diff --git a/notebooks/05.04-Feature-Engineering.ipynb b/notebooks/05.04-Feature-Engineering.ipynb
index 7315fb277..987709b44 100644
--- a/notebooks/05.04-Feature-Engineering.ipynb
+++ b/notebooks/05.04-Feature-Engineering.ipynb
@@ -71,7 +71,10 @@
    "metadata": {
     "collapsed": false,
     "deletable": true,
-    "editable": true
+    "editable": true,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [],
    "source": [
@@ -99,7 +102,10 @@
    "metadata": {
     "collapsed": false,
     "deletable": true,
-    "editable": true
+    "editable": true,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [],
    "source": [
@@ -126,7 +132,10 @@
    "metadata": {
     "collapsed": false,
     "deletable": true,
-    "editable": true
+    "editable": true,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [
     {
@@ -135,7 +144,7 @@
        "array([[     0,      1,      0, 850000,      4],\n",
        "       [     1,      0,      0, 700000,      3],\n",
        "       [     0,      0,      1, 650000,      3],\n",
-       "       [     1,      0,      0, 600000,      2]], dtype=int64)"
+       "       [     1,      0,      0, 600000,      2]])"
       ]
      },
      "execution_count": 3,
@@ -168,7 +177,10 @@
    "metadata": {
     "collapsed": false,
     "deletable": true,
-    "editable": true
+    "editable": true,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [
     {
@@ -207,7 +219,10 @@
    "metadata": {
     "collapsed": false,
     "deletable": true,
-    "editable": true
+    "editable": true,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [
     {
@@ -257,7 +272,6 @@
    "cell_type": "code",
    "execution_count": 6,
    "metadata": {
-    "collapsed": true,
     "deletable": true,
     "editable": true
    },
@@ -285,7 +299,10 @@
    "metadata": {
     "collapsed": false,
     "deletable": true,
-    "editable": true
+    "editable": true,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [
     {
@@ -324,13 +341,29 @@
    "metadata": {
     "collapsed": false,
     "deletable": true,
-    "editable": true
+    "editable": true,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [
     {
      "data": {
       "text/html": [
        "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
@@ -406,13 +439,29 @@
    "metadata": {
     "collapsed": false,
     "deletable": true,
-    "editable": true
+    "editable": true,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [
     {
      "data": {
       "text/html": [
        "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
@@ -522,17 +571,22 @@
