{"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)\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."
 },
 {
  "cell_type": "markdown",
  "metadata": {},
  "source": "## what do we have in the files? "
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "import glob \nfrom IPython.display import display \nfrom IPython.display import display, HTML\n\nfiles = glob.glob(\"../input/*\")\nfor file_ in files:\n    print(file_)\n    #display(pd.read_csv(file_,nrows=100).head(2))\n    #HTML(pd.read_csv(file_,nrows=5).to_html())\n    print(pd.read_csv(file_,nrows=2).head(2))"
 },
 {
  "cell_type": "markdown",
  "metadata": {},
  "source": "### prepare some useful functions \npreparing a method to get random samples for a given file "
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "##\nimport random \ndef gimme_a_sample(filename, sample_size):\n    #n = sum(1 for line in open(filename)) - 1 #number of records in file (excludes header)\n    n = pd.read_csv(filename, usecols=[0]).shape[0]\n    skip = sorted(random.sample(range(1,n+1),n-sample_size)) #the 0-indexed header will not be included in the skip list\n    return pd.read_csv(filename, skiprows=skip)"
 },
 {
  "cell_type": "markdown",
  "metadata": {},
  "source": "## Take a peak into the training file "
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "train = gimme_a_sample(\"../input/train.csv\",10000)\ntrain.head()"
 },
 {
  "cell_type": "code",
  "execution_count": null,
  "metadata": {
   "collapsed": false
  },
  "outputs": [],
  "source": "train.corr()"
 }
],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"}}, "nbformat": 4, "nbformat_minor": 0}