sklearn_digit_recognition.ipynb

sklearn_digit_recognition.ipynb

{
 "metadata": {
  "name": "sklearn_digit_recognition"
 }, 
 "name": "sklearn_digit_recognition", 
 "nbformat": 2, 
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "code", 
     "collapsed": true, 
     "input": "from sklearn.datasets import load_digits\ndigits = load_digits()", 
     "language": "python", 
     "outputs": [], 
     "prompt_number": 1
    }, 
    {
     "cell_type": "code", 
     "collapsed": false, 
     "input": "X, y = digits.data, digits.target\n\nprint(\"data shape: %r, target shape: %r\" % (X.shape, y.shape))\nprint(\"labels: %r\" % list(np.unique(y)))", 
     "language": "python", 
     "outputs": [
      {
       "output_type": "stream", 
       "stream": "stdout", 
       "text": "data shape: (1797, 64), target shape: (1797,)\nlabels: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]"
      }
     ], 
     "prompt_number": 2
    }, 
    {
     "cell_type": "code", 
     "collapsed": true, 
     "input": "def plot_gallery(data, labels, shape, interpolation='nearest'):\n    f,ax = plt.subplots(1,5,figsize=(16,5))\n    for i in range(data.shape[0]):\n        ax[i].imshow(data[i].reshape(shape), interpolation=interpolation, cmap=plt.cm.gray_r)\n        ax[i].set_title(labels[i])\n        ax[i].set_xticks(()), ax[i].set_yticks(())", 
     "language": "python", 
     "outputs": [], 
     "prompt_number": 3
    }, 
    {
     "cell_type": "code", 
     "collapsed": false, 
     "input": "subsample = np.random.permutation(X.shape[0])[:5]\nimages = X[subsample]\nlabels = ['True label: %d' % l for l in y[subsample]]\nplot_gallery(images, labels, shape=(8, 8))", 
     "language": "python", 
     "outputs": [
      {
       "output_type": "display_data", 
       "png": "iVBORw0KGgoAAAANSUhEUgAAA4sAAAC3CAYAAAC7Q8soAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAEHxJREFUeJzt3W1oXXcdB/DfTeNYm6a57dZhsbS3U6rQsXQPakW3prJq\nGUzj1o1t3TQVrI9gBBHBUWNBxU3kquCLIS5Thg5hS1nZYNgtNesYY9pk+DCk1VRtfZjQtJXazTbH\nF7L04d9safpv7u29n8+rpuee7zk393fPOd/cm5tSURRFAAAAwElaar0DAAAA1B9lEQAAgISyCAAA\nQEJZBAAAIKEsAgAAkFAWAQAASCiL09Df3x/XXXfdlG7b19cXd99997S2cy7rwrkw4zQy802jM+M0\nOjM+cy7osjh37txob2+P9vb2aGlpiTlz5kx8/dOf/rTWuxcREaVSacbWHRgYiBUrVsS8efNixYoV\nsXXr1mlvm/pgxk947rnnYu3atXHJJZfEZZddFrfddlv8/e9/n/a2qT3zfaojR47EZz7zmVi4cGGU\ny+VYvXr1tLdNfTDjJziGNyYzfsJDDz00cd/b29ujra0tWlpaYteuXdPefj24oMviv//97zh8+HAc\nPnw4li5dGtu2bZv4+o477pi43bFjx2q2j0VRzMi6//znP2PDhg3xne98Jw4dOhT33Xdf3HnnnfGv\nf/1r2tun9sz4CWNjY/GpT30q9u7dG3v37