    "metadata": {
     "collapsed": false,
     "deletable": true,
-    "editable": true
+    "editable": true,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [
     {
      "data": {
-      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAWoAAAEACAYAAACatzzfAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAD1JJREFUeJzt3X+M5PVdx/HX67q7OAcuJnYCthdmSxuyQbuWawKN1Pjd\n0G1pG+GvRqqmCX80IalCGmOKJOaGP2riH1ZJ7P1BmCI1MG64gFZTCRjua4OasuVHD7g7ayTfBQpc\nvo2IIhvTyts/5nvXu+X25jvszH4/OzwfyYXZuc9+9z1w97zPfWaWcUQIAJCuPU0PAAA4N0INAIkj\n1ACQOEINAIkj1ACQOEINAImrFWrbX7b9rO0jtu+1PTfpwQAAA0NDbft9kn5X0v6IWJI0I+mGSQ8G\nABiYqbnuPZLOt/2WpL2SXp7cSACA0w3dUUfEy5L+RNILkn4o6T8j4h8mPRgAYKDO0cfPSbpeUkfS\n+yRdYPs3Jz0YAGCgztHHJyQ9HxH/IUm2H5D0K5LuO32Rbf6nIQAwoojwsDV1XvXxgqSP2f4Z25Z0\njaRjW3zBqfxx4MCBxmfg8fH4eHzT96OuOmfUj0s6JOkpSd+XZEl31v4KAIBtqfWqj4i4XdLtE54F\nAHAWfGdiDVmWNT3CRPH4djce3/TzKOck57yQHeO6FgC8G9hWjOnJRABAgwg1ACSOUANA4gg1ACSO\nUANA4gg1ACSOUANA4gg1ACSOUANA4gg1ACSOUANA4gg1ACSOUANA4gg1ACSOUANA4gg1ACSOUANA\n4oaG2vZltp+y/WT1z9dt37wTwwEARnwrLtt7JL0k6aqIeHHTz/FWXAAwgkm9FdcnJP375kgDwCSU\nZam1tTWVZdn0KI0aNdS/Iak/iUEA4HT9/qo6nUWtrNykTmdR/f5q0yM1pvbRh+1ZSS9Lujwi3vbH\nG0cfAMalLEt1Oova2DgsaUnSEbVay1pfP652u930eGNT9+hjZoRrflrSE2eL9EndbvfU7SzLlGXZ\nCJcHgIGiKDQ3t6CNjaXqniXNznZUFMWuDnWe58rzfOTPG2VH3Zf0UETcs8XPs6MGMBbsqM9U64za\n9l4Nnkh8YLuDAcAw7XZbvd5BtVrLmp/fr1ZrWb3ewamK9ChGenneOS/EjhrAmJVlqaIotLCwMJWR\nrrujJtQA0JBJvY4aALDDCDUAJI5QA0DiCDUAJI5QA0DiCDUAJI5QA0DiCDUAJI5QA0DiCDUAJI5Q\nA0DiCDUAJI5QA0DiCDUAJI5QA0DiCDUAJI5QA0DiCDUAJK7um9teaPt+28dsP2f7qkkPBgAYmKm5\n7g5J346Iz9mekbR3gjMBAE4z9M1tbc9LeioiPjhkHW9uCwAjGOeb235A0o9s3237Sdt32m5tf0QA\nQB11jj5mJO2X9KWI+J7tP5N0q6QDmxd2u91Tt7MsU5Zl45kSAKZAnufK83zkz6tz9HGRpH+JiEur\njz8u6SsR8eub1nH0AQAjGNvRR0SckPSi7cuqu66RdHSb8wEAahq6o5Yk278s6S5Js5Kel3RjRLy+\naQ07agAYQd0dda1Q1/yChBoARjDOV30AABpEqAEgcYQaABJHqAEgcYQaABJHqAEgcYQaABJHqAEg\ncYQaABJHqAEgcYQaABJHqAEgcYQaABJHqAEgcYQaABJHqAEgcYQaABJHqAEgcYQaABI3U2eR7ULS\n65LekvTjiLhykkMBAH6qVqg1CHQWEa9NchgAwNvVPfrwCGsBAGNUN74h6RHba7a/OMmBAABnqnv0\ncXVEvGK7rUGwj0XEY5sXdbvdU7ezLFOWZWMZEgCmQZ7nyvN85M9zRIz2CfYBSf8dEV/bdH+Mei0A\neDezrYjwsHVDjz5s77V9QXX7fEmflPTs9kcEANRR5+jjIkkP2o5q/b0R8fBkxwIAnDTy0ceWF+Lo\nAwBGMrajDwBAswg1ACSOUANA4gg1ACSOUANA4gg1ACSOUANA4gg1ACSOUANA4gg1ACSOUANA4gg1\nACSOUANA4gg1ACSOUANA4gg1ACSOUANA4gg1ACSOUANA4mqH2vYe20/a/tYkBwIAnGmUHfUtko5O\napBUlWWptbU1lWXZ9CgA3qVqhdr2PkmfkXTXZMdJS7+/qk5nUSsrN6nTWVS/v9r0SADehRwRwxfZ\n90v6qqQLJf1eRFx3ljVR51q7RVmW6nQWtbFxWNKSpCNqtZa1vn5c7Xa76fEATAHbiggPWzdT40Kf\nlXQiIp62nUna8qLdbvfU7SzLlGVZnVmTVBSF5uYWtLGxVN2zpNnZjoqiINQA3pE8z5Xn+cifN3RH\nbfuPJP