{"cells":[
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport scipy as sc\nimport matplotlib.pyplot as plt\n\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\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.\n\ntrain_csv = pd.read_csv('../input/train.csv')\ntest_csv = pd.read_csv('../input/test.csv')"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "train_csv[:5]"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "test_csv[:5]"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "train_csv.describe()"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "train_csv_length = len(train_csv)\ntrain_csv_length"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "x = train_csv['x']\ny = train_csv['y']\n\nfrom matplotlib.colors import LogNorm\n\nbins = 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": "len(train_csv['place_id'].unique())"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "train_place_distribution = train_csv['place_id'].value_counts().tolist()\nplt.title('Histogram of place_id frequency')\nplt.xlabel('place_id frequency')\nplt.ylabel('Frequency')\n_, _, _ = plt.hist(train_place_distribution, 50, normed=1, facecolor='green', alpha=0.75)"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "train_norm = (train_csv - train_csv.mean()) / (train_csv.max() - train_csv.min())"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "print (np.correlate(train_norm['x'], train_csv['place_id']))\nprint (np.correlate(train_norm['y'], train_csv['place_id']))"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "corr_matrix = train_norm.corr(method='pearson', min_periods=1)\nprint (corr_matrix)"
 },
 {
  "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}