{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Populating the interactive namespace from numpy and matplotlib\n"
     ]
    }
   ],
   "source": [
    "from gdsctools import elastic_net\n",
    "reload(elastic_net)\n",
    "%pylab inline\n",
    "rcParams['figure.figsize'] = 10,5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from gdsctools import IC50, gdsctools_data, GenomicFeatures"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "ic50 = IC50(gdsctools_data(\"IC50_v5.csv.gz\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "gf = GenomicFeatures(gdsctools_data(\"genomic_features_v5.csv.gz\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "gd = elastic_net.ElasticNet(ic50, gf)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "ElasticNet requires 2 parameters called alpha and l1_ratio\n",
    "note that this is different from glmnet terminology\n",
    "\n",
    "\n",
    "| sklearn  |  glmnet |\n",
    "|-----------------------\n",
    "|l1_ratio  | alpha|\n",
    "|alpha     | lambda|\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "elatic_net takes the drugname as input + 11_ratio set to 0.5 by dfault and an alpha parameter. If we naively try 0.01 for alpha, we get a set of scores and plot showing the predicted versus test sets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAmsAAAFFCAYAAACzAqo/AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x6414150>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "scores = gd.elastic_net(1047, alpha=0.1, n_folds=10, show=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.text.Text at 0x611b590>"
      ]
     },
     "execution_count": 50,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAlUAAAFFCAYAAADFOBi0AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAFJNJREFUeJzt3bGPHNedJ/Dvz1B0wZIig93spNlzLppWdkFDQ99iLzRl\nK91AlNfApjqfNjEz07D+AK3F1AtZt1ZuUySYGVhLFJOLZFHeAw7YBUxRcnChfxdMDdka9XT39Lwh\n1ZzPBxioql5VvdeP1aUvXlVXVXcHAIDj+caTbgAAwNNAqAIAGECoAgAYQKgCABhg7VBVVa8fsvxy\nVe1W1ZVxzQIA2C5rhaqq2k1yacHyC0m6u29O8y+MbR4AwHY47uW/V5J8Pk3fy4LgBQBwGqwMVVV1\nYRqJqgXFZ5N8Njd/flTDAAC2yTojVc+eeCsAALbc0lA1jVLdmmYXPXr9QZJz0/TZJPcHtg0AYGs8\ns6J8p6qez95lvfNV9UJ3362qM939RZJ3k1xMcivJTpIbB3dQVd6DAwBsje5edMvTSktHqrr7V939\n3jR7Zq7o/an8o+ThrwMfdPfdQ/bjb8O/H//4x0+8Ddv6p+/0n/7b3j/9p++mBPGY/nKg3s2sGqna\nr+jtJG/Pzb84N339WC0AAHgKeKI6AMAAQtXX3Gw2e9JN2Fr67nj03/Hov+PRf5vTd09OHff64coK\nqvqk6wAAni5VlcUPHjiR2h7eT1VV6ZO4UR0AgPUIVQAAAwhVAAADCFUAAAMIVQAAAwhVAAADCFUA\nAAMIVQAAAwhVAAADCFUAAAMIVQAAAwhVAAADCFUAAAMIVQAAAwhVAAADCFUAAAMIVQAAAwhVAAAD\nCFUAAAMIVQAAAwhVAAADCFUAAAMIVQAAAwhVAAADrAxVVXW5qnar6q1Dyq9N/70yunEAANtiaaiq\nqt0kl7r7ZpKdqnphwWqvVdXHST45iQYCAGyD6u71Vqz6XXe/uGD5d7v7vSXb9bp1AAAkSVUleVz5\nobKfVaoq3V2b7GWdy39nqur1JD85ZJVz0+XB1zdpAADA0+AoI1W/SfJad//hkPJrSX7T3bcOLDdS\nBQAcyTaOVD2ztIqqC0m6u+8muZPk5SRvzpVfSXJ/uvx3P8lOklsH93P16tWH07PZLLPZbJO2AgAM\ndjvJl7PKppaOVE2X9D7s7lvTr/9+093vVdWZ7v6iql5K8kF3/2kaqXpnCmDz+zBSBQAcyTaOVK0K\nVX+R5PtJKslOd78xLX9403pVXZ5Wf76731ywD6EKADiSpy5UjSBUAQBHtY2hyhPVAQAGEKoAAAYQ\nqgAABhCqAAAGEKoAAAYQqgAABhCqAAAGEKoAAAYQqgAABhCqAAAGEKoAAAYQqgAABhCqAAAGEKoA\nAAYQqgAABhCqAAAGEKoAAAYQqgAABhCqAAAGEKoAAAYQqgAABhCqAAAGEKoAAAYQqgAABhCqAAAG\nEKoAAAZYGaqq6nJV7VbVWyvKr4xvHgDAdlgaqqpqN8ml7r6ZZKeqXjhQfiFJT+U5WA4AcFosDVXd\nfbO7fzjNPtvddw+s8kqSz6fpe0kuDW4fAMBWeGbVClV1JslrSX6yoPhsks/m5s8PahcAwFZZeU9V\nd3/R3T9L8vdV9dyJtwgAYAstHamau2fqbpI7SV5O8ubcKg+SnJumzya5v2g/V69efTg9m80ym802\nbjAAwDi3k3w5q2yquvvwwqrXk3zY3bemX//9prvfq6oz3f3FFLoudvf1ad0bB++7qqpeVgcAwEFV\nleRx5YfKflapqnR3bbKXVZf//il7v/q7kuRBd783LX8/Sbr7o6kBu1P5wRvZAQBOhaUjVUMqMFIF\nABzR0zhSBQDAGoQqAIABhCoAgAGEKgCAAYQqAIABhCoAgAGEKgCAAYQqAIABhCoAgAGEKgCAAYQq\nAIABhCoAgAGEKgCAAYQqAIABhCoAgAGEKgCAAYQqAIABhCoAgAGEKgCAAYQqAIABhCoAgAGEKgCA\nAYQqAIABhCoAgAGEKgCAAYQqAIABVoaqqroy/V07pPza/nqjGwcAsC2Whqqq2k1yo7vfTrJTVS8t\nWO21qvo4yScn0UAAgG2waqRqJ8mlafreNH/Qq939ze6+NbRlAABb5JllhdMI1b5vJXlnwWrnphGt\nb3X3z0Y2DgBgW6x1o3pVXUjyYXffPVjW3de7+2aS84dcHgQAeOotHamas9vdbxxcON2cfr+730ty\nP3uXB79yGfDq1asPp2ezWWaz2SZtBQAY7HaSL2eVTVV3L1+h6sr+ZcCq2u3um1V1pru/mEamPuju\nP02/Anzn4GhWVfWqOgAA5lVVkseVHyr7WaWq0t21yV7W+fXftar6fVXdz6NP936STDenf6eqLif5\n46LLgwAAp8HKkapjV2CkCgA4oqdupAoAgPUIVQAAAwhVAAADCFUAAAMIVQAAAwhVAAADCFUAAAMI\nVQAAAwhVAAADCFUAAAMIVQAAAwhVAAADCFUAAAMIVQAAAwhVAAADCFUAAAMIVQAAAwhVAAADCFUA\nAAMIVQAAAwhVAAADCFUAAAMIVQAAAwhVAAADCFUAAAMIVQAAAzyzaoWqujJN/nV3/88F5ZeTfJ5k\np7vfHtw+AICtsHSkqqp2k9yYwtJOVb10oPxCku7um9P8CyfWUgCAr7FVl/92klyapu9N8/Neyd4o\n1X75pQAAnEJLL/8duJz3rSTvHFjlbJLP5ubPD2oXAMBWWetG9eky34fdffeE2wMAsJVW3qg+2e3u\nNxYsf5Dk3DR9Nsn9RRtfvXr14fRsNstsNlu/hQAAJ+Z2ki9nlU1Vdy9foerK/mXAqtrt7ptVdaa7\nv5hGsC529/Wqej17N7XfPbB9r6oDAGBeVSV5XPmhsp9VqirdXZvsZZ1f/12rqt9X1f08+nTvJ0l3\nfzS33gOXBwGA02rlSNWxKzBSBQAc0VM3UgUAwHqEKgCAAYQqAIABhCoAgAGEKgCAAYQqAIABhCoA\ngAGEKgCAAYQqAIABhCoAgAGEKgCAAYQqAIABhCoAgAGEKgCAAYQqAIABhCoAgAGEKgCAAYQqAIAB\nhCoAgAGEKgCAAYQqAIABhCoAgAGEKgCAAYQqAIABhCoAgAHWClVVdW1VWVVdGdUoAIBtszJUTWHp\n8pJVXquqj5N8MqxVAABbprp79UpVv+7uvzmk7Lvd/d6SbXudOgAA9lVVkseVHyr7WaWq0t21yV5G\n3FN1rqp2q+r1AfsCANhKxw5V3X29u28mOV9VLw1oEwDA1jlWqKqqK1X13Wn2fpKd4zcJAGD7PLPm\nel+6tlhVZ7r7i+zdnP7BtPh8khuLNr569erD6dlsltlsdtR2AgCcgNtJvpxVNrXyRvWqupzk50l+\n1N3Xp2W/6+4X58qT5PnufnPB9m5UBwCOZBtvVF/r13/HIVQBAEe1jaHKE9UBAAYQqgAABhCqAAAG\nEKoAAAYQqgAABhCqAAAGEKoAAAYQqgAABhCqAAAGEKoAAAYQqgAABhCqAAAGEKoAAAYQqgAABhCq\nAAAGEKoAAAYQqgAABhCqAAAGEKoAAAYQqgAABhCqAAAGEKoAAAYQqgAABhCqAAAGEKoAAAYQqgAA\nBlgrVFXVtSVll6tqt6qujGsWAMB2WRmqprB0+ZCyC0m6u29O8y+MbR4AwHZYGaq6++0k9w4pfiXJ\n59P0vSSXBrULAGCrHPeeqrNJPpubP3/M/QEAbCU3qgMADPDMMbd/kOTcNH02yf1j7u9I/uEffpRf\n/OIXj6Wuv/3b/55//uefP5a6AIDts26oqi/NVJ3p7i+SvJvkYpJbSXaS3Fi08dWrVx9Oz2azzGaz\nDZr6Vb/97Qf5/PM3k/zXIfs73P/Ob3/7oxOug23zV3/1XP7jP/7tsdT1l3/5n/Pv//6Hx1IXX3+O\nveN5GvvvcX6mb3zjP+XPf/5/j6Wux+N2ki9nlU1Vdy9foepykp8n+VF3X5+W/a67X5ymX03yaZLn\n98sPbN+r6tjUxYu7uXPnH5Psnsj+H7mb5577u3z66d0TrodtUlVJTubYXlBbTup7xPZx7B3P09h/\nj/szPZ66nsy/U1Wlu2vFBgutHKnq7l8l+dWBZS/OTX8lSAEAnDZuVAcAGECoAgAYQKgCABhAqAIA\nGECoAgAYQKgCABhAqAIAGECoAgAYQKgCABhAqAIAGECoAgAYQKgCABhAqAIAGECoAgAYQKgCABhA\nqAIAGECoAgAYQKgCABhAqAIAGECoAgAYQKgCABhAqAIAGECoAgAYQKgCABhAqAIAGECoAgAYYGWo\nqqrLVbVbVVcOKb82/XdhOQDAabA0VFXVhSTd3Ten+RcWrPZaVX2c5JMTaB8AwFZYNVL1SpLPp+l7\nSS4tWOfV7v5md98a2jIAgC2yKlSdTfLZ3Pz5Beucmy4Pvj6uWQAA2+XYN6p39/Xp8uD5qnppQJsA\nALbOMyvKHyQ5N02fTXJ/vnC6Of1+d783le0k+cplwKtXrz6cns1mmc1mGzcYAGCc20m+nFU2Vd19\neOHejeoXu/v6dHnvRnffraoz3f3FNDL1QXf/afoV4DvdfffAPnpZHcdx8eJu7tz5xyS7J7L/R+7m\nuef+Lp9+enf1qpwaVZXkZI7tBbXlpL5HbB/H3vE8jf33uD/T46nryfw7VVW6uzbZy9LLf9390VTB\nbpIHc4Hp/an8VpLvVNXlJH88GKgAAE6LVZf/0t3XFyx7cW76V6MbBQCwbTxRHQBgAKEKAGAAoQoA\nYAChCgBgAKEKAGAAoQoAYAChCgBgAKEKAGAAoQoAYAChCgBgAKEKAGAAoQoAYAChCgBgAKEKAGAA\noQoAYAChCgBgAKEKAGAAoQoAYAChCgBgAKEKAGAAoQoAYAChCgBgAKEKAGAAoQoAYAChCgBgAKEK\nAGCAZ1atUFWXk3yeZKe73z5qOQDAabB0pKqqLiTp7r45zb9wlHKO7/bt20+6CVtL3x2P/jse/Xc8\n+u84bj/pBpxaqy7/vZK9UagkuZfk0hHLOSYnls3pu+PRf8ej/45H/x3H7SfdgFNrVag6m+Szufnz\nRywHADgVVt5T9fX3f5P8/oTr+D8nvH8AYNtVdx9eWPWTJDe6+9Z0Q/rz3f3muuXTOodXAADwNdPd\ntcl2q0aq3k1yMcmtJDtJbiRJVZ3p7i8OKx/RMACAbbL0nqru/ihJqmo3yYPuvjsVvb+iHADgVFl6\n+Q8AgPV4ojrAAFV1uap2q+rKknWuLZpfts1psWH/rdwGDlp13CwqX/dYGx6qjtDYt+aWObFMNuw/\nJ5bJGv13Zfq7NrfM8ZeN+86xl/UehDz10eUDi1+rqo+TfHLyrfz62qT/PHz6kQ1Dwqk8723wUPML\nRznWhoaqNRq7m+TSVL4zV+7Eks36z4nlkTX778b0OqWdqnppKjr1x98mfefY+5KVD0Ke+u7egcWv\ndvc3u/vWCbfv626T/vPw6RzrzSen9by3yUPN1z7WRo9ULa24u2929w+n2Wfnbmx3YtmzSf85sTyy\nqi925pbdm+YTx1+yWd859h7Z9EHI56YRhNdPoE3bZN3+m/81uYdP79n0zSen9by3yUPNz6zY5qHR\noWrlQV5VZ6YTyE/mFjux7Nmk/5xYHlnaF939dndfn2a/leSDadrxt1nfOfaOqbuvTyMI5+dGTuEo\nNn3zifPeCXjsT1Sfnm/1s6r6TVXd6e4/7J+sq+o7VfXSKUzOazvQfx896fZso2k4/MP9kVLH3/rm\n+67qdD2Cbrr3ZP7n0pXkfne/l72RgHPT8rNJ7q+5v/3t72dv9O+pPfYG9d/89g/W3IYFTvF5b9Vx\nc7D8j9k77tY61o4cqo7zxZi7tns3yZ0k36uqz+PEsmn/vZxTdmIZdGLe7e435vZ3Ko6/0X2XU3bs\nTff0HOaXWf6g5H3zSfSTPBotPZ8FD09+mpxA/618+PTT4pjf3a98T0/TeW+BTR9q/u0Fy77iyKHq\nmF+MS0k+nNY9m+Rfs3dAOLHs2aT/bmTNf+ynwXFPzFV1Zf9VStPN16fmf2wn0He/zCk69pbp7o+q\n6mItflDyi8neL7CSXKyqV6fLfremX2UlyR9P88OTN+y/w7Z56hzzu7soJJzLKTnvHbTqWDusvKq+\nvc6xNvzhn1X1apJPs/cewP3hxd9194tVdSbJ97KXsnfmRgv2fyb7lXcHnjYb9t9XtjmtVvTfbvZO\nMA+SPJvke/3ovZXJKT/+Nuw7xx48Ycu+u0vKnfdOgCeqAwAM4InqAAADCFUAAAMIVQAAAwhVAAAD\nCFUAAAMIVcATNb0d4NUjbnNm/yfh06s2rm1Q725V/bmqnptb9vqitixr4/Ssqa/UX1W/P2qbgO0m\nVAFPTFXtZO8tAUd9xtW57L0odt+mz4a5l+R/LVthzTYuqt/zauCUEargFKuq56dRmF9X1S+r6i+m\n5e9Oy3+3P5JzYNnutOxyVb1VVR9X1XPT9AfTOheW1TH5H0m+XVXfXbeOabsfJdnd3y57T9p+d9ru\nytzne2ta9rA9B9xJ8sH8Ngvst/HyovbN1XVm7nO+u6qPgafPY3+hMvC18nL2XpD8xhQSzlXVD5L8\na3e/WVUvJLlUVc/OLTuTvacz779P7GJ3f3MKJt3d357W+TDJf1lUR5I/Tdv+NHtPdH6vql5fVcdc\nu3+a5Nlpu91p+r/N1fv2XHtePNCeed3dP5wC2/uH9NFPs/d6j+eXtK+SvJHk3e6+PgW4/f0t+/zA\nU8RIFZxuP09SVfXrPHpB94uZAkF3350ue/119kZ1Mr1PbP7S1n54uJhkp6p+meTtaV+L6vjskLas\nU8dh9ts7v91h7VnkB0n+aUUdy9qXJA+DVHd/NLd83c8PbDmhCk637yd5p7v/Jnv3F72WvZdMfydJ\nqurSdBP277MXUvbvMVrkwyR3uvuV7v5+9l70elgdi3yyRh3zasXyw9rzFd19a2rbD5bUt6p9d/Ko\n3741t3zdzw9sOZf/4HT7IMm/VNXn2Rt5+V53/2H/3qHsvTz55e7+t4PLDu6ou98+sM5PDqtjUUO6\n+2er6pjzWZIL0z1VXxzc1Yr2LNTdf19V9w8v7jeXtK+n/f9LVb08temTqWytzw9sPy9UBgAYwOU/\nAIABhCoAgAGEKgCAAYQqAIABhCoAgAGEKgCAAYQqAIABhCoAgAH+P+fEQ4puLVIkAAAAAElFTkSu\nQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7513490>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "_ = hist(scores,bins=20); xlabel('scores for the N folds ')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We see here that scores are pretty bad (zero or even less)\n",
    "\n",
    "If we try another value (0.01), we get better results"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAmkAAAFFCAYAAAC393oCAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x6153590>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "scores = gd.elastic_net(1047, alpha=0.01, n_folds=10, show=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.text.Text at 0x74fcc50>"
      ]
     },
     "execution_count": 53,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAlMAAAFFCAYAAADIJmjzAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nDf8Ps0Pr1BTss2kAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x642ac50>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "_ = hist(scores,bins=20); xlabel('scores for the N folds ')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now the question is how to get the alpha value?"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAmUAAAFOCAYAAADHDGpPAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nBijKAAAAYuD/A4pQ9WEH7Y/CAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x61324d0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "alphas, all_scores, maximum, alpha_best = gd.tune_alpha(1047, alphas=logspace(-6,0,40), n_folds=10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.0070170382867038297"
      ]
     },
     "execution_count": 56,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "alpha_best"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "-4.9594140464487131"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "log(alpha_best)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This is not instateneous but can be speed up by preventing the plotting, or playing on the number of alphas or the number of N_folds"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "res = gd.tune_alpha(1047, alphas=logspace(-6,0,40), n_folds=10, show=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "res = gd.tune_alpha(1047, alphas=logspace(-6,0,20), n_folds=4, show=False)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAmUAAAFOCAYAAADHDGpPAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nB5Ds+do/PgAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x6136ed0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "alphas, all_scores, maximum, best_alpha = gd.tune_alpha(1047, alphas=logspace(-6,0,20), n_folds=4, show=True)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Using only 4 folds and 20 alphas decrease the computing time to 286ms instead of 1.34s"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Another method to identify the best alpha is to use the method based on concordance index. Although it is much longer to compute, it may be interesting for further detailled analysis"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " [-----------------95%----------------  ] 19 of 20 complete in 271.5 sec"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAlQAAAE3CAYAAABsEN9AAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzt3Xl4nNVh7/HfGcmrvEky2JIBW5YMZjNaMCFA8BjZkKWJ\nwcJ2UznUbbyQ9pI8uQQCbR1JdVPC0t57S28SllLfBLf1Qpq0uTeJFzE0JBiMbWEwBGxZEsTygmUt\neLc05/4xM9JoNNJImhm9M6Pvx888865zzrySZ34658wZY60VAAAABs/ldAUAAACSHYEKAAAgSgQq\nAACAKBGoAAAAokSgAgAAiFLEQGWMKTPGlBpjVoXZV2SM8RpjDhhjDhpjfuDf/j3/fY9zAAAAUk2f\ngcoYUyTJWmt3+NcLQw7JtNa6rLWzJN0r6XH/9tXGmAOSamNdYQAAgEQTqYVqmaQW//IhSQuCd1pr\nq4NW51pr6/3LK621s0L2AwAApKRIgWqSpJNB69nhDjLGlEraGLQpy99N+FCU9QMAAEh4sRqUvtBa\n2xZYsdY+7+8mzDbG3BGjMgAAABJSpEDVLCnLvzxJUlMvxxUHFowxq4wxi/2rTZJmRlVDAACABJce\nYf8mSSWSquULRtskyRgz0Vrb6l/OkxT8hYC1kt70L2cHzglmjOELBAEAQNKw1pq+9vfZQmWt3St1\njpFqttbW+HdtDzn0UNA51ZIWGmPKJJ0IOif0sbmF3CoqKhyvQ6LduCZcl2ivS6X/n9N1S7TrMtxv\nXBOuy0Bu/RGphUrW2ufDbJsbtFwn6Wsh+1/qV+kAAAApgJnSAQAAokSgSiBut9vpKiQcrkl4XJfw\nuC7hcV164pqEx3UZPNPfvsGYFmqMdaJcAMNPlamSJFXYCodrAiBZGWNkIwxKjziGCgAApLYZM2ao\noaHB6Wo4bvr06aqvrx/UuQQqAACGuYaGhn5/mi2VGdNnI1SfGEMFAAAQJVqoAABADx6P7xZYDoxX\nd7u7lofiMZJFwg1K99R75Kn3dC67Z7glSe4Z7s7laA1FGUNVTqqUMVRS6Xql0s8lnhiUDkTmH3Td\nx34p2rgw2MdwuVzyer0DOmfv3r1avXq1du3aNaDzersO/RmUnnCBqttxVUa2Ir71G4oyhqqcZC9j\nqANCsl+voSgnFUIbgQqILJEDVVpamjo6OgZ0Tmtrq3bv3q077rhjQOdFE6jo8kPCCH6TNlVGnhUe\nR+uD1PqZpEI4BIabO++8U9ZaZWdn680339SaNWtUXFysHTt2aNeuXXr22Wf1yCOPqLW1VcXFxdq8\nebNmzJihQ4cO6eGHH9abb76puro6LVmyRMuWLdNjjz2m7Oxsbd68WYWFhTGtK4EKgKOGKuikUjgE\nhoutW7cqLS1NTU1Nqqur0/bt21VQUKAtW7aotbVVX/va17Rnzx7l5eVp5cqVeuaZZ/TYY49J6v6J\nvT179ujLX/6yTp48qfvvv1/f/va39atf/SqmdSVQAXAUQQdAfxlj9P3vf79zvbm5WRMmTJAkZWVl\nqaWlJex5mZmZevDBByVJa9as0erVq2NeNwIVAACIKIopmmJm5syZ3da/+93vaseOHcrOzg67PyAr\nKyvudSNQAQCAiGIxKH1w5YYv+KWXXlJ1dbVefvlljR8/Xs8995z27NkTRQ2jw8SeAAAgYQWPhQoO\nVydPnlRWVpbGjx+vlpYWPfPMMzp58mTYxxiKGQ1ooQKAGOGThEDslZWVKS0tTbW