22pJ9Iakn6WUkPRMQXNq1jRw0AI6i7ox56Rh0Rt0XEJRFxqaQbJD26OdLTqN1uq9c7qFZr\nWfPz+9VqLavXO0ikAey4WmfUpxbbv6Z3yRn1SWVZqigKLSwsEGkAY1V3Rz1SqId8wakMNQBMytiO\nPgAAzSLUAJA4Qg0AiSPUAJA4Qg0AiSPUAJA4Qg0AiSPUAJA4Qg0AiSPUAJA4Qg0AiSPUAJA4Qg0A\niSPUAJA4Qg0AiSPUAJA4Qg0AiSPUAJA4Qg0AiZsZtsD2eZK+I2muWn8oIm6f9GAAgIGhO+qI+F9J\nyxFxhaSPSPq07SsnPhmAocqy1NramsqybHoUTFCto4+IeLO6eZ4Gu2rebhxoWL+/qk5nUSsrN6nT\nWVS/v9r0SJgQRwxvru09kp6Q9EFJX4+IPzjLmqhzLQDbV5alOp1FbWwclrQk6YharWWtrx9Xu91u\nejzUZFsR4WHrhp5RS1JEvCXpCtvzkv7a9uURcXTzum63e+p2lmXKsqz2wADqK4pCc3ML2thYqu5Z\n0uxsR0VREOqE5XmuPM9H/rxaO+ozPsH+Q0n/ExFf23Q/O2pgh7Cjng51d9RDz6htv9f2hdXtlqQV\nSce3PyKAd6rdbqvXO6hWa1nz8/vVai2r1ztIpKfU0B217Q9LukeDqO+RtBoRXz3LOnbUwA4ry1JF\nUWhhYYFI70J1d9QjH32c4wsSagAYwdiOPgAAzSLUAJA4Qg0AiSPUAJA4Qg0AiSPUAJA4Qg0AiSPU\nAJA4Qg0AiSPUAJA4Qg0AiSPUAJA4Qg0AiSPUAJA4Qg0AiSPUAJA4Qg0AiSPUAJA4Qg0AiavzLuT7\nbD9q+znbz9i+eScGAwAM1HkX8oslXRwRT9u+QNITkq6PiOOb1vHmtrsQ72INNGdsb24bEa9GxNPV\n7TckHZP0/u2PiKb1+6vqdBa1snKTOp1F9furTY8E4CyG7qjPWGwvSMol/VIV7dN/jh31LlKWpTqd\nRW1sHJa0JOmIWq1lra8fZ2cN7JC6O+qZES54gaRDkm7ZHOmTut3uqdtZlinLsrqXxw4rikJzcwva\n2Fiq7lnS7GxHRVEQamBC8jxXnucjf16tHbXtGUl/J+nvI+KOLdawo95F2FEDzRvbGXXlG5KObhVp\n7D7tdlu93kG1Wsuan9+vVmtZvd5BIg0kqM6rPq6W9B1Jz0iK6sdtEfHQpnXsqHchXvUBNKfujnqk\nJxOHfEFCDQAjGPfRBwCgIYQaABJHqAEgcYQaABJHqAEgcYQaABJHqAEgcYQaABJHqAEgcYQaABJH\nqAEgcYQaABJHqAEgcYQaABJHqAEgcYQaABJHqAEgcYQaABI3NNS2e7ZP2D6yEwMBAM5UZ0d9t6RP\nTXoQAMDZDQ11RDwm6bUdmAUYu7Istba2prIsmx4FeMc4o8bU6vdX1eksamXlJnU6i+r3V5seCXhH\nHBHDF9kdSX8bEUvnWBN1rgXshLIs1eksamPjsKQlSUfUai1rff242u120+MBkiTbiggPWzczzi/a\n7XZP3c6yTFmWjfPyQG1FUWhubkEbGyf3Fkuane2oKApCjcbkea48z0f+vLo76gUNdtQfPscadtRI\nBjtq7AZ1d9R1Xp53n6R/lnSZ7Rds3ziOAYFJarfb6vUOqtVa1vz8frVay+r1DhJp7Eq1dtS1LsSO\nGgkqy1JFUWhhYYFIIzl1d9SEGgAaMrajDwBAswg1ACSOUANA4gg1ACSOUANA4gg1ACSOUANA4gg1\nACSOUANA4gg1ACSOUANA4gg1ACSOUANA4gg1ACSOUANA4gg1ACSOUANA4gg1ACSuVqhtX2v7uO0f\n2P7KpIcCAPxUnXch3yPpzyV9StIvSvq87cVJD5aSPM+bHmGieHy7G49v+tXZUV8p6d8iYj0ifizp\nryRdP9mx0jLtv1B4fLsbj2/61Qn1+yW9eNrHL1X3AQB2AE8mAkDiHBHnXmB/TFI3Iq6tPr5VUkTE\nH29ad+4LAQDeJiI8bE2dUL9H0r9KukbSK5Iel/T5iDg2jiEBAOc2M2xBRPyf7d+R9LAGRyU9Ig0A\nO2fojhoA0KxtP5k4zd8MY7tn+4TtI03PMgm299l+1PZztp+xfXPTM42T7fNsf9f2U9XjO9D0TONm\ne4/tJ21/q+lZxs12Yfv71X+/x5ueZ9xsX2j7ftvHqt+DV225djs76uqbYX6gwfn1y5LWJN0QEcff\n8UUTYvvjkt6Q9M2IWGp6nnGzfbGkiyPiadsXSHpC0vXT8t9PkmzvjYg3q+da/knSzRExNb/pbX9Z\n0kclzUfEdU3PM062n5f00Yh4relZJsH2X0j6x4i42/aMpL0R8V9nW7vdHfVUfzNMRDwmaSp/kUhS\nRLwaEU9Xt9+QdExT9hr5iHizunmeBs/JTM1Zn+19kj4j6a6mZ5kQa0pfQmx7XtKvRsTdkhQRP9kq\n0tL2/yXwzTBTwvaCpI9I+m6zk4xXdTTwlKRXJT0SEWtNzzRGfyrp9zVFf/hsEpIesb1m+4tNDzNm\nH5D0I9t3V0dXd9pubbV4Kv+0wmiqY49Dkm6pdtZTIyLeiogrJO2TdJXty5ueaRxsf1bSiepvRK5+\nTJurI2K/Bn9r+FJ1FDktZiTtl/T16jG+KenWrRZvN9Q/lHTJaR/vq+7DLlGdjR2S9JcR8TdNzzMp\n1V8rD0u6tulZxuRqSddV57h9Scu2v9nwTGMVEa9U/ywlPajBUeu0eEnSixHxverjQxqE+6y2G+o1\nSR+y3bE9J+kGSdP27PO07lZO+oakoxFxR9ODjJvt99q+sLrdkrQiaSqeKI2I2yLikoi4VIPfd49G\nxBeanmtcbO+t/qYn2+dL+qSkZ5udanwi4oSkF21fVt11jaSjW60f+g0vQ77YVH8zjO37JGWSft72\nC5IOnDz8nwa2r5b0W5Keqc5xQ9JtEfFQs5ONzS9Iuqd6ddIeSasR8e2GZ0I9F0l6sPpfU8xIujci\nHm54pnG7WdK9tmclPS/pxq0W8g0vAJA4nkwEgMQRagBIHKEGgMQRagBIHKEGgMQRagBIHKEGgMQR\nagBI3P8DWfnC9JC1xVsAAAAASUVORK5CYII=\n",
+      "image/png": "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\n",
       "text/plain": [
-       "<matplotlib.figure.Figure at 0x114836550>"
+       "<Figure size 432x288 with 1 Axes>"
       ]
      },
-     "metadata": {},
+     "metadata": {
+      "needs_background": "light"
+     },
      "output_type": "display_data"
     }
    ],
@@ -562,17 +616,22 @@
    "metadata": {
     "collapsed": false,
     "deletable": true,
-    "editable": true
+    "editable": true,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [
     {
      "data": {
-      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAWoAAAEACAYAAACatzzfAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAEmtJREFUeJzt3X+M5HV9x/Hn+7w9ugc9NHUDInFWMeRi67YeiRix6Zx4\nakEhMR7eXRvRIAmpLcY0jdakYf3Dpv2jtjb1JNaVasONJwSEViooMDXiD04EAYFahFlQlAypPbGs\nCSfv/jFzcCx7t9/hZvb72dnnI9nc7OxnZt9zP1732ff3Pd9vZCaSpHKtq7sASdKRGdSSVDiDWpIK\nZ1BLUuEMakkqnEEtSYWrFNQR8cGIuDsi7oyIyyNiw6gLkyT1LBvUEXES8GfAlsycAdYDO0ZdmCSp\nZ33FdS8Ajo2Ip4CNwCOjK0mSdKhld9SZ+Qjwd8BDwE+A/83Mr426MElST5XWxwuBc4EGcBJwXETs\nGnVhkqSeKq2PNwEPZOb/AETEVcDrgT2HLooITxoiSQPKzFhuTZWpj4eA10XEb0REAGcC9x7mG47l\nxyWXXFJ7Db4+X5+vb/w+qqrSo74VuBK4Hfg+EMCnK38HSdJRqTT1kZkfBT464lokSUvwnYkVNJvN\nuksYKV/f6ubrG38xSJ/kiE8UkcN6LklaCyKCHNLBRElSjQxqSSqcQS1JhTOoJalwBrUkFc6glqTC\nGdSSVDiDWpIKZ1BLUuEMakkqnEEtSYUzqCWpcAa1JBXOoJakwhnUklQ4g1qSCmdQS1Lhlg3qiDg1\nIm6PiO/1f90fERevRHGSpAEvxRUR64AfA6dn5sOLvualuCRpAKO6FNebgB8tDmlJGoVut8u+ffvo\ndrt1l1KrQYP6XUBrFIVI0qFarb00GpvZtu0iGo3NtFp76y6pNpVbHxExATwCvCozn/Pfm60PScPS\n7XZpNDazsHAzMAPcyeTkVubn72Nqaqru8oamautj/QDP+YfAbUuF9EGzs7NP3242mzSbzQGeXpJ6\nOp0OGzZMs7Aw079nhomJBp1OZ1UHdbvdpt1uD/y4QXbULeArmfm5w3zdHbWkoXBH/WyVetQRsZHe\ngcSrjrYwSVrO1NQUc3O7mZzcyqZNW5ic3Mrc3O6xCulBDDSed8Qnckctaci63S6dTofp6emxDOmq\nO2qDWpJqMqo5aknSCjOoJalwBrUkFc6glqTCGdSSVDiDWpIKZ1BLUuEMakkqnEEtSYUzqCWpcAa1\nJBXOoJakwhnUklQ4g1qSCmdQS1LhDGpJKpxBLUmFM6glqXBVL257fERcERH3RsQPIuL0URcmSepZ\nX3HdJ4DrMnN7RKwHNo6wJknSIZa9uG1EbAJuz8xTllnnxW0laQDDvLjty4HHIuKyiPheRHw6IiaP\nvkRJUhVVWh/rgS3A+zPzuxHxD8CHgUsWL5ydnX36drPZpNlsDqdKSRoD7Xabdrs98OOqtD5OAL6V\nma/of/4G4EOZ+fZF62x9SNIAhtb6yMxHgYcj4tT+XWcC9xxlfZKkipbdUQNExO8CnwEmgAeA92bm\n/kVr3FFL0gCq7qgrBXXFb2hQS9IAhjn1IUmqkUEtSYUzqCWpcAa1JBXOoJakwhnUklQ4g1qSCmdQ\nS1LhDGpJKpxBLUmFM6glqXAGtSQVzqCWpMIZ1JJUOINakgpnUEtS4QxqSSqcQS1JhTOoJalw66ss\niogOsB94CngyM187yqIkSc+oFNT0ArqZmT8fZTGSpOeq2vqIAdZKkoaoavgm8NWI2BcRF46yIEnS\ns1VtfZyRmT+NiCl6gX1vZn5j8aLZ2dmnbzebTZrN5lCKlKRx0G63abfbAz8uMnOwB0RcAjyemR9f\ndH8O+lyStJZFBJkZy61btvURERsj4rj+7WOBNwN3H32JkqQqqrQ+TgCujojsr788M28YbVmSpIMG\nbn0c9olsfUjSQIbW+pCklXbgAFx/PVx4IfzqV3VXU7+qUx+SNFKZ8K1vwZ49cMUVMD0Nu3bBr39d\nd2X1M6gl1equu3rh3GrBxo29cL7lFnjlK+uurBwGtaQV9+CDvWDeswcefxx27IBrroGZGYhlO7Zr\njwcTJa2IRx+FL36xF84/+hG885293fPrXw/r1ujRsqoHEw1qSSOzfz9cdVVv93zrrfD2t/fC+U1v\ngomJuqurn0EtqRYLC/DlL/fC+Wtfgze+EXbuhLe9rdeD1jMMakkr5sABuPHGXlvj2mvhtNN6O+d3\nvANe+MK6qyuXQS1ppA43TnfeefCSl9Rd3epQNaid+pA0EMfpVp5BLWlZh47T/eIXvZ6z43Qrx9aH\npCU5Tjd69qglDcxxupVlUEuqxHG6+hjUkg5rqXG6nTt743QvelHd1a0dBrWkZ3GcrjyO50kCHKcb\nBwa1NIYcpxsvtj6kMXHoON3998P27Y7TlW7oPeqIWAd8F/hxZp6zxNcNammFOU63uo2iR/0B4B5g\n0/OuahXqdrt0Oh2mp6eZmpqquxzpOeN0W7fC+94HX/qS43TjqtIPRBFxMnAW8JnRllOWVmsvjcZm\ntm27iEZjM63W3rpL0hp18GKv558PJ50El14KZ50FnU4voM87z5AeZ5VaHxFxBfAx4Hjgz9dC66Pb\n7dJobGZh4WZgBriTycmtzM/f585aK8JxuvE3tNZHRJwNPJqZd0REEzjsk87Ozj59u9ls0mw2q9Ra\npE6nw4YN0ywszPTvmWFiokGn0zGoNVKO042vdrtNu90e+HHL7qgj4q+BPwYOAJPAbwJXZea7F61z\nRy09T0uN0+3a5TjduBvJOxMj4g9YI60P6PWoL7jgT5iYaPDkk/PMze1m58531V2WxoRnp5NBPSRO\nfWiYHKfToTzXh1QIz06nwzGopRp5sVdVYVBLK8xxOg3Ks+dJK8RxOo2aQS09D4eO0z3+OOzY4dnp\nNDq2PqSKFo/Tbd/eOyjoOJ2eL3vU0hAsHqc755xeODtOp2EwqKXnaalxul274OyzHafTcBnU0gAO\njtO1Wr1es+N0WgkGtbSMxeN0L395r63hOJ1WiuN50mEcHKf7whdgcrK3c/7mN+GUU+quTFqaQa01\nYfE43c6dvRPuO06n1cDWh8aW43QqnT1qrUn798PVV/fCed++3tnpHKdTqQxqrRmO02m1Mqg11hyn\n0zgwqDV2Do7TtVq93rPjdFrtHM/T2HCcTmudQa0iHRyna7Weudir43Raq2x9qBiO02mtGVqPOiKO\nAb4ObKC3A78yMz+6xDqDWgNbapxu1y4480zH6TT+hnowMSI2ZuYTEfEC4Bbg4sy8ddEag1qVLCzA\nddf1wtlxuqPT7XbpdDpMT08zNTVVdzkaUNWgrvQDZWY+0b95DL1dtYmsgRw4ADfcAO95D5x0Enzq\nU71gnp/v7ai3bzekB9Vq7aXR2My2bRfRaGym1dpbd0kakao76nXAbcApwCcz8y+XWOOOWs/iON3o\ndLtdGo3NLCzcDMwAdzI5uZX5+fvcWa8iQx3Py8yngNdExCbgSxHxqsy8Z/G62dnZp283m02azWbl\ngjU+7rrrmYkNx+lGo9PpsGHDNAsLM/17ZpiYaNDpdAzqgrXbbdrt9sCPG3jqIyL+Cvi/zPz4ovvd\nUa9hDz7Ym3Pes+eZcbqdOx2nGxV31ONhaDvqiHgx8GRm7o+ISWAb8DdDqFGr3MFxulYL7r+/12f+\n1Kccp1sJU1NTzM3t5oILtjIx0eDJJ+eZm9ttSI+pKuN5rwY+R+/A4zpgb2Z+bIl17qjXAM9OVxan\nPlY3z/WhofnVr3pnp3OcThoug1pH5cABuOmmXjhfey1s2eLZ6aRhM6g1sEz49rd74ew4nTR6nj1P\nld19dy+cHaeTymRQr1GHjtPt3+/Z6aSS2fpYQ5Yap/PsdFJ97FELcJxOKplBvYZ5djppdTCo15hD\nx+m82Ku0OhjUa4Bnp5NWN8fzxpgXe5XWFoN6lVh8sdcdOxynk9YKWx8F82Kv0nizR71KHTpOd+ut\ncM45jtNJ48qgXkUWFnpnp2u1HKeT1hKDunAHDsCNNz5zdjrH6aS1x6Au0MFxuj174IorHKeT1jrH\n8wpycJyu1eq1MhynkzQIg3pEDo7T7dkDjz/e2zlfc43jdJIGZ+tjiBynkzSIofWoI+Jk4PPACcBT\nwD9n5j8usW5NBvX+/XDVVb3ds+N0kgYxzKA+ETgxM++IiOOA24BzM/O+RevWTFCP0zidV7GW6lM1\nqJf9gTwzf5aZd/Rv/xK4F3jp0Ze4uhw4ANdfD+efDyedBJde2gvm+fneG1S2b199Id1q7aXR2My2\nbRfRaGym1dpbd0mSljBQjzoipoE28Dv90D70a2O5o37sMZidHb9xum63S6OxmYWFm4EZ4E4mJ7cy\nP3+fO2tphQx9PK/f9rgS+MDikD5odnb26dvNZpNms1n16Yt17LG9UB63cbpOp8OGDdMsLMz075lh\nYqJBp9MxqKURabfbtNvtgR9XaUcdEeuBfwf+IzM/cZg1Y7mjHlfuqKX6Da1H3fdZ4J7DhbRWn6mp\nKebmdjM5uZVNm7YwObmVubndhrRUoCpTH2cAXwfuArL/8ZHM/Mqide6oVyGnPqT6eK4PSSrcsFsf\nkqSaGNSSVDiDWpIKZ1BLUuEMakkqnEEtSYUzqCWpcAa1JBXOoJakwhnUklQ4g1qSCmdQS1LhDGpJ\nKpxBLUmFM6glqXAGtSQVzqCWpMIZ1JJUuGWDOiLmIuLRiLhzJQqSJD1blR31ZcBbRl2IJGlpywZ1\nZn4D+PkK1CINXbfbZd++fXS73bpLkZ43e9QaW63WXhqNzWzbdhGNxmZarb11lyQ9L5GZyy+KaAD/\nlpkzR1iTVZ5LWgndbpdGYzMLCzcDM8CdTE5uZX7+PqampuouTwIgIsjMWG7d+mF+09nZ2advN5tN\nms3mMJ9eqqzT6bBhwzQLCwf3FjNMTDTodDoGtWrTbrdpt9sDP67qjnqa3o761UdY445axXBHrdWg\n6o66ynjeHuCbwKkR8VBEvHcYBUqjNDU1xdzcbiYnt7Jp0xYmJ7cyN7fbkNaqVGlHXemJ3FGrQN1u\nl06nw/T0tCGt4lTdURvUklSTobU+JEn1MqglqXAGtSQVzqCWpMIZ1JJUOINakgpnUEtS4QxqSSqc\nQS1JhTOoJalwBrUkFc6glqTCGdSSVDiDWpIKZ1BLUuEMakkqnEEtSYUzqCWpcJWCOiLeGhH3RcQP\nI+JDoy5KkvSMKlchXwf8E/AW4LeBnRGxedSFlaTdbtddwkj5+lY3X9/4q7Kjfi3w35k5n5lPAl8A\nzh1tWWUZ978ovr7Vzdc3/qoE9UuBhw/5/Mf9+yRJK8CDiZJUuMjMIy+IeB0wm5lv7X/+YSAz828X\nrTvyE0mSniMzY7k1VYL6BcB/AWcCPwVuBXZm5r3DKFKSdGTrl1uQmb+OiD8FbqDXKpkzpCVp5Sy7\no5Yk1euoDyaO85thImIuIh6NiDvrrmUUIuLkiLgpIn4QEXdFxMV11zRMEXFMRHwnIm7vv75L6q5p\n2CJiXUR8LyKurbuWYYuITkR8v//nd2vd9QxbRBwfEVdExL39f4OnH3bt0eyo+2+G+SG9/vUjwD5g\nR2be97yftCAR8Qbgl8DnM3Om7nqGLSJOBE7MzDsi4jjgNuDccfnzA4iIjZn5RP9Yyy3AxZk5Nv/o\nI+KDwGnApsw8p+56hikiHgBOy8yf113LKETEvwD/mZmXRcR6YGNm/mKptUe7ox7rN8Nk5jeAsfxL\nApCZP8vMO/q3fwncy5jNyGfmE/2bx9A7JjM2vb6IOBk4C/hM3bWMSDCmI8QRsQn4/cy8DCAzDxwu\npOHofxN8M8yYiIhp4PeA79RbyXD1WwO3Az8DvpqZ++quaYj+HvgLxug/n0US+GpE7IuIC+suZshe\nDjwWEZf1W1efjojJwy0ey/+tNJh+2+NK4AP9nfXYyMynMvM1wMnA6RHxqrprGoaIOBt4tP8TUfQ/\nxs0ZmbmF3k8N7++3IsfFemAL8Mn+a3wC+PDhFh9tUP8EeNkhn5/cv0+rRL83diXwr5l5Td31jEr/\nx8qbgbfWXcuQnAGc0+/jtoCtEfH5mmsaqsz8af/XLnA1vVbruPgx8HBmfrf/+ZX0gntJRxvU+4BX\nRkQjIjYAO4BxO/o8rruVgz4L3JOZn6i7kGGLiBdHxPH925PANmAsDpRm5kcy82WZ+Qp6/+5uysx3\n113XsETExv5PekTEscCbgbvrrWp4MvNR4OGIOLV/15nAPYdbv+wbXpb5ZmP9ZpiI2AM0gd+KiIeA\nSw42/8dBRJwB/BFwV7+Pm8BHMvMr9VY2NC8BPtefTloH7M3M62quSdWcAFzdPzXFeuDyzLyh5pqG\n7WLg8oiYAB4A3nu4hb7hRZIK58FESSqcQS1JhTOoJalwBrUkFc6glqTCGdSSVDiDWpIKZ1BLUuH+\nH1pY4+tXGp0xAAAAAElFTkSuQmCC\n",
