xccds/r_and_python.ipynb

## r_and_python.ipynb
{
 "metadata": {
  "celltoolbar": "Slideshow",
  "name": "",
  "signature": "sha256:07cf24c0b82f7afa22dc46b9d67f54385b82f38fbcc636a55aa92b89812f885b"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown",
     "metadata": {
      "slideshow": {
       "slide_type": "slide"
      }
     },
     "source": [
      "# R\u548cPython\u7684\u76f8\u9047\n",
      "- **\u8096\u51ef** \n",
      "![alt text](intro.jpg)"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {
      "slideshow": {
       "slide_type": "slide"
      }
     },
     "source": [
      "## \u9635\u8425\u4e4b\u4e89\n"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {
      "slideshow": {
       "slide_type": "fragment"
      }
     },
     "source": [
      "- Windows vs Linux"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {
      "slideshow": {
       "slide_type": "fragment"
      }
     },
     "source": [
      "- iPhone vs Andriod"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {
      "slideshow": {
       "slide_type": "fragment"
      }
     },
     "source": [
      "- \u751c\u8c46\u82b1 vs \u54b8\u8c46\u82b1"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {
      "slideshow": {
       "slide_type": "fragment"
      }
     },
     "source": [
      "- R vs Python"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {
      "slideshow": {
       "slide_type": "subslide"
      }
     },
     "source": [
      "## \u5927\u7eb2\n",
      "- \u4e8c\u79cd\u5de5\u5177\u7684\u4ecb\u7ecd\n",
      "- \u7ec4\u5408R\u548cPython\u7684\u65b9\u5f0f\uff08rpy2\uff09\n",
      "- \u5728ipython notebook\u91cc\u4f7f\u7528R\n",
      "- \u4e00\u4e2a\u7b80\u5355\u4f8b\u5b50"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {
      "slideshow": {
       "slide_type": "slide"
      }
     },
     "source": [
      "## \u4e24\u79cd\u5de5\u5177\u7684\u4ecb\u7ecd\uff1a\u5171\u540c\u70b9\n",
      "- \u5747\u4e3a\u5f00\u6e90\u514d\u8d39\n",
      "- \u5747\u53ef\u5728\u4e09\u79cd\u64cd\u4f5c\u7cfb\u7edf\u4e2d\u8fd0\u884c\n",
      "- \u5747\u6709\u5927\u91cf\u7684\u7528\u6237\u7fa4\u548c\u793e\u533a\u652f\u6301\n",
      "- \u5747\u6709\u5927\u91cf\u7684\u6269\u5c55\u5305\u548c\u6559\u7a0b\u8d44\u6e90\n",
      "- \u6700\u8fd1\u7684\u4e00\u9879\u8c03\u67e5\u663e\u793a\u5b83\u4eec\u662f\u4e1a\u754c\u4eba\u58eb\u6700\u4e3a\u559c\u7231\u7684\u4e24\u79cd\u5de5\u5177"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {
      "slideshow": {
       "slide_type": "subslide"
      }
     },
     "source": [
      "![alt text](kdpoll.png)"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {
      "slideshow": {
       "slide_type": "subslide"
      }
     },
     "source": [
      "![alt text](language.jpg)"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {
      "slideshow": {
       "slide_type": "subslide"
      }
     },
     "source": [
      "## Python\u7684\u6570\u636e\u5206\u6790\u80fd\u529b\n",
      "\n",
      "- [NumPy/Scipy](http://www.numpy.org/)  \n",
      "- [pandas](http://pandas.pydata.org/)  \n",
      "- [statsmodels](https://pypi.python.org/pypi/statsmodels)\n",
      "- [scikit-learn](http://scikit-learn.org/stable)\n",
      "- [PyMC](https://github.com/pymc-devs/pymc)  "
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {
      "slideshow": {
       "slide_type": "subslide"
      }
     },
     "source": [
      "## \u4e24\u79cd\u5de5\u5177\u7684\u4ecb\u7ecd\uff1a\u5dee\u5f02\u70b9\n",
      "\n",
      "- Python\u662f\u4e00\u79cd\u901a\u7528\u7f16\u7a0b\u5de5\u5177\n",
