{"cells":[
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "import pandas as pd\nfrom collections import Counter\nimport matplotlib.pyplot as plt\nimport numpy as np"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "df = pd.read_csv('../input/train.csv')"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "place_counts = Counter(df.place_id.values)"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "fig = plt.figure(figsize=(10,5))\nbins = np.arange(0.5, max(list(place_counts.values()))+1, 1)\nplt.hist(list(place_counts.values()),\n         bins=bins, alpha=0.5)\nplt.xlabel('Number of place_id occurrences')\nplt.ylabel('Frequency')\nplt.show()"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "print(\"Total number of place_id's:    {}\".format(len(df)))\nprint(\"Unique place_id's:             {}\".format(len(place_counts)))\nprint('Average number of occurrences: {:.0f}'.format(np.mean(list(place_counts.values()))))"
 }
],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"}}, "nbformat": 4, "nbformat_minor": 0}