{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Problem Sheet 10 - A Complete scikit-learn Project" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "In this exercise, we will cover a complete data science project.\n", "The underlying data set consists of different predictors (variables) explaining the median home values in different regions of California, USA.\n", "\n", "This week, we focus on all the steps that come *before* our typical learning procedure starts, i.e., data preparation, data wrangling, feature generation, etc.\n", "\n", "## Loading the data\n", "We begin with the usual data and library imports and set the figure size for subsequent plots.\n", "\n", "**Task**: Execute the following code cell and customize the path as necessary." ] }, { "cell_type": "code", "execution_count": 1, "metadata": {}, "outputs": [], "source": [ "import pandas as pd\n", "import numpy as np\n", "import matplotlib.pyplot as plt\n", "\n", "# Set standard figure size\n", "plt.rcParams['figure.figsize'] = (16,9)\n", "\n", "# Read csv file\n", "df = pd.read_csv('datasets/housing.csv')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Getting an overview\n", "\n", "**Task**: Use the methods `head()`, `info()` and `describe()` applied to a `pandas DataFrame` to get an overview of the data. Try to answer the following questions:\n", "- Are there any missing values and, if so, in which columns/variables do they occur?\n", "- Are there non-numerical variables?" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Observation**:" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Solution**:" ] }, { "cell_type": "code", "execution_count": 2, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " longitude latitude housing_median_age total_rooms total_bedrooms \\\n", "0 -122.23 37.88 41.0 880.0 129.0 \n", "1 -122.22 37.86 21.0 7099.0 1106.0 \n", "2 -122.24 37.85 52.0 1467.0 190.0 \n", "3 -122.25 37.85 52.0 1274.0 235.0 \n", "4 -122.25 37.85 52.0 1627.0 280.0 \n", "\n", " population households median_income median_house_value ocean_proximity \n", "0 322.0 126.0 8.3252 452600.0 NEAR BAY \n", "1 2401.0 1138.0 8.3014 358500.0 NEAR BAY \n", "2 496.0 177.0 7.2574 352100.0 NEAR BAY \n", "3 558.0 219.0 5.6431 341300.0 NEAR BAY \n", "4 565.0 259.0 3.8462 342200.0 NEAR BAY \n", "\n", "RangeIndex: 20640 entries, 0 to 20639\n", "Data columns (total 10 columns):\n", "longitude 20640 non-null float64\n", "latitude 20640 non-null float64\n", "housing_median_age 20640 non-null float64\n", "total_rooms 20640 non-null float64\n", "total_bedrooms 20433 non-null float64\n", "population 20640 non-null float64\n", "households 20640 non-null float64\n", "median_income 20640 non-null float64\n", "median_house_value 20640 non-null float64\n", "ocean_proximity 20640 non-null object\n", "dtypes: float64(9), object(1)\n", "memory usage: 1.6+ MB\n", "None\n", " longitude latitude housing_median_age total_rooms \\\n", "count 20640.000000 20640.000000 20640.000000 20640.000000 \n", "mean -119.569704 35.631861 28.639486 2635.763081 \n", "std 2.003532 2.135952 12.585558 2181.615252 \n", "min -124.350000 32.540000 1.000000 2.000000 \n", "25% -121.800000 33.930000 18.000000 1447.750000 \n", "50% -118.490000 34.260000 29.000000 2127.000000 \n", "75% -118.010000 37.710000 37.000000 3148.000000 \n", "max -114.310000 41.950000 52.000000 39320.000000 \n", "\n", " total_bedrooms population households median_income \\\n", "count 20433.000000 20640.000000 20640.000000 20640.000000 \n", "mean 537.870553 1425.476744 499.539680 3.870671 \n", "std 421.385070 1132.462122 382.329753 1.899822 \n", "min 1.000000 3.000000 1.000000 0.499900 \n", "25% 296.000000 787.000000 280.000000 2.563400 \n", "50% 435.000000 1166.000000 409.000000 3.534800 \n", "75% 647.000000 1725.000000 605.000000 4.743250 \n", "max 6445.000000 35682.000000 6082.000000 15.000100 \n", "\n", " median_house_value \n", "count 20640.000000 \n", "mean 206855.816909 \n", "std 115395.615874 \n", "min 14999.000000 \n", "25% 119600.000000 \n", "50% 179700.000000 \n", "75% 264725.000000 \n", "max 500001.000000 \n" ] } ], "source": [ "print(df.head())\n", "print(df.info())\n", "print(df.describe())" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Observations**:\n", "- There are some missing values in the number of total bedrooms $\\leadsto$ We have to decide how to handle this.\n", "- The variable 'ocean_proximity' seems to be categorical, all others numerical." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "You should observe one categorical variable.\n", "\n", "**Task**: How many different classes occur in this attribute?\n", "You can use the method `value_counts()` of a `Series` object to count the occurences in each of the categories." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Observations**:" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Solution**:" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "<1H OCEAN 9136\n", "INLAND 6551\n", "NEAR OCEAN 2658\n", "NEAR BAY 2290\n", "ISLAND 5\n", "Name: ocean_proximity, dtype: int64" ] }, "execution_count": 3, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.ocean_proximity.value_counts()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Observations**: Thus, there are 5 categories that might be important." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Next, we take a look at histograms of the data.\n", "We have already seen in previous labs that this can reveal important features of a data set." ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYoAAAEICAYAAABBBrPDAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDMuMC4wLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvqOYd8AAAIABJREFUeJztnXm4HVWVt98fCWOYEgIxBOQyKolRJBEQaIyKzBq/T0WQBgIoDvgJ3SgE1Ia2UYaWFlBbUEHmIYrYmCAQIVcFGwiRmYiEcCETCSEhkIBIYH1/7HVy656cc+659575rPd5znOqdlXtWrXXrlp7rz3JzAiCIAiCYqxTbwGCIAiCxiYMRRAEQVCSMBRBEARBScJQBEEQBCUJQxEEQRCUJAxFEARBUJKWNBSSuiTtX285ACRdKemcfl7bKenzRY51SDJJgwcm4cCodVpLWilph1rdr9K4znby7UslfbveMrUC/c2Hkv5J0lMVlGOCpPmViq9RqOtHJgj6ipltXG8ZKoWZfaneMrQbkgzY2czmAJjZn4B3ZY53AZ83s9/XR8LGpCVrFEEQBEHlaGVDsZukRyWtkHSTpA0AJH1B0hxJyyTdKmlrD1/LlZN1/UjaSdIfPL6lkm7KnPduSdM9zqckHZ4ny1BJ0yS9Kul+STtmrt1b0kyPd6akvQs9jKRBkr7v954LHJp3fJKkuX6PZyUdNdAE7AO1TOus6+ZKST8ukbYHuD5WSPpvj7OgKy9zzSRJ90r6gaSXPU339vB5kpZIOjZz/vqul+clLXZ30oaZ49+QtEjSQknH591rjVtS0lBJUyW9KGm5b2+Tlz7/4bK9KulOScN7U4ykX0p6wdPgj5LGZI5tIem3kl7xvHeOpHsyx3vL1w2HpD0k/a/rbpGkH0laz4/90U97RMmF+VllXEWSrgHeCfzWj5+mAq4kZdxckjZ0PS6X9CTwgbxzt5Z0s+v1WUlfq3YaVAUza7kf0AU8AGwNDANmA18CPgIsBXYH1gd+CPzRr+kADBiciaeTVA0FuAH4Jsm4bgDs6+FDgHnAcSRX3u5+jzF+/EpgGbCHH78OuNGPDQOWA0f7sSN9f4sC9/8S8FdgW79uRk5el+EV4F1+7sjc/Vsprf2YATuVkbbDPU3+rx87GXgzd48SzzMJWO36HAScAzwP/Nif4wDgVWBjP/8i4FZ/9k2A3wLn+rGDgMXAe1xH1xeQ/xzf3gL4FLCRx/NL4Dd56fMMsAuwoe+fV4Z+jvf41ndZH84cu9F/GwGjSfn4nnLydaP9PB/uD4wD9nKZOzw/nlIo//j+BGB+fjzFjuefA5wH/Mn1vy3weO58Uv6dBfwbsB6wAzAXOLDe6dXXXyvXKC4xs4Vmtoz08u4GHAVcYWZ/MbM3gDOAD0rqKCO+N4HtgK3N7O9mlit5HQZ0mdkvzGy1mf0FuBn4dObaX5vZA2a2mvQx283DDwWeNrNr/NobSMbg4wXufzhwkZnN82c6N+/428B7JG1oZovM7IkynqlS1CqtC1EsbQ8BnjCzX/uxS4AXynyeZ12fbwE3kT4A3zGzN8zsTuAfwE6SBHwB+BczW2ZmrwLfA47weA4HfmFmj5vZKuDsYjc0s5fM7GYze83j+S7wobzTfmFmfzOz14EpmWctipldYWavug7OBt4naTNJg0iG6Sy/55PAVZlLy8nXDYeZzTKz+1zmLuAy1k7HSnI48F3X/zxSPsvxAWBLM/uOmf3DzOYCP6M7fzQNrWwosh+F14CNSaXe53KBZrYSeAkYVUZ8pwECHpD0RMaNsB2wp1d1X5b0Mukj+Y5eZCFfHue5IvJsTSrhZc/LPccq4LOkkvwid8W8u4xnqhS1Suty7w156WWpiFdub5TFme3X/fr8sI2BLUml8VkZ3d/u4WvJwNq6XoOkjSRdJuk5Sa8AfwQ29w96jmLPWizOQZLOk/SMx9nlh4a7jIPz5Mtul5OvGw5Ju7jb7gV/5u+RnrdalNLxdsDWeWl4JjCiivJUhXbr9bSQpDwAJA0hVfkXAKs8eCOSywIyL4WZvUAqPSJpX+D37vOcB/zBzD42UHmcd5I+NvksIpVss+etwczuAO5w//g5pJLLP/VDpkpR8bQ276lSJouArI9f2f0KsZRkNMaY2YIiMhTVWR6nknrf7GlmL0jaDXiIZDD7y+eAiSSXTBewGcm1KeBFkottG+Bvfn5W1oHk63ryE1K6HWlmr0o6hb7VgvKn015FyqdAMr50FwSgW8e5GnxWx/NItdOd+3D/hqSVaxSFuB44TtJuktYnlTbuN7MuM3uR9BH7Zy+JHQ9kG0Y/k2lcXE7KUG8BU4FdJB0taV3/fUDSrmXIc5tf+zlJgyV9luQrnlrg3CnA1yRtI2koMDkj2whJn/CP8RvASpetnlQjrfvCNGCspE8qNZqfRIVLw2b2Nskg/0DSVgCSRkk60E+ZAkySNFrSRsBZJaLbhGR0XpY0rJdzy2UTUn54ifSx+15G9reAXwNne23m3cAxmWsHkq/rySakwsdKf6Yv5x1fTGorKEb+8b8BG0g6VNK6wLdI7T05pgBnKHVG2Ab4f5ljDwCvSDrdG70HSXqPpB4N3s1AWxkKM7sL+DbJ17qI9HHK+gu/AHyD9GKNAf6cOfYB4H5JK0mNlyeb2bPuTz7A41lIcg+cT8/MVEyel0i+4FP9nqcBh5nZ0gKn/wy4A3gE+AvpJc+xjsexkNS4+yHgK73dv5pUI637eP+lwGeAC/weo4EHSR/OSnI6MAe4z10dv8f75ZvZ70gNyHf7OXeXiOciUiP1UuA+Ctcq+8rVJFfIAuBJjzfLV0m1jBeAa0idCN5w2fudr+vM10k1qVdJ78xNecfPBq5yV1ChXlznAt/y4183sxWkd+nndNeGsy7Mfyel8bPAnaR0BNYY44+T2pKeJen256Q0byqUXLdB0NpIWof0gh9lZjPqLU8jIul84B1mdmyvJwdtRVvVKIL2QtKBkjZ319eZJN98fqm6bVEaJ/FeJfYATgBuqbdcQeMRhiJoZT5IGnuwlOQC+KSZva40KG5lgd+l9RW370g6qsizlNM9ehOSC3MVydd+IfA/1ZQ3aE7C9RQEQRCUJGoUQRAEQUkaehzF8OHDraOjo0fYqlWrGDJkSH0EakA5oLKyzJo1a6mZbdn7mZUhq+NGSNN2kKGeOq4mjaC7vlItmSuu40rNBVKN37hx4yyfGTNmrBVWDxpFDrPKygI8aHXScSOkaTvIUE8dV5NG0F1fqZbMldZxuJ6CIAiCkjS066k3OiZPA6DrvEN7OTMI2o9WeT9yz5Gj2Z+nGYkaRRAEQVCSMBRBEARBScJQBEEQBCUJQxEEQRCUJAxFEARBUJIwFEEQBEFJyjYUvujGQ5Km+v72ku6X9LSkmySt5+Hr+/4cP96RieMMD38qs7hLEARB0MD0pUZxMjA7s38+8ANLy/wtJ01RjP8vN7OdgB/4eUgaTVoEZQxwEPDf6rkecL/J72cdBEEQVI6yDIUv8XcoaXWm3PrDHwF+5adcBXzStyf6Pn78o37+ROBGM3vD0mplc4A9KvEQQRAEQfUod2T2RaRlOjfx/S2Al81ste/PB0b59ijSouKY2WpJK/z8UfRcNCZ7zRoknQicCDBixAg6Ozt7HF+5cuWasFPHrl4Tnn9etcnKUW8aSZYgCFqPXg2FpMOAJWY2S9KEXHCBU62XY6Wu6Q4w+ynwU4Dx48fbhAkTehzv7OwkFzYp43LqOqrnedUmK0e9Gagsxx9/PFOnTmWrrbZaEyZpGGm94Q6gCzjczJZ77fBi4BDgNWCSmf3FrzmWtPg8wDlmdhVBEDQ95bie9gE+IakLuJHkcroI2FxSztBsQ1qAHVJNYVsAP74ZsCwbXuCaoI5MmjSJ22+/PT94MnCXt0Hd5fsABwM7++9E4CewxrCcBexJcimeJWlo9aUPgqDa9GoozOwMM9vGzDpIjdF3m9lRwAzg037asXQvoXir7+PH7/Zpb28FjvBeUduTPjQPVOxJgn6z3377MWzYsPzgbFtTfhvU1T6b8X2kAsNI4EBgupktM7PlwHRSp4UgCJqcgcweezpwo6RzgIeAyz38cuAaSXNINYkjAMzsCUlTgCeB1cBJZvbWAO4fVJcRZrYIwMwWScr5pda0QTm5tqZi4WtRrB2qEdpaWkmGXBtevZ8naH76ZCjMrBPo9O25FOi1ZGZ/Bz5T5PrvAt/tq5BBQzGgNigo3g7VCO0+rSRDrg2v1u13QesRI7ODYix2lxL+v8TDi7U1RRtUELQoYSiCYmTbmvLboI5RYi9ghbuo7gAOkDTUG7EP8LCgAZg3bx4f/vCH2XXXXQHGSDoZUicESdN9hoXpuQ4Irt9LfCaFRyXtnotL0rF+/tPe0y1occJQBBx55JF88IMf5KmnngJ4r6QTgPOAj0l6GviY7wPcBswlDZj8GfAVADNbBvwHMNN/3/GwoAEYPHgwF154IbNnz4Y0w8JJPltC9G4LeqWpl0INKsMNN9ywZlvSo2aW65jw0fxzvQfbSYXiMbMrgCuqIWMwMEaOHMnIkSNzu2+TjMUoUi+2CR5+FakN8nQyvduA+yTlerdNwHu3AUjK9W7rzkRByxGGIgjqQJ3Xs14PeD9wP1Xq3dbbDAt9ITsDAxTvxdUIPdb6SrPIHIYiCNqIlStXAuwIHG1mr6SB9gWp6gwLfWFS3qSfxXpxNUKPtb7SLDKHoQiCGlLPmY7ffPNNPvWpTwEsM7Nfe/BiSSO9NlFu77YJeeGd1ZQ7qD/RmB0EbYCZccIJJ+R6PS3OHIrebUGvRI0iaCvq3DZQN+69916uueYaxo4dCzBa0sPAmaTebFO8p9vzdA+WvY008eMc0uSPx0Hq3SYp17sNondbW9CUhqJQ9b1dPwBBUA777rsvqQMTSHrSzMZnDjdk77ZYkKxxCNdTEARBUJIwFEFb0jF5WpRYg6BMwlAEQY0Iw9TctHPhIgxFEARBUJIwFEEQBEFJejUUkraVNEPSbElPxKyTQbvTVxdEO7ssgtagnBrFauBUM9sV2IuYdTIIgqCt6HUchY/GzE0a9qqkmHWyjZDUBbwKvAWsNrPxbvRvAjqALuBwM1uuNHHQxaSBWq8Bk8zsL/WQu1w6Jk8re+xNX2sFUYsIWoU+DbiT1EGdZ51cuXIlp44tvtR2rWZibKRZH2sgy4fNbGlmP1ebPE/SZN8/nZ61yT1Jtck9qylYs9MXQxUE9aJsQyFpY+Bm4JR6zjrZ2dnJhfesKipnrdYHbqRZH+sgS59qk7kCRT2J0n0Q9J+yDIWkdUlG4rqYdbLtMOBOSQZc5oa8r7XJHoaiWK2xmjWj/DUNsvzwujQP3thRm5WUodx1Ecq5Z6l4KpUOufs3Ss03aF56NRTud74cmG1m/5U5lJt18jzWnnXyq5JuJLkdVvjH5A7ge5kG7AOAMyrzGN3EnE8VZx8zW+jGYLqkv5Y4d0C1xmrWjPLXNChE11ETisqQ8lXe6/JYd802l9+yrqRy7pm7b5ZKpUPu/rWqZQetSzk1in2Ao4HHfMZJiFkn2wYzW+j/SyTdQuqx1tfaZFPQMXkap45dzaTMx75cl1X2vHBztTbt2K5UTq+neyhcUoQGnXUyqAyShgDreG+3IaRa4HfoY22y9pIHQWVoR6NQiKacZjyoGSOAW7zjwmDgejO7XdJM+lCbrDf9KeFHrSAIuglDERTFzOYC7ysQ/hJ9rE0GxYl2taDRCUMRBA1CzmBcedCQtcKyhEEJak1MChgEQV2IObCahzAUQRAEQUla1vUUvRWCZi2tPrZgRckxGNGmEdSapqtRPLZgRb1FCBqQcGO0D7XWc+StFq5RBK1FuTXEdnqho2bRWLSyPpquRhEEQdBotHoBJWoUQUNT6gVs9ZezXKI9rjL0Z22Sdkn3ljYU7abMdiEMxNo0U14vR3+h48aipQ1F0FrExyNoNNolT7aFoWim0lYQDIR2+XAFtaUtDEUQBI1NXwtzlSz8FZoiPgqVPWmrXk9R2gqCxqNa7+VA4q3k2IlW+O7UvEYh6SDgYmAQ8HMzO6+W948SQ/UZiI5b4aVqder9DmfJ5pfcZIq95aFq57FWzMM1NRSSBgE/Bj5GWg1tpqRbzezJWsoBayszDEdlaCQdB5Wn2vodyEe2t6lPBhr/QMgvoBbrituo36Va1yj2AOb4Ogf4SmgTgbp/RHrLQL0pOFhDw+o4qAhNpd9GK93nt4fklt4t5/wchZbprfY3qdaGYhQwL7M/n7Rk5hoknQic6LsrJT2VF8dwYGnVJCyCzl9ruy5yFKGSsmw3wOsHouO6p+nXWlCGbN51BqLjXvULZb3HFacRdNdX+iNzAX1WWsdrUWtDUWjtbeuxY/ZT4KdFI5AeNLPxlRasrzSKHNBYsjAAHTfCc4QMvdKrfqH397gaNHi6FaRZZK51r6f5wLaZ/W2AhTWWIaguoePWJvTbhtTaUMwEdpa0vaT1gCOAW2t1c0ldkvav8j1WStqhgvGZpJ0qFV8NqKuOg6oT+m1DamoozGw18FXgDmA2MMXMnuhjNDWtzpagoBxmtnGmoe9KSefUS5Z6MEAd93gOSWdLuta33+lGeFBFBe55vyuBxdWKvw9UTZ+SOiV9vr/XV+gdrgj5+QN4T5Xzx6WSvl3haBvm3S1FzcdRmNltwG0DuL4hErZR5IDGkgX6r+NSz2FmzwMbD0SuMnmoBvcoSaPpM5+BvsPVwPPHBlW+x5eqEGdD6zpHW43MziFpfUkXSVrov4skre/HJkiaL+lUSUskLZJ0XObaLST9VtIrkmZKOkfSPZnjJmkn7/VxFHCal4R/mz2eOb9HrUPSN/yeCyUdX0Du70t6XtJiL+FsWL2UCoIgaFNDAXwT2AvYDXgfqW/4tzLH3wFsRuoKeALwY0lD/diPgVV+zrH+WwsvKVwHXODuqI/3JpSPeP06aTDTzkB+e8r5wC4u904u37/1Fm+18bafb0h6VNIqSZdLGiHpd5JelfT7XPpJ2kvSnyW9LOkRSRMy8Wwv6Q9+zXRS18HcsQ43soN9/zhJs/3cuZK+mDm3pLHvhaGSpnm890vaMRPv3l44WOH/e+elwf6Z/axbZANJ10p6yZ97pqQRfmwzT69FkhZ4waOo+8QLCy9Lek8mbEtJr0vaStJQSVMlvShpuW9vUySuNTIWSeM+yVZC5pbIH8oU6nqLQ9KGki6U9Jznl3vkhTpJn5D0hD9jp6Rd+5NWvaVXRTGzpvgBBwFPAXOAyf2Mo4v08X0GOCQTfiCpb/gM4DngbeBf/NjZwFvA34CHgdXAu/zYGcAy4DXgQA8z4DiX9RXg7jwZDNgps38lcI5vXwGcl5H1KT//MVK3xFXAPcDTwHTgAOBZP3aJp82jwO6Z+I/1858Gjq2SbrqA+4ARJOO1BPgL8H5gfeBu4Cw/9hJwCKmQ8jHf/6w/6+vAn/ya/YBXgWv9Hh2eFoN9/1BgR3/2D7kOdvdjE1xP3wHW9fu9BgzNyLyt63s28ARwsutiOXC/p9ci4GY/f5gfO5rksj3S97fI5q1M/GdnZP8i8FtgI9K0F+OATf3Yb0h+6keAO4EHgDMzMtwErJeX3lcA383snwTc7ttbAJ/ye20C/BL4TebcTuDz+TIWSePfAJcBQ4CtXLYv1iF/bOnx/C/wX37N/qT3crnr7yKX/SrSOzGXNAhwt/7kjyLPcSXd72rJOEgFyk5/pkHA3i73LqT3eA4wDTjN0+cB1/cq133JtPJ7lEyvir7j1fhwVOFDNIj0cd8BWI/0Uo3uZ4bdn/RBGpMJfzfwD2B3zwALSIZhNOllWubXvcMz40Z+7BHSSzrT5Rvkx59zWa8mNY6OztyrlKG4HTgpI+vWufNJL6q57C/7/xvASs8ovyN9NPcC7s983Ob6/1DfLvky9FM/XcBRmf2bgZ9k9v8f6aNzOnBN3rV3eBrtS3rxHsulF3A9RQxFARl+A5yceYlfz57rL9xemf2RdH84NnF93+I6nezhvwBe8u2jgQfy7vm/wKRs3socOzsj+/HAn4H35l0/wnV4mj/rVJIBWgIc4edcCnw577r9gbmZ/XuBY4qky27A8sx+J2UYioxsG2aOHwnMqEP+OBZ4p+ePIR4uYApwLelD/RDdhuLTA80fRZ7jSnoaioJxkD7arwPvKxDHt0kFzpy+1yEZmO/48VeBK3pLK98uml6VfsebxfW0ZtoAM/sHkJs2oL8spOfIxXcCC83sL75vpJLmqLzrXiRl1m38/jeSPjhvkEoIe/h5z1nq+fQWqbSTlfU1kqHJ8Y7M9iLW7qOeY6nLtbeZbU4yRF1mtrHHf7Ul7gM2lzSSVFOabmbLzGw5qRZyUNFUGRjZ3kKvF9jfmJTmn/Fq8suSXibVHFaQ0nU56QXKpddzxW4m6WBJ90la5vEcQsYVQfrAr87sv0amMdzMFuX0bWavkvS9ESnNr/LTfgts6ttbF5DnOdbOI4W4hvQC36jU9nSBpHVJ6bEu8F3gEyR9XUYy7L/ya68CPpkX393AhpL2lLQdyRjc4umykaTL3OXxCvBHUn7oq8soJ9uijK4uIxVY+kN/88e+pHdsa5LBWwVg6av4jF+/rv/WMND8USbF4hhOalh/psA1O5MKbT/3fXPZn/b9lcDYzPnF0gpKp1dFaRZDUWjagHJe0GLcAHzLfbvDSX7+azPHB5Gqevf7/qYk98DPSB+Ps0lKWg0cU0CmF/x/MSnDZGV9GPicpEFKbRIfyhybAkySNNr3b/f/z5rZ28CbwBmStjKzRcAISQdSPH0qnW4DZR6pBLR57kcqqf+RZCSHkoxxTsZ3FopEqePBzcD3gREez20UHjXcK5I6SPpeSiqxLvJDy0h5AdYuXOTkW+DbqyhSADCzN83s381sNMkFcRgp38wjfSj28bA76C4A5D5Aa+nM88IUUgn/c8BUN3YApwLvAvY0s01JhhgKp01RmV22N4DhGX1tamZjCsRTKdbKH2Y2xNLstItI7UdDMudvRzIAS0guyxzfI7l1lgLbDjR/9IOlwN9JrtF8xpFqr2/7/hYuV+49XU1Pg1aKUulVUZrFUJQ1bUAfOAd4kOTPf4zkA8z1PNqQpLxTzOwV4Cekl/WLpMz6d1JD9/HAl0lG540iMl1Oesm/IOk3HnYy8HGS++goUpU4XWz2O5Kv9W6Sgfm6H/pnSfuRShNzgPu8tLgJ6aNQLH0qnW4D5Vrg45IOdEO5ATAG2MjMniPp5P8CkrQvKZ0KsR7JX/sisFrSwaT2mj4jaWOS0TmFZIiLcRuwi6TPSRos6bMk9+NUP/4wcISkdSWNBz6duceHJY31Uv0rfp+3SB+N50n5IPfB3p61u3kW0tn1pLado3w7xya4e1LSMJLvvxgPA/spjVHZjNTmlm6YjOWdwIWSNpW0jqQdJX2oWGQVYK384Y3G22Tyx79LWs/zx2EkvWxDqlVB6qgyjm4X2qkDyR/9wQ35FcB/Sdran+WDkj5Jcm3uTXJzi+S6NpJrck0UZd6qaHpV7mkSzWIoKjJtgJl1mNnvzezvZvY1Mxvpv6+Z2d/dHXAKyUf9a79msV83nVSjeK+ZHUp6AX+WkS8n094kQ4KZPU3yMZ9tZp/0sAfNbIyZbWJmR5vZkWb2rYyM55nZO/x3hZmJ1KC5B6mG8kMz24FkIOaY2SUl0qehplsws3kkt9KZpI/8PNILnCsxfw7YFfg8KX2vLhLPq8DXSKXq5X5dn0cHu75vBq7L6RtY5W47SC6gt/yeL5E+TKeSGgxPAw4zs9yEbt8mlSCXA/9Oz4/3O0iupFdILq4/kF7yfUhG7zhSTfVQUq1iU3nvHYrozMzuJ9UItia1T+W4iFTYWUpqQL49/9pMHNNJeetRYBbdRi/HMS7fk/5cv6IKbo2MPIXyxzfo/k59jjQB4TIy+cPMXiY9K8ALmfyxB0kv/cofA+TrpELoTJf3fJK+9yPp7QJSbegrJHdTroYxmJS/eqWM9KoclW70qMbPE28uqbSVa8weU+F7iJTxLsoLH5nZ/hdSlfa9pJLw30gv5Iku36BKyErqZbJJZvvPpLaF/6S7oXUyqestpA9MtjH7AQ8fRuoBMtR/zwLD6q3PWuu2j/oumMY1kGcCyYUEqadStjH7K/XWU6P9gC2BzX17Q5Lr6bDc++r6vQjvRdhov2bTd90F6EPCHuIf5meAb1Yh/n1JVb5HSVXyh/2e15BKBo+SSiUHkdw/r5FKWS+RunYeXClZSX7qR/z3RC4OkkvsLlLD1125j76/FD/2+z0GjM/EdbzLOwc4rt56rIdu+6jvgmlcA3myH44dSN0l5/hHZP1666jRfqTC2kOuv8eBf/Pwu/0deJxUa9u43rK2gr7lggZBWyDpCQrP1f9FM7uu1vIUQ9KlwD8XOHStVWEqiSDRLPmj1oShCIIgCEpS80kB+8Lw4cOto6Oj3mKUZNWqVQwZMqT3E+tMuXLOmjVrqZltWQORgG4dN1I6tros9dDxlltu2TBpWm0aIf9UXMf19n2V+o0bN84anRkzZtRbhLIoJedxxx1nW265pY0ZM8aAB83WNIRPp3u6kNzUBBWdLiSn40ZKx1aXJafjWv3GjRvXUGlabRrhWSut42bpHhtUkUmTJnH77Wv1opwM3GVmO5MadSd7+MGk0aU7k3p7/QQg02d/T1K3xLOyk5cFQdC8hKGoEx2Tp9ExeVq9xQBgv/32Y9iwYfnBE+meyiI7jUQjTBcSlEEj5bFK0orP1Og0dBtFUFdGmE9lYWaLJOXm+BnwdCFKa3WcCDBixAg6OztZuXIlnZ2dlX2CftIqspw6Ns0C0ijP0l9yhqHrvEPrLEn7EoYi6CsDni7E0lodPwUYP368TZgwgc7OTiZMmFAxIQdCq8gyKfeBPap/1wdBjjAUQTEWSxrptYmRpInXoPR0IRPywjtrIGfQJmRdTlHLqC3RRhEU41a6V+87FvifTPgxSuwFrHAX1R3AAUorrA0lzeF0R62FLpdW9d8HQTWIGkXAkUceSWdnJ0uXLgV4r6QTgPOAKb79PPAZP/020lQXuWlMjgMws2WS/oM0CRqkhViW1fAxgiCoEmEoAm644YY125IeNbOvo3tCAAAerklEQVTLffej+ed6H+2TCsVjZleQplduWKIWEQR9J1xPQRA0PVEAqC69GgpJ20qaIWm2pCcknezhwyRNl/S0/w/1cEm6RNIcSY9K2j0T17F+/tOSji12zyDoK9HmEATVoxzX02rgVDP7i6RNgFmSpgOTSCN3z5M0mTRy93R6jtzdkzRyd8/MyN3xpG6TsyTd6oOzgiAIehCGv3HotUZhhRehH0WM3A2CoEqEkWgs+tSYnVmE/n6qNHK30KjdRqa/I2drPWq2kUYb15qOydOiv30QDICyDUV2EXoze0UqNBA3nVogrOyRu4VG7TYy/R05W+tRs4002riSFCp5FhqMVaqEGoO3mpeoedSGsno9FVmEfnFuEfo+jNwtFB4EdSM+NEHQO+X0ehJwOTDbzP4rc6ilR+4GQRAEiXJcT/sARwOPSXrYw84kRu4GQRC0Bb0aCjO7h8LtC9CCI3eDIAiCnsQUHnUg/OK1IdI5CCpDGIo6Ez1uKstAjEPu2isPGlIpcYKgJYi5noKgDTj++OPZaquteM973rMmLKbhCcolDEXQdNRyXqdWmUNq0qRJ3H777fnBk0nT8OwM3OX70HManhNJ0/CQmYZnT2AP4KyccQlam3A9BUEbsN9++9HV1ZUfPJHuVQmvIq1IeDqZaXiA+yTlpuGZgE/DA+Bzvh0E3ECFaAWj3IqEoQiC9qUq0/DA2lPxlDuFTG5qm/7ww+vSUK6xozbrdxyVoBWnywlDEQQFaPOS7YCm4YG1p+LZeOONy5pCZlIF0r1W0+IUoxWny4k2iiBoX1pyGp5WaVdqJMJQBEEZtOiHJ6bhCcoiXE9BSSR1Aa8CbwGrzWy89365CegAuoDDzWy5zwt2MWkKl9eASbm1TIL6cuSRR9LZ2cnSpUsB3utT78Q0PEFZtK2hiIFufeLDZrY0s5/rVlnW6oaVEiK/VN+ipfyqcMMN3R2TJD1qZpf7bkzDE/RK27mewn9ZEfq6umEQ1Jx4zytH29YogrIx4E5JBlzmvVn62q1yUTbCQqsYltOlcCBdJ/vCkmUrOHXs2uH16H45kK6WtV5FMWhdwlAEvbGPmS10YzBd0l9LnNvvVQzL6VJYia6T5XDq2NVc+FjxV6OW3S8H0tWy1qsoBq1LOQsXXSFpiaTHM2ExR0ybYGYL/X8JcAtp6oa+dqtsWcKVGbQD5bRRXEkapp8l5oipAfX+AEkaImmT3DapO+Tj9L1bZRDUhTDklaGchYv+KKkjL7jh5ogJqsII4JbU65XBwPVmdrukmfShW2WrER+eyhNp2tj0t42iZnPEVLIh7rEFazdSDjT+/jQ2FmqU/eF1/7NWI+mpY1dX7Pn7I6eZzQXeVyD8JfrYrTIIgual0o3ZFZ8jppJzphRsDH1sFdD/8RT9aWws1iib3+g4afK0ijVEtuL8M0EQ1Ib+jqNoyTliGpHwsQZBUG/6ayhijpggCJqGKHANjF5dT5JuIDVGD5c0n9R7KeaICYIgaBPK6fV0ZJFDMUdMEDjZ0mrMHxa0Gm0311MQBO1NuKH6ThiKIKgD8bEKmokwFEEQBEFJYlLADPklvPA1Nw6tUvpuledoViL9+0cYiiCoMvFxCpqdMBQNRKy61xqEYegbkV6NT7RRBEHQlkSHgvIJQxEEdSQ+VPUnDEbvhOupAYlM216EyzFodKJGUYJyP9ilzouPflAuUbINGpW2qFGU8/IN9AXNLxXGCx8MhFz+ufKgIXWWJAiiRlFTosQYlEM2jzy2YEXRPNPs+anR5G8kWRqNtqhRDIRCmSd8yUGt6Zg8LWqrNSDe98KEoQiCJiEMRH2IzgZ1MBSSDgIuBgYBPzez86p1r2q/WB2Tp/n614N7hFVDjmbKrJXUcXwce6dQbaOa+aSW73Aj0UzvYKWpaRuFpEHAj4GDgdHAkZJG11KGStBovtVGolV03Gzk58lq5c/Qb+9pW6pdqRqy1OJeta5R7AHMMbO5AJJuBCYCT5YbQW8LxLT6B7w3H2oDlHoGrGNofT02MRV9h5uVUs9w6tji5zRrbURpUboa3Uz6NHCQmX3e948G9jSzr2bOORE40XffBTxVMwH7x3Bgab2FKINy5dzOzLbs700GoONGSsdWl6XfOi5Hvx6er+OXaJw0rTaNkH8G9B7nU+sahQqE9bBUZvZT4Ke1EWfgSHrQzMbXW47eqKGc/dJxI6VjyFKSXvULa+u4AZ+jarTis9Z6HMV8YNvM/jbAwhrLEFSX0HFrE/ptQ2ptKGYCO0vaXtJ6wBHArTWWoapI6pT0+X5e+05JK73BsFlpeR23OaHfNqSmhsLMVgNfBe4AZgNTzOyJWspQBfrtJpPUJWn/3L6ZPW9mG5vZW5URrQc1cecNQMdVkU/SlZLO6eWcCZLmV0oWSSZpp4HEUSlZKk2j6bevlJMfKkBDPGslqfk4CjO7Dbit1vetFu6LbXhqKWdfdSypCyirFpY718x+3y/hyqCRdNpIsuTozzvcl+foi45rkR/6SiPqbKC09FxPXmI/Q9KTkpZL+oWkDfzYFyTNkbRM0q2Sts5cZ5K+JmmupKWS/lPSOn7sbEnXZs7t8PPXMrqSdpR0t6SXPJ7rJG3ux64B3gn81t1Np+XHJWlrl22Zy/qFTNxnS5oi6WpJr0p6QlJLNaC1Ik3uVmxLCr3b7UZLGwrnKOBAYEdgF+Bbkj4CnAscDowEngNuzLvu/wDjgd1J/cSP78e95ffZGtiV1Ah4NoCZHQ08D3zc3U0XFLj+BlLj4dbAp4HvSfpo5vgnXO7NSX7iH/VDxrpSxGB+wg3fy97ms2uxcz38l5JekLRC0h8ljemnLGe6Qe+SdFQmfH1J35f0vKTFki6VtGHm+DckLZK0UNLxeXFeKeknkm6TtAr4sKTN3MC/KOk5Sd/KFETW8f3nJC3x8zbzY7mCxHGS5nnh50uSPiDpUU+vH2XuvZOkP3i6LJV0U3/SpZY0Qn6QuyIlnS7pBeAXHl6qcLm3pJl+z5mS9s4c65R0jqQ/u5y/lbSFFxxf8fM7/FxJ+oHrfoXr9T0DStRKYGYt+wO6gC9l9g8BngEuBy7IhG8MvAl0+L6R+ornjn8FuAv4DLDEj4/3Yx2+Pwt4DHgV+H7m2nEePgeYCjyUJ9/+mf1cXINJRuUtYJPM8XOBK337bOD3mWOjgdd9+zPAE8DbOTk9fAtgBrAS+FFeWnWSxjM87L+taqSjgzztFwCTScZ8FfAxYF3gNE+79QqlmYcdD2xCKgzMA/7uz38ycCXwfWA68LT/D/XrBFzi9zbgWmB94EPAG36vp0n++FuBYcA/Aa8Ay/zag4DFwN6eR17xuHYnTXHxkj/fPsAOwAN+zgKPr8Pv8YA/51y/7w6kfPm4n/8UcIzHfSnwcX/Wt/1ZtwJGkfrvP+lxPgf8G6lAuAGwb53ew4Nc/jnA5DLf2/19eyD5YX3gIuDhzLErgXN6uf8EYDVwvsexIfART9vdPeyHwB+BK4AXSe/q0aR39/Ou82c8v93jMu8IbOb6+Ruwv59/NfALv/eBpG/J5qT8uSswsh5665Em9Ragyhm0Czg0sz8GeB34HXBS3rkvAPv4tgFjMscOJTXc7eoZZDFrG4ptfX8msNy3tyJ9KF70l3018GKhFyIvrsHAntlz/fiXgOm+fTZwbZFrdyUNcuqkp6EYAuzr8RQyFOOLpWWV9DPIX6b5pI/JI6SP75TMOeuQPqoTCqVZXnwjgf08HUb5y3gL8Gf8A0UyRuf79iGeFya4bmZ6+DCSMf0eMJT0MX6/H3sA+ALwrF97B3AecAHdhs6Ay4B/JX345/u1U4AjSUboJuDLHn49sNC3Hwdm+fZo4K+kj85OpA+/kQoRz5CMyUueJqP9mvnAVb79FPAnYJs6voODMrKu5zoeXcZ7mzMU3+5vfvDjm3uabeb7V1KeofgHsEEmrFjh8nDgW8BrmWMXuK4meZ54Hvhm5viFwO8y+x/HjRnJIP0N2AtYp156y/+1g+sp2+f7naQ+3wuB7XKBkoaQStsLSl1nZrNJSs+m2zv8f5H/rwLWlZQrzawLvNvMNiVNpLZh5tpSw+IXAsMkbZInx4Ii53dHajbbzNYa0W5mq8zsHlKJuxHYg1TSWu2/Gz3sudwJZvY2qeQ8qlAEkgZJOk/SM6QPY66r5gYk474RyWhe5eFXAZ/07Ymk0hzAcmBTSSNJpbo5JCOxLqlkd4+kFaQa4veBLf3a0S7fRI87J/tBpALG34DXJYn0EfgD6YN5aUaOXUglUkgf1p38/InAdSTj/zrpowgp7+am0XgduBOY6NcMJ32YIRmqDuABd930x306UNZM+WFm/yDpeGIfrt+afuYHSa/QnWbD+yj3i2aWfU/y5VhJMtIL6DYaOSYCD7mMV/m9F2eOv15gf2OP926SC/nHwGJJP5W0aR9lrzjtYChOkrSNpGHAmaSS3PXAcZJ28w/694D7zawrc903JA2VtC3JhZHz7z5MKqWMcN/xGXn32xJ43sze8O1XgZcljQIOIH0IciwmlbTWwszmkUrC50raQNJ7gRNIH45q8QtJD0v6tn90qs0o0kufM5i5LqpZIy6S0c4ZyHzj+jnSi7k/qVrf4eHbAO8nuQuGmNkiAP/fKu/+kIzCQg8bRdLTQr/+TVIp8KPADDPbzMw2zsi7LTDC436nh40kuUlybAG8TNL5myTjMypzbi6uhaTS7BZ+/HWSEV1MqvVC+mjl5IZUYx3l17xJqgEBPAqsMLOtgS8C/63Kddstl2waQ3rOgh/5DFkd5xfq+psf+pqf8+MtVbhcTCpQ5BhBymMLPE9kj/V+Y7NLzGwcyQOyC/CNPspecdrBUFxPKnHN9d85ZnYXqUp7M6kmsCNp4BCSct3sdiVlgGdJJYIXAcxsOqmd4kaSL3Fq7kbeaLYDcI0H/ZzkK10BTCOVJrOcS2pcf1nS1wvIfiQpoy8kuVDO8vtD8lcfJulxSY+TXCCQqrH94SgzG0vywf8Tyd9abXIvb9ZgPg0cKumjktYFTiW5av5c4FxI6fsGqXS3EcnoQyqRnULPkl6x++fYgWQgdiDVQn7pJdhZpI4DwwAkjZJ0oF+zgORiWEfSRsBZHm5mNiv/XpbGyEwhGRFJ2o6Uv37t591A+sBtS6p5HA7cZGn8QjG5IX3Y8sMPpbtgstzPqcYYnVKUNeVHHlkdT6Ey+WGglCpczgDWl/Q5pR5S65JqmlOLxlYE75iwpz/rKlLtv9Y6W5t6+76q+aMX/2WJ6wzYqcTxTvL8+aQS7N/wdg4PGwn8NbN/JHBZDZ9/LTk9fBJ5bRR9OV5B+T5IMnATSS6910n98/8PqcFvBcm4ZtuLcue+DHydVGX/H1LN7TngONffd/38K0kfjZEZnTzl25e5TiaQSrov0j153