snow_depth_min_temp_chaitanya_data_science.ipynb

{
 "metadata": {
  "name": "",
  "signature": "sha256:b3555aaf2fdc56e13fc11db217d7e44d797ca20442b73f18c9a83eefb709d0f3"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "cd \\users\\chaitu\\Desktop"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "/Users/chaitu/Desktop\n"
       ]
      }
     ],
     "prompt_number": 3
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import pandas as pd\n",
      "from pandas import *\n",
      "import numpy as np\n",
      "import csv\n",
      "import datetime\n",
      "import matplotlib.pyplot as plt\n",
      "\n",
      "cities = ['ALBANY', 'ANNAPOLIS', 'ATLANTA', 'AUGUSTA', 'AUSTIN', 'BATON ROUGE', 'BISMARCK',\n",
      " 'BOISE', 'BOSTON', 'CARSON CITY', 'CHARLESTON', 'CHEYENNE', 'COLUMBIA',\n",
      " 'COLUMBUS', 'CONCORD', 'DENVER', 'DES MOINES', 'DOVER', 'FRANKFORT',\n",
      " 'HARRISBURG', 'HARTFORD', 'HELENA', 'HONOLULU', 'INDIANAPOLIS', 'JACKSON',\n",
      " 'JEFFERSON CITY', 'JUNEAU', 'LANSING', 'LINCOLN', 'LITTLE ROCK', 'MADISON',\n",
      " 'MONTGOMERY', 'MONTPELIER', 'NASHVILLE', 'OKLAHOMA CITY', 'OLYMPIA', 'PHOENIX',\n",
      " 'PIERRE', 'PROVIDENCE', 'RALEIGH', 'RICHMOND', 'SACRAMENTO', 'SAINT PAUL',\n",
      " 'SALEM', 'SALT LAKE CITY', 'SANTA FE', 'SPRINGFIELD', 'TALLAHASSEE', 'TOPEKA',\n",
      " 'TRENTON']"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 4
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "rawData = {}\n",
      "for city in cities:\n",
      "    cityData = pd.read_csv(city+'.csv',index_col=0, usecols=[0, 'SNOW'], parse_dates=True)\n",
      "    cityData.columns = [city]\n",
      "    rawData[city] = cityData"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 5
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "data = rawData.values()[0].join(rawData.values()[1:], how='outer')\n",
      "startDate = data.index[0]\n",
      "endDate = data.index[-1]\n",
      "if endDate < startDate:\n",
      "    endDate = startDate\n",
      "xmasIndicies = pd.date_range(start=startDate, end=endDate, freq='A').to_series().shift(periods=-1,freq='6D').index\n",
      "data = data.reindex(index=xmasIndicies)\n",
      "data = data.sort_index(axis=1)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 6
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "snowRawData = {}\n",
      "for city in cities:\n",
      "    cityData = pd.read_csv(city+'.csv',index_col=0, usecols=[0, 'TMIN'], parse_dates=True)\n",
      "    cityData.columns = [city]\n",
      "    snowRawData[city] = cityData"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 7
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "snowdata = snowRawData.values()[0].join(snowRawData.values()[1:], how='outer')\n",
      "startDate = snowdata.index[0]\n",
      "endDate = snowdata.index[-1]\n",
      "if endDate < startDate:\n",
      "    endDate = startDate\n",
      "xmasIndicies = pd.date_range(start=startDate, end=endDate, freq='A').to_series().shift(periods=-1,freq='6D').index\n",
      "snowdata = snowdata.reindex(index=xmasIndicies)\n",
      "snowdata = snowdata.sort_index(axis=1)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 8
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "dfs = pd.DataFrame()\n",
      "for city in cities:\n",
      "    df = DataFrame(data[city])\n",
      "    df['TMIN'] = Series(snowdata[city], index=df.index)\n",
      "    df.columns = [ 'SNWD', 'TMIN']\n",
      "    for i in range(len(df)):\n",
      "            dfs  = dfs.append(df.irow(i))"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 9
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "dfs_montpelier = dfs[5280:5445]\n",
      "dfs_montpelier = dfs_montpelier[np.isfinite(dfs_montpelier['SNWD'])]\n",
      "dfs_montpelier = dfs_montpelier[np.isfinite(dfs_montpelier['TMIN'])]\n",
      "plt.scatter(dfs_montpelier['TMIN'], dfs_montpelier['SNWD'])\n",
      "plt.title('Montpelier')\n",
      "plt.xlabel('Minimum Temperature')\n",
      "plt.ylabel('Snow Depth')\n",
      "plt.show()    "
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 12
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "dfs_augusta = dfs[495:660]\n",
      "dfs_augusta = dfs_augusta[np.isfinite(dfs_augusta['SNWD'])]\n",
      "dfs_augusta = dfs_augusta[np.isfinite(dfs_augusta['TMIN'])]\n",
      "plt.scatter(dfs_augusta['TMIN'], dfs_augusta['SNWD'])\n",
      "plt.title('Augusta')\n",
      "plt.xlabel('Minimum Temperature')\n",
      "plt.ylabel('Snow Depth')\n",
      "plt.show() "
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 11
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "dfs_saintpaul = dfs[6930:7095]\n",
      "dfs_saintpaul = dfs_saintpaul[np.isfinite(dfs_saintpaul['SNWD'])]\n",
      "dfs_saintpaul = dfs_saintpaul[np.isfinite(dfs_saintpaul['TMIN'])]\n",
      "plt.scatter(dfs_saintpaul['TMIN'], dfs_saintpaul['SNWD'])\n",
      "plt.title('Saint Paul')\n",
      "plt.xlabel('Minimum Temperature')\n",
      "plt.ylabel('Snow Depth')\n",
      "plt.show()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 13
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "dfs_bismarck = dfs[990:1155]\n",
      "dfs_bismarck = dfs_bismarck[np.isfinite(dfs_bismarck['SNWD'])]\n",
      "dfs_bismarck = dfs_bismarck[np.isfinite(dfs_bismarck['TMIN'])]\n",
      "plt.scatter(dfs_bismarck['TMIN'], dfs_bismarck['SNWD'])\n",
      "plt.title('Bismarck')\n",
      "plt.xlabel('Minimum Temperature')\n",
      "plt.ylabel('Snow Depth')\n",
      "plt.show() "
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 14
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "dfs_concord = dfs[2310:2475]\n",
      "dfs_concord = dfs_concord[np.isfinite(dfs_concord['SNWD'])]\n",
      "dfs_concord = dfs_concord[np.isfinite(dfs_concord['TMIN'])]\n",
      "plt.scatter(dfs_concord['TMIN'], dfs_concord['SNWD'])\n",
      "plt.title('Concord')\n",
      "plt.xlabel('Minimum Temperature')\n",
      "plt.ylabel('Snow Depth')\n",
      "plt.show()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 15
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "dfs_lansing = dfs[4455:4620]\n",
      "dfs_lansing = dfs_lansing[np.isfinite(dfs_lansing['SNWD'])]\n",
      "dfs_lansing = dfs_lansing[np.isfinite(dfs_lansing['TMIN'])]\n",
      "plt.scatter(dfs_lansing['TMIN'], dfs_lansing['SNWD'])\n",
      "plt.title('Lansing')\n",
      "plt.xlabel('Minimum Temperature')\n",
      "plt.ylabel('Snow Depth')\n",
      "plt.show()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 16
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [],
     "language": "python",
     "metadata": {},
     "outputs": []
    }
   ],
   "metadata": {}
  }
 ]
}