|
| 1 | +{ |
| 2 | + "cells": [ |
| 3 | + { |
| 4 | + "cell_type": "code", |
| 5 | + "execution_count": 1, |
| 6 | + "metadata": { |
| 7 | + "collapsed": true |
| 8 | + }, |
| 9 | + "outputs": [], |
| 10 | + "source": [ |
| 11 | + "#Digit Recognizer\n", |
| 12 | + "#sklean PCA + SVM " |
| 13 | + ] |
| 14 | + }, |
| 15 | + { |
| 16 | + "cell_type": "code", |
| 17 | + "execution_count": 2, |
| 18 | + "metadata": { |
| 19 | + "collapsed": true |
| 20 | + }, |
| 21 | + "outputs": [], |
| 22 | + "source": [ |
| 23 | + "import numpy as np\n", |
| 24 | + "from sklearn.decomposition import PCA \n", |
| 25 | + "from sklearn.svm import SVC " |
| 26 | + ] |
| 27 | + }, |
| 28 | + { |
| 29 | + "cell_type": "code", |
| 30 | + "execution_count": 3, |
| 31 | + "metadata": { |
| 32 | + "collapsed": true |
| 33 | + }, |
| 34 | + "outputs": [], |
| 35 | + "source": [ |
| 36 | + "#为什么设置为35 \n", |
| 37 | + "COMPONENT_NUM = 35 " |
| 38 | + ] |
| 39 | + }, |
| 40 | + { |
| 41 | + "cell_type": "code", |
| 42 | + "execution_count": 6, |
| 43 | + "metadata": { |
| 44 | + "collapsed": false |
| 45 | + }, |
| 46 | + "outputs": [], |
| 47 | + "source": [ |
| 48 | + "#导入数据\n", |
| 49 | + "\n", |
| 50 | + "with open('train.csv','r') as fd:\n", |
| 51 | + " fd.readline()\n", |
| 52 | + " train_label=[]\n", |
| 53 | + " train_data = []\n", |
| 54 | + "\n", |
| 55 | + " \n", |
| 56 | + " for line in fd.readlines():\n", |
| 57 | + " data = list(map(int, line.rstrip().split(',')))\n", |
| 58 | + " train_label.append(data[0])\n", |
| 59 | + " train_data.append(data[1:])\n", |
| 60 | + " " |
| 61 | + ] |
| 62 | + }, |
| 63 | + { |
| 64 | + "cell_type": "code", |
| 65 | + "execution_count": 7, |
| 66 | + "metadata": { |
| 67 | + "collapsed": true |
| 68 | + }, |
| 69 | + "outputs": [], |
| 70 | + "source": [ |
| 71 | + "#赋值\n", |
| 72 | + "train_label = np.array(train_label)\n", |
| 73 | + "train_data = np.array(train_data)\n", |
| 74 | + "\n", |
| 75 | + "#PCA \n", |
| 76 | + "pca = PCA(n_components=COMPONENT_NUM,whiten=True)\n", |
| 77 | + "pca.fit(train_data)\n", |
| 78 | + "train_data = pca.transform(train_data)\n" |
| 79 | + ] |
| 80 | + }, |
| 81 | + { |
| 82 | + "cell_type": "code", |
| 83 | + "execution_count": 14, |
| 84 | + "metadata": { |
| 85 | + "collapsed": false |
| 86 | + }, |
| 87 | + "outputs": [ |
| 88 | + { |
| 89 | + "data": { |
| 90 | + "text/plain": [ |
| 91 | + "SVC(C=1.0, cache_size=200, class_weight=None, coef0=0.0,\n", |
| 92 | + " decision_function_shape=None, degree=3, gamma='auto', kernel='rbf',\n", |
| 93 | + " max_iter=-1, probability=False, random_state=None, shrinking=True,\n", |
| 94 | + " tol=0.001, verbose=False)" |
| 95 | + ] |
| 96 | + }, |
| 97 | + "execution_count": 14, |
| 98 | + "metadata": {}, |
| 99 | + "output_type": "execute_result" |
| 100 | + } |
| 101 | + ], |
| 102 | + "source": [ |
| 103 | + "#训练\n", |
| 104 | + "svc = SVC()\n", |
| 105 | + "svc.fit(train_data, train_label)\n" |
| 106 | + ] |
| 107 | + }, |
| 108 | + { |
| 109 | + "cell_type": "code", |
| 110 | + "execution_count": 15, |
| 111 | + "metadata": { |
| 112 | + "collapsed": true |
| 113 | + }, |
| 114 | + "outputs": [], |
| 115 | + "source": [ |
| 116 | + "#导入测试数据\n", |
| 117 | + "with open('test.csv','r') as fd:\n", |
| 118 | + " fd.readline()\n", |
| 119 | + " test_data=[]\n", |
| 120 | + " for line in fd.readlines():\n", |
| 121 | + " pixels = list(map(int, line.rstrip().split(',')))\n", |
| 122 | + " test_data.append(pixels)\n", |
| 123 | + " " |
| 124 | + ] |
| 125 | + }, |
| 126 | + { |
| 127 | + "cell_type": "code", |
| 128 | + "execution_count": 16, |
| 129 | + "metadata": { |
| 130 | + "collapsed": true |
| 131 | + }, |
| 132 | + "outputs": [], |
| 133 | + "source": [ |
| 134 | + "#赋值\n", |
| 135 | + "test_data = np.array(test_data)\n", |
| 136 | + "test_data = pca.transform(test_data)\n", |
| 137 | + "\n" |
| 138 | + ] |
| 139 | + }, |
| 140 | + { |
| 141 | + "cell_type": "code", |
| 142 | + "execution_count": 17, |
| 143 | + "metadata": { |
| 144 | + "collapsed": true |
| 145 | + }, |
| 146 | + "outputs": [], |
| 147 | + "source": [ |
| 148 | + "#预测\n", |
| 149 | + "predict = svc.predict(test_data)" |
| 150 | + ] |
| 151 | + }, |
| 152 | + { |
| 153 | + "cell_type": "code", |
| 154 | + "execution_count": 20, |
| 155 | + "metadata": { |
| 156 | + "collapsed": false |
| 157 | + }, |
| 158 | + "outputs": [], |
| 159 | + "source": [ |
| 160 | + "#保存到本地\n", |
| 161 | + "with open('predict.csv','w') as fd:\n", |
| 162 | + " fd.write('\"ImageID\",\"Label\"\\n')\n", |
| 163 | + " count = 0\n", |
| 164 | + " for p in predict:\n", |
| 165 | + " count+=1\n", |
| 166 | + " fd.write(str(count)+',\"'+str(p)+'\"\\n')" |
| 167 | + ] |
| 168 | + } |
| 169 | + ], |
| 170 | + "metadata": { |
| 171 | + "kernelspec": { |
| 172 | + "display_name": "Python [Root]", |
| 173 | + "language": "python", |
| 174 | + "name": "Python [Root]" |
| 175 | + }, |
| 176 | + "language_info": { |
| 177 | + "codemirror_mode": { |
| 178 | + "name": "ipython", |
| 179 | + "version": 3 |
| 180 | + }, |
| 181 | + "file_extension": ".py", |
| 182 | + "mimetype": "text/x-python", |
| 183 | + "name": "python", |
| 184 | + "nbconvert_exporter": "python", |
| 185 | + "pygments_lexer": "ipython3", |
| 186 | + "version": "3.5.2" |
| 187 | + } |
| 188 | + }, |
| 189 | + "nbformat": 4, |
| 190 | + "nbformat_minor": 0 |
| 191 | +} |
0 commit comments