d2Ze/4c+I3H/xbJpfW1nD5JfujVpBL/8X7/Nz3/ve7b13m8g0m1l9tJNYd5JOO4t98r94GYR2oneYjuxvc/eNz7And42HzSAK8zSB/lvwP/5seu9f2VJHfUiXV4Bz+Yk9X3zwDO6OWafB0PJD/kOgDslMkP5bRRzC8Q/iVPx2UkI7CNh3eQCqGzXMa/AxMz+e010liPXDzn4J1SfH9/knsOUq31UdfZUs83G9dab2s9e70FqHIm7aIGhoLkinoE+FSBc2eSGqZEavw8pIbP30POTPgkMoaA9PEa7tvrAr8i01usivIN9hdse7obOscMID6R2g0uygv/T3o2Zl/g24e6TuQ6esDDh5FqkkP99ywwrJQ+S9xjAjDVt38JHOHblwJf8e2TgEt9+wi88ZbkeniE1Mtme0+rQaXSrdg96vWrtI4b8UcyFI/3lt+a+Vd3AaqswC4qaChIJZv5pKrtYrpLdd8ilQIfJq97KWksxuOkksiP8Kndq/zcBeXMpMkyUollPqmKPIRUGnqU1NXyYmBQjXR0CKkm9gyZniH9jGtf192jGT0cQvIl30Uqud+V+eiL5KJ6htSFOWv8jyc1aM8BjsuEF9RniXtMoNtQ5LrHzvEP+voevoHvz/HjO2Tu902/11PAwb2lW7F71PNXSR032o/kKlxEqjXOJ7UjFswLzfyr6XoUQVAvJJ1J6syQz5/M7OBayxPUl8gPfSMMRRAEQVCShp7DZPjw4dbR0dEjbNWqVQwZMqQ+Ag2QZpB91qxZS62CK2P1Rr6OGyGNWl2G0HH5NKusFddxvX1fpX7jxo2zfGbMmLFWWLPQDLIDD1odddwIadTqMoSOy6dZZa20jtthHEUQBEEwAJrSUHRMnkbH5Gn1FiOoAaHr1if02/g0paEIgiAIakcYiiAIgqAkYSiCIAiCkoShCIIgCEoShiIIgiAoSRiKIAiCoCRhKII1vPXWWwCjJU0FkLS9pPslPS3pJknrefj6vj/Hj3fk4pB0hoc/lVmzIQiCJiYMRbCGiy++GNL6CTnOB35gZjuTFr45wcNPIK0LvhPwAz8PSaNJ02SPIS0F+t+Ssiv6BUHQhIShCACYP38+06ZNg7RYSm7JyY+Q1qaAtdeazq1B/Svgo5k1nm80szfM7FnSVNd7VEK+GJQVBPWjoScFDGrHKaecwgUXXMD48eNzQVsAL1v3EpzZtY7XrINsZqslraB7jef7MtEWXB9Z0onAiQAjRoygs7NzzbGVK1f22D91bPcKoNnwapIvQz1oBBmqTRj/5iEMRcDUqVPZaqutGDduXDa41FrH5a7ZnL2mO8Dsp6TlOxk/frxNmDBhzbHOzk6y+5MyH5Ouo7rDq0m+DPWgEWQIghzhegq49957ufXWW/GpoHcguZwuAjb3xeIhrQm+0LfnA9sC+PHNSKvmrQkvcE0QBE1KGIqAc889l/nz59PV1QVpfeO7zewoYAbwaT/tWNKi9QC3+j5+/G6f2vhW4AjvFbU9sDNpWc4gCJqYMBRBKU4H/lXSHFIbxOUefjmwhYf/K2kBeczsCWAK8CRwO3CSmb1Vc6mDokQX6KA/RBtFkM+rZnYYgJnNpUCvJTP7O/CZQheb2XeB71ZVwqDflOgCfaOkS0ldn39Cpgu0pCP8vM/mdYHeGvi9pF2iQNDaRI0iCNqERu8CHTQuUaMIgjah0bpA16Prc19ppm7K1ZQ1DEUQtAGN2AW6Hl2f+0ozdVOupqzhegqCNiC6QAcDIQxFELQBjd4FOtZGb2zC9RQE7c3pwI2SzgEeomcX6Gu8C/QyUk8nzOwJSbku0KuJLtBtQRiKIGg/ogt00CfKcj1J6pL0mKSHJT3oYcMkTfeBOtMlDfVwSbrEB+Q8Kmn3TDzH+vlPSzq22P2CIAiCxqEvbRQfNrPdzCzXt24ycJevVXCX7wMcTPJb7kzqHvcTSIYFOAvYk1SCOStnXIIgCILGZSCup4nABN++Cugk+TsnAld7w9d9kjaXNNLPnW5mywAkTSctbnPDAGQIWpRo2AyCxqFcQ2HAnZIMuMz7SI8ws0UAZrZI0lZ+7pqBOk5uQE6x8B6UGqgDaVDJqWNT21mzDITJ0UyDdxqRnPHoOu/QOksSBO1FuYZiHzNb6MZguqS/lji3agN1IBmHC+9ZBTTuIJ1iNNPgnSAIghxltVGY2UL/XwLcQmpjWOwuJfx/iZ9ebEBODNQJgiBoQno1FJKGSNoktw0cADxOzwE5+QN1jvHeT3sBK9xFdQdwgKSh3oh9gIcFQRAEDUw5rqcRwC1p4kgGA9eb2e2SZgJTJJ0APE93n+vbgENIs0q+BhwHYGbLJP0HMNPP+06uYbu/hM86CIKg+vRqKHxAzvsKhL8EfLRAuAEnFYnrCuCKvovZzWMLVhDjBCvLvHnzOOaYY3jhhRcAxkg62cwu9i7NNwEdQBdwuJkt9+mmLyYVCF4DJpnZXyCNlQG+5VGfY2ZXEQRBUxNzPQUMHjyYCy+8kNmzZwPMBk7yBWpirEwQBGEoAhg5ciS7775mAP3bJGMxip6L1+QvanO1Je4jzUA6EjgQHytjZsuB3FiZIAiamPDhBPmsB7wfuJ86jJUptKhNPtUei9II410qLcOSJUs499xzWbZsGYR7MegjYSiCNaxcuRJgR+BoM3vFOzAUoqaL2uRT7fEzjTDepdIyLFq0iJ122ondd98dSTn34nRgEsm9eJ6kyST34un0dC/uSXIv7plxL44n6XaWpFu9Bhm0KOF6CgB48803+dSnPgWwzMx+7cExVqZFCPdiMBCiRhFgZpxwwgnsuuuu3HnnnYszh3JjZc5j7bEyX5V0I6m0ucJdU3cA38s0YB8AnFFpeaNb9IBpWPfiD69LWWzsqM3692QVphHckOUSa2YHVeXee+/lmmuuYezYsQCjJT0MnEkyEHUdKxNUlnAv9o1GcEOWSzVlDUMRsO+++5KGv4CkJzNTyUMdxsoE1aGUe9FrE+W6FyfkhXdWU+6g/kQbRRC0AVn3IlDIvQgxFU9QhKhRBEEbEO7FYCCEoQiCNiDci8FACNdTEAQ15bEFK2IFwyYjDEUQBEFQkjAUQdMSpdIgqA1hKIIgaDiiENBYhKEIGorwXwdB49EShiI+LEEQBNWjJQxFEARBUD3CUARNTcfkaVGjDIIqE4YiCIIgKEkYiiAIGpKoLTYOLWMoIlO1N6H/IKgeLWMoggCiB1wrEoWA+lNzQyHpIElPSZrja/QGLUa9dRwflupSL/2GXutHTQ2FpEHAj0kLt48GjpQ0upL3iMxUX2qh43LJ5YXID5WjEfQb+qw9tZ5mfA9gjpnNBfA1lycCT1b6RoUyU9d5h8Z6y9WnZjruC+V8XHJ54rEFK3os4Rb0oCH0W0qfOT12TJ4W73mFqLWhKLQw+57ZE7KLsgMrJT2VF8dwYGl/bq7zC2/XkH7LXkO2G+D1A9Vx3dIokyeGf+2f666naqbDQHTcq36hvjqu8HveDO9sjqysA32Pe1BrQ9HrwuzZRdkLRiA9mLfoStPQzLL3gQHpuBHSKGQoSa/6hcbXcbmErIlaN2YXW7A9aB1Cx61N6LcNqbWhmAnsLGl7SesBR5AWcQ9ah9BxaxP6bUNq6noys9WSvgrcAQwCrjCzJ/oYTVG3VBPQzLKXRQV03AhpFDIUoQ3f4ZAVUG7B9SAIgiAoRIzMDoIgCEoShiIIgiAoSdMYinpPC5GRY1tJMyTNlvSEpJM9fJik6ZKe9v+hHi5Jl7jcj0raPRPXsX7+05KOzYSPk/SYX3OJpEJdEluOaum4hM7OlrRA0sP+OyRzzRkux1OSDqyEjJK6XK8PS3rQwyqWb5qBerzHzfjOShok6SFJU31/e0n3+31v8o4ESFrf9+f48Y5MHJXLw2bW8D9So9kzwA7AesAjwOg6yTIS2N23NwH+RprK4AJgsodPBs737UOA35H6n+8F3O/hw4C5/j/Ut4f6sQeAD/o1vwMOrrcOmlnHJXR2NvD1AueP9vuvD2zvcg0aqIxAFzA8L6xi+abRf/V6j5vxnQX+FbgemOr7U4AjfPtS4Mu+/RXgUt8+AripGnm4WWoUa6YNMLN/ALlpA2qOmS0ys7/49qvAbNJo1YnAVX7aVcAnfXsicLUl7gM2lzQSOBCYbmbLzGw5MB04yI9tamb/a0njV2fiamWqpuMSOivGROBGM3vDzJ4F5rh81ZCxIvlmgDLUirq8x832zkraBjgU+LnvC/gI8Ksisuae4VfAR/38iubhZjEUhaYNKPWi1wSv5r0fuB8YYWaLIGVMYCs/rZjspcLnFwhvdWqi4zydAXzV3QtX5FwPJWQZqIwG3ClpltIUF1C5fNMM1F32JnlnLwJOA972/S2Al81sdYH418jkx1f4+RXNP81iKMqaNqCWSNoYuBk4xcxeKXVqgTDrR3irU/XnLqCznwA7ArsBi4ALe5FloDLuY2a7k2ZePUnSfqXErZIM9aSusjfDOyvpMGCJmc0qQ55Sxyoqa7MYioaaNkDSuqQMd52Z/dqDF3sVFP9f4uHFZC8Vvk2B8FanqjoupDMzW2xmb5nZ28DPSNXyUrIMSEYzW+j/S4Bb/H6VyjfNQN1kb6J3dh/gE5K6SG6hj5BqGJtLyg2Qzsa/RiY/vhmwrB/PUJpqNyRV4kcaQT6X1CiTa4AZUydZRPJBXpQX/p/0bBi7wLcPpWfD2APW3TD2LKlRbKhvD/NjM/3cXMPYIfXWQTPruITORma2/4Xk0wUYQ8+GwLmkRsB+ywgMATbJbP+Z1LZQsXzT6L96vcfN+s4CE+huzP4lPRuzv+LbJ9GzMXtKNfJw3TNPHxLtEFJvhWeAb9ZRjn1JVbVHgYf9dwjJL3gX8LT/5zKQSAu9PAM8BozPxHU8qZFpDnBcJnw88Lhf8yN8BH2r/6ql4xI6u8Z18ihpvqKs4fimy/EUmR4s/ZWR1MvkEf89kbu2kvmmGX71eI+b9Z2lp6HYgdSzag7JaKzv4Rv4/hw/vkM18nBM4REEQRCUpFnaKIIgCII6EYYiCIIgKEkYiiAIgqAkYSiCIAiCkoShCIIgCEoShiIIgiAoSRiKIAiCoCT/H5RFHoqdNftDAAAAAElFTkSuQmCC\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "df.hist(bins=50);" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Observations**:\n", "- The values of `housing_median_age` and `median_house_value` have been capped. This is not a priori a problem, but can lead to wrong price predictions beyond this level. We have to take care of this.\n", "- The variables have different scales. A proper scaling can be necessary.