+      "image/png": "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\n",
       "text/plain": [
-       "<matplotlib.figure.Figure at 0x1143bf2b0>"
+       "<Figure size 432x288 with 1 Axes>"
       ]
      },
-     "metadata": {},
+     "metadata": {
+      "needs_background": "light"
+     },
      "output_type": "display_data"
     }
    ],
@@ -604,18 +663,21 @@
    "metadata": {
     "collapsed": false,
     "deletable": true,
-    "editable": true
+    "editable": true,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[[   1.    1.    1.]\n",
-      " [   2.    4.    8.]\n",
-      " [   3.    9.   27.]\n",
-      " [   4.   16.   64.]\n",
-      " [   5.   25.  125.]]\n"
+      "[[  1.   1.   1.]\n",
+      " [  2.   4.   8.]\n",
+      " [  3.   9.  27.]\n",
+      " [  4.  16.  64.]\n",
+      " [  5.  25. 125.]]\n"
      ]
     }
    ],
@@ -643,17 +705,22 @@
    "metadata": {
     "collapsed": false,
     "deletable": true,
-    "editable": true
+    "editable": true,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [
     {
      "data": {
-      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAWoAAAEACAYAAACatzzfAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
+      "image/png": "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\n",
       "text/plain": [
-       "<matplotlib.figure.Figure at 0x114819c50>"
+       "<Figure size 432x288 with 1 Axes>"
       ]
      },
-     "metadata": {},
+     "metadata": {
+      "needs_background": "light"
+     },
      "output_type": "display_data"
     }
    ],
@@ -696,7 +763,10 @@
    "metadata": {
     "collapsed": false,
     "deletable": true,
-    "editable": true
+    "editable": true,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [],
    "source": [
@@ -720,7 +790,7 @@
     "This is known as *imputation* of missing values, and strategies range from simple (e.g., replacing missing values with the mean of the column) to sophisticated (e.g., using matrix completion or a robust model to handle such data).\n",
     "\n",
     "The sophisticated approaches tend to be very application-specific, and we won't dive into them here.\n",
-    "For a baseline imputation approach, using the mean, median, or most frequent value, Scikit-Learn provides the ``Imputer`` class:"
+    "For a baseline imputation approach, using the mean, median, or most frequent value, Scikit-Learn provides the ``SimpleImputer`` class:"
    ]
   },
   {
@@ -729,17 +799,20 @@
    "metadata": {
     "collapsed": false,
     "deletable": true,