o329vbYuHHjtLdN7ZnvU23atCnGxsbipZdeigMHDkS1\nWp32tqkPZvwEx/DGZMZP2LBhw8R9P3z4cPzgBz+It771rXHVVVdNe/v14IIui5MZHByMxYsXx733\n3huLFi2Kj3/84/Hggw8mL1e3tLTEH//4x4iIeOWVV+KLX/xiLF26NN785jfHpz/96Th69OiUtvf5\nz38+lixZEh0dHXHttdfGM888M7GsVCrF0aNH4/bbb4958+bFNddcEy+++OLE8v3798ctt9wSl112\nWVx++eXx/e9/f1r3effu3TF37tz44Ac/GBERN954Y7S1tcWePXumlUd9a8YZX7duXdxyyy0xd+7c\nmD17dnz2s5+NnTt3TiuL+taM8/3SSy/FY489Fvfff39ccsklUSqVLvgLDCbXjDPuGN5cmnHGT9ff\n3x8f/ehHs2TVUkOWxYiIf/zjH3HgwIH485//HPfff/8b/mTgy1/+cuzevTtGRkZi9+7dsW/fvtiy\nZcuUtvWud70rRkZG4sCBA3HnnXfGrbfeGq+++mpE/P8nElu3bo3bbrttYnl3d3ccP348xsfH46ab\nboqrrroq9u/fH9u3b49qtRpPPvnkGbfT2dkZP/vZzyZd1traGtu2bYvjx4/HwMBAXHzxxXHllVdO\n6T5w4Wm2GT/dL3/5y7jiiiumdFsuPM02388//3wsXbo0Nm/eHAsXLowrr7wyHnnkkSntPxemZpvx\n0zmGN75mnvG9e/fG0NBQQ5TFKBpEpVIptm/fXhRFUTz99NPFRRddVLzyyisTyx944IHife973ynr\nlEqlYs+ePcX4+HjR1tZW7NmzZ2LZs88+WyxbtuyM2zpT1snmz59fvPjii0VRFMVXv/rV4j3vec/E\nsvHx8WLRokXF0NBQ8dxzzxVLliw5Zd1vfOMbxcaNGyfWveuuu6Zy94uiKIrHHnusmDNnTtHa2lrM\nmTOnePzxx6e8LvXPjJ8wMjJSLFiwoHjmmWfOel3qU7PP99e//vWiVCoVX/va14r//ve/xY4dO4q5\nc+cWv//976e0PvWv2Wf8ZI7hjcmMn7Bly5ZizZo1Z71ePWqtdVk9XxYuXBgXXXTRlG778ssvx5Ej\nR+Kaa66Z+L+iKGJ8fHxK63/729+OH/3oR7F///4olUpx6NChU35XcPHixRP/LpVKsXjx4onb7t+/\nP+bPnz+x/Pjx43H99ddPabsn+/Wvfx2bNm2KoaGhuPrqq+OFF16ID33oQ/HEE09EZ2fnWedR/5pt\nxl+ze/fuuPHGG+N73/tevPe97512DvWt2eZ79uzZ8aY3vSnuueeeaGlpieuvvz7WrFkTTz75ZLzj\nHe846zzqX7PN+Gscw5tHs854RMSPf/zjuOeee84po140bFk8/dOL2tra4siRIxNfn/wJXJdeemnM\nnj07fve738WiRYvOajtDQ0Nx3333xVNPPRUrVqyIiIgFCxac8lL7X/7yl4l/j4+Px1//+td4y1ve\nErNmzYply5bFH/7whyndh9ezffv2WLVqVVx99dUREXHttdfGu9/97vjFL36hLDaoZpvxiP+/rWPt\n2rWxefPm2LBhw1mty4Wl2eb7tV8ZKE57m9a5fIof9a3ZZjzCMbzZNOOMR0Ts3Lkz/va3v8X69evP\net161LC/s3i6zs7O+O1vfxsjIyNx9OjR6Ovrm1jW0tISn/jEJ6K3tzdefvnliIjYt2/fpO9XPtnh\nw4ejtbU1Lr300nj11Vdjy5YtcejQoVNu86tf/SoeffTROHbsWFSr1bj44otj1apV8c53vjPa29vj\n3nvvjf/85z9x/Pjx+M1vfhMvvPBCRJzdJzB1dnbG0NBQjIyMRETErl27YmhoSFFsIo0+4/v27Yv3\nv//98bnPfS42bdo05fVoDI0+36tXr44lS5bEN7/5zTh27Fjs3LkzBgcHJz60jMbX6DPuGE6jz/hr\nHnzwwVi/fn20tbWd9br1qGHL4uk/CVi+fHls3rw5brjhhnj7298e11133Sm3+da3vhVve9vbYtWq\nVdHR0RFr16593Z8yvLbuunXrYt26dbF8+fKoVCoxe/bsWLJkySm37e7ujocffjgWLFgQDz30UDzy\nyCMxa9asmDVrVmzbti2Gh4fj8ssvj4ULF8amTZsmBvzk7UREXHHFFZP+zZoPfOAD8aUvfSluvvnm\naG9vj/Xr18dXvvKVuOGGG6b3DaTuNduM//CHP4w//elP0dfXN/E3jObNmze9bx51r9nmu7W1NbZu\n3RqPP/54lMvl+OQnPxk/+clPYvny5dP7BlL3mm3GHcObT7PNeETE0aNH4+c//3l87GMfO/tvWJ0q\nFdOpzAAAADS0hn1lEQAAgOlTFgEAAEgoiwAAACQm/dMZPq6bmVKrX5s148wUM06jq8WMm29mimM4\nje71Zvx1/85iPX/2zejoaLas3t7ebFnDw8PZsiIiKpVKtqxqtZotKyJi5cqV55