{ "metadata": { "name": "smoothing" }, "nbformat": 3, "nbformat_minor": 0, "worksheets": [ { "cells": [ { "cell_type": "code", "collapsed": false, "input": [ "import pandas as pd\n", "import numpy as np" ], "language": "python", "metadata": {}, "outputs": [], "prompt_number": 1 }, { "cell_type": "code", "collapsed": false, "input": [ "cols = ['time', 'cd4', 'age', 'packs', 'drugs', 'sex', 'cesd', 'id']\n", "cd4Data = pd.read_csv('https://spark-public.s3.amazonaws.com/dataanalysis/cd4.data', header=None, names=cols, skipinitialspace=True, delimiter=' ')" ], "language": "python", "metadata": {}, "outputs": [], "prompt_number": 23 }, { "cell_type": "code", "collapsed": false, "input": [ "cd4Data = cd4Data.ix[cd4Data['time'].order().index]\n", "cd4Data.index = cd4Data.index + 1\n", "cd4Data.head()" ], "language": "python", "metadata": {}, "outputs": [ { "html": [ "
\n", " | time | \n", "cd4 | \n", "age | \n", "packs | \n", "drugs | \n", "sex | \n", "cesd | \n", "id | \n", "
---|---|---|---|---|---|---|---|---|
1279 | \n", "-2.989733 | \n", "814 | \n", "6.17 | \n", "3 | \n", "1 | \n", "5 | \n", "-3 | \n", "30183 | \n", "
2190 | \n", "-2.989733 | \n", "400 | \n", "-6.02 | \n", "0 | \n", "0 | \n", "3 | \n", "-4 | \n", "41406 | \n", "
1167 | \n", "-2.984257 | \n", "467 | \n", "13.94 | \n", "0 | \n", "1 | \n", "1 | \n", "0 | \n", "30046 | \n", "
1427 | \n", "-2.956879 | \n", "749 | \n", "-4.54 | \n", "0 | \n", "1 | \n", "-1 | \n", "-7 | \n", "30498 | \n", "
2032 | \n", "-2.951403 | \n", "1218 | \n", "5.57 | \n", "3 | \n", "1 | \n", "5 | \n", "3 | \n", "41032 | \n", "