data-science-ipython-notebooks/numpy/numpy.ipynb

{
 "metadata": {
  "name": "",
  "signature": "sha256:cb8fc4454a69123dcb745c323968d06c15444cee91494edb720893b06e98c249"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "# NumPy\n",
      "\n",
      "* NumPy Arrays, dtype, and shape\n",
      "* Common Array Operations\n",
      "* Reshaping and In-Place Updating\n",
      "* Combining Arrays\n",
      "* Creating Fake Data and Adding Noise"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import numpy as np"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 1
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## NumPy Arrays, dtypes, and shapes"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "a = np.array([1, 2, 3])\n",
      "print(a)\n",
      "print(a.shape)\n",
      "print(a.dtype)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "[1 2 3]\n",
        "(3,)\n",
        "int64\n"
       ]
      }
     ],
     "prompt_number": 2
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "b = np.array([[0, 2, 4], [1, 3, 5]])\n",
      "print(b)\n",
      "print(b.shape)\n",
      "print(b.dtype)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "[[0 2 4]\n",
        " [1 3 5]]\n",
        "(2, 3)\n",
        "int64\n"
       ]
      }
     ],
     "prompt_number": 3
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "np.zeros(5)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 4,
       "text": [
        "array([ 0.,  0.,  0.,  0.,  0.])"
       ]
      }
     ],
     "prompt_number": 4
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "np.ones(shape=(3, 4), dtype=np.int32)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 5,
       "text": [
        "array([[1, 1, 1, 1],\n",
        "       [1, 1, 1, 1],\n",
        "       [1, 1, 1, 1]], dtype=int32)"
       ]
      }
     ],
     "prompt_number": 5
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Common Array Operations"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "c = b * 0.5\n",
      "print(c)\n",
      "print(c.shape)\n",
      "print(c.dtype)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "[[ 0.   1.   2. ]\n",
        " [ 0.5  1.5  2.5]]\n",
        "(2, 3)\n",
        "float64\n"
       ]
      }
     ],
     "prompt_number": 6
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "d = a + c\n",
      "print(d)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "[[ 1.   3.   5. ]\n",
        " [ 1.5  3.5  5.5]]\n"
       ]
      }
     ],
     "prompt_number": 7
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "d[0]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 8,
       "text": [
        "array([ 1.,  3.,  5.])"
       ]
      }
     ],
     "prompt_number": 8
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "d[0, 0]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 9,
       "text": [
        "1.0"
       ]
      }
     ],
     "prompt_number": 9
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "d[:, 0]"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 10,
       "text": [
        "array([ 1. ,  1.5])"
       ]
      }
     ],
     "prompt_number": 10
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "d.sum()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 11,
       "text": [
        "19.5"
       ]
      }
     ],
     "prompt_number": 11
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "d.mean()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 12,
       "text": [
        "3.25"
       ]
      }
     ],
     "prompt_number": 12
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "d.sum(axis=0)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 13,
       "text": [
        "array([  2.5,   6.5,  10.5])"
       ]
      }
     ],
     "prompt_number": 13
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "d.mean(axis=1)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 14,
       "text": [
        "array([ 3. ,  3.5])"
       ]
      }
     ],
     "prompt_number": 14
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Reshaping and In-Place Updating"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "e = np.arange(12)\n",
      "print(e)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "[ 0  1  2  3  4  5  6  7  8  9 10 11]\n"
       ]
      }
     ],
     "prompt_number": 15
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# f is a view of contents of e\n",
      "f = e.reshape(3, 4)\n",
      "print(f)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "[[ 0  1  2  3]\n",
        " [ 4  5  6  7]\n",
        " [ 8  9 10 11]]\n"
       ]
      }
     ],
     "prompt_number": 16
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Set last five values of e to zero\n",
      "e[5:] = 0\n",
      "print(e)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "[0 1 2 3 4 0 0 0 0 0 0 0]\n"
       ]
      }
     ],
     "prompt_number": 17
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# f is also updated\n",
      "f"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 18,
       "text": [
        "array([[0, 1, 2, 3],\n",
        "       [4, 0, 0, 0],\n",
        "       [0, 0, 0, 0]])"
       ]
      }
     ],
     "prompt_number": 18
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# OWNDATA shows f does not own its data\n",
      "f.flags"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 19,
       "text": [
        "  C_CONTIGUOUS : True\n",
        "  F_CONTIGUOUS : False\n",
        "  OWNDATA : False\n",
        "  WRITEABLE : True\n",
        "  ALIGNED : True\n",
        "  UPDATEIFCOPY : False"
       ]
      }
     ],
     "prompt_number": 19
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Combining Arrays"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "a"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 20,
       "text": [
        "array([1, 2, 3])"
       ]
      }
     ],
     "prompt_number": 20
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "b"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 21,
       "text": [
        "array([[0, 2, 4],\n",
        "       [1, 3, 5]])"
       ]
      }
     ],
     "prompt_number": 21
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "d"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 22,
       "text": [
        "array([[ 1. ,  3. ,  5. ],\n",
        "       [ 1.5,  3.5,  5.5]])"
       ]
      }
     ],
     "prompt_number": 22
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "np.concatenate([a, a, a])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 23,
       "text": [
        "array([1, 2, 3, 1, 2, 3, 1, 2, 3])"
       ]
      }
     ],
     "prompt_number": 23
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Use broadcasting when needed to do this automatically\n",
      "np.vstack([a, b, d])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 24,
       "text": [
        "array([[ 1. ,  2. ,  3. ],\n",
        "       [ 0. ,  2. ,  4. ],\n",
        "       [ 1. ,  3. ,  5. ],\n",
        "       [ 1. ,  3. ,  5. ],\n",
        "       [ 1.5,  3.5,  5.5]])"
       ]
      }
     ],
     "prompt_number": 24
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# In machine learning, useful to enrich or \n",
      "# add new/concatenate features with hstack\n",
      "np.hstack([b, d])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 25,
       "text": [
        "array([[ 0. ,  2. ,  4. ,  1. ,  3. ,  5. ],\n",
        "       [ 1. ,  3. ,  5. ,  1.5,  3.5,  5.5]])"
       ]
      }
     ],
     "prompt_number": 25
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "## Creating Fake Data and Adding Noise"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import pylab as plt\n",
      "import seaborn\n",
      "\n",
      "seaborn.set()\n",
      "\n",
      "x = np.random.uniform(1, 100, 1000)\n",
      "y = np.log(x) + np.random.normal(0, .3, 1000)\n",
      "\n",
      "plt.scatter(x, y)\n",
      "plt.show()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAeQAAAFVCAYAAAA+OJwpAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\ngDAbFwFblP8fiXMFbXvocncG
       "text": [
        "<matplotlib.figure.Figure at 0x108053c50>"
       ]
      }
     ],
     "prompt_number": 26
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 26
    }
   ],
   "metadata": {}
  }
 ]
}