakqGsE5Eth3bFYuFmuJ8L+oJgxynMUk0yhS13663HrN4n516mtJVlKZRaycZu0ZdIcQU8AohxBtQ5eWLwGsGbZhm+4So8eaN6yCGoS78jReGuDF2lFRdv26WVFzS2g0jUqeoT/Gp9Za0WOzRA9NqXESU4qMhgnK9oGkIXy2Cak7xuV5AqeolY0kuPDwTzdXyufqSpSjNCJ/60tN1r6s4Pk+fKyFOLLKyVq5zfOtFJ/keNkvtxWZjcd04Smw3QDFOPdYdL4NkZELVVaKwaeFPw1Tiu/HNTRyldWJHjbrQ80V0ryhF9IPe9PrieVDdtzW7RVDm9m8+BkEvV6c7gTdTP1FXN86OIWGo0kWN6uIqgjIjle7a43Hf0Thh9eig4u3SKbjYoaRTSN9y+TLZjMUFB6f5VnGoQTAzclANRRKup9KkrfT+PD9IRFUBXn7zSSzToOwoPcP4NZ/+8qm618Xj5pdm8zx9roQfBHz0808Ayl7bqkWU7UgPi3tyZattkUQ2Y5Kxa03I8bFQfU5xii9TlwiyTAMnOhaGYTCVt5vU4lux7fPHoGVvWV/2vUfpud/M6H3irWHQ8fvtNWobNL2sQeWllM/uvplm1IRhyNpmtSmCivXtzIY7XtvaeYpvUMwUMlx2vHvq0DSUzFLdGlRcJBGGTSoEpqGUKdK/uXiheD5dJBFdqOdts2loHtCUVjMMdWwrjpJiUoUVIafOl5Jx9KAixZCQ44dnWN2s4gchDz25zu3Xq8mtc9NZNosOm2W3rSK1qnhUNxqf+vKpthejjK2aKmPi7XxfDaerOj6FvI1VrE9tKt3BuHIy07FKMH7NDvp0dQS1TQyjN+X2JH3aU4qv2xpU52nHw6IXE/5ZCHGw+2aaURNEEZRaB6k9HleXGWb9ndg4pPgayWYsLjrcvREwn7V4/vXHmxyUH2nxtbr7U6rq9RFU1aldlNVjSiYoY8cRVP0+XK/ZKViWqRxUNEgxCGB2KsPKWjnZRkVeIceWZ8hGhQhnNypJGi1jmdHAw/bzsGpaeapAom2RRMZiKp9pHt4YRWBxkUTaAaj5WmoNyjDUjUK7FGLdZ992BGUk40y6MQ4ppnEgn7WYm+oupKOcP91l4KndiLXd105UQgZAp3lQ8RwoG3hACPE1lA6fAYR6HtQYEskcLc7l61NfSQRltFiDGv1JuBMMw6CQtdkq1ZpITaMWQbWcEkr9b9c01BiKxj6oqltzNo0/0laFCZZp1Dm1quszN5WtKzRwvSApcnjlrRfj+yGbJTcpN7ejwoZy1Y8inebPrByUusB7ftC2nHg6b7MwnaWQrf95q+IRVdAxlbexopL1eKhk7LgMVIqvm4PaSRrIIBr53kOlmXZQioPzBQ7ONw9sbMSIIv5ejpoBbW9w4n2NtYNCz4GaOMIQNstupDlXe9w0lIZb4wW3kLW76oCNM2k9Maiv4mtVARan49L/jlXSk33EpedRJNG4n3YOquJ4SYpvs+SwMJOr61NyIxULgAsOTKtSbsejWHGTcQZVx08cUCvU+AsT31dNuq1EPgFOHpnjmy890HSBiUv4HTdgadbGstQa3HQ+Q8Y261oUFmZzlFvMlWpkp0USvQTunXQANc3EVXy9afF1Hp0RV7GOmrZngJTyE1LKTwBfBM5Gf+dRxRJySPZpuuB6AaVINSAI1d1wo0p3MrLZrM8rz01nedaVhxt3OTTUSIud/wiMhj4ly2wWi216T6u+Ys9xgqi0urbPuJqt1WyqVusylmlQripHZxoGmyWXhdlsfQSSaqyNpwHnszanV8vMz+SwLZNSRY1GaVc+7vmqiMEPgjpl+q9843yTsnnGMink6u8/4xEpfqAUIiyzpqSRsdQok3iw3VWXHOharDI7lW05ir0jRm99ULG9mt5R0WlvBShmtFba6flxOPy93KL8BXCBEOIylEL5OeBdA7VK0zOPn9ni/kdqc4EWZnKRpE9tm3zW5oU3XNi0BjVqLjo8qyR3dkhjBKVGUgdRmXnr1zRW8VU9P5kmDGrEQ5ziS3fTx7RKi1iWQanqqjlVdRFUbVvbqjk7yzQoVlwWZrKcPl9ifjqLbatCi7iMvBVxii8IQlzPT9KV5zYqfPGhs3Xb2nazg4qj6CCaomqbJk7U+5Sx1RqYUh0xWZzJdx0DsTib4+Kjcx23aSSe5NrTRXQcrpCTRMPvoeOmRnOPX93zY3Kt6MVBTUkpP4zSxvsDKeUfAnr0xYDpVC5aTI0erzgefhAmw+vmZ7JqvHnD6+2oWXWcRhhcfuECV+5CjcKgQSI/+mxqDar1qV1XGGDEqtmNEVQcDdU7NNM06nqHavsxqDoBuayFYRpslFwWZnJ1EZRtmbVZWpaJ4wZMFzKsbqp5XbZpUnH9qBG3fYovY5l40bTb+AJeqXrJiJWYjGUmvVrJY5EjDiPFiDjFl8moPjHXC5I0qG2bu2rEboeRRFDdt53U9dFRYWBEFaA9bGtAp+ntY5/iSzEthFgGvhu4UwhhoJp1NQPi9PkSd9/3VNvn//rjDyV/Vx0fPwiS7Q/M5bGiSq9Gxi2nX8jZHOsyFqATrfqUILoAtvmo6bvyWhVfY5FEkERQ6R+pGjPf/H5x31C8xrdVVhFUnA4MwhDbrjkoM0rxFbI260WHrK2EcFUEZTY12cbEE259P8T1arO9Kq7fNLb78gsXOH6o/tjGnzMIwyTl67gBWVvN4lIOStk3yLlWag1K90H1GyPqA+ypSCJer2rDBQenmdlFdqNf9HIW/iXwIPAxKeXjqBHtHx+kUfudUtXj0dPtp6XGz4VhSMXx8YOQp84VCcKQ77rtkqbUV0xa0mcvEFctNdKuzBxoKJJQfVB1RRKmiqps22iKoCyzeUR8zHT0YzZArUHN1NagPC8gn7WS/rR4DaqQs9koOqqx1jKpOB75rN0+xecpxxmEYd2k3yAIyWetOgHaueks+YYqvrQjjlXj44nG8SBEwzC46NBMnT5iP4lTS72ciTrFtz3iNajelCTU/9s5qWccm2cqP/oCqq4uUkr5TuCdqYfeKaVcG5xJmqrjc/p8eyn8ta0qq5tVPnv/aXIZtZhfdXxWN6pq2mybyGLcIqjd0jiyPKbTGkdjFV/jDzqubrJME8OoV/NuF0EByY/ZjKKSQq5Wph0XRGQyaQcVUshZbBQdlZINQipVn2zGbKtS7gVqHIYfVQTWVWTmbCpt9POCUK0/pR2xZanzxnXjNSgr2ed0PsP8TI6VcntVi92gWnV0BNV3jGZx4/abxjc3O3+7XtcSd8O2r1jaOQ2equt3VHiwTIOz62XKVY+K6yfiqHFKyWwXQY2ZasRuMaDlnOXGuVdp0nflptH88riXKv47vRtVxt7alulCFEEZShPRtsykSOKBx9dZmMk2RVBTOZvNkkM2o4Q4q9Ea1ENPrbd8jziC8lNrUPEdcNruptf56nXZVFm6EuVVacV8Vk3cjSv4BnnNaRfdt0JHUNsjXlfqdQ0KOlfydePOf3p0x6/tlb11S71HcLyAnN26xwXUBW6zpBQHKlUfL4oC4utTu/yy1aVseOKInEEjnQbiNUZQjRFRuvzWNOsvkvFMrVbMxBFUpD4Rp8wAHjm1wa3XXFBXJOH5AfmczWbJTcRs4yq+T32xXmg2djyxkkScAsxmzKSq0OwQ3XmeWruqW2uLSs5BKRVkbJOsraLvQY5hUjcVvV0UdQS1PQziRt3uxy1WiuhUydeNUqV7n9xu2WNXrL1B1alX+G7ENA02Sw5BNLcnVimPp7+2u8b0IsI6ScSyQo100iNrXINqvFam5Y3SIweS17aNoDLJa1qtA1ipFFvcf2RFTiJjm1GRhEc+a7GeEox1vYA7P6PuVOMy85hslJaLP0vnCMqoK6efm85y05WHMUwjWR+LG40HmrYxjB6TUNpBbZftjNswDbUmvRsH1UkqqV/0Mm7jOiHE5yKpI4QQPyuEeNbALdtDfO3R1W1tX3X9tioBEDsoN6mGii/I8anWeGGN2WspPmidzuhUJdZYxdcYaTamzeoiqA4pvljgtl3hhnIAVrIfNa9JNbsahhK+rTgqxZcuT3c8n3LUiO35qhowvnBnMyaun0rxtYlMNssu04VM3fh20zCYncpimYZaH7PNRKppoP4JneIbJGrcRvft1Dln4u8ixdfLzLDd0sst9W8BPwDEeYf3Ar8zMIv2GGEY8oUHz3bfMIXTwUHFJcIbJSdazDdqKb7U2kmrk7RR5XzSafc5gwCsHqv4Gn+f6QITw6ChSMJsuwh94xWHU69vfv74oRmeednBxIa4Ym5uWrUUplN86QZfxw2S6bZeNJI9timXsepSfO2c52OnN7no8GzL0nHbVCrvtq1SgI2Cun1nG7vWEdT2MJMoupcqvmie2i4iqF7EhHdLL1esQEr5xfgfUsoHUKKxmh5wvaDr2IJGHE9J0bQKUodK1gAAIABJREFUv30/JGebiUhqnEduvLC2StPstTUotaDf/Dl7jaBMw6gbSxHvMz52jdp9Vg8X73brf7GiPKjvwfVVz1E8TdiOtPhyDVV8juvXOyjbSJqusylnZhrttdUuPjrHocVCnWp7zFQ+k9xNZ2yzSVC338TrJL1w5YmdN3HvS7aR4jMMkoKbnTIuDgohxMVEGSQhxEsY6DLq3kINqtveFxmGYVOqJ8bzA7IZi1LVI2tbGIYao6BGuqttzP2S4jNa64V16gVpjKAaI1U1N8pquX3cO9QJ06yPylqV4pqGKhU3UxFU3LzbGEFVUw7Kj25ELFOtJ+UieaLYtnZ3wz/8yqsxDYObWuguxnJIdlRq3i493C+2s/9vOqH1ALZDnD7tOcVnt27o75WxWIMC/iPwfuAWIcQ68GvAWwdq1R6i4vptpWs6kUldfNLEIxsc108cjh+oMuK6CKrFN7sXiyRa3St1iqDSEkgGRlMxihkVDcSkj5llGV2dfGME5fthU8uAkhhSTvSaSw8kj8cK5ZZV24fr1VJ88f7jwop0BNVNGQBUmrGRWAvRNAwuODCFOeAycxj8/vctxnaq+NS5vasiCdfn9GppoNV8vVyxHpZSXgMcB45LKa8FNgdm0R6jUvV2tBCZtU3u/doZnjxbrHvc91X6L60J50eL57Xy6NZ3qeM2PbcftIug2orFdomgGh9rHOrXLU3a+L5xhWWaeA3KNODaZxys2zabtZgtZPAjx+O0uMGJS8ZVmXmtJH4nd8OXXlATe33etxzHaHPu9IuBVwnuY5JCmZ6q+Ixo+OXO38/xAr7x9EZd1Wm/6cVBfUQIcVBKuSKl3BRC/CvgowOzaI9RcXYWQWVti7XNalLBFeP5aqRGep9+JCKaLo9udRFYms1v245xpl0qMwjbL7BbjWtQjRFUw2Nph3Ti8CwXLs90vIDHKbiYWJWi0Ya4SCJNIWdzaKHA9eJQMrm36tWPA4lfH/ctKVXzuKelrVltuemqIw32D3bMwqDXuPY7Qfs5lnWoNajOM6G64XlqSvQgMzO9qAH+LPAhIcQbgLcBFwG3DsyiPUbcp7RdMrZJseJS9epLOb1AiXum9+kHak5QuaqcWbuLwO3XH9+2HeNMO9UDP2i++MfUrUE1pPPifaYjqHRKb3YqSyFvd7zANhZWVF2/yVnWeqXqXzudt8lnLZYXCnhBLYLKNkR5tmkmKb5SPIfKVHOeukUn8VpXJ/sHi6HLxweEgWpc7+U7jNegdlPF53h+0jw+KLruORq18QbgA0BJSvlcKeUTA7Noj1Fx/B2VlCgH5eG69RcTzw/JZdXMoCBUJ5oXhA1rUOM1VmNwNFfV2ZaJ6wY9VvG1KJIwjQYHVf8TUeMM2h9btf5Xe/599zzc0pZWenTThUxSoReXjztuUNe/BCpVm7Utchl1UxKPp/f89goayWvNzpHWoFNwhsFgy9j3MYZhtG0kb96WOlWSneC4anDmIJcO2kZQQoj3UP9xHwJeJoT4cwAp5b8emFV7iIrjdWy6bYVhGGSjCMrxfL7wwArXXnYwqf7KRFNVHddnYSanUnx2qorPHI9pmIOm1YJ+1jZZLzo9i8W2quKrS/E1HMhOwxDj16dTeqWq1zLdGIbN39FMIaNmMaV0/NRAwXob4xRfLmuxVXbJ59SgRD9a1+pEN3mbdmnTfrLHNIvHBsOg5zUlI+qD2k2puOMFSW/eoOiU4vvIwN51H1GueE2D49qRSBaFIbmszWbRper6fP3Jda44uUgQhKqKL0rxVV0/iqYCpqxsXQS1LxaiW/RBZWw1+K9XsdjGNaimIomGu0PlWDpHUOn3LlXaOajmSGx2KhtVCtZ6oRw3YCpv13XtW1HP0uJsnjNrZZ5xbE4p2neIHJPPbHau9hu4kkSL70zTT3rzUGbUB5Ue0bIdglDNJPP8gMwAx/h0cn13SSnfDdzT5j9ND5SqHvkGB/WZ+0+13Pauex9no6QqYgo5i42Sg+MGFMseT54t8jm5onplootqrM3mRxNSa31QjMU0zEHT6mJq2yaO47e9yB5Zmkr+Xl4ocNOV9UUC89O5utLvF91wUf0Ows4X2LQIK6jvv5XTaNUf9cpvO4llmnURVMXxuODANKub1dpnNFWEPZ2P5klF/UsVx2vZjFtnX4eGXvX8YB2IwX5JPw+fbWT4OLw4xfVieccpPt8PCcNQtVGMKIL6beC1qIq9Rv2MELhkYFbtMRqvTw89sdFyu42SQymq2ivkbMpVD9cLKFZcNooOnq+qZmL167iCprHMXEVQA/1IY0HrFJ8VqTS0PgC3fPPR5G+1UNwcgS0vFJJ/zxTqh7Z169RPF0n4QYjTJppr1VAZ/9AztlGnJrE0l+PcRiWp0nzOdRewslbGNFLj6U2DctVrKvpopKcIquMedsmAqwT3M9tZgzJN1ZC+03sFPwiiMvXepiPvlLYOSkr52uj/Fw/s3fcpxTaNbVslN6nEK2RtclnVkFusuGyWXDwvwAtqzZyerxSx/SAkkxoFMYx1hPGg+XNmbBPHHVyHe7eJpekiCc8PEtXyRjoVW1ipCApgaS7P1x5dTS4mU/lMNFARLrtwgbnpLGGoorXZSDqpHWnV+5bPDzrFh+6DGhQG2+uFO7de4cDczlpPPD/EtlrrTvaTjosjQohrgFNSyjNCiDcDLwa+BPyKlLI8WNP2LlvtHFTZpVh2o7sbk6mcTRCGlCoe60UHyzQ4s1rm2MFpLNOMThIzKTOPq7P2SzNkuyKJ7WofboduUjKmYSSLxp6vIqjWKb72kUTGqn0GwzCYKWR49PQmJw7PJtvYtnLOL7/5JKBmTql0crcUHx3TOoNeI9JrUANkm4f12VcdSUSOt4sfSa7tRiqpF9omD4UQvwr8FfBPQoifBp4NvAvIA388UKv2MJ4fqNLzFlimwepWNVlTmI902gzDYDNK8a1tORw/NKNKkYMgGowXRkrl6TLzYX2iEdLCEWdsE3eAYwBCOo+5To/o8P2Aqhe0zNF3jqCMREkC1EDBp8+VWJqv3e02lr+bhkG56pPPdC7I6SXFN9gU3P5IP4+Cdkr67chlrUTqart4frhrLb9e6GTd84FvAg4CXwGOSik94G+FEJ8aqFV7GKUsEbBRdJKLVLHiMp3PUMjZPH56i8svXABIhEQz0XgNVU5sJGoFSudN6Wnls3ZywTP3SQTVUhB3wBFUN+efruILAddtl+JrH4nZZr1SiGGo+V+zqfWw5153rO41pmFQqrhd16Aa993K/kHe3Rj7pIBnVPSqFL9b/EApnOxGy68XOjmoopQyAM4IIe6PnFNMT+JLQojfQKlO2MCvAvcC7wEs1Hyp10kpq5F80o8DAfDHUsr/JoTIAP8dOAH4wBuklA9v69ONIdVI+ugDn3yYm688RCFr89efeJjXvehyCjmbB59Y4znPVBefueks5arPzFRGpf6iCrS4VyYIQ+xIYfuCg9PJdWW/RFAmzU5Kyf8M0kF1qeIzalV8VhSt9FrFFxOvKwZhmGRtXM+vK9g4MF+/dmCYKoLqNIkZogizw/EZ9BqUeo/B7n+/Yhi9TyveLUkENWBB817rAxtzJl2PgxDiecDVUspnA98O/B7wS8B/kVLeCjwC/IAQYhr4OeAFwHOBnxRCLKEqCNeklN8G/DrKwU0Ure5mKq6PH4RsFB0eO7XJJ+57iidWtljbcjiyVGCz5HB4UVWRPf9bjlOsuCxMZ+suKnGvTCxeurxYYCqfjqD2iZxMi3RUxjYHOgag2wU8HUHFqb3tF0koB+X7Nec2lbebKgrr7YJStXsE1e34DENJYj9E96PAgN7rzHdJEKnXjDLFd7MQ4rHo70Opvw1U2q8bdwP/L/p7FZhGOaAfjh57P/ATgATulVKuAwgh7gFuAW4H/jza9h+AP+3hPYdGt7HsoJoscxmrblxC1fHJZkw2ig5ff2qDfMbi1LkST50rcmRpil9/083JD/jI0hSOF3BoocBT50rJPuK79CBU4x9eddslVFw/uVjvl4XoVj072V12x/f2vl36oGLHlIqkGgk6pPhiXT0/CJJ9LM7mmzT5Gl9TrvpdHVTWNrsWeQzyzNF9UINjO31QuyUIo+WFEToosZsdSyl9IJ4V8Ubgg8CLpZRxx+Ep4ChwBFhJvbTpcSmlL4QIhBBZKWXb9OLi4hR21Ki4vDzbbrO+8OcfvJ9//dIrO25zdq3M4eUZzq5VEnueWqswO51jo1il4nhccXKJfM7m/JbLjVcd5vCheruXl6Y4fmiWB55YY3o6B8ChQ3PMzuQoVzyWD85y8ugcp84VyWZslpdnWS17rJW9vh2DQR/LnXJ6o8rM+XJi3/LyLAuL06wXnYHZPD2dY34u33b/DgZzZ4osL88yO5Mjl7U4cGC6bvvl5Vksy2RpabrlfkLL4unVCouL08zPFVhenuWKSw50/Ey+qdbejh6Z7+gAzhVd8rlM232V/JBzRTexs98EQUguZ/d13+N6fjYyaDvnT22SyVi7ep9ur52ZznHgwAzrFZ/pqSzZbH+/y0Y69UE92o83EEK8EvhB4EXAA6mnDJobgHt5vC2rqyrKWF6eZWWl/yOrHju9yfnNKtc94yDnVktd3+Nv7n6YCw/NUCpVWVnZ5J77nmJmKoOJuoM+fa7I/FSGo0tTPP70Ot90fI6VxpSVATZqrWlzq0LGMllZ2ST0AzzXZ2O9xIptsLpexvN9VlY2WV8vUSxW+3IMBnUs+8H6eplS9DnTdgZBODCbK2WHra32x3Z1tUS55LCyskm14pK1TTbWy6xE1VKxnY7js75WYqVFWfjaZpW19TKnz2wm+3r+tUc7fqa19QqeF3D27FZH+7c2K7iu13Zf62sltrYqAAM5hmEY4rl+3/Y9zudnmmHYubFRoVpt/912oxcby2WH02c2OHt+i8APKEXn525p5+QGKtsohHgx8A7gJVEKryiEiNv0j6EKJZ5ERUu0ezwqmDCklIMb3dgD5zerbBYdgjBsWyqe5nPyDNOpMs7PP7DC+Y0quaxFIWfjByGbJZeDC3mKbTTbLj46x4H5PFP5TKRsrS5oWdvCSA3QSzfnqjRKPz7xeDOKhuRuBSh1RRKWqZqqW3yvnSSFkjWooKYU3e1zmmZnEdiYbMbsuD45eC2+fbI+OgKGcVRjrdAwUKNoRtYHtVuEEPPAbwJ3SCnPRw9/BHhV9PergA8BnwVuEEIsCCFmUOtP9wB3Aa+Otn058I+DsrVXtkouZcfHdYOeLgYzhQwH5vP4QYh8bBXPD3jwiTVyGeWgZgsZHNcnFw2ea/XDvfYZB5mfzlLIqbWsxEFlTFXNZ9YuYPGXuW8Wols06gL8/o8NblxZt/W9Qs7mcCSVZJtKGb3V92qY7fuB4io+329dot4K0+ztwp+xzY7nxtJsDnHhYk/vuVO0gxoMhmEMvMzcNAxcT1WYWubgy8wHGUG9BlVM8b+FEB8XQnwc+BXg9VEhxBLw7kiR4u2oQoiPAL8YRVvvBSwhxCeBtwA/NUBbe2Kz7FCuelQ9v2M3vh8ElCouV5xY5NDiFEEQ8tVHV5kpZDizWlZCn4UM8zM53Gh8huO1V6K2bZOpXOTMotlAL73pBKZRa9hM35HHvVJ7nXaOuFO12+7fs3OEMVPIcMXJJUA5GiVL1fwz6xT9WUmRRNjzKAPTUM6nG1m7tcNMns9YTSXs/WY/nJsjYQhFEqfOl/i9/3NfJFBt9DzeY6fsrI24B6SUfwL8SYunXthi279CqVakH/NRgxLHhlia3mkxJffMaomZQobHTm+Rz1k88NhaUuVnmgauHzCVz7C6uUY+Z7E4l8epemyWHLIZs61mG6hG3ULO4txGkKhVF3I2pmkkE18Ns3bhTP+9lzEwhpPXqHvP3i+wSYqvxfam2b6Kz4qaab2g92FwZqRw3g0VQfW0y4Ex6vffqxgwcG28177wcv7+M4+qHkxrsC0dMOA1qL2K4wZNudcvPHiWLzx4lnu++DSrm1VOnS8xHd3JW6aB6wVM5WzKjkfGtliYzXHz1UeiYYNWRweVz1o857pjVB0v2SfUD8dL35EvzuQ4eXRuEB99rDCM4U9n3U4Jfzydt1XE0inKtaL1pG2l+Ayjtwgq0znFNwx0im8wqEbdwXqo+KY7CJSDymcHFuMA2kE1EYQh9z9yvuM2TosU35nVMl97bBXTgAcfX+f0ajkZVHjtMw6Sz9rYlsFsIYttGUznM5w4MosfhknvTruLkWEYLM7mME2zbp5RevZQWjh1Km/XbbdXMQeuG9f6PXt9y4xlks9ZLaOgTg2/sV6eH/Q+a8c0jEiPsTOWaZLZ5oTnftOr09VsD8MYfAQVkzioAZ9L2kE18NmvnObu+55iq9y+YNBpUSRxZq3MRtHF9QM+9oUnqDgeC7Oqb+nio3PJhXRxLodtmhSi6j4/kgxx2hRJpJnO2yzM1MYpWGZt9pAxgoq2cWD4VXy9v+fNVx/h0EKhdRWf2f378reV4qNnxxOvY44KHUENBqUkMRwPpVJ8RtfG8N2iHVQDp1dLvOBbL+ShJ9fbbuO4fhJIB0HIA4+vsTiTo1R1ueGbDvOjr7oGyzI5vjxde42nVCWWZnPYlpGoCAdBSDajUnzdUi/PfeaxuotarHoOw9FQGzeUsOmw39Og1wGiZqSZ2Op77UXQdzspPqPHCAoYeJVeN7SDGhDDVJKIIqhu2o+7RTuoFhyYy7NebK+HW3WDZEH68TNb/M+PPsgzLzuI4wZcL5a58uQS11++XJefrThKyPPgfAHLMpP0Xzyu3e8yCA9IVM5jDi3VJr/um9LyFMYIqhW3KyN14xWHWv6IeylkUSm+bRRJ9BgZXXdZL0plg6NV0Yhm96gy8+G8VxASrUFpBzV0shkzqdhb3azyxYfO1T3veLV+pIrj8eRKkeXFQp0G3ItvvKjuNZVoHPd33nYxV55c5PABFV3tRrY+PXJh4KO6xxCjTR/UYN9ze+tehxan2kRQvab4trEG1UORxDigx20MBlXFN6QUX3RjrSOoEZC1LRxPOah7v3qaLz9c76AqTk0otlz1ObI0RS7TecxDseIlo7oPzheS1/tBSNa2OvZV9YIqW95fP/xRrLv1S4i3lwIP3+89ggK6DiscF3SRxGAY5lENovVRXcU3AmxLlYV//cl1SlWvaepkxfEo5GIH5fHGO64gY5sdf3hhGNbJHtWeIJqrsjsHtV9mQKUZwRJU32SkeimSeGJla1sX82x2Mn7O+y0VPSyGm+ILObo0xfGD09033gWTcUYPCT9Qi9LxheO9H3uQYtlr2q7q+EnDbNnxmJ/JkbVNMh3WADK2yVS+WeEgXjvY7cLxvpkBlWIUKb5OGnrb3U+37+vu+57qOcUHcNs1F+zWrKGw387TYaHKzIc1UTfk4HyBgwuF7hvvAu2gUqTFWAFmC1kePb3JocUCj51Wir1mpJMWX6PKVY9C1iJjmx07+TN2rTAijWUaXaOvXtlvqZPRpPiMvvxozB6KJBzX39Z3enhCet90BDU4hjkPahg3GtpBpXAahhAeW55maS7HjVcc5gsPngWi9SlXrTWdW6/gekpLz7bMJKpqRcYyW6b4TNMgY7du5twu+89BDT+Coo9rUN3KWtxtrkFNCnvxM40Dwxz5HgbDcVCTsao6JJRaeM1nW6bBa194ObZlJqFzLqOaags5iw9/7nHOb1SSC1bjWlWaQs5uWWVlmgaZaIT7btlvqROjh4t8v+lXv1kva4Y3X32EA3ODFW4dBYa+LR4IhsHQQig/CIei4qIdVArHDZqioLmpbN2/sxkLJxrhbpoGF6QWCadbrDHFPP/64y3vvK1oTEI/SoT3253pwfk8s2J5qO/Ztyo+s3Oqy/NDFmaye/KmY7+dp8PCYPDjNmKCcDjfo76XSVF1/aSuv12TZC5TS/FlbZPvuPWS5LlOEVQ7bbxY8LUXJepu9KrbtlcwDYNCi3W9QdKv5uBukZjj+h1TxpNMbsRagHuWISpJVF1/KOu/++uK1oWvPHI+cRRVxyfXosa/kLPbdk8/+6ojLR/vhBnp6WX6cDHai3fb44Zh9CdF1W3AYGO6eS/x0ptOjNqEPcmwxGKLFY+Pfv4JHUENmy8/fD6JoFw/qBPVtEzVY3DVxUv84B1Xtnz9iSOz235P2zJ6nuXTDZ06GTwG/alC6xZB+ZFG415kvzWUDwuD4aj7ZyyTStXTVXzDZmkul6RVDs7n62Q8lApE/7+QWOCzH2tQOoIaPP1qiO4mdTRTyOzZFJ9mMBjGcG5SX3LTRVGRhK7iGypLc/kkrXLBgek6mYLpgk3FaW7a3S3xiARdJDEZ9GtIomF2VsGYncqMfCyGZvLYTmP3TpmdypLLWENp8dAOKsVVJ5eYiSbWXnXxUp0+3kw+w9pme4XzndLPCOrogclo1Jxk+lVmbptmxwhqbiq7Z1N8msGgCq6Gc5Oaz1lDSdVqB5XiqouXkr8bLw7ThQx2H5ppG4kjtn6kc26++uiu96HpTL/GmnRrzD5xZDa5WdJoeqUf/ZS9UBiwSGyMdlA9ohxU/7/8fkZQmsHTrzWoy47Pd3z+osPbL7jR7G+GtQYFDHwOVIy+KvbI8nyeb7umFqH0Szk4FpjVDmoyMOhPFdo1l452aKBmb9IPybReGPQcqBgdQfWIYRh1KT7TNPD89vOfeuWSo3MA3HrtZChR73euvuTA0O4eNZrtEDf9DwOd4htzTINdz3ACuF4cAuDQgGXrNf1BrwtpxhZjeBGUTvGNOdmMRTCs6WAajUbTBQOwh7YGNZzYRjuoHSIuXBhaxYxGo9F0wxhmiq+D7mg/0Sm+HXLhoZmO4rAajUYzTIwhpvheccvJobyPDgF2iGEYHJzX60YajWZ8GJaDGlb2SDsojUaj2QMMM8U3LPbWp9FoNJp9imEwELWbUaIdlEaj0ewBDPaeYLR2UBqNRrMX2IMpvrEuQxNC/C5wE2qS8Y9JKe8dsUkajUYzlpgMr0hiWIytuxVCPAe4TEr5bOCNwB+M2CSNRqMZX4zhVdcNi3H+NLcD7wOQUt4PLAoh5kZrkkaj0YwnhZzN4cW91foyzim+I8DnU/8+HT220e4Fi4tT2NFcpeXl8R9XMAk2graz32g7+4u2M9o/cPLCpa7bddzHmB3LcXZQjclUA7UW1ZbV1RKgDvLKyuaAzOoPk2AjaDv7jbazv2g7+8cobWznGMc5xfckKmKKuQA4NSJbNBqNRjNkxtlB3QV8N4AQ4pnAU1LK8b4F0Wg0Gk3fGFsHJaX8NPB5IcSngf8MvGXEJmk0Go1miIzzGhRSyreP2gaNRqPRjIaxjaA0Go1Gs7/RDkqj0Wg0Y4kR6rHlGo1GoxlDdASl0Wg0mrFEOyiNRqPRjCXaQWk0Go1mLNEOSqPRaDRjiXZQGo1GoxlLtIPSaDQazViiHZRGo9FoxpJ96aCEEHtrLrJmz6DPTc24Mopzc186KE3/EELoc0gzluhzc/LZd0oSQojnAK8DPgl8RUp574hNakIIcRvwfcDdwD1SyidGbFJLhBDPA74XeC/wWSllccQmtUQI8SzgFuDTwCkp5SOjtag1+tzsH/rc7C+jOjf31R2GEOK5wK8CnwNOAC8TQtjjlFYRQrwAZePXgdcAV43WotZEP6zfBP4FKI/xBeD5wH9BTWP+duAtQohbRmtVM/rc7B/63Owvozw395WDAk4C75JS/lfgg8AdwGEp5ViEkdEXfhPwC1LK3wb+EbhRCHGjEOKK0VrXxDTwGSnlHwHfEEK8RQjx8mi45DhxBfB7UsrfBd4NHALeHP3oxomT6HOzX+hzs7+cZETn5n5zUEeAeYAoRH0AWBipRSmiL7wKHBNCzAKvBi4Cfgj499Gd4bhwFjgqhDgE/BJwOfAi4E1jZmcA/DCAlPIbwGPAV4HnCSHmRmlYA/rc7B/63OwvIzs3x3pgYT8QQlwMbEgpz0kpf63h6QJgRdvdBqxKKb80AhtvB74VOAf8vpSyKoRYAH5cSvk5IcSFwA+i7mQ+O2z7Guz8FmAL+DPgIVRO+pellO8RQpxA5anHwc7rgVXgvwLfLIS4B5WamgN+FpWyOAZsjNBOfW721059bvbPzrE4N/d0BBUd5M8A3yeEuCj1eC5KWcwARSHES4GfQp00w7bxZuAXUXd916DG3B+RUq4BXwKQUj6OOiFuGLZ9Lew8D1wJ3AP8AvBR1LFDSvkoKp8+DnaeA65DLT6/DfhR4I+BV0sp70ddwE6OyEx9bg7GTn1u9oFxOjf3egRVQoXN3wx4Qoj3SymfllJWAYQQ70edICeAnxhRRdJNwN1SyndFNv0K8EEhxEuAnBDi11AVU7cDrx+BfTGNdv4G8CFU6uSXhRDvAR4Eng/825FZWW/nuyI7Pwa8XEp5RgjxQ0KIw6jj+TsjtFOfm/1Dn5v9ZWzOzT0dQQEG8GvAnwI3A68QQhxLPT8FvAr4ESnlV0dgH8C9QFYIcRxASvkO1I/rQ8AZ1J2qAfyAlPLBEdkIzXb+JCpV8jHg7cDvRn+Po50fAz4shMihooHHgdeMuERan5v9Q5+b/WVszs093QcVhaMZKaUT1fH/IPApVI76W6WUnxVCHJZSnh6hjceAX4/seo+Ucit6/I+Av5dS/u2obEvTxc6PSCn/epT2xXSw8w+Bu6SU7xulfTH63Owf+tzsL+N0bu7pCCqqPHKjvz8BvAu4Nvr/u4QQF47yAhDZ9SSqZ+M7gNcJIS6NnjqNqp4ZC7rYuTQywxroYOcZYHlkhjUwzuemEMIQQpjjfm72aOfIz80e7ByLczNyTGN1bu6ZCEoIcRUqdxpKKR8RQlgAUko/KtnclFKGQohfRYWnL5dSyiHbmJdSVlL/NgBLSukJ1aD3RqCIWhu8Avh3w7ZR2zl4O2Nbo/NxXM7NZ6JSN+tSyi9Hvx9TSumO2bHUdg7WThNAShmMw7n9cDTcAAAHD0lEQVS5JxyUUB3Zvwt8GLUQ+nYp5V3RczejurR/B1XG+TOo5rj7R2Dj9wO/I6X8cvRYfJG6BVXK+yEghyqX/YRUvRFDRds5VDufDbyE0Z+bzwPeCfwt8G+A10op746eG6djqe0cnp1jcW5OtIOK7pjngb8EfktK+Y9CiDuAPwLeJKX8gBDiC8DPSCnvFEIUAFtKuTkCW98I/AjwHlT+/v7o8cOo7uyfk1LeOWy7GtF29pcudt4J/KyU8u9HcW6KWsnwXwLvlFJ+VAjxBlSfzo8Bh4G/Y8THUts5Ejv/lhGemzETvQYlpQyl6sn4F2BZCJGVUn4AeBPwx9Hdyo2RczKllOVRHOSIMvA+VH/Da4QQV0af4TTw3bGNI7Itjbazv3Sy89XRBcAaxbkZ/X42gUeIGi9RKgEHpZS+lPIp4DujYzkyTUBt50js/K5Rnpsx4/AD3hFCya3EdwOPoxrwlqP0yQeAt6JKJQ+CyqmOysaIO6WUv4BqIDwIfK8Q4uroufXo/yMJZ7Wd/WUHdo7s3Iyc+LvjlDjwFJBNbVodtm1ptJ39ZQd2Dv3cTDORDkoIcSvwv4QQt0lVcfLfUT/+t6G0wjJSyv8L3Ac4I7bxVgAp5ZoQwpZSngN+BTgAvFgI8VPAnwsh8tpObeeQbXyOlDKQUn4+9bRJpLsmhPg3wHuEEFNyBKK12s79aWeaiXRQqA7nNZQ8/fOlqpB6M+oA/zjwA0KI7wduBDIjtvFHhOolQKrqMjsKoX8E+C7U2IK3SSkrIzoZtJ37z87YxjfHNqbwgBUhxPegBGF/TEpZGrJ9MdrO/jIpdiZMqoNaROltfRB1sG+XUpZRysD/jIqmXgK8Tkp5agxsfGv6YhU9fzWqxPT75OiUAkDb2W8mwc6WNkKiWVcA3gH8h3E8lqDt3CGTYmfCxFTxCSGuQy3oPQaclapMdwn4TuClwB9G1SgXSCmfEkLkZKQdNUY2/r6U8hNCdZQfBx6P7qqHirZz/9m5TRtfBvxDdNEaKtrO/WlnOybCQQkhXoSqw/8GavHuESnlf4qeO4I60M9BdY7PoFInQ52iuU0bs8A7hm2jtnN/2rkNG89EL/lFGcnwaDu1naNk7B2UECIL/C/URMc7hep8/hngYSnl21Lb/RnwXOAVcviNjmNvo7Zzf9q5AxtfKaX8yjBt1HbuXzu7MdZrUFHYeQFKmfhs9PC/AD8BXCyEeFu03e2oMvOXjeACMPY2ajv3p507tHEUF1Nt5z60sxfGNoISQrwM5fFPA69ALe59j5TytFC6Vs8CXota1LOAeTlkuZBJsFHbuT/tnAQbtZ37185eGcsISqh5KT8KvF5K+R3AB1CCip8QQhyXUvqoiY9HgGNSyvMjuACMvY3azv1p5yTYqO3cv3Zuh3GdqOsAeSLJd+DdwF