1td3C1apVq7R5\n82ZlZWUpPz9fTzzxhJYsWaLq6mplZmZ2e4xovlKmvwhUABAjDLAHYm/Tpk2dywcOHOi2b+vWrd3W\nm5qaOpcDk3rm5eV1O6+oqGjAE372B11+AAAAUaKFCgAA9BD8PXzz5kmVlb7lwX6X32AfI1kQqAAA\nQA+xCD2pGJx6Q5cfAABAlAhUAAAAUSJQAQAARIkxVAAAoIdYzKs2nOZmI1ABAIAeYjGvWiwew+Vy\nyev1Dvi8WJ3f73LiXgIAAMAgRTvL+VDMki4RqAAAQIK68847Za1Vdna2JGn79u0qKChQWlqa7rrr\nLrW1tXUeu2bNGmVlZSk7O1tPPvlk2PPjiUAFAAAS0tatW2WMUVNTk1paWrR06VI999xzam5u1syZ\nM7Vy5UpJ0pYtW1RdXa2Ghgbt2LFDjzzyiNra2rqdH2+MoQIAAAlv8+bNWrhwoebPny9J+sEPfqCs\nrCxJXd16Bw8eVFFRkZqbmzVhwoQhrR+BCgAARGSqhmYsUm9qa2u1efNmbd++XZJkrZXL5etoKysr\nU3Nzs5YsWaLm5mY98sgjeuihh4a0fgQqAAAQka2wUZ0fbSDLz8/XkiVLtHHjxs5tNTU1kqS6ujqV\nlpZq5cqVqq+v14IFC5Sfn6/FixfL2ujq3V+MoQIAAAlv6dKl2r59u3bs2KGWlhatWbNG3/72tyX5\nxlAtWbJEra2tnVMkBLoB+ZQfAAAY9srKypSWlqaJEydq06ZNWrNmjbKzs9XQ0KDNmzdLkh566CFl\nZWUpMzNTc+fO1dKlS3XPPfd0Oz/e6PIDAAAJa9OmTZ3LpaWlOnjwYNjjtm7dGvH8eKKFCgAAIEq0\nUAEAgB6Cv4dv3vR5qvRUShr8d/kN9jGSBYEKAAD0EIvQk4rBqTd0+QEAAEQpYqAyxpQZY0qNMavC\n7CsyxniNMQeMMQeNMT+IdA4AAECq6TNQGWOKJFlr7Q7/emHIIZnWWpe1dpakeyU93o9zAAAAUkqk\nFqplklr8y4ckLQjeaa2tDlq90VpbH+kcAACQWKZPny5jzLC/TZ8+fdDXMNKg9EmSTgatZ4c7yBhT\nKikw0UO/zgEAAImhvr7e6SokvVgNSl9orW2L0WMBAAAklUgtVM2SsvzLkyQ19XJc8UDPqays7Fx2\nu91yu90RqgIAABB/Ho9HHo9nQOdEClSbJJVIqpY0U9I2STLGTLTWtvqX8yTZSOeECg5UAID+CZ4o\n0VPv6ZzjZzjN9wPEW2hDT1VVVcRz+gxU1tq9xpgS/xipZmttjX/Xdklzgw491I9zAABRCg5OpsrI\ns8LjaH0A+EScKd1a+3yYbXODluskfS3SOQAwlDwe38341wON4owuABAPfPUMgCEXCDuB5c6QUz8v\nZmW43b5boKW+2yiDV2JWDABIIlABSaO3EBLrFpehDDuSZExXeVVVJB0AyYlAhZQ2HEKIpJi2uKRS\n2Kmra+hcXr68SvevLtWOZ3+o234jVR1YrhXr1ml6Xp6DNQSQKhwPVKn0hjcUz4XrNTCEkMRVV9eg\ntWvXS/LqnrtbVGAbdNu+2AWduroGLVz4tL6i8ZKkDRvu1fmNt2p9e6sqJJ2u36CKnTv1wLZthCoA\nUTPW2shHxbpQY2y4co2RgjebKiNbEfv6BZczFGXEqxyuV+KVEVpOrMsIhJANG7wqL3d1trhs/80G\nLbi1PGYtLsHl3L3IF3Z27vtZzMoIhJ3a2ipJx7VIpdqgOmVIOi2pIj9fD2zbpitm5OnsWemTT6S2\ntp63vrbX1FTp5MlvqVJPSZJe1AHVaIMygupxWtJT5eWqePHFQT+X3v4wqKp3y673DPpx+yNev8MA\nujPGyFpr+jrG8RYqIN6CW0KWL3fFrdtnqFpcfCEkQxs27I9Li0to2LE/K1VlIOz0s4yODl+o6S3w\nfP/76zufR4HWdoYpScqQVFVbq5tmr9X7HS9qxAhpwoSu2/jx3dcDt9zc7vsfftirkye74tNUHe4W\npgJl7f1Fox5+WLruOt/t6qulMWP6f71onQQgJUigSpU3vNAy4vVcuF4De/xkCSEBXq907px05ox0\n9mzX7eGHu0KIJBXoMa1vb+0RRP77n67V4kdelDGSy+V7kw/cQtfDbauoiBx2ln12rSZ/+sWwYamt\nzVffceN6D0LHj3s7n0dvQWfRTY2q3CGNHDm4n8nVV7u0Z8/pzvWjmqbTnaX6nJZ0yfW5ysyUfvUr\n6e/+TvrgA+nyy7sCVuA2a5Y0YkT4sobi/wqABGetHfKbr1ifQ4fqbX7+g1Y6ZX0dJe/Ye9Mn2lO+\nFXtKsg/m59v6Q4dsNLqXc8guUl6cy4jPc+F69eT1Wtvebu3Fi9aeP2/t2bPWnjlj7alT1i5dWhn0\n+NYWqLzz8W1QOd/8Qrndt8/avXut3bXL2p07rf3Nb6x95RVrq6ut3brV2l/8wtr//E9rf/pTa7ds\nsXbjRms3bLD2Rz+y9uabu8rprYwF08vt3Xdbe9dd1t5+u7Vz51p77bXWzpxpbU6OtZMmWTtqlLXG\nWDt6tLVZWdZOm2ZtQYG1119v7fjx3wl+SHub3N3KCNy+lDnfLlxo7YIF1paWWjt/vrVut7Xz5vnK\nve02a2+91dpbbrH205+29uabrb3pJl99brzR2nHjvhOxjD+ZNd/+8z/7rsPWrb7r9e671v7+99a2\ntVnb0dH3z768PPL1qiwvj8nvV6UqbaUq+/37deGC77ls2mTtd75j7eLF1s6a5fuZXH+9tV/+srXf\n/a61P/uZtbW11h48GP//K71RpSIfBCBq/tzSZ7ZxfAzV8uVV2rDhW+r6q3t52HEO8yaU63Ru93EO\nfVU9dN+RI1X65BNfOb2Vcfv4cp3KCT+WwvTZc+rT2NhVxkCfS381NlaprS1yGbeP7yoj3HWKtO3o\n0SqdOtX39boto1zNk1/sPK+v+3DbWlurdO5c5OdyY1q56kf4yvF61e2+c6xSUEuLy9W1fP58hbze\nrq8MuE3z9Wt5ejz3u8bM1+GZ1UpLk9LTNeD7bdsqdOxYVZ9lrLlmvu5aV60xY9R5GztW3dbHjJFG\njw7/+9bf/yvRjgkKLideZfR3DFUsWnN/NHO9JOlAuaIac3b2rPTee9I773S/NTZWqaMjvterN4yh\nAoZGUoyhOny4q+lf6r353z27UV9d3/P8voJO8L777vPqjTf67mKYf02jVv2fno/T38z5x3/cVUZf\n5fT2XPpjxYr+lTH/6katDHou4a5TX9u+8hWvXn+97+u18PpGfe1furqKgs8Pdx+67d57vfrtbyM/\nl7JbG/UXv+gemEK7qnqzfLlLGzZ0dfT01u1zy+JcVUTxfhdcTm9l5BblavHiwZexbt0K7dxZ0dkd\nd1CPakX6zzu7/TqDyLp1gy8kpJyDWqdy/bZn2ImyjLy86dq27QGtXfuUNmzwyiz6oiqDBr4/4A86\n1lp12A61e9vV4fXfh6z3uS29vbPMP666RafsKd34nS+r8l836Idfe1Sjx47VxY6LGpHWS19ekDFj\npOJi3y3YZz7j1auv9v1/xdvYGNX1ApD4HA9U06a5JEV+wxs/K1dXXz34cmbNcumNN/p+wxtfkKur\nropNGVJ8nstAypg9e3BlSFJBgUuvv9739crIz1U0DQh5eS799reRn8uIy3M1duzgykjFEPJXf/Wk\n/uVf2lW2zKs/vO+f9J0X1uuN3T9XcdHndMdDq3Q4/YgaGj5Su7ddFzsudgaMdm+7LnpD1nvZ/7m/\nvqjqfyrXu3sz9M6VM3SPpLPH6jTuinyN/6NCra2pUPueriDT74ATcmxHSYc0tV2vTmnXK94ONRdL\nu9N/or/dsFnt3nZ5rVdpJk1prjSlu9KVZvz3/vW+tp09na5TbWlaqc9Kktb8+HG5lK7J2S5J0pLN\nS3TizAmdPHtS40aO0+Sxk3vcssdkh92eOSZT6S7fy+f06S69+mrf/1dcublR/ewBJD7Hu/xCBw1L\n+3Vv+q093/BiPGg4Hl0MQ/FcuF6DK2egUw1Ya2Vl5bXeHjdrw2+vr/tQj//NFv37S9KddzarQPXa\n9942lRR/XvMe/KomTJ2oMxfP6PTF0zpz8Yxv+cLpntv8y4F94bbZ9pHKHDdWGSMzNCZ9jA6cPKDC\nqYWdgWKEa0TXclrXcui+sOtBx//lo+n6+yd961//5df17B882yPc9DfgBB+7e1e63ng9TS6la+dv\n03XbLb7lJxq+pFPP/KrzuDSTJtOf/vY+VBlfV2yFrejcFtxV5rVetZ5r1YkzJ7rdms429bqt+Wyz\nJoyaoMljJ2vc6fF6/3/O1pljzyqe3Zfh0OUHDI3+dPk5Hqik8G94T//NA2o8UKO03FylLblKoy8d\n0/lmFnijC7cceLMLt3zm+Dk1/scYNf8+WxOyf68C06CxbW06d8lEffLFSzVi8igF18vKtxzYFlgP\nty2wfv7ERZ38v5k6dXSyxk09oQmfPqYpr7Upo+mUTmVn6MRnJ8o1Ob3znEDd+roPPba9qUPntl6m\ni82XKj3zmNLn1ilvV7uyW9t1cuIIHb5zjNInj1CaK00u4+p2SzNhtvVy3IUTF/XRT0fpREO2Jk9t\n1CzzodKaT8jkTJUtm6kxl2YEfp5dP1v/V9EGtgXWw20zxuj08bN6f1O7Gg9malpBi2bccVEjXq5X\n++HDcuXmyJQVaMQlo+S1XnV4O9RhO8Iue61XHbaj23LocUePdSh7ctdxn1z4RGNHjA0bjgL1DL0u\nxvTc1rnPf/yRRpcuv8y3raG1Qdddep0yRmRo7IixGjvCF4LGjhjbfZt/Oey+kG1jRozRiLT0pJ9T\nK2x5cSgjUqAajA5vh1rOtXSGrHfef1cv/P1/6fXfuFRw7e91RfsBXTj+kU5cmKMvfHmLHn+iQGlp\nUT+VHuL5M/HUe+Sp93Quu2e4JUnuGe7O5WQoA4iFpAlUXdu7XrzfOPyGPvX8p/SzP/xZ5xuVMabP\n5cCbXaTluTe6tGe3b7nomSK9df9bvvJDwkC4bZECQmD9yit9H78ObJv19CzVfr22sw7B5wRv6+0+\n3LFZWUYtzV3rE743Qc3fbu4WMoJvgWDRbVs/jvvM7V5Vv+zbtuDHC7R1+dYeQVIaXAANbFu0SPrp\nT7uOuWfjPfr5l3/eGfYCQTDQahEcBANdQuGWg8/JzXHp4+Nd+yY9PkmnHj0VNjQFrvNgxCuE9DWz\n/PxX4l9Osk5UGY9A1ZvQn/3NU+fpd++5NPt3P9Lm5y/TZZfFuLwhaqFK1jANxEpSDErvzU3TbpIk\nfemqL8X+wY9IRTldq3OmzIl9GSelWdndN83MnBnbMs5JE0d33zRp9KTYliFJDdL8oN6KhfkLY1/G\n+9KikDFfX7jyC7Et47Q0OWQsVsbI0CHEgxMcQubNkyor/Tvi9F1+PcTpa3SCMVFleH397F9du0N/\n++vv6XFPia6794da/8g9uvtuZ+oJIL4cD1S9vRjF87vp4vWGNxTPheuVeGUEHo8QMjz19bNPc6Vp\n7by/1ML8Ut07plz3bfqVlvzy7/X0348d9ActACQmxwNVKv3VPRTPheuVeGUAkdx82c169xt7teqn\nf6Yt+0rkWfiv+vcfFGpOHBrHATjD5XQFAGA4mDBqgjYue1H/e9lf6uPPLtQt//1/6h/+wfZ7njsA\niY1ABQBDaPmc5dr75ztVcM+/6Tvvf0F33nNMH3/sdK0ARItABQBDLD8rX7vu/7W+dnexdhYWafYf\n/FLbtjldKwDRIFABgANGpI3QYwv/Rj9f8a9Kv2e17nnmm/rmQ+d14YLTNQMwGAQqAHDQvBnz9N43\nauRe9KFecH1KRXe+pw8+cLpWAAaKQAUADssak6X/XL5FTy79c314x+0qWf2sXniBAetAMiFQAUAC\nMMZodckq7fqzX+uyu3+gb+4s0+LlTWppcbpmAPrD8XmoAABdZk+erZr/tlMP/+ov9MLrhZr9uR/p\nL/9ovg4ebNDLL6/Xhx96lTOlRQWmQbe1TFTVgeVhv+AbwNAiUAFAghmVPkr/6wt/p89dtVB/NKpc\nD/1sscbuGaXm5r+WdFzu1lJtUJ0yJJ3esEEVO3fqgW3bCFWAg+jyA4AE9dmCz+q9b+zVpFNv+8NU\nhgq0tjNMSVKGpKraWq1fu9bBmgIgUAFAApsyboquHjNP8keoqTqs0K/0zpDkbWwc6qoBCEKgAoAE\nN21amqTTkqSjmuZf6nJakis3d6irBSAIgQoAEty6dSuUn18h6bQOap3KldcZqk5LqsjP14p165yr\nIAACFQAkury86dq27QGVlz8lab3Moi/qq7ffpM9ckaY78m7Wn/w7A9IBp/EpPwBIcB6P5PFMV0FB\nhebNk24o9G3f+OGnNW7aEZX+9b/ptSceUV6ecbSewHBGoAKABOd2+26hqqp26nffPKyb/uFzuu7h\n3+v/ff0fNO8zaUNdPQCiyw8Aktq0Cbl691v/pVm3vKc7n1uiZ18463SVgGGJQAUASW7i6Il6/YFf\naOH80frG7oX682+dVEeH07UChhcCFQCkgFHpo/QfK17UV++6Wetdt+nOJR+qrc3pWgHDB4EKAFKE\ny7j0j196SlWLVun1625V8ef26dAhp2sFDA8RA5UxpswYU2qMWdXL/iL/MauCtn3Pfx/2HABA/Hzr\n1m/qn5Y+pWN3LdCN976sV15xukZA6uszUBljiiRZa+0O/3phmMMetda+JGli0P7VxpgDkmpjWlsA\nQL8su26Z/uMrG+UtW6Yv/cVGPf+80zUCUlukFqplklr8y4ckLQjeaYwpk/SGJFlrn7LW1vh3rbTW\nzrLWVseysgCA/pufN1//tXK7xt79Lf3Ff/wPffObUnu707UCUlOkQDVJ0smg9eyQ/XMlZfu7/R4K\n2p7l7yZ8SAAAx8yZMkevr/6NMhc8p5+cflB/8EWvWludrhWQemIxKL3JWrtX6myxkrX2eX83YbYx\n5o4YlAEAGKQrJl6h11a9qss+9boOFZXrplvO6+BBp2sFpJZIgapZUpZ/eZKkppD9TfJ1BUq+rsEb\njTGrjDGLg/bPjEVFAQCDlzUmS9vv26brCy9I5Z/TLXe06uWXna4VkDoiffXMJkklkqrlC0bbJMkY\nM9Fa2yppi6Qy/7GTJO2SL1i96d+WHTgnVGVlZeey2+2WO9z3KgAAYmbMiDHadO8mfeOX39Avvn67\nln71F/ruI7lavdrpmgGJxePxyOPxDOicPgOVtXavMabEGFMqqTlo0Pl2SXOttXXGmBZ/V1+WtfZJ\nqXOqBUk6EXRON8GBCgAwNNJcaXr6c0/r8QmP6x91ix57/hd6552rtWiR9Otf+47xeLq+OzDWf+v6\nvui5ZzmqnxfbgoAohDb0VFVVRTwn4pcjW2t7fNjWWjs3zP6Xgra9FHoOACAxGGP0yG2PKHd8rr7l\ndWvnGy/p/Sdu0xNPNOjJJ9frlVe8uuwyl+5fXaodz/5Qt/1GqjqwXCvWrdP0vLyoyna7penTG7R2\nra+czEktKrANum3fK6paHpsyACdEDFQAgNR03w33aUrGFC0392jcB3+juXMP6OLFKkkZ2rBhv85v\nvFXr21tVIel0/QZV7NypB7Ztiyrw1NU1aOHCp1VbWyXpuOzPSlWpOmXEsAzACQQqABjG7iq4S78s\n/6Vu+4M/0cWLr0nKkCQV6DGtb2/1r/m2VtXW6tE/W6v71r046PLWrl3vD1MZKtBabfCHqeAynlq7\nVhUvDr4MwAkEKgAY5kpyS3RDxmf1eme0kabqcNCaT4akg6826v77B1/W++97FQhtvZXhbWwcfAGA\nQwhUAAAVTM/Q66+eViDsHNU0da35nJb0qUW5qoii8Wj5cpc2bPA9cm9luHJzB18A4JBYTOwJAEhy\n69atUH5+hXyRRjqoR7UifaJ/zbe1Ij9fK9ati1k5B7VO5cqLeRmAEwhUAADl5U3Xtm0PqLz8KUlr\nlX/7t7Tv61O0bulifWaG9FR5eUwGiwfK+fznn5K0XmbRF1X5pUUxLQNwAl1+AAD//FDTVVBQoXnz\npHluq1dUpR8X/1iN10hfXDBHGxs3S1EOb6qtlQ4dkrwlY2TapNbrM1STNk2v5tTp1z9kIDqSF4EK\nACC3O3QSTyOpUpv2X6NlW5bpxJkTMSlnYo5UlONbfqdOyi2QRk1qkmr2xeTxAacQqAAAvVp67VIt\n27JMTyx8IuaPfXKjVHJG+pPyc3qh5gWdaz+n0emjY14OMBQYQwUAcERhobR3rzpD1DvH33G4RsDg\n0UIFADHiqffIU++RJM2bPk+VnkpJknuGW+4ZbsfqlaiKiqQf/ahrfXfjbt2Ye6NzFQKiQKACgBgh\nOA3MnDnS/v1Se7tvfc+RPc5WCIgCgQrAsEDrUeIZP16aNk16/33f+p6jBCokLwIVAEcNVdAhOCWm\noiLfOCpJ2n98vy50XNDItJHOVgoYBAIVAEcRdIa3wkKppkbSeGnGpBl69+N3VTi10OlqAQNGoALQ\nK7rJEG9FRdKTT0q63fclzXuO7CFQISkRqAD0iuCEeOtsofqMVDy1WHuO7NGfFv2p09UCBoxABSQp\nWo+QCqZOlUaOlNR6uYpzirXp3U1OVwkYFAIVEGMMskY8pWKQLiyUfnm0UEU5Rdp3bJ/ave1Kd/H2\nhOQyLH9jh+oFaSjKSZUyhqqcoSgjmd/YkPhS8ferqEj65WtFmjBqgqaNn6b3T7yvay+91ulqAQNi\nrLVDX6gxtrdyg9/wPPWezheOVHwRARB/VaZKklRhKxyuSfIyVUa2In7vFZs2Scsq/l32vXv0h1v+\nUJ+f9Xndd8N9cSsPGChjjKy1pq9jEq6FiuAEAMNLUZGkI0WSpJIc3yf9CFRINnw5MgDAUfn5ks5m\nq7lZKs4p5itokJQIVAAAR7lckqa8pZoaqSinSDVHa+S1XqerBQwIgQoA4LypNdq7V8oak6Xssdk6\n0HTA6RoBA0KgAgA4L2evb4JPdY2jApIJgQoA4Dx/C5XEOCokJwIVAMB5l+zXwYPSuXO+QLX7yG6n\nawQMCIEKAOC8Eec1a5b0zjtdLVROzJMIDBaBCgCQEIqKfF+UfGnGpRo/arzqWuqcrhLQbwQqAEBC\nKCxUt3FUuxvp9kPyIFABABJCoIVKkoqnMjAdyYVABQBICDfcIO3bJ3V0SCW5JdpzlECF5EGgAgAk\nhMxMafJkqbaWgelIPgQqAEDCCIyjyhmXozSTpo/aPnK6SkC/EKgAAAkjMI7KGOPr9mMcFZIEgQoA\nkDC6fdKPgelIIgQqAEDC6PZJP2ZMRxKJGKiMMWXGmFJjzKpe9hf5j1nV33MAAAjnssukixelI0dE\nlx+SSp/K01HtAAARMklEQVSByhhTJMlaa3f41wvDHPaotfYlSRONMYX9PAcAgB6M6WqlunzC5brY\ncVFHPjnidLWAiCK1UC2T1OJfPiRpQfBOY0yZpDckyVr7lLW2JtI5AAD0JTCOyhjTOX0CkOgiBapJ\nkk4GrWeH7J8rKdvf7fdQP88BAKBXjKNCMorFoPQma+1eqbPFilnYAACDFvxJv5IcxlEhOaRH2N8s\nKcu/PElSU8j+Jvm69SRfN99c/31f50iSKisrO5fdbrfcbnc/qwwASGVXXSU1NkqffOJroXpw64NO\nVwnDjMfjkcfjGdA5kQLVJkklkqolzZS0TZKMMROtta2Stkgq8x87Sb7xVIck3Rh6TqjgQAUAQEB6\nunTdddJbb0m33jpTbefb9PHpj3VJxiVOVw3DRGhDT1VVVcRz+uzyC+rKK5XU7B90Lknb/fvrJLX4\nu/qyrLU/CRwT5hwAAPqlsLBrxnQGpiMZRGqhkrX2+TDb5obZ/1Jf5wAA0F9FRdKuXb7lQKC6q+Au\nZysF9IGZ0gEACSfQQiX5A9VRWqiQ2CK2UAEAhh9PvUeeeo8kad70ear0VEqS3DPccs9wx72Mm+a4\n9d57vlnTS3JK9FfVfxWTMoF4IVABAHqIZXAabBnTp0vvvSddd/0sfXzmYzWfbVbmmMy41gkYLLr8\nAAAJqajINx+Vy7hUOLVQe4/udbpKQK8IVACAhNRtHNXUYu1uZMZ0JC4CFQAgIQVaqCSpJLeEgelI\naAQqAEBCCrRQWSvmokLCI1ABABLSJZdI48ZJ9fXS7Mmz9fu236vtfJvT1QLCIlABABJW4IuS013p\nmjNljmqO8uUbSEwEKgBAwioq6j4wnW4/JCoCFQAgYQVaqCTGUSGxEagAAAmrWwtVTrF2H2HqBCQm\nAhUAIGHNmCG1tUknTkjXXnqt6prrdPrCaaerBfRAoAIAJCyXq2v6hJFpI3XNJddo37F9TlcL6IFA\nBQBIaKHjqOj2QyIiUAEAElrwOKqSnBIGpiMhEagAAAmNT/ohGRCoAAAJ7ZprpLo66cwZ6fop1+uD\npg90rv2c09UCuiFQAQAS2siR0uzZ0ttvS6PTR+vK7Cv19rG3na4W0A2BCgCQ8ELno6LbD4mGQAUA\nSHiMo0KiI1ABABIeM6Yj0RGoAAAJ74YbfGOoOjqkG6bcoHc/flcXOi44XS2gE4EKAJDwJkyQcnKk\nDz6QMkZmKC8zT+9+/K7T1QI6EagAAEmhx4zpjXT7IXEQqAAASYEZ05HICFQAgKTQ45N+RwlUSBwE\nKgBAUgi0UFkrFU4t1L5j+9TubXe6WoAkAhUAIEnk5Egul3T4sDRh1ARNGz9NvzvxO6erBUgiUAEA\nkoQxvm6/znFUuYyjQuIgUAEAkkZRUdA4qqnMmI7EQaACACSN4BYqZkxHIiFQAQCSRrcWqpxi1Ryt\nkdd6na0UIAIVACCJFBRIx49LLS1S5phMXTL2Eh1oOuB0tQACFQAgeaSlSXPmSG+95VsvzmEcFRID\ngQoAkFS6fdIvp4RxVEgIBCoAQFIJHUdFCxUSQcRAZYwpM8aUGmNW9bL/e/77VX1tAwAgFoJbqIpy\nirTnyB5Za52tFIa9PgOVMaZIkrXW7vCvF4Y5bLUx5oCk2gjbAACI2nXXSR98IJ0/L12acanGjxqv\nQ82HnK4WhrlILVTLJLX4lw9JWhDmmJXW2lnW2uoI2wAAiNqYMdLMmdL+/b71khxmTIfzIgWqSZJO\nBq1nhzkmy98l+FCEbQAAxETgi5IlxlEhMUQ9KN1a+7y/SzDbGHNHb9sAAIiVwsLuA9P5pB+cFilQ\nNUvK8i9PktQUvNMYs8oYs9i/2iRpZrhtsaosAABS9xaqQJcfA9PhpPQI+zdJKpFULV8w2iZJxpiJ\n1tpW+Qadv+k/Ntu/PyvMth4qKys7l91ut9xu92DqDwAYhgoLfZN7er1SzvgcjUgboY/aPtIVE69w\numpIAR6PRx6PZ0DnmEiJ3hizUlKdpDxr7fP+bbustXP9y2X+Q/OstU/1ti3kMS1/SQAYClWmSpJU\nYSscrglibfp0accO39fRfOFfvqBVxat09+y7na4WUpAxRtZa09cxkVqoFAhRIdvmBi2/FGZ/j20A\nAMRSYBxVQYFUPLVYuxt3E6jgGGZKBwAkpW7jqHJLtOcon/SDcwhUAICkFPpJP6ZOgJMIVACApBTc\nQnX5hMt1seOiGj9pdLZSGLYIVACApHTFFdK5c9KxY75BwyW5zJgO5xCoAABJyZjuX5RcPJVuPziH\nQAUASFqMo0KiIFABAJJW6Cf9+AoaOIVABQBIWsEtVHmT8vTJ+U90/PRxZyuFYYlABQBIWrNnSx99\nJJ065RuYXpxTrL1H9jpdLQxDBCoAQNIaMUK65hpp3z7fenFOMd1+cASBCgCQ1LqNo8ph6gQ4g0AF\nAEhqRUV80g/OI1ABAJJa8FxUs7Jn6cSZEzp59qSzlcKwQ6ACACS1OXOk/fulixcll3GpcGohA9Mx\n5AhUAICkNm6cdPnl0vvv+9bp9oMTCFQAgKTXYxzVUQIVhhaBCgCQ9ILHUZXklGh3I1MnYGgRqAAA\nSS+4heqqyVfp8CeH1Xa+zdlKYVghUAEAkl6ghcpaKd2VrjlT5qjmaI3T1cIwQqACACS9KVOk0aOl\nDz/0rRdPLabbD0OKQAUASAndxlHlljAwHUOKQAUASAnMmA4nEagAACmhsLArUF1zyTWqa67T6Qun\nna0Uhg0CFQAgJQR/SfLItJG69tJr9daxt5ytFIYNAhUAICXMnCk1N0tNTb714ql0+2HoEKgAACnB\n5ZJuuEF6y98oxTgqDCUCFQAgZQSPoyrOKdbuI0ydgKFBoAIApIzgcVTXT7leB5oO6Fz7OWcrhWGB\nQAUASBnBLVSj00fryuwr9faxt52tFIYFAhUAIGVce61UWyudPetbp9sPQ4VABQBIGaNGSVdeKb3z\njm+9JKeEgekYEgQqAEBKCR5HxSf9MFQIVACAlBI8juqGqTfo3Y/f1YWOC85WCimPQAUASCnBLVRj\nR4zVzMyZ2n98v7OVQsojUAEAUsoNN0j79kkdHb51uv0wFAhUAICUMmmSdOml0sGDvnUCFYYCgQoA\nkHKYMR1DjUAFAEg5weOoiqYW6e3jb6vd2+5spZDSIgYqY0yZMabUGLOql/3f89+v6u85AADEU3AL\n1fhR43XZhMv0uxO/c7ZSSGl9BipjTJEka63d4V8vDHPYamPMAUm1AzgHAIC4KSryBSprfeuMo0K8\npUfYv0zSVv/yIUkLJNWEHLPSWvuTAZ4DAEDcXLjQoNbW9br1Vq9mznQp69NZ2vyPf6ta/bNc06Zp\nxbp1mp6XF1UZdXUNWrt2vQ4f9mraNJfuX12qHc/+UN7Dh2NWRmg5kya2qMA2aGxba9zKiOdzSWWR\nAtUkSSeD1rPDHJNljCmVVGytfbKf5wAAEBd1dQ26886ndeFClV57LUOvvbZfZRtv0b+1tylD7+u0\npIqdO/XAtm2DDgl1dQ1auPBp1dZWScqQtF/nN96q9e2typBiUkbPco5rkUpVqbo4lhG/55LqIgWq\niKy1z0uSMWahP1gBAOCYtWvXB4UDqUCP6f+0t/nXfFuramu1+N4/Us5X1gyqjP/6cbXqan/QrYxA\nAIlVGaHlFGitNvjDVLzK6Ou5PLV2rSpefHHQ5aS6SIGqWVKWf3mSpKbgnf5B503+Lr8mSXmRzgmo\nrKzsXHa73XK73QOrOQAAYbz+ulfqjAPSVB0OWvPJkHSxab9+2+gZVBkfHTkX9zJCyxmKMvoqp+G9\n1wddRrLxeDzyeDwDOidSoNokqURStaSZkrZJkjFmorW2Vb6B6G/6j832739T0o2h54QKDlQAAMTK\npz7l0sGDpxUICUc1TV1rPqclzbvtS6p4Yv2gyljeWKUNG+JbRmg5Q1GG1PtzmX71pwZdRrIJbeip\nqqqKeE6fn/Kz1u6VJH9XXrO1NjC4fLt/f7WkhcaYMkknrLU1gWPCnAMAQNytW7dC+fkV8sUA6aAe\n1Yr0if41/5ig/HytWLcuocsILeeg1qlceXEtQ4rfc0l1xgY+UzqUhRpjnSgXwPBTZXx/WVbYCodr\ngqEU+NRaY6NXublBn1prbJQrNzemn/KLZxmh5Uyc4P+U3ydtcSsjns8lWRljZK01fR5DoAKQyghU\nAKLVn0DFV88AAABEiUAFAAAQJQIVAABAlAhUAAAAUSJQAQAARIlABQAAECUCFQAAQJQIVAAAAFEi\nUAEAAESJQAUAABAlAhUAAECUCFQAAABRIlABAABEiUAFAAAQJQIVAABAlAhUAAAAUSJQAQAARIlA\nBQAAECUCFQAAQJQIVAAAAFEiUAEAAESJQAUAABAlAhUAAECUCFQAAABRIlABAABEiUAFAAAQJQIV\nAABAlAhUAAAAUSJQAQAARIlABQAAECUCFQAAQJQIVAAAAFEiUAEAAESJQAUAABAlAhUAAECUIgYq\nY0yZMabUGLMqwnEPBS1/z3/f5zkAAACpoM9AZYwpkmSttTv864W9HFcqaUHQptXGmAOSamNVUQAA\ngEQVqYVqmaQW//IhdQ9NfVlprZ1lra0edM0AAACSRKRANUnSyaD17NADjDFF/hYsE7Q5y99N+FDo\n8eidx+NxugoJh2sSHtclPK5LeFyXnrgm4XFdBi8Wg9IzQzdYa5/3h6xsY8wdMShjWOAXuSeuSXhc\nl/C4LuFxXXrimoTHdRm8SIGqWVKWf3mSpKbgnf7WqUC3nvVvW2WMWezf1iRpZozqCgAAkJDSI+zf\nJKlEUrV8wWibJBljJlprWyXNNMbkydcVmO0ftF4r6U3/+dmBcwAAAFKVsdb2fYAxKyXVScqz1j7v\n37bLWjs36JhVkh6WtMRaW2OMKfPvyrPWPhXmMfsuFAAAIIFYa01f+yMGKgAAAPSNmdIBAACi5Fig\nCsymHmb7sJ5qIfS6+Af5r+rteg0XYa5Lv2bwB9DTcH+dRXi8rvY0kPdgRwKV/4dVFmZ76Izrw0ro\ndfFfj23W2ufk+wDAsJyCIsx16dcM/sNF0IvgSqfrkkiMMUX+a8ObQ5Dh/jobDn+48roazkDfgx0J\nVP7KHXKi7EQW5rrMVNcL3yEN0ykowlyXwc7gn3L8L4KH/C+CdbwIdvOotfYlSRO5LugNf7h24nW1\npwG9ByfMGKpeZlwf1qy1zwU+WSmpWF3TUQxHwb8XEWfwH2Ye99/PtNbWOFqTBOH/pPEbkmStfYrr\n4sPrbFj84erD62qIgb4HJ0ygUpgZ1+Hjb4XYzZsCQllr90o6ZIw5qZCJd4e5ufLNjVfEeKFueJ0N\nwR+uiKS/78GRJvYcbOGr5J85PchJa+1Pejm+x4zrqWig1yVIqbX20ThVy3H9vC7B+/ucwX84McZM\nlHRQ0kpJzxlj9lhr652tVcJostbuNcYsMMaU+bv/UlqY/0tGvuvwk+HyOjtY/OHK62of+vUeHJdA\n5e+LjiS4ybnHjOup+Es9iOsiY8yqwOSoxpjSwIDBVDKI6xJ2Bv9U1debpKTVkp6x1rYZY1okLZH0\npAPVHHIRrkuTusbdtUi6UVLKB6oI/5eGxetsOP38oy2l/3Dth2H1utpfA3kPjkugisQ/vqHEGLPS\n/0XKL/m3r5I00Yk6JYLQ6+IfLPk9Y8y35WuqX+JsDZ0R5vdlrzGmxH99mlP9TSHCm6S11rb5F6qN\nMcNm/EeE67JFXZ8MnSRpV/xrlNiG8+tspD/ahsMfrpEMt9fV/hjoezAzpQNJzj9GqFZSVtBYkGHP\nP41Es6Qbh3nLA/rgf9PcJN/vSqZ8X6FW3fdZQE8EKgAAgCgl0qf8AAAAkhKBCgAAIEoEKgAAgCgR\nqAAAAKJEoAIAAIgSgQoAACBKBCoAAIAo/X90KDrXVYfXewAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x8a6c4d0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "CI_best_alpha = gd.plot_cindex(1047, pylab.logspace(-6,0,20))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "-5.8170570770375898"
      ]
     },
     "execution_count": 66,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "log(CI_best_alpha)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This is much longer that tuning_alpha method. The other point is that the 2 values\n",
    "found differe slightly from -4.9 to -5.8 In this case, the CI values \n",
    "from -14 to -6 are pretty flat and may not be so precise as compare to the other\n",
    "method.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Coming back on the previous value of 0.000701, let re-run the elastic net with this value:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAmkAAAFFCAYAAAC393oCAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nrkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x8a6ca90>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "scores = gd.elastic_net(1047, alpha=0.00701,n_folds=10, show=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can also now look at the weights for that model:\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "ename": "RuntimeError",
     "evalue": "dvipng was not able to process the following file:\n/home/cokelaer/.cache/matplotlib/tex.cache/1b72844dd7a94ad6e211af28a517e002.dvi\nHere is the full report generated by dvipng: \n\n",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mRuntimeError\u001b[0m                              Traceback (most recent call last)",
      "\u001b[1;32m/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/IPython/core/formatters.pyc\u001b[0m in \u001b[0;36m__call__\u001b[1;34m(self, obj)\u001b[0m\n\u001b[0;32m    337\u001b[0m                 \u001b[1;32mpass\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    338\u001b[0m             \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 339\u001b[1;33m                 \u001b[1;32mreturn\u001b[0m \u001b[0mprinter\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mobj\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    340\u001b[0m             \u001b[1;31m# Finally look for special method names\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    341\u001b[0m             \u001b[0mmethod\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0m_safe_get_formatter_method\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mobj\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mprint_method\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/IPython/core/pylabtools.pyc\u001b[0m in \u001b[0;36m<lambda>\u001b[1;34m(fig)\u001b[0m\n\u001b[0;32m    224\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    225\u001b[0m     \u001b[1;32mif\u001b[0m \u001b[1;34m'png'\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mformats\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 226\u001b[1;33m         \u001b[0mpng_formatter\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfor_type\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mFigure\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;32mlambda\u001b[0m \u001b[0mfig\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mprint_figure\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfig\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'png'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    227\u001b[0m     \u001b[1;32mif\u001b[0m \u001b[1;34m'retina'\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mformats\u001b[0m \u001b[1;32mor\u001b[0m \u001b[1;34m'png2x'\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mformats\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    228\u001b[0m         \u001b[0mpng_formatter\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfor_type\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mFigure\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;32mlambda\u001b[0m \u001b[0mfig\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mretina_figure\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfig\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/IPython/core/pylabtools.pyc\u001b[0m in \u001b[0;36mprint_figure\u001b[1;34m(fig, fmt, bbox_inches, **kwargs)\u001b[0m\n\u001b[0;32m    115\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    116\u001b[0m     \u001b[0mbytes_io\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mBytesIO\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 117\u001b[1;33m     \u001b[0mfig\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcanvas\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mprint_figure\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mbytes_io\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkw\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    118\u001b[0m     \u001b[0mdata\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mbytes_io\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mgetvalue\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    119\u001b[0m     \u001b[1;32mif\u001b[0m \u001b[0mfmt\u001b[0m \u001b[1;33m==\u001b[0m \u001b[1;34m'svg'\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/matplotlib/backend_bases.pyc\u001b[0m in \u001b[0;36mprint_figure\u001b[1;34m(self, filename, dpi, facecolor, edgecolor, orientation, format, **kwargs)\u001b[0m\n\u001b[0;32m   2178\u001b[0m                     \u001b[0morientation\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0morientation\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   2179\u001b[0m                     \u001b[0mdryrun\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mTrue\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 2180\u001b[1;33m                     **kwargs)\n\u001b[0m\u001b[0;32m   2181\u001b[0m                 \u001b[0mrenderer\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfigure\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_cachedRenderer\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   2182\u001b[0m                 \u001b[0mbbox_inches\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfigure\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_tightbbox\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mrenderer\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/matplotlib/backends/backend_agg.pyc\u001b[0m in \u001b[0;36mprint_png\u001b[1;34m(self, filename_or_obj, *args, **kwargs)\u001b[0m\n\u001b[0;32m    525\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    526\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0mprint_png\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfilename_or_obj\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 527\u001b[1;33m         \u001b[0mFigureCanvasAgg\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdraw\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    528\u001b[0m         \u001b[0mrenderer\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_renderer\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    529\u001b[0m         \u001b[0moriginal_dpi\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mrenderer\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdpi\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/matplotlib/backends/backend_agg.pyc\u001b[0m in \u001b[0;36mdraw\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    472\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    473\u001b[0m         \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 474\u001b[1;33m             \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfigure\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdraw\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrenderer\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    475\u001b[0m         \u001b[1;32mfinally\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    476\u001b[0m             \u001b[0mRendererAgg\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mlock\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrelease\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/matplotlib/artist.pyc\u001b[0m in \u001b[0;36mdraw_wrapper\u001b[1;34m(artist, renderer, *args, **kwargs)\u001b[0m\n\u001b[0;32m     59\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0mdraw_wrapper\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0martist\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mrenderer\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     60\u001b[0m         \u001b[0mbefore\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0martist\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mrenderer\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 61\u001b[1;33m         \u001b[0mdraw\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0martist\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mrenderer\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     62\u001b[0m         \u001b[0mafter\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0martist\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mrenderer\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     63\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/matplotlib/figure.pyc\u001b[0m in \u001b[0;36mdraw\u001b[1;34m(self, renderer)\u001b[0m\n\u001b[0;32m   1157\u001b[0m         \u001b[0mdsu\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msort\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mitemgetter\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1158\u001b[0m         \u001b[1;32mfor\u001b[0m \u001b[0mzorder\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0ma\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfunc\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0margs\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mdsu\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1159\u001b[1;33m             \u001b[0mfunc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1160\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1161\u001b[0m         \u001b[0mrenderer\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mclose_group\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'figure'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/matplotlib/artist.pyc\u001b[0m in \u001b[0;36mdraw_wrapper\u001b[1;34m(artist, renderer, *args, **kwargs)\u001b[0m\n\u001b[0;32m     59\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0mdraw_wrapper\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0martist\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mrenderer\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     60\u001b[0m         \u001b[0mbefore\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0martist\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mrenderer\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 61\u001b[1;33m         \u001b[0mdraw\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0martist\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mrenderer\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     62\u001b[0m         \u001b[0mafter\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0martist\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mrenderer\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     63\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/matplotlib/axes/_base.pyc\u001b[0m in \u001b[0;36mdraw\u001b[1;34m(self, renderer, inframe)\u001b[0m\n\u001b[0;32m   2322\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   2323\u001b[0m         \u001b[1;32mfor\u001b[0m \u001b[0mzorder\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0ma\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mdsu\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 2324\u001b[1;33m             \u001b[0ma\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdraw\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mrenderer\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   2325\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   2326\u001b[0m         \u001b[0mrenderer\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mclose_group\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'axes'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/matplotlib/artist.pyc\u001b[0m