{"cells":[
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "from numpy import savetxt, loadtxt\r\n\r\nfrom sklearn.externals import joblib\r\n\r\ndataset = loadtxt(open('train.csv', 'r'), dtype='f8', delimiter=',', skiprows=1)\r\ntestset = loadtxt(open('test.csv', 'r'), dtype='f8', delimiter=',', skiprows=1)\r\n\r\njoblib.dump(dataset, 'training_set.pkl')\r\njoblib.dump(testset, 'test_set.pkl')\r\n\r\n\r\ndataset = joblib.load('training_set.pkl')\r\ntestset = joblib.load('test_set.pkl')\r\n\r\ntarget = [x[0] for x in dataset[:42000]]\r\n\r\ntrain = [x[1:] for x in dataset[:42000]]\r\n\r\ntest = [x[0:] for x in testset[:28000]]\r\n\r\ntargetarr = [[0 for i in range(10)] for j in range(42000)]\r\n\r\nfor i in range(0, 42000):\r\n\ttargetarr[i][int(target[i])] = 1;\r\n\t\r\nimport numpy as np\r\n\r\ntrainT = list(map(list, zip(*train)))\r\n\r\ntrainNum = np.array([train])\r\ntrainTNum = np.array([trainT])\r\ntargetarrNum = np.array([targetarr])\r\ntestNum  =np.array([test])\r\n\r\nS = trainTNum[0][:][:].dot(trainNum[:][:][0])\r\n\r\nA = np.linalg.lstsq(trainNum[0][:][:],targetarrNum[0][:][:])[0]\r\n\r\nout =testNum.dot(A)\r\n\r\n(out.T).argmax(0)\r\n\r\nnp.savetxt('Submit_MMNRM.csv', np.c_[range(1, len(test) + 1), (out.T).argmax(0)], delimiter=',', comments = '', header = 'ImageId,Label', fmt='%d')"
 }
],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"}}, "nbformat": 4, "nbformat_minor": 0}