Brownian Motion IPython notebook with pandas

Brownian-motion-pandas.ipynb

{
 "metadata": {
  "name": "",
  "signature": "sha256:44e074445e8f30cf2fbb55047abada9626e135925840daa132170157ba210209"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "# Brownian Motion"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Brownian motion in a few lines of Python thanks to Numpy and pandas.\n",
      "\n",
      "*author*: Damien Garaud"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Some import"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import string"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 2
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Specify a style: only for matplotlib >= 1.4\n",
      "from matplotlib import pyplot as plt\n",
      "plt.style.use('ggplot')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 3
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import numpy as np\n",
      "import pandas as pd"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 4
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Size"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Size\n",
      "Nsample = 1000\n",
      "Nvar = 5"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 5
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Generate a Timeseries"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Business days frequency\n",
      "ts = pd.date_range(\"2013-07-17\", periods=Nsample, freq=\"B\")"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 6
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Random Drawing"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Normal random drawing with Numpy\n",
      "colname = [x for x in string.ascii_letters[:Nvar].upper()]\n",
      "df = pd.DataFrame(np.random.randn(Nsample, Nvar), index=ts, columns=colname)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 10
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Computing"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Cumulative sum along each column (i.e. random variable)\n",
      "df = df.cumsum()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 11
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Plotting"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Plotting\n",
      "df.plot()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 12,
       "text": [
        "<matplotlib.axes._subplots.AxesSubplot at 0xa2fb0b0>"
       ]
      },
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAXgAAAEQCAYAAAC6Om+RAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nhDj1/ygWsgzM3yUUAAAAAElFTkSuQmCC\n",
       "text": [
        "<matplotlib.figure.Figure at 0xa1ff270>"
       ]
      }
     ],
     "prompt_number": 12
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Some Stats"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.describe()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>A</th>\n",
        "      <th>B</th>\n",
        "      <th>C</th>\n",
        "      <th>D</th>\n",
        "      <th>E</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>count</th>\n",
        "      <td> 1000.000000</td>\n",
        "      <td> 1000.000000</td>\n",
        "      <td> 1000.000000</td>\n",
        "      <td> 1000.000000</td>\n",
        "      <td> 1000.000000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>mean</th>\n",
        "      <td>   14.030357</td>\n",
        "      <td>  -17.144765</td>\n",
        "      <td>  -34.057633</td>\n",
        "      <td>   31.699834</td>\n",
        "      <td>   10.790943</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>std</th>\n",
        "      <td>   14.028685</td>\n",
        "      <td>   10.624860</td>\n",
        "      <td>   25.834110</td>\n",
        "      <td>   27.256422</td>\n",
        "      <td>   13.157504</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>min</th>\n",
        "      <td>  -14.001927</td>\n",
        "      <td>  -35.433858</td>\n",
        "      <td>  -69.091946</td>\n",
        "      <td>   -6.529099</td>\n",
        "      <td>  -12.013689</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>25%</th>\n",
        "      <td>    2.842337</td>\n",
        "      <td>  -24.324322</td>\n",
        "      <td>  -57.089766</td>\n",
        "      <td>    3.659572</td>\n",
        "      <td>    0.741046</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>50%</th>\n",
        "      <td>   15.455272</td>\n",
        "      <td>  -19.542616</td>\n",
        "      <td>  -43.869296</td>\n",
        "      <td>   34.179318</td>\n",
        "      <td>    9.337162</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>75%</th>\n",
        "      <td>   25.585590</td>\n",
        "      <td>  -14.198276</td>\n",
        "      <td>   -4.609570</td>\n",
        "      <td>   55.805421</td>\n",
        "      <td>   23.070588</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>max</th>\n",
        "      <td>   37.953450</td>\n",
        "      <td>   14.465962</td>\n",
        "      <td>    8.499197</td>\n",
        "      <td>   80.448755</td>\n",
        "      <td>   40.028421</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 13,
       "text": [
        "                 A            B            C            D            E\n",
        "count  1000.000000  1000.000000  1000.000000  1000.000000  1000.000000\n",
        "mean     14.030357   -17.144765   -34.057633    31.699834    10.790943\n",
        "std      14.028685    10.624860    25.834110    27.256422    13.157504\n",
        "min     -14.001927   -35.433858   -69.091946    -6.529099   -12.013689\n",
        "25%       2.842337   -24.324322   -57.089766     3.659572     0.741046\n",
        "50%      15.455272   -19.542616   -43.869296    34.179318     9.337162\n",
        "75%      25.585590   -14.198276    -4.609570    55.805421    23.070588\n",
        "max      37.953450    14.465962     8.499197    80.448755    40.028421"
       ]
      }
     ],
     "prompt_number": 13
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.mean().plot(kind='bar', title=u\"Mean for each rand. variable\")"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 32,
       "text": [
        "<matplotlib.axes._subplots.AxesSubplot at 0xc40f3f0>"
       ]
      },
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAXgAAAEMCAYAAADOLq1xAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n4ImIJMWAJyKS1P8HeU39yEYBdLYAAAAASUVORK5CYII=\n",
       "text": [
        "<matplotlib.figure.Figure at 0xc3602d0>"
       ]
      }
     ],
     "prompt_number": 32
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "df.std().plot(kind='bar', color=plt.rcParams[\"axes.color_cycle\"][1], title=u\"Standard deviation for each rand. variable\")"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 34,
       "text": [
        "<matplotlib.axes._subplots.AxesSubplot at 0xc20e690>"
       ]
      },
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAXAAAAEMCAYAAADd+e2FAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nRK5CYII=\n",
       "text": [
        "<matplotlib.figure.Figure at 0xc67ab70>"
       ]
      }
     ],
     "prompt_number": 34
    }
   ],
   "metadata": {}
  }
 ]
}