in \u001b[0;36mdraw_wrapper\u001b[1;34m(artist, renderer, *args, **kwargs)\u001b[0m\n\u001b[0;32m     59\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0mdraw_wrapper\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0martist\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mrenderer\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     60\u001b[0m         \u001b[0mbefore\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0martist\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mrenderer\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 61\u001b[1;33m         \u001b[0mdraw\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0martist\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mrenderer\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     62\u001b[0m         \u001b[0mafter\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0martist\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mrenderer\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     63\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/matplotlib/axis.pyc\u001b[0m in \u001b[0;36mdraw\u001b[1;34m(self, renderer, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1109\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1110\u001b[0m         \u001b[1;32mfor\u001b[0m \u001b[0mtick\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mticks_to_draw\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1111\u001b[1;33m             \u001b[0mtick\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdraw\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mrenderer\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1112\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1113\u001b[0m         \u001b[1;31m# scale up the axis label box to also find the neighbors, not\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/matplotlib/artist.pyc\u001b[0m in \u001b[0;36mdraw_wrapper\u001b[1;34m(artist, renderer, *args, **kwargs)\u001b[0m\n\u001b[0;32m     59\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0mdraw_wrapper\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0martist\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mrenderer\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     60\u001b[0m         \u001b[0mbefore\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0martist\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mrenderer\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 61\u001b[1;33m         \u001b[0mdraw\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0martist\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mrenderer\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     62\u001b[0m         \u001b[0mafter\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0martist\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mrenderer\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     63\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/matplotlib/axis.pyc\u001b[0m in \u001b[0;36mdraw\u001b[1;34m(self, renderer)\u001b[0m\n\u001b[0;32m    250\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    251\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mlabel1On\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 252\u001b[1;33m             \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mlabel1\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdraw\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mrenderer\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    253\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mlabel2On\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    254\u001b[0m             \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mlabel2\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdraw\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mrenderer\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/matplotlib/artist.pyc\u001b[0m in \u001b[0;36mdraw_wrapper\u001b[1;34m(artist, renderer, *args, **kwargs)\u001b[0m\n\u001b[0;32m     59\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0mdraw_wrapper\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0martist\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mrenderer\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     60\u001b[0m         \u001b[0mbefore\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0martist\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mrenderer\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 61\u001b[1;33m         \u001b[0mdraw\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0martist\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mrenderer\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     62\u001b[0m         \u001b[0mafter\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0martist\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mrenderer\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     63\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/matplotlib/text.pyc\u001b[0m in \u001b[0;36mdraw\u001b[1;34m(self, renderer)\u001b[0m\n\u001b[0;32m    790\u001b[0m                     textrenderer.draw_tex(gc, x, y, clean_line,\n\u001b[0;32m    791\u001b[0m                                           \u001b[0mtextobj\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_fontproperties\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mangle\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 792\u001b[1;33m                                           mtext=mtext)\n\u001b[0m\u001b[0;32m    793\u001b[0m                 \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    794\u001b[0m                     textrenderer.draw_text(gc, x, y, clean_line,\n",
      "\u001b[1;32m/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/matplotlib/backends/backend_agg.pyc\u001b[0m in \u001b[0;36mdraw_tex\u001b[1;34m(self, gc, x, y, s, prop, angle, ismath, mtext)\u001b[0m\n\u001b[0;32m    251\u001b[0m         \u001b[0mtexmanager\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_texmanager\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    252\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 253\u001b[1;33m         \u001b[0mZ\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mtexmanager\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_grey\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0ms\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0msize\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdpi\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    254\u001b[0m         \u001b[0mZ\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0marray\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mZ\u001b[0m \u001b[1;33m*\u001b[0m \u001b[1;36m255.0\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0muint8\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    255\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/matplotlib/texmanager.pyc\u001b[0m in \u001b[0;36mget_grey\u001b[1;34m(self, tex, fontsize, dpi)\u001b[0m\n\u001b[0;32m    581\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    582\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0malpha\u001b[0m \u001b[1;32mis\u001b[0m \u001b[0mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 583\u001b[1;33m             \u001b[0mpngfile\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mmake_png\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtex\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfontsize\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdpi\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    584\u001b[0m             \u001b[0mX\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mread_png\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mos\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpath\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtexcache\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mpngfile\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    585\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/matplotlib/texmanager.pyc\u001b[0m in \u001b[0;36mmake_png\u001b[1;34m(self, tex, fontsize, dpi)\u001b[0m\n\u001b[0;32m    522\u001b[0m                     \u001b[1;34m'dvipng was not able to process the following '\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    523\u001b[0m                     \u001b[1;34m'file:\\n%s\\nHere is the full report generated by '\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 524\u001b[1;33m                     'dvipng: \\n\\n' % dvifile + report)\n\u001b[0m\u001b[0;32m    525\u001b[0m             \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    526\u001b[0m                 \u001b[0mmpl\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mverbose\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mreport\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mreport\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'debug'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mRuntimeError\u001b[0m: dvipng was not able to process the following file:\n/home/cokelaer/.cache/matplotlib/tex.cache/1b72844dd7a94ad6e211af28a517e002.dvi\nHere is the full report generated by dvipng: \n\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "<matplotlib.figure.Figure at 0x8a8f9d0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "ename": "KeyboardInterrupt",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "Traceback (most recent call last):\n",
      "  File \"/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/ipykernel/ipkernel.py\", line 175, in do_execute\n    shell.run_cell(code, store_history=store_history, silent=silent)\n",
      "  File \"/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/IPython/core/interactiveshell.py\", line 2729, in run_cell\n    self.events.trigger('post_execute')\n",
      "  File \"/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/IPython/core/events.py\", line 74, in trigger\n    func(*args, **kwargs)\n",
      "  File \"/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/ipykernel/pylab/backend_inline.py\", line 113, in flush_figures\n    return show(True)\n",
      "  File \"/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/ipykernel/pylab/backend_inline.py\", line 36, in show\n    display(figure_manager.canvas.figure)\n",
      "  File \"/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/IPython/core/display.py\", line 158, in display\n    format_dict, md_dict = format(obj, include=include, exclude=exclude)\n",
      "  File \"/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/IPython/core/formatters.py\", line 177, in format\n    data = formatter(obj)\n",
      "  File \"<decorator-gen-9>\", line 2, in __call__\n",
      "  File \"/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/IPython/core/formatters.py\", line 222, in catch_format_error\n    r = method(self, *args, **kwargs)\n",
      "  File \"/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/IPython/core/formatters.py\", line 339, in __call__\n    return printer(obj)\n",
      "  File \"/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/IPython/core/pylabtools.py\", line 226, in <lambda>\n    png_formatter.for_type(Figure, lambda fig: print_figure(fig, 'png', **kwargs))\n",
      "  File \"/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/IPython/core/pylabtools.py\", line 117, in print_figure\n    fig.canvas.print_figure(bytes_io, **kw)\n",
      "  File \"/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/matplotlib/backend_bases.py\", line 2182, in print_figure\n    bbox_inches = self.figure.get_tightbbox(renderer)\n",
      "  File \"/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/matplotlib/figure.py\", line 1708, in get_tightbbox\n    bb.append(ax.get_tightbbox(renderer))\n",
      "  File \"/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/matplotlib/axes/_base.py\", line 3679, in get_tightbbox\n    bb_xaxis = self.xaxis.get_tightbbox(renderer)\n",
      "  File \"/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/matplotlib/axis.py\", line 1075, in get_tightbbox\n    renderer)\n",
      "  File \"/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/matplotlib/axis.py\", line 1058, in _get_tick_bboxes\n    extent = tick.label1.get_window_extent(renderer)\n",
      "  File \"/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/matplotlib/text.py\", line 961, in get_window_extent\n    bbox, info, descent = self._get_layout(self._renderer)\n",
      "  File \"/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/matplotlib/text.py\", line 352, in _get_layout\n    ismath=False)\n",
      "  File \"/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/matplotlib/backends/backend_agg.py\", line 229, in get_text_width_height_descent\n    renderer=self)\n",
      "  File \"/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/matplotlib/texmanager.py\", line 678, in get_text_width_height_descent\n    page = next(iter(dvi))\n",
      "  File \"/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/matplotlib/dviread.py\", line 89, in __iter__\n    have_page = self._read()\n",
      "  File \"/home/cokelaer/Work/virtualenv/lib/python2.7/site-packages/matplotlib/dviread.py\", line 149, in _read\n    byte = ord(self.file.read(1)[0])\n",
      "KeyboardInterrupt\n"
     ]
    }
   ],
   "source": [
    "weights = gd.plot_weight(1047, alpha=0.00701)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "# Here are the largest weigths (in absolute value)\n",
    "weights.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "drugs = gd.ic50.drugIds"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.012742749857031322"
      ]
     },
     "execution_count": 22,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "res = gd.tune_alpha(drugs[0], alphas=logspace(-6,0,20), n_folds=4, plot=False)\n",
    "res[3]"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}