+gysc/JIR4B+ogL6Dq+kfBJNgI2s5+Mwl2ToKNoO3sN5NiZ8+Mq4NaRVWUxN49g8qTvk4IcQq4BLgKeOuwy3UnzEbQdvabSbBzEmwEbWe/mRQ7e2YsHZSU0kWNQo7ZopaOtFEzSt44dMNSTIKNoO3sN5Ng5yTYCNrOfjMpdm6HsVyDasEZ4EtCzSj5IeCfRmxPKybBRtB29ptJsHMSbARtZ7+ZFDvbMrZVfGmEECeA+4GvAv9KyuFPnuzGJNgI2s5+Mwl2ToKNoO3sN5NiZycmJYJ6HPhN4HvH+CBPgo2g7ew3k2DnJNgI2s5+Myl2tmUiIigAodSgve5bjo5JsBG0nf1mEuycBBtB29lvJsXOdkyMg9JoNBrN/mJSUnwajUaj2WdoB6XRaDSasUQ7KI1Go9GMJdpBaTQajWYsGUslCY1mPyCEOAlIag2UGZT69C9JKUsdXvf9Usq/GLyFGs1o0RGURjNaVqSUz5VSPhe4HZgF/ke7jaORCT83JNs0mpGiIyiNZkyQUlaEED8OPCiEuAr4JWAJ5bT+j5Ty14H/BpwQQtwlpXyREOJ7gLeilKzXgH8npTw3oo+g0fQVHUFpNGNEJPj5OeAO4H1SyucBtwA/LYSYA34eFXW9SAhxIWrw3AuklLcDdwM/PSLTNZq+oyMojWb8mAdOAbcKId5Ebc7PUsN2zwaOAv8ghADIAWM9gE6j2Q7aQWk0Y4QQYgq4Fvg4yuHcIqUMhRBnW2xeBf6flPKOIZqo0QwNneLTaMYEIUQG+H3g/wKHgYcj5/QKYArlsAJUNAVwL3CjEOJI9PpXCyFeOXzLNZrBoLX4NJoR0VBmbqIc0F3ALwNXAv8TeBp4P3A18EzgJuDzgAfcBrwC+A9AKfrv9VLK08P8HBrNoNAOSqPRaDRjiU7xaTQajWYs0Q5Ko9FoNGOJdlAajUajGUu0g9JoNBrNWKIdlEaj0WjGEu2gNBqNRjOWaAel0Wg0mrHk/wMtqEDo/JX+1gAAAABJRU5ErkJggg==\n",
"text/plain": [
"<Figure size 576x396 with 1 Axes>"
"<Figure size 432x288 with 1 Axes>"
]
},
"metadata": {},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
......@@ -923,21 +934,50 @@
"%matplotlib inline\n",
"import seaborn as sns\n",
"\n",
"# Hourly counts over time\n",
"# Daily counts over time\n",
"plt.plot(rides.groupby(by='dteday').sum().index,\n",
" rides.groupby(by='dteday').sum().cnt)\n",
" rides.groupby(by='dteday').sum().cnt, linewidth=0.5)\n",
"plt.xlabel('Date')\n",
"plt.ylabel('Bike sharing counts')\n",
"plt.title('Bike sharing counts per day')\n",
"plt.xticks(rotation=45);"
"plt.xticks(rotation=45)\n",
"plt.tight_layout()\n",
"plt.savefig('counts_per_day.png');"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
"execution_count": 29,
"metadata": {
"ExecuteTime": {
"end_time": "2018-10-25T15:08:38.467781Z",
"start_time": "2018-10-25T15:08:38.048415Z"
}
},
"outputs": [
{
"data": {
"image/png": "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\n",
"text/plain": [
"<Figure size 432x288 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"# Hourly counts over time\n",
"plt.plot(rides['dteday'].index, rides['cnt'], linewidth=0.1)\n",
"plt.xlabel('Date')\n",
"plt.ylabel('Bike sharing counts')\n",
"plt.title('Bike sharing counts per hour')\n",
"plt.xticks(rotation=45)\n",
"plt.tight_layout()\n",
"plt.savefig('counts_per_hour.png');"
]
},
{
"cell_type": "code",
......@@ -1129,37 +1169,14 @@
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": null,
"metadata": {
"ExecuteTime": {
"end_time": "2018-10-24T17:48:07.833369Z",
"start_time": "2018-10-24T17:48:07.686421Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"> Applied one-hot encoding on categorical features\n",
"> (17379, 63) rows and columns.\n",
"> Dropped unnecessary fields.\n",
"> Separated into features X and target y\n",
"> (17379, 55) rows and columns in features dataset.\n",
"> (17379, 1) rows and columns in target dataset.\n",
"> Features selected: ['holiday', 'temp', 'hum', 'windspeed', 'season_1', 'season_2', 'season_3', 'season_4', 'weathersit_1', 'weathersit_2', 'weathersit_3', 'weathersit_4', 'mnth_1', 'mnth_2', 'mnth_3', 'mnth_4', 'mnth_5', 'mnth_6', 'mnth_7', 'mnth_8', 'mnth_9', 'mnth_10', 'mnth_11', 'mnth_12', 'hr_0', 'hr_1', 'hr_2', 'hr_3', 'hr_4', 'hr_5', 'hr_6', 'hr_7', 'hr_8', 'hr_9', 'hr_10', 'hr_11', 'hr_12', 'hr_13', 'hr_14', 'hr_15', 'hr_16', 'hr_17', 'hr_18', 'hr_19', 'hr_20', 'hr_21', 'hr_22', 'hr_23', 'weekday_0', 'weekday_1', 'weekday_2', 'weekday_3', 'weekday_4', 'weekday_5', 'weekday_6']\n",