      "- R\u6709\u66f4\u4e3a\u4e30\u5bcc\u7684\u7edf\u8ba1\u5206\u6790\u51fd\u6570\n",
      "- R\u6709\u66f4\u597d\u7684\u53ef\u89c6\u5316\u5305\n",
      "- R\u7684\u6838\u5fc3\u8bed\u6cd5\u8f83\u4e3a\u7b80\u6d01\uff0c\u4f46R\u5305\u7684\u8bed\u6cd5\u517c\u6536\u5e76\u84c4\uff0c\u9519\u7efc\u590d\u6742\n",
      "\n",
      "Python:\n",
      "```\n",
      "results = sm.OLS(y, X).fit()\n",
      "```\n",
      "\n",
      "R:\n",
      "```\n",
      "results <- lm(y ~ x1 + x2 + x3, data=A)\n",
      "```\n"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {
      "slideshow": {
       "slide_type": "subslide"
      }
     },
     "source": [
      "## \u8fd0\u7528\u573a\u666f\n",
      "\n",
      "- \u7b97\u6cd5\u7814\u7a76R\uff0c\u751f\u4ea7\u5b9e\u8df5python\n",
      "- \u6839\u636e\u73b0\u6709\u8d44\u6e90\u8fdb\u884c\u9009\u62e9\n",
      "- \u5404\u81ea\u505a\u64c5\u957f\u7684\u4e8b\u60c5\uff0c\u5c06\u4ed6\u4eec\u7ec4\u5408\n",
      "![alt text](zuhe.jpg)"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {
      "slideshow": {
       "slide_type": "slide"
      }
     },
     "source": [
      "## \u7ec4\u5408R\u548cPython\u7684\u65b9\u5f0f\n",
      "\n",
      "- rpy2 \u63d0\u4f9b\u4e86\u7528Python\u8c03\u7528R\u7684\u5305\n",
      "- rPython \u63d0\u4f9b\u4e86\u7528R\u6765\u8c03\u7528Python\u7684\u5305"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {
      "slideshow": {
       "slide_type": "subslide"
      }
     },
     "source": [
      "## rpy2\u4f7f\u7528\u4f8b\u5b50\n",
      "\n",
      "- \u4f7f\u7528rpy2.robjects\u5305\u7684r\u5bf9\u8c61\n",
      "- r\u5bf9\u8c61\u53ef\u4ee5\u770b\u4f5c\u662fpython\u5185\u90e8\u7684\u4e00\u4e2aR\u63a7\u5236\u53f0"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import rpy2.robjects as robjects\n",
      "pi = robjects.r('pi')\n",
      "pi[0]"
     ],
     "language": "python",
     "metadata": {
      "slideshow": {
       "slide_type": "subslide"
      }
     },
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 126,
       "text": [
        "3.141592653589793"
       ]
      }
     ],
     "prompt_number": 126
    },
    {
     "cell_type": "markdown",
     "metadata": {
      "slideshow": {
       "slide_type": "subslide"
      }
     },
     "source": [
      "**\u7528R\u505a\u7ebf\u6027\u56de\u5f52**"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "rscript = '''\n",
      "df = read.csv('iris.csv')\n",
      "m = lm(Sepal_Length~Sepal_Width, data = df)\n",
      "'''\n",
      "pymodel = robjects.r(rscript)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 127
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "print pymodel.names"
     ],
     "language": "python",
     "metadata": {
      "slideshow": {
       "slide_type": "fragment"
      }
     },
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        " [1] \"coefficients\"  \"residuals\"     \"effects\"       \"rank\"         \n",
        " [5] \"fitted.values\" \"assign\"        \"qr\"            \"df.residual\"  \n",
        " [9] \"xlevels\"       \"call\"          \"terms\"         \"model\"        \n",
        "\n"
       ]
      }
     ],
     "prompt_number": 128
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import numpy as np\n",
      "print np.mean(pymodel.rx2('residuals'))"
     ],
     "language": "python",
     "metadata": {
      "slideshow": {
       "slide_type": "subslide"
      }
     },
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "-9.47390314347e-17\n"
       ]
      }
     ],
