log-loss function plotting is not working properly

plotting-error.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAhEAAAGHCAYAAAAOSQDRAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x10522ac90>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#Visualize Log Loss when True value = 1\n",
    "#y-axis is log loss, x-axis is probabilty that label = 1\n",
    "#As you can see Log Loss increases rapidly as we approach 0\n",
    "#But increases slowly as our predicted probability gets closer to 1\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "from sklearn.metrics import log_loss\n",
    "\n",
    "x = [i*.0001 for i in range(1,10000)] # 10000\n",
    "y = [log_loss([0,1 if i > 0 else 0],[[0.0001, 0.9999],[1-(i*.0001), i*.0001]],eps=1e-15) for i in range(1,10000,1)]\n",
    "\n",
    "plt.plot(x, y)\n",
    "plt.axis([-.05, 1.1, -.8, 10])\n",
    "plt.title(\"Log Loss when true label = 1\")\n",
    "plt.xlabel(\"predicted probability\")\n",
    "plt.ylabel(\"log loss\")\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "ename": "ValueError",
     "evalue": "y_true contains only one label (1). Please provide the true labels explicitly through the labels argument.",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mValueError\u001b[0m                       Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-2-4b3d43fb690a>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0mx\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0;36m.0001\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mi\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mrange\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m10000\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0my\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mlog_loss\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0;36m.0001\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m-\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0;36m.0001\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0meps\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m1e-15\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mi\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mrange\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m10000\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      3\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0mplt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mplot\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m \u001b[0mplt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0maxis\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m-\u001b[0m\u001b[0;36m.05\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m1.1\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m-\u001b[0m\u001b[0;36m.8\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m10\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/Users/Natsume/miniconda2/envs/ml/lib/python2.7/site-packages/sklearn/metrics/classification.pyc\u001b[0m in \u001b[0;36mlog_loss\u001b[0;34m(y_true, y_pred, eps, normalize, sample_weight, labels)\u001b[0m\n\u001b[1;32m   1620\u001b[0m             raise ValueError('y_true contains only one label ({0}). Please '\n\u001b[1;32m   1621\u001b[0m                              \u001b[0;34m'provide the true labels explicitly through the '\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1622\u001b[0;31m                              'labels argument.'.format(lb.classes_[0]))\n\u001b[0m\u001b[1;32m   1623\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1624\u001b[0m             raise ValueError('The labels array needs to contain at least two '\n",
      "\u001b[0;31mValueError\u001b[0m: y_true contains only one label (1). Please provide the true labels explicitly through the labels argument."
     ]
    }
   ],
   "source": [
    "x = [i*.0001 for i in range(1,10000)]\n",
    "y = [log_loss([1],[[i*.0001,1-(i*.0001)]],eps=1e-15) for i in range(1,10000,1)]\n",
    "\n",
    "plt.plot(x, y)\n",
    "plt.axis([-.05, 1.1, -.8, 10])\n",
    "plt.title(\"Log Loss when true label = 1\")\n",
    "plt.xlabel(\"predicted probability\")\n",
    "plt.ylabel(\"log loss\")\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "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": "2.7.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}