xR6wNhzhkfGxvL\nlhUR0dXVlS0r5/Olnme8HjXSjOd28semn6tyuZwtK+c5oRnUcsbreb5znnP7+/vrMisiz7VAPXMM\nn1zOGc95Psh9vdvT05M1r9680Yx7GyoAAAAJZREAAICEsggAAEBCWQQAACChLAIAAJBQFgEAAEgo\niwAAACSURQAAABLKIgAAAAllEQAAgISyCAAAQEJZBAAAIKEsAgAAkFAWAQAASCiLAAAAJJRFAAAA\nEsoiAAAAiVJRFMUZF5RKMcmiulCpVGq9C2fU3d2dNa+/vz9bVm9vb7asiIi+vr5zzqjlnOXeds7H\nKiL/45VLT09P1rxqtZo1r9400oznlvN4OTY2li1rcHAwW1YzqNWc1ft8l8vlbFkHDx7MlvXhD384\nW1ZExMDAQNa8euMYPrnR0dFsWV1dXdmycp4PIiKGh4ezZdVjf3mjOfPKIgAAAAllEQAAgISyCAAA\nQEJZBAAAIKEsAgAAkFAWAQAASCiLAAAAJJRFAAAAEsoiAAAACWURAACAhLIIAABAQlkEAAAgoSwC\nAACQUBYBAABIKIsAAAAklEUAAAASyiIAAAAJZREAAICEsggAAECidaY2NDAwkDWvUqlkyxocHMyW\nlft+9vf3Z8vq6enJlkVqeHg4a15vb2+2rNHR0WxZOZ8vNLecs+T4Rr0pl8vZsur5WiDnuW/lypXZ\nsjj/cl6LV6vVbFkf+chHsmVFOFd5ZREAAICEsggAAEBCWQQAACChLAIAAJBQFgEAAEgoiwAAACSU\nRQAAABLKIgAAAAllEQAAgISyCAAAQEJZBAAAIKEsAgAAkFAWAQAASCiLAAAAJJRFAAAAEsoiAAAA\nCWURAACAhLIIAABAonWmNlSpVLLm7dixI1tWd3d3tqzBwcFsWbnzcj8GnKqrqytrXs7Hq7e3N1tW\nuVzOlsWFpVqtZs07ePBgtqzvfve72bJyy3mOyX2c4fzp6+vLlrVy5cpsWbmP4aOjo9myct5PyGV4\neDhbVs7nS8TMXNt7ZREAAICEsggAAEBCWQQAACChLAIAAJBQFgEAAEgoiwAAACSURQAAABLKIgAA\nAAllEQAAgISyCAAAQEJZBAAAIKEsAgAAkFAWAQAASCiLAAAAJJRFAAAAEsoiAAAACWURAACAhLII\nAABAQlkEAAAg0TpTG1q5cmXWvAMHDmTLyrlvBw8ezJYVETE2NpY1j/Onu7s7a97w8HC2rB07dmTL\neuCBB7JlcWGpVCq13oVJLV26NFvW6OhotqyIiDVr1mTLevTRR7NlReQ/bnFCT09PrXfhjHI/j3Oe\nq8zj+TUwMJA1r7e3N1vW3r17s2V1dHRky4rIe07IfX6ZifOyVxYBAABIKIsAAAAklEUAAAASyiIA\nAAAJZREAAICEsggAAEBCWQQAACChLAIAAJBQFgEAAEgoiwAAACSURQAAABLKIgAAAAllEQAAgISy\nCAAAQEJZBAAAIKEsAgAAkFAWAQAASCiLAAAAJEpFURRnXFAqxSSLGk65XM6W1d/fny0rIqKnpydb\n1tjYWLasXGo5Z7m3PTAwkC0rIu9jn9Po6GjWvJzPv3rUSDOe+7FftmxZ1rxccj9eXV1ddZkVEdHX\n13fOGbWa8Wa6Tsl5bbFx48ZsWRERTz/9dNa8nHI8XxrpGJ77OiXnOSHnvuW+rsj9fas3bzRnXlkE\nAAAgoSwCAACQUBYBAABIKIsAAAAklEUAAAASyiIAAAAJZREAAICEsggAAEBCWQQAACChLAIAAJBQ\nFgEAAEgoiwAAACSURQAAABLKIgAAAAllEQAAgISyCAAAQEJZBAAAIKEsAgAAkGit9Q5M19jYWLas\ngwcPZssaGBjIlhUR0dXVlTWP8yfnTEbkncuOjo5sWd3d3dmyciuXy1nzcj+fL3SVSiVrXs65zCn3\nc3l4eDhbVk9PT7Yszq9qtZot6wtf+EK2rNzWrFlT612Y1K5du2q9C3Ul9/l7cHAwW1ZfX1+2rNHR\n0WxZeGURAACAM1AWAQAASCiLAAAAJJRFAAAAEsoiAAAACWURAACAhLIIAABAQlkEAAAgoSwCAACQ\nUBYBAABIKIsAAAAklEUAAAASyiIAAAAJZREAAICEsggAAEBCWQQAACChLAIAAJBQFgEAAEgoiwAA\nACRaa70D01Uul7NldXR0ZMsaHh7OlhURMTAwkDWP86e7uztrXs7HfnR0NFvWjh07smXltnr16lrv\nAmehr68vW1a1Ws2WNX/+/GxZERGdnZ3ZsnIfZzh/6vU6JedzJSL/dU9OlUql1rvQ0Pr7+7NldXV1\nZcvK+dzDK4sAAACcgbIIAABAQlkEAAAgoSwCAACQUBYBAABIKIsAAAAklEUAAAASyiIAAAAJZREA\nAICEsggAAEBCWQQAACChLAIAAJBQFgEAAEgoiwAAACSURQAAABLKIgAAAAllEQAAgESpKIrijAtK\npZneF5rUJCN43plxZooZp9HVYsbNNzPFMZxG93ozPmlZBAAAoHl5GyoAAAAJZREAAICEsggAAEBC\nWQQAACChLAIAAJBQFgEAAEj8D+jTiULarcGDAAAAAElFTkSuQmCC\n"
