Pandas_Categories.ipynb

{
 "cells": [
  {
   "metadata": {
    "trusted": true,
    "collapsed": true
   },
   "cell_type": "code",
   "source": "import numpy as np\nimport pandas as pd\nfrom lsst.sims.photUtils import BandpassDict",
   "execution_count": 1,
   "outputs": []
  },
  {
   "metadata": {
    "trusted": true,
    "collapsed": true
   },
   "cell_type": "code",
   "source": "bpdict = BandpassDict.loadTotalBandpassesFromFiles()",
   "execution_count": 2,
   "outputs": []
  },
  {
   "metadata": {
    "trusted": true,
    "collapsed": false
   },
   "cell_type": "code",
   "source": "# Let us make up a set of observation times and filters \nnum = 1000000\nbands = np.random.choice(list('ugrizy'), replace=True, size=num)\nmjds = np.random.uniform(0, 10000, size=num)",
   "execution_count": 3,
   "outputs": []
  },
  {
   "metadata": {
    "trusted": true,
    "collapsed": false
   },
   "cell_type": "code",
   "source": "df = pd.DataFrame(dict(mjd=mjds, band=bands))",
   "execution_count": 4,
   "outputs": []
  },
  {
   "metadata": {
    "trusted": true,
    "collapsed": true
   },
   "cell_type": "code",
   "source": "df_long = pd.DataFrame(dict(mjd=mjds, band=map(lambda x: bpdict[x], bands)))",
   "execution_count": 5,
   "outputs": []
  },
  {
   "metadata": {
    "trusted": true,
    "collapsed": false
   },
   "cell_type": "code",
   "source": "df_category = df_long.copy()\ndf_category.band = df_category.band.astype('category')",
   "execution_count": 6,
   "outputs": []
  },
  {
   "metadata": {
    "trusted": true,
    "collapsed": true
   },
   "cell_type": "code",
   "source": "import sys",
   "execution_count": 7,
   "outputs": []
  },
  {
   "metadata": {
    "trusted": true,
    "collapsed": false
   },
   "cell_type": "code",
   "source": "x = np.array(map(sys.getsizeof, [df, df_long, df_category]), dtype=np.float)",
   "execution_count": 8,
   "outputs": []
  },
  {
   "metadata": {
    "trusted": true,
    "collapsed": true
   },
   "cell_type": "code",
   "source": "x = x/x.min()",
   "execution_count": 9,
   "outputs": []
  },
  {
   "metadata": {
    "trusted": true,
    "collapsed": false
   },
   "cell_type": "code",
   "source": "x",
   "execution_count": 10,
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": "array([ 5.99978223,  5.33314104,  1.        ])"
     },
     "metadata": {},
     "execution_count": 10
    }
   ]
  },
  {
   "metadata": {
    "trusted": true,
    "collapsed": false
   },
   "cell_type": "code",
   "source": "df.info()",
   "execution_count": 11,
   "outputs": [
    {
     "output_type": "stream",
     "text": "<class 'pandas.core.frame.DataFrame'>\nRangeIndex: 1000000 entries, 0 to 999999\nData columns (total 2 columns):\nband    1000000 non-null object\nmjd     1000000 non-null float64\ndtypes: float64(1), object(1)\nmemory usage: 15.3+ MB\n",
     "name": "stdout"
    }
   ]
  },
  {
   "metadata": {
    "trusted": true,
    "collapsed": false
   },
   "cell_type": "code",
   "source": "df_long.info()",
   "execution_count": 12,
   "outputs": [
    {
     "output_type": "stream",
     "text": "<class 'pandas.core.frame.DataFrame'>\nRangeIndex: 1000000 entries, 0 to 999999\nData columns (total 2 columns):\nband    1000000 non-null object\nmjd     1000000 non-null float64\ndtypes: float64(1), object(1)\nmemory usage: 15.3+ MB\n",
     "name": "stdout"
    }
   ]
  },
  {
   "metadata": {
    "trusted": true,
    "collapsed": false
   },
   "cell_type": "code",
   "source": "df_category.info()",
   "execution_count": 13,
   "outputs": [
    {
     "output_type": "stream",
     "text": "<class 'pandas.core.frame.DataFrame'>\nRangeIndex: 1000000 entries, 0 to 999999\nData columns (total 2 columns):\nband    1000000 non-null category\nmjd     1000000 non-null float64\ndtypes: category(1), float64(1)\nmemory usage: 8.6 MB\n",
     "name": "stdout"
    }
   ]
  },
  {
   "metadata": {
    "trusted": true,
    "collapsed": false
   },
   "cell_type": "code",
   "source": "sys.getsizeof(bands)",
   "execution_count": 14,
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": "1000096"
     },
     "metadata": {},
     "execution_count": 14
    }
   ]
  },
  {
   "metadata": {
    "trusted": true,
    "collapsed": false
   },
   "cell_type": "code",
   "source": "type(bands)",
   "execution_count": 15,
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": "numpy.ndarray"
     },
     "metadata": {},
     "execution_count": 15
    }
   ]
  },
  {
   "metadata": {
    "trusted": true,
    "collapsed": false
   },
   "cell_type": "code",
   "source": "bands.dtype",
   "execution_count": 16,
   "outputs": [
    {
     "output_type": "execute_result",
     "data": {
      "text/plain": "dtype('S1')"
     },
     "metadata": {},
     "execution_count": 16
    }
   ]
  },
  {
   "metadata": {
    "trusted": true,
    "collapsed": true
   },
   "cell_type": "code",
   "source": "",
   "execution_count": null,
   "outputs": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "name": "python2",
   "display_name": "Python [default]",
   "language": "python"
  },
  "anaconda-cloud": {},
  "language_info": {
   "mimetype": "text/x-python",
   "nbconvert_exporter": "python",
   "name": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.12",
   "file_extension": ".py",
   "codemirror_mode": {
    "version": 2,
    "name": "ipython"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}