-    "editable": true
+    "editable": true,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "array([[ 4.5,  0. ,  3. ],\n",
-       "       [ 3. ,  7. ,  9. ],\n",
-       "       [ 3. ,  5. ,  2. ],\n",
-       "       [ 4. ,  5. ,  6. ],\n",
-       "       [ 8. ,  8. ,  1. ]])"
+       "array([[4.5, 0. , 3. ],\n",
+       "       [3. , 7. , 9. ],\n",
+       "       [3. , 5. , 2. ],\n",
+       "       [4. , 5. , 6. ],\n",
+       "       [8. , 8. , 1. ]])"
       ]
      },
      "execution_count": 15,
@@ -748,8 +821,8 @@
     }
    ],
    "source": [
-    "from sklearn.preprocessing import Imputer\n",
-    "imp = Imputer(strategy='mean')\n",
+    "from sklearn.impute import SimpleImputer\n",
+    "imp = SimpleImputer(strategy='mean')\n",
     "X2 = imp.fit_transform(X)\n",
     "X2"
    ]
@@ -770,13 +843,16 @@
    "metadata": {
     "collapsed": false,
     "deletable": true,
-    "editable": true
+    "editable": true,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "array([ 13.14869292,  14.3784627 ,  -1.15539732,  10.96606197,  -5.33782027])"
+       "array([13.14869292, 14.3784627 , -1.15539732, 10.96606197, -5.33782027])"
       ]
      },
      "execution_count": 16,
@@ -814,13 +890,16 @@
    "metadata": {
     "collapsed": false,
     "deletable": true,
-    "editable": true
+    "editable": true,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [],
    "source": [
     "from sklearn.pipeline import make_pipeline\n",
     "\n",
-    "model = make_pipeline(Imputer(strategy='mean'),\n",
+    "model = make_pipeline(SimpleImputer(strategy='mean'),\n",
     "                      PolynomialFeatures(degree=2),\n",
     "                      LinearRegression())"
    ]
@@ -841,7 +920,10 @@
    "metadata": {
     "collapsed": false,
     "deletable": true,
-    "editable": true
+    "editable": true,
+    "jupyter": {
+     "outputs_hidden": false
+    }
    },
    "outputs": [
     {
@@ -849,7 +931,7 @@
      "output_type": "stream",
      "text": [
       "[14 16 -1  8 -5]\n",
-      "[ 14.  16.  -1.   8.  -5.]\n"
+      "[14. 16. -1.  8. -5.]\n"
      ]
     }
    ],
@@ -889,9 +971,9 @@
  "metadata": {
   "anaconda-cloud": {},
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python [conda env:root] *",
    "language": "python",
-   "name": "python3"
+   "name": "conda-root-py"
   },
   "language_info": {
    "codemirror_mode": {
@@ -903,9 +985,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.5.1"
+   "version": "3.7.3"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 0
+ "nbformat_minor": 4
 }