"> Target: cnt\n",
"> Targets and features scaled.\n",
"> Split into training, validation, and testing sets.\n",
"> X_test: (480, 55)\n",
"> X_valid: (1440, 55)\n",
"> X_train: (15459, 55)\n",
"> y_test: (480, 1)\n",
"> y_valid: (1440, 1)\n",
"> y_train: (15459, 1)\n"
]
}
],
"outputs": [],
"source": [
"# Import packages\n",
"from sklearn.preprocessing import MinMaxScaler, StandardScaler\n",
......@@ -1570,7 +1587,7 @@
"plt.scatter(y_train2, y_pred)\n",
"plt.xlabel('True values')\n",
"plt.ylabel('Predicted Values')\n",
"plt.title('Predicted values vs true valus (hourly count)');"
"plt.title('Predicted values vs true values (hourly count)');"
]
},
{
......@@ -1618,7 +1635,7 @@
"plt.scatter(y_valid2, y_pred)\n",
"plt.xlabel('True values')\n",
"plt.ylabel('Predicted Values')\n",
"plt.title('Predicted values vs true valus (hourly count)');"
"plt.title('Predicted values vs true values (hourly count)');"
]
},
{
......@@ -1669,7 +1686,7 @@
"plt.scatter(y_test2, y_pred)\n",
"plt.xlabel('True values')\n",
"plt.ylabel('Predicted Values')\n",
"plt.title('Predicted values vs true valus (hourly count)');"
"plt.title('Predicted values vs true values (hourly count)');"
]
},
{
......@@ -2087,7 +2104,7 @@
"plt.scatter(y_train2, y_pred)\n",
"plt.xlabel('True values')\n",
"plt.ylabel('Predicted Values')\n",
"plt.title('Predicted values vs true valus (hourly count)');"
"plt.title('Predicted values vs true values (hourly count)');"
]
},
{
......@@ -2135,7 +2152,7 @@
"plt.scatter(y_valid2, y_pred)\n",
"plt.xlabel('True values')\n",
"plt.ylabel('Predicted Values')\n",
"plt.title('Predicted values vs true valus (hourly count)');"
"plt.title('Predicted values vs true values (hourly count)');"
]
},
{
......@@ -2186,7 +2203,7 @@
"plt.scatter(y_test2, y_pred)\n",
"plt.xlabel('True values')\n",
"plt.ylabel('Predicted Values')\n",
"plt.title('Predicted values vs true valus (hourly count)');"
"plt.title('Predicted values vs true values (hourly count)');"
]
},
{
......@@ -2328,7 +2345,7 @@
"plt.scatter(y_train2, y_pred)\n",
"plt.xlabel('True values')\n",
"plt.ylabel('Predicted Values')\n",
"plt.title('Predicted values vs true valus (hourly count)');"
"plt.title('Predicted values vs true values (hourly count)');"
]
},
{
......@@ -2376,7 +2393,7 @@
"plt.scatter(y_valid2, y_pred)\n",
"plt.xlabel('True values')\n",
"plt.ylabel('Predicted Values')\n",
"plt.title('Predicted values vs true valus (hourly count)');"
"plt.title('Predicted values vs true values (hourly count)');"
]
},
{
......@@ -2427,7 +2444,7 @@
"plt.scatter(y_test2, y_pred)\n",
"plt.xlabel('True values')\n",
"plt.ylabel('Predicted Values')\n",
"plt.title('Predicted values vs true valus (hourly count)');"
"plt.title('Predicted values vs true values (hourly count)');"
]
},
{
......@@ -2609,7 +2626,7 @@
"plt.scatter(y_train2, y_pred)\n",
"plt.xlabel('True values')\n",
"plt.ylabel('Predicted Values')\n",
"plt.title('Predicted values vs true valus (hourly count)');"
"plt.title('Predicted values vs true values (hourly count)');"
]
},
{
......@@ -2657,7 +2674,7 @@
"plt.scatter(y_valid2, y_pred)\n",
"plt.xlabel('True values')\n",
"plt.ylabel('Predicted Values')\n",
