{"cells":[
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "import pandas as pd\nimport numpy as np\nimport time\n\nstart = time.time()\n\ndf_train = pd.read_csv('../input/train.csv')\ndf_test = pd.read_csv('../input/test.csv')\n\nprint('Size of training data: ' + str(df_train.shape))\nprint('Size of testing data:  ' + str(df_test.shape))\n\nprint('\\nColumns:' + str(df_train.columns.values))\n\nprint(df_train.describe())\n\n#print(df_train['place_id'])\n\nprint('\\nNumber of place ids: ' + str(len(list(set(df_train['place_id'].values.tolist())))))\n\nend = time.time()\nprint('\\nTime Elapsed: ' + str(end-start))"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "print('Target values:')\nprint(df_train['place_id'].value_counts())"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "import matplotlib.pyplot as plt\nimport matplotlib.mlab as mlab\nfrom matplotlib.colors import LogNorm\n\ntime = df_train['time']\nx = df_train['x']\ny = df_train['y']\naccuracy = df_train['accuracy']\n\nn, bins, patches = plt.hist(time, 50, normed=1, facecolor='green', alpha=0.75)\nplt.title('Data density at different time dimension')\nplt.xlabel('Time')\nplt.ylabel('Frequency')\nplt.grid(True)\nplt.show()\n\nn, bins, patches = plt.hist(accuracy, 50, normed=1, facecolor='green', alpha=0.75)\nplt.title('Histogram of location accuracy')\nplt.xlabel('Accuracy')\nplt.ylabel('Frequency')\nplt.show()\n"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "bins = 20\nwhile bins <=160:\n    plt.hist2d(x, y, bins=bins, norm=LogNorm())\n    plt.colorbar()\n    plt.title('x and y location histogram - ' + str(bins) + ' bins')\n    plt.xlabel('x')\n    plt.ylabel('y')\n    plt.show()\n    bins = bins * 2"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": ""
 }
],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"}}, "nbformat": 4, "nbformat_minor": 0}