      }
     ], 
     "prompt_number": 4
    }, 
    {
     "cell_type": "code", 
     "collapsed": true, 
     "input": "from sklearn.svm import SVC", 
     "language": "python", 
     "outputs": [], 
     "prompt_number": 5
    }, 
    {
     "cell_type": "code", 
     "collapsed": true, 
     "input": "svc = SVC()", 
     "language": "python", 
     "outputs": [], 
     "prompt_number": 6
    }, 
    {
     "cell_type": "code", 
     "collapsed": false, 
     "input": "svc.fit(X, y)", 
     "language": "python", 
     "outputs": [
      {
       "output_type": "pyout", 
       "prompt_number": 7, 
       "text": "SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0, degree=3, gamma=0.0,\n  kernel='rbf', max_iter=-1, probability=False, random_state=None,\n  shrinking=True, tol=0.001, verbose=False)"
      }
     ], 
     "prompt_number": 7
    }, 
    {
     "cell_type": "code", 
     "collapsed": false, 
     "input": "from sklearn.cross_validation import train_test_split\n\nX_train, X_test, y_train, y_test = train_test_split(X, y, \\\n                                test_size=0.25, random_state=1)\n\nprint(\"train data shape: %r, train target shape: %r\"\n      % (X_train.shape, y_train.shape))\nprint(\"test data shape: %r, test target shape: %r\"\n      % (X_test.shape, y_test.shape))", 
     "language": "python", 
     "outputs": [
      {
       "output_type": "stream", 
       "stream": "stdout", 
       "text": "train data shape: (1347, 64), train target shape: (1347,)\ntest data shape: (450, 64), test target shape: (450,)"
      }
     ], 
     "prompt_number": 8
    }, 
    {
     "cell_type": "code", 
     "collapsed": false, 
     "input": "svc = SVC().fit(X_train, y_train)\ntrain_score = svc.score(X_train, y_train) \ntrain_score", 
     "language": "python", 
     "outputs": [
      {
       "output_type": "pyout", 
       "prompt_number": 9, 
       "text": "1.0"
      }
     ], 
     "prompt_number": 9
    }, 
    {
     "cell_type": "code", 
     "collapsed": false, 
     "input": "test_score = svc.score(X_test, y_test)\ntest_score", 
     "language": "python", 
     "outputs": [
      {
       "output_type": "pyout", 
       "prompt_number": 10, 
       "text": "0.40888888888888891"
      }
     ], 
     "prompt_number": 10
    }, 
    {
     "cell_type": "code", 
     "collapsed": true, 
     "input": "svc_2 = SVC(C=100, gamma=0.001).fit(X_train, y_train)", 