"plt.title('Predicted values vs true valus (hourly count)');"
"plt.title('Predicted values vs true values (hourly count)');"
]
},
{
......@@ -2708,7 +2725,7 @@
"plt.scatter(y_test2, y_pred)\n",
"plt.xlabel('True values')\n",
"plt.ylabel('Predicted Values')\n",
"plt.title('Predicted values vs true valus (hourly count)');"
"plt.title('Predicted values vs true values (hourly count)');"
]
},
{
......@@ -2890,7 +2907,7 @@
"plt.scatter(y_train2, y_pred)\n",
"plt.xlabel('True values')\n",
"plt.ylabel('Predicted Values')\n",
"plt.title('Predicted values vs true valus (hourly count)');"
"plt.title('Predicted values vs true values (hourly count)');"
]
},
{
......@@ -2938,7 +2955,7 @@
"plt.scatter(y_valid2, y_pred)\n",
"plt.xlabel('True values')\n",
"plt.ylabel('Predicted Values')\n",
"plt.title('Predicted values vs true valus (hourly count)');"
"plt.title('Predicted values vs true values (hourly count)');"
]
},
{
......@@ -2989,7 +3006,7 @@
"plt.scatter(y_test2, y_pred)\n",
"plt.xlabel('True values')\n",
"plt.ylabel('Predicted Values')\n",
"plt.title('Predicted values vs true valus (hourly count)');"
"plt.title('Predicted values vs true values (hourly count)');"
]
},
{
......@@ -3171,7 +3188,7 @@
"plt.scatter(y_train2, y_pred)\n",
"plt.xlabel('True values')\n",
"plt.ylabel('Predicted Values')\n",
"plt.title('Predicted values vs true valus (hourly count)');"
"plt.title('Predicted values vs true values (hourly count)');"
]
},
{
......@@ -3219,7 +3236,7 @@
"plt.scatter(y_valid2, y_pred)\n",
"plt.xlabel('True values')\n",
"plt.ylabel('Predicted Values')\n",
"plt.title('Predicted values vs true valus (hourly count)');"
"plt.title('Predicted values vs true values (hourly count)');"
]
},
{
......@@ -3270,7 +3287,7 @@
"plt.scatter(y_test2, y_pred)\n",
"plt.xlabel('True values')\n",
"plt.ylabel('Predicted Values')\n",
"plt.title('Predicted values vs true valus (hourly count)');"
"plt.title('Predicted values vs true values (hourly count)');"
]
},
{
......@@ -3453,7 +3470,7 @@
"plt.scatter(y_train2, y_pred)\n",
"plt.xlabel('True values')\n",
"plt.ylabel('Predicted Values')\n",
"plt.title('Predicted values vs true valus (hourly count)');"
"plt.title('Predicted values vs true values (hourly count)');"
]
},
{
......@@ -3501,7 +3518,7 @@
"plt.scatter(y_valid2, y_pred)\n",
"plt.xlabel('True values')\n",
"plt.ylabel('Predicted Values')\n",
"plt.title('Predicted values vs true valus (hourly count)');"
"plt.title('Predicted values vs true values (hourly count)');"
]
},
{
......@@ -3552,7 +3569,7 @@
"plt.scatter(y_test2, y_pred)\n",
"plt.xlabel('True values')\n",
"plt.ylabel('Predicted Values')\n",
"plt.title('Predicted values vs true valus (hourly count)');"
"plt.title('Predicted values vs true values (hourly count)');"
]
},
{
......@@ -3746,7 +3763,7 @@
"plt.scatter(y_train2, y_pred)\n",
"plt.xlabel('True values')\n",
"plt.ylabel('Predicted Values')\n",
"plt.title('Predicted values vs true valus (hourly count)');"
"plt.title('Predicted values vs true values (hourly count)');"
]
},
{
......@@ -3794,7 +3811,7 @@
"plt.scatter(y_valid2, y_pred)\n",
"plt.xlabel('True values')\n",
"plt.ylabel('Predicted Values')\n",
"plt.title('Predicted values vs true valus (hourly count)');"
"plt.title('Predicted values vs true values (hourly count)');"
]
},
{
......@@ -3845,7 +3862,7 @@
"plt.scatter(y_test2, y_pred)\n",
"plt.xlabel('True values')\n",