{"cells":[
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nfrom sklearn.ensemble import RandomForestClassifier\nfrom subprocess import check_output\nprint(check_output([\"ls\", \"../input\"]).decode(\"utf8\"))\n\n# Any results you write to the current directory are saved as output."
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "data = pd.read_csv('../input/train.csv')\ndata.info()"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "X = data.drop('label', axis=1)\nY = data.label\nmodel = RandomForestClassifier(n_estimators=100, n_jobs=-1)\nmodel.fit(X, Y)"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "print(model.score(X, Y))\ntest_data = pd.read_csv('../input/test.csv')\nresults = model.predict(test_data)"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "sub = pd.DataFrame({'ImageId':test_data.index +1,\n                    'Label':results})\nsub[['ImageId','Label']].to_csv('submission.csv', index=False)"
 }
],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"}}, "nbformat": 4, "nbformat_minor": 0}