     "language": "python", 
     "outputs": [], 
     "prompt_number": 11
    }, 
    {
     "cell_type": "code", 
     "collapsed": false, 
     "input": "svc_2.score(X_train, y_train)", 
     "language": "python", 
     "outputs": [
      {
       "output_type": "pyout", 
       "prompt_number": 12, 
       "text": "1.0"
      }
     ], 
     "prompt_number": 12
    }, 
    {
     "cell_type": "code", 
     "collapsed": false, 
     "input": "svc_2.score(X_test, y_test)", 
     "language": "python", 
     "outputs": [
      {
       "output_type": "pyout", 
       "prompt_number": 13, 
       "text": "0.99111111111111116"
      }
     ], 
     "prompt_number": 13
    }, 
    {
     "cell_type": "code", 
     "collapsed": true, 
     "input": "from sklearn import cross_validation", 
     "language": "python", 
     "outputs": [], 
     "prompt_number": 14
    }, 
    {
     "cell_type": "code", 
     "collapsed": false, 
     "input": "cv = cross_validation.ShuffleSplit(len(X), n_iter=3, test_size=0.2,\n    random_state=0)\n\nfor cv_index, (train, test) in enumerate(cv):\n    print(\"# Cross Validation Iteration #%d\" % cv_index)\n    print(\"train indices: {0}...\".format(train[:10]))\n    print(\"test indices: {0}...\".format(test[:10]))\n    \n    svc = SVC(C=100, gamma=0.001).fit(X[train], y[train])\n    print(\"train score: {0:.3f}, test score: {1:.3f}\\n\".format(\n        svc.score(X[train], y[train]), svc.score(X[test], y[test])))", 
     "language": "python", 
     "outputs": [
      {
       "output_type": "stream", 
       "stream": "stdout", 
       "text": "# Cross Validation Iteration #0\ntrain indices: [1109  940  192  260 1148  966 1720  554  308  512]...\ntest indices: [1081 1707  927  713  262  182  303  895  933 1266]...\ntrain score: 1.000, test score: 0.992"
      }, 
      {
       "output_type": "stream", 
       "stream": "stdout", 
       "text": "\n# Cross Validation Iteration #1\ntrain indices: [1642  586  142   15  701  472  380 1405 1551  450]...\ntest indices: [1014  755 1633  117  181  501  948 1076   45  659]...\ntrain score: 1.000, test score: 0.997"
      }, 
      {
       "output_type": "stream", 
       "stream": "stdout", 
       "text": "\n# Cross Validation Iteration #2\ntrain indices: [ 396 1083 1184 1569  560 1502 1722 1162 1316 1685]...\ntest indices: [ 795  697  655  573  412  743  635  851 1466 1383]...\ntrain score: 1.000, test score: 0.989"
      }, 
      {
       "output_type": "stream", 
       "stream": "stdout", 