\n", "- Many of the variables are not normally distributed, but heavy-tailed, i.e., they tend to extend farther to the extremal values (in our case to the right). Since some of our algorithms assume that the data is normally distributed, we have be cautious.\n", "- The medium income seems to be scaled in thousands of dollars, and the value seems to be capped at a medium income of 15, since there are exceptionally many samples with the value 15.0001.\n", "\n", "**Task**: Have a look at `df.medium_income.value_counts()` to verify the last observation." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Solution**:" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "3.1250 49\n", "15.0001 49\n", "2.8750 46\n", "4.1250 44\n", "2.6250 44\n", "Name: median_income, dtype: int64" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "df.median_income.value_counts().head()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Stratified Training-Test Splits\n", "\n", "Until now, we have tried to get a better understanding of the data.\n", "Before we look closer into price prediction\n", "we want to make sure not to include what is known as data snooping bias.\n", "\n", "In this project, we want to employ a split into a test and training set:\n", "The function `train_test_split` splits the data randomly into two distinct sets.\n", "This works well for fairly uniformly or normally distributed data, but can cause some problems for heavy-tailed attributes or categorical data with varying numbers of samples in each category.\n", "\n", "For this reason we want to stratify our random split according to the attribute `median_income`.\n", "Stratifying means that we choose our split in accordance with different classes.\n", "This means nothing else than that the algorithm makes sure to include the same proportion of each class in both the test and the training set.\n", "\n", "Pandas provides a method to set up categories from of a numerical variable that splits the data into equal-sized bins based on sample quantiles. This function is called `pd.qcut`.\n", "\n", "**Task**: Use the function `pd.qcut` to split `median_income` into 5 categories. Store the output in a variable `income_cat`.\n", "One could also label the categories using the optional `labels` parameter.\n", "By default, labels is equal to the interval boundaries of the corresponding class.\n", "You should keep the labels parameter unchanged because we only want to use this in our training-test split. " ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Solution**:" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [], "source": [ "income_cat = pd.qcut(df.median_income,5)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Task**: Split the data using the `train_test_split` function from `sklearn.model_selection` such that the test set contains approximately 20\\% of the samples.\n", "Set `random_state = 1` and `stratify = income_cat`." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Solution**:" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [], "source": [ "from sklearn.model_selection import train_test_split\n", "\n", "ttsplit = train_test_split(df, test_size = 0.2, random_state=1, stratify=income_cat)\n", "train, test = ttsplit" ] }, { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(16512, 10)\n", "(4128, 10)\n" ] } ], "source": [ "print(train.shape)\n", "print(test.shape)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Visualizing the data\n", "Here we try to visualize as many features of the data as possible.\n", "In previous labs, we already used the scatterplot, but mainly with standard options.\n", "The nice thing about scatterplots is that we can represent more than two features of the data set.\n", "The following code cell plots every sample in our training set as one circle.\n", "The variable `longitude` sets up the x-axis, `latitude` the y-axis. \n", "\n", "The optional parameters are as follows:\n", "- `alpha = 0.4`: opacity of cicles\n", "- `s = train.population / 100`: size of circles, i.e., the larger the population in the region, the larger the circle\n", "- `c = 'median_house_value'`: color of the circle, i.e., the higher the median house value in the region, the brighter the color (this depends on the colormap `cmap`)\n", "\n", "**Task**: Execute the following code and identify the two regions with higher house values." ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "train.plot(kind='scatter', x = \"longitude\", y =\"latitude\", alpha=0.4,\n", " s = train.population/100, c = 'median_house_value',\n", " label='population', cmap = plt.get_cmap('viridis'),\n", " colorbar='true')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Observation**:" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Solution**:" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Observation**: The two clusters of high median house values are the surrounding areas of San Francisco (North) and Los Angeles (South)." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Task**: Copy and paste the code fragment from above. Adapt the code so that the color is determined by the `median_income` variable." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Solution**:" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "train.plot(kind='scatter', x = \"longitude\", y =\"latitude\", alpha=0.4,\n", " s = train.population/100, c = 'median_income',\n", " label='population', cmap = plt.get_cmap('viridis'),\n", " colorbar='true')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Take a look at the correlation matrix\n", "\n", "**Task**: Compute the correlation matrix of the training set.