R.Ass.2

gistfile1.txt

{
 "metadata": {
  "name": "R Programming Assignment 1"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "heading",
     "level": 2,
     "metadata": {},
     "source": "CfDA R Course Programming Assignment 2"
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "import pandas as pd\nimport numpy as np\nimport scipy\n\ndirectory = \"/home/john/Moocs/Computing for Data Analysis JH Coursera/L2/specdata\"\nID = range(1,333)",
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 1
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "def getmonitor(id, directory = \"\", summary = False):\n    \n    df = pd.read_csv('{0}/{1:03.0f}.csv'.format(directory, int(id)))\n    if summary: \n        print df.describe()\n    return df\n\n# getmonitor(\"1\", directory, True)",
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 2
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "def complete(directory, id=range(1,332)):\n    \n    data = pd.DataFrame(columns = [\"nobs\"], index = [id])\n    for i in id: \n        df = getmonitor(id = i, directory = directory)\n        data.ix[i] = len(df.dropna())\n    return data\n\nprint complete(directory, [1,20,31,50]) ",
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": "   nobs\n1   117\n20  124\n31  483\n50  459\n"
      }
     ],
     "prompt_number": 3
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": "def corr(directory, threshold = 0): \n    # build df then extract indexes of rows > threshold na values\n    df = complete(directory)\n    filelist = df[df['nobs'] > threshold].index\n\n    corrs = [] \n    for i in filelist:\n        corrs.append(getmonitor(i,directory).corr(method='pearson').ix[0,1])\n    return corrs\n\n\ncr = corr(directory, 150)\nprint cr[0:6], '\\n'\nprint pd.DataFrame(cr).describe()",
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": "[-0.018957540970254896, -0.14051254401589205, -0.043897372138784689, -0.06815956229777316, -0.12350666584148721, -0.075888144218988859] \n\n                0\ncount  234.000000\nmean     0.125253\nstd      0.218957\nmin     -0.210568\n25%     -0.049993\n50%      0.094626\n75%      0.268445\nmax      0.763129\n"
      }
     ],
     "prompt_number": 4
    }
   ],
   "metadata": {}
  }
 ]
}