       "text": ""
      }
     ], 
     "prompt_number": 15
    }, 
    {
     "cell_type": "code", 
     "collapsed": true, 
     "input": "n_iter = 5 # the number of iterations should be more than that ... \n\ngammas = np.logspace(-7, -1, 10) # should be more fine grained ... \n\ncv = cross_validation.ShuffleSplit(len(X), n_iter=n_iter, test_size=0.2)\n\ntrain_scores = np.zeros((len(gammas), n_iter))\ntest_scores = np.zeros((len(gammas), n_iter))\n\nfor i, gamma in enumerate(gammas):\n    for j, (train, test) in enumerate(cv):\n        C = 1\n        clf = SVC(C=C, gamma=gamma).fit(X[train], y[train])\n        train_scores[i, j] = clf.score(X[train], y[train])\n        test_scores[i, j] = clf.score(X[test], y[test])", 
     "language": "python", 
     "outputs": [], 
     "prompt_number": 16
    }, 
    {
     "cell_type": "code", 
     "collapsed": false, 
     "input": "f, ax = plt.subplots(figsize=(12,8))\n#for i in range(n_iter):\n#    ax.semilogx(gammas, train_scores[:, i], alpha=0.2, lw=2, c='b')\n#    ax.semilogx(gammas, test_scores[:, i], alpha=0.2, lw=2, c='g')\nax.semilogx(gammas, test_scores.mean(1), lw=4, c='g', label='test score')\nax.semilogx(gammas, train_scores.mean(1), lw=4, c='b', label='train score')\n\n\nax.fill_between(gammas, train_scores.min(1), train_scores.max(1), color = 'b', alpha=0.2)\nax.fill_between(gammas, test_scores.min(1), test_scores.max(1), color = 'g', alpha=0.2)\n\nax.set_ylabel(\"score for SVC(C=%4.2f, $\\gamma=\\gamma$)\" % ( C ),fontsize=16)\nax.set_xlabel(r\"$\\gamma$\",fontsize=16)\nbest_gamma = gammas[np.argmax(test_scores.mean(1))]\nbest_score = test_scores.mean(1).max()\nax.text(best_gamma, best_score+0.05, \"$\\gamma$ = %6.4f | score=%6.4f\" % (best_gamma, best_score),\\\n        fontsize=15, bbox=dict(facecolor='w',alpha=0.5))\n[x.set_fontsize(16) for x in ax.xaxis.get_ticklabels()]\n[x.set_fontsize(16) for x in ax.yaxis.get_ticklabels()]\n#ax.legend(fontsize=16,  loc=0)\nax.set_ylim(0, 1.1)", 
     "language": "python", 
     "outputs": [
      {
       "output_type": "pyout", 
       "prompt_number": 18, 
       "text": "(0, 1.1)"
      }, 
      {
       "output_type": "display_data", 
       "png": "iVBORw0KGgoAAAANSUhEUgAAAu8AAAH5CAYAAAAx5NBKAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n/H+teUr1WznpXQAAAABJRU5ErkJggg==\n"
      }
     ], 
     "prompt_number": 18
    }, 
    {
     "cell_type": "code", 
     "collapsed": true, 
     "input": "", 
     "language": "python", 
     "outputs": []
    }
   ]
  }
 ]
}