\n", "Determine the variables with the highest correlation with `median_house_value`.\n", "The output of the method `corr()` is a `pandas DataFrame` itself, and possesses the same methods, e.g., `sort_values()`." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Observation**:" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Solution**:" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "latitude -0.147158\n", "longitude -0.043252\n", "population -0.022518\n", "total_bedrooms 0.050363\n", "households 0.067951\n", "housing_median_age 0.100355\n", "total_rooms 0.138906\n", "median_income 0.689024\n", "median_house_value 1.000000\n", "Name: median_house_value, dtype: float64\n" ] } ], "source": [ "cm = train.corr()\n", "print(cm.median_house_value.sort_values())" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Observations**:\n", "The attributes that exhibit the strongest correlation with `median_house_value` are `median_income`, `total_rooms` and `latitude`. Especially the latter is surprising, because the correlation is negative, which indicates higher prices in the South than in the North of California." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "The next plot generates a heatmap of the correlation (assuming you named the correlation matrix `cm`).\n", "Blue squares indicate a negative correlation, red ones a positive correlation." ] }, { "cell_type": "code", "execution_count": 12, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "plt.matshow(cm, cmap=plt.get_cmap('jet'))\n", "plt.xticks(range(len(cm.columns)), cm.columns, rotation='vertical');\n", "plt.yticks(range(len(cm.columns)), cm.columns);" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Finally, we look at the scatter matrix of the 4 most strongly positively correlated variables.\n", "These are\n", "\n", " attr = [\"median_house_value\", \"median_income\", \"total_rooms\", \"housing_median_age\"]\n", "\n", "**Task**: Execute the following code. What do you observe?" ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [ { "data": { "image/png": "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\n", "text/plain": [ "
" ] }, "metadata": { "needs_background": "light" }, "output_type": "display_data" } ], "source": [ "attr = [\"median_house_value\", \"median_income\", \"total_rooms\", \"housing_median_age\"]\n", "pd.plotting.scatter_matrix(train[attr], alpha=0.1);" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Observations**:" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Solution**:" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Observation**:\n", "- The correlation between `median_income` and `median_house_value` is quite obvious, the same is true for `total_rooms` and `median_house_value`.\n", "- The capping of `median_house_value`, `median_income` and `housing_median_age` has to be kept in mind." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Generate Combinations of Attributes\n", "\n", "Now we want to try if we can do better with derived attributes.\n", "This is an important step, and we did this already by the incorporation of powers of variables.\n", "In this lab, we want to use a more reflected approach.\n", "Since the number of total rooms in an area depends heavily on the size of the area, we might take the rooms per household into consideration.\n", "Another interesting quantity could be the number of bedrooms per room, which we can get by dividing `total_bedrooms` through `total_rooms`.\n", "\n", "**Task**: Expand your training set by two new variables `rooms_per_household` and `bedrooms_per_room`.\n", "Afterwards, check the correlation of the new variables with `median_house_value`.\n", "You should observe a correlation of -0.256096 for `bedrooms_per_room` vs. `median_house_value` and a corralation of 0.151931 for `rooms_per_household` vs. `median_house_value`." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Observations**:" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Solution**:" ] }, { "cell_type": "code", "execution_count": 21, "metadata": {}, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/LOCAL/Software/DataScience2018/miniconda3/envs/DS2018/lib/python3.6/site-packages/ipykernel_launcher.py:2: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame.\n", "Try using .loc[row_indexer,col_indexer] = value instead\n", "\n", "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n", " \n", "/LOCAL/Software/DataScience2018/miniconda3/envs/DS2018/lib/python3.6/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning: \n", "A value is trying to be set on a copy of a slice from a DataFrame.\n", "Try using .loc[row_indexer,col_indexer] = value instead\n", "\n", "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n", " self.obj[item] = s\n" ] }, { "data": { "text/plain": [ "bedrooms_per_room -0.256096\n", "latitude -0.147158\n", "longitude -0.043252\n", "population -0.022518\n", "total_bedrooms 0.050363\n", "households 0.067951\n", "housing_median_age 0.100355\n", "total_rooms 0.138906\n", "rooms_per_household 0.151931\n", "median_income 0.689024\n", "median_house_value 1.000000\n", "Name: median_house_value, dtype: float64" ] }, "execution_count": 21, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# Generate new variables\n", "train['rooms_per_household'] = train['total_rooms'] / train['households']\n", "train.loc[:,'rooms_per_household'] = train.loc[:,'total_rooms'] / train.loc[:,'households']\n", "train.loc[:,'bedrooms_per_room'] = train.loc[:,'total_bedrooms'] / train.loc[:,'total_rooms']\n", "\n", "# Take a look at the correlation\n", "newcm = train.corr()\n", "newcm.median_house_value.sort_values()" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Observation**: Both new variables have a very high correlation (in absolute values) with median house value." ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Data Wrangling\n", "Now we want to start to clean up the data.\n", "We've already noted that the variable `total_bedrooms` contains some missing values.\n", "\n", "In previous labs, we used to delete the samples from the data set, and this might be reasonable for this data set as well.\n", "In this lab, we employ another common way to get around missing values, which is replacing the missing value with some *standard* value.\n", "This *standard* value could be anything, even a constant or a optimistic/pessimistic guess.\n", "\n", "Scikit-learn provides a class to do this job, called `SimpleImputer` from the module `sklearn.impute`.\n", "\n", "**Task**:\n", "Define a `SimpleImputer` that assigns the median value of an attribute over all (training) samples to all missing values (**Hint**: Use the option `strategy`).\n", "\n", "**Caution**: As with other scaling methods, we should use the *training median* to fill out the missing values in both the *training and the test set*." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Solution**:" ] }, { "cell_type": "code", "execution_count": 22, "metadata": {}, "outputs": [], "source": [ "from sklearn.impute import SimpleImputer\n", "imp = SimpleImputer(strategy='median')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Unfortunately, the `SimpleImputer` is not able to handle non-numerical data.\n", "Thus we have to split our data into the numerical attributes (i.e. everything but `ocean_proximity`) and the categorical one (`ocean_proximity`).\n", "\n", "**Task**: If you defined your `SimpleImputer` as a variable `imp`, the following code cell should execute. It splits the data into numerical and non-numerical ones, and fits the imputer." ] }, { "cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "SimpleImputer(copy=True, fill_value=None, missing_values=nan,\n", " strategy='median', verbose=0)" ] }, "execution_count": 23, "metadata": {}, "output_type": "execute_result" } ], "source": [ "train_num = train.drop('ocean_proximity',axis=1)\n", "train_cat = train['ocean_proximity']\n", "imp.fit(train_num)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Task**:\n", "You can look at the trained median values in each of the attributes with numerical values by calling `imp.statistics_`." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Solution**:" ] }, { "cell_type": "code", "execution_count": 24, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array([-1.18490000e+02, 3.42500000e+01, 2.90000000e+01, 2.12800000e+03,\n", " 4.35000000e+02, 1.16400000e+03, 4.09000000e+02, 3.53700000e+00,\n", " 1.80400000e+05, 5.23454779e+00, 2.03096930e-01])" ] }, "execution_count": 24, "metadata": {}, "output_type": "execute_result" } ], "source": [ "imp.statistics_" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Caution**:\n", "The output of `imp.transform(train_num)` is a `numpy array`.\n", "It can be converted easily into a `pandas DataFrame`.\n", "This can be done by executing the following code snippet." ] }, { "cell_type": "code", "execution_count": 25, "metadata": {}, "outputs": [], "source": [ "X = imp.transform(train_num)\n", "df_num = pd.DataFrame(X, columns=train_num.columns)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "Next, we want to look at the categorical data.\n", "\n", "Simply assigning numerical values to the categories might be possible, but not the best choice, because this would introduce:\n", "- an ordering among the categories\n", "- the same distance between each of the categories in terms of *predictive power*\n", "\n", "A better choice is the so-called *one-hot encoding* or *one-of-K scheme*.\n", "We introduced this transformation in Homework 9 as well as in the lecture on Slide 112.\n", "There, we used the pandas method `get_dummies` to do the job.\n", "This time, we want to use the class `LabelBinarizer` from `sklearn.preprocessing`.\n", "It essentially generates a `numpy array` $X$ with \n", "\n", "$$ X_{i,j} = \\begin{cases} 1 & \\text{sample $i$ belongs to category $j$}, \\\\ 0 & \\text{otherwise}. \\end{cases} $$\n", "\n", "**Task**: Use a `LabelBinarizer` to transform the categorical data `train_cat` into an $n_\\text{samples} \\times 5$ `numpy array`." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [] }, { "cell_type": "markdown", "metadata": {}, "source": [ "**Solution**:" ] }, { "cell_type": "code", "execution_count": 19, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "(16512, 5)" ] }, "execution_count": 19, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from sklearn.preprocessing import LabelBinarizer\n", "cat_enc = LabelBinarizer()\n", "X = cat_enc.fit_transform(train_cat)\n", "X.shape" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "You can see the classes via `cat_enc.classes_`." ] }, { "cell_type": "code", "execution_count": 20, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "array(['<1H OCEAN', 'INLAND', 'ISLAND', 'NEAR BAY', 'NEAR OCEAN'],\n", " dtype='