     "prompt_number": 129
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "res = robjects.r('summary(m)')\n",
      "print res"
     ],
     "language": "python",
     "metadata": {
      "slideshow": {
       "slide_type": "subslide"
      }
     },
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "\n",
        "Call:\n",
        "lm(formula = Sepal_Length ~ Sepal_Width, data = df)\n",
        "\n",
        "Residuals:\n",
        "    Min      1Q  Median      3Q     Max \n",
        "-1.5546 -0.6397 -0.1106  0.5569  2.2125 \n",
        "\n",
        "Coefficients:\n",
        "            Estimate Std. Error t value Pr(>|t|)    \n",
        "(Intercept)   6.4812     0.4813  13.466   <2e-16 ***\n",
        "Sepal_Width  -0.2089     0.1560  -1.339    0.183    \n",
        "---\n",
        "Signif. codes:  0 \u2018***\u2019 0.001 \u2018**\u2019 0.01 \u2018*\u2019 0.05 \u2018.\u2019 0.1 \u2018 \u2019 1\n",
        "\n",
        "Residual standard error: 0.8259 on 148 degrees of freedom\n",
        "Multiple R-squared:  0.01196,\tAdjusted R-squared:  0.005286 \n",
        "F-statistic: 1.792 on 1 and 148 DF,  p-value: 0.1828\n",
        "\n",
        "\n"
       ]
      }
     ],
     "prompt_number": 130
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "print res.names"
     ],
     "language": "python",
     "metadata": {
      "slideshow": {
       "slide_type": "subslide"
      }
     },
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        " [1] \"call\"          \"terms\"         \"residuals\"     \"coefficients\" \n",
        " [5] \"aliased\"       \"sigma\"         \"df\"            \"r.squared\"    \n",
        " [9] \"adj.r.squared\" \"fstatistic\"    \"cov.unscaled\" \n",
        "\n"
       ]
      }
     ],
     "prompt_number": 131
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "print res.rx2('coefficients')"
     ],
     "language": "python",
     "metadata": {
      "slideshow": {
       "slide_type": "fragment"
      }
     },
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "              Estimate Std. Error   t value     Pr(>|t|)\n",
        "(Intercept)  6.4812232  0.4812951 13.466214 1.726233e-27\n",
        "Sepal_Width -0.2088703  0.1560406 -1.338564 1.827652e-01\n",
        "\n"
       ]
      }
     ],
     "prompt_number": 132
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "print res.rx2('coefficients').rx(2,4) # p value of slope"
     ],
     "language": "python",
     "metadata": {
      "slideshow": {
       "slide_type": "fragment"
      }
     },
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "[1] 0.1827652\n",
        "\n"
       ]
      }
     ],
     "prompt_number": 133
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "print np.mat(res.rx2('coefficients'))\n",
      "np.mat(res.rx2('coefficients'))[1,3]"
     ],
     "language": "python",
     "metadata": {
      "slideshow": {
       "slide_type": "subslide"
      }
     },
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "[[  6.48122321e+00   4.81295118e-01   1.34662143e+01   1.72623298e-27]\n",
        " [ -2.08870294e-01   1.56040557e-01  -1.33856414e+00   1.82765215e-01]]\n"
       ]
      },
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 134,
       "text": [
        "0.18276521527136932"
       ]
      }
     ],
     "prompt_number": 134
    },
    {
     "cell_type": "markdown",
     "metadata": {
      "slideshow": {
       "slide_type": "slide"
      }
     },
     "source": [
      "## \u5728IPython Notebook\u91cc\u4f7f\u7528R"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {
      "slideshow": {
       "slide_type": "fragment"
      }
     },
     "source": [
      "## \u4ec0\u4e48\u662fIPython Notebook\n",
      "\n",
      "- IPython \u662f\u4e00\u4e2a\u52a0\u5f3a\u7248\u7684\u4ea4\u4e92\u5f0f Shell\n",
      "- IPython Notebook\u662f\u4e00\u4e2a\u4ea4\u4e92\u8ba1\u7b97\u5e73\u53f0\uff0c\u4e5f\u662f\u4e00\u4e2a\u8bb0\u5f55\u8ba1\u7b97\u8fc7\u7a0b\u7684\u7b14\u8bb0\u672c\n",
      "- \u6ee1\u8db3\u4ea4\u4e92\u8ba1\u7b97\u548c\u6279\u5904\u7406\u8ba1\u7b97\uff0c\u540c\u65f6\u80fd\u4fdd\u5b58\u811a\u672c\u6587\u4ef6\u4ee5\u8bb0\u5f55\u8ba1\u7b97\u8fc7\u7a0b\n",
      "- \u80fd\u517c\u5bb9markdown\u7b49\u8bed\u6cd5\uff0c\u6ee1\u8db3\u53ef\u91cd\u590d\u6570\u636e\u5206\u6790\u7684\u9700\u6c42\uff0c\u4ee5\u53ca\u8bfe\u7a0b\u6559\u5b66\u3001\u535a\u5ba2\u5199\u4f5c\n",
      "- \u80fd\u5728\u672c\u5730\u7684\u8ba1\u7b97\u673a\u4e0a\u5bf9\u8fdc\u7a0b\u670d\u52a1\u5668\u4e2d\u7684\u6570\u636e\u8fdb\u884c\u5206\u6790"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import numpy as np\n",
      "import matplotlib.pylab as plt\n",
      "from scipy import stats\n",
      "%matplotlib inline\n",
      "x = np.random.randn(300)\n",
      "density = stats.kde.gaussian_kde(x)\n",
      "plt.hist(x, 30, normed=1, alpha=0.5, facecolor='#377EB8')\n",
      "xd = np.linspace(min(x), max(x), 100)\n",
      "plt.plot(xd, density(xd), lw=2, alpha=0.2,color='r') #line\n",
      "plt.fill_between(xd, 0, density(xd), alpha=0.2, color='r')\n",
      "plt.show()"
     ],
     "language": "python",
     "metadata": {
      "slideshow": {
       "slide_type": "subslide"
      }
     },
     "outputs": [
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAXIAAAEACAYAAACuzv3DAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nlVKqxmmQK6VUjfv/QOPssTa0hewAAAAASUVORK5CYII=\n",
       "text": [
        "<matplotlib.figure.Figure at 0x10d85ac50>"
       ]
      }
     ],
     "prompt_number": 135
    },
    {
     "cell_type": "markdown",
     "metadata": {
      "slideshow": {
       "slide_type": "subslide"
      }
     },
     "source": [
      "## \u5982\u4f55\u5728notebook\u4e2d\u4f7f\u7528R\n"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%load_ext rpy2.ipython"
     ],
     "language": "python",
     "metadata": {
      "slideshow": {
       "slide_type": "fragment"
      }
     },
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "The rpy2.ipython extension is already loaded. To reload it, use:\n",
        "  %reload_ext rpy2.ipython\n"
       ]
      }
     ],
     "prompt_number": 136
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%%R\n",
      "df = read.csv('iris.csv')\n",
      "m = lm(Sepal_Length~Sepal_Width, data = df)\n",
      "res = summary(m)\n",
      "res$coefficients"
     ],
     "language": "python",
     "metadata": {
      "slideshow": {
       "slide_type": "subslide"
      }
     },
     "outputs": [
      {
       "metadata": {},
       "output_type": "display_data",
       "text": [
        "              Estimate Std. Error   t value     Pr(>|t|)\n",
        "(Intercept)  6.4812232  0.4812951 13.466214 1.726233e-27\n",
        "Sepal_Width -0.2088703  0.1560406 -1.338564 1.827652e-01\n"
       ]
      }
     ],
     "prompt_number": 137
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%%R -w 500 -h 300 \n",
      "# \u753b\u56fe\n",
      "x = rnorm(1000)\n",
      "hist(x,c='gray')"
     ],
     "language": "python",
     "metadata": {
      "slideshow": {
       "slide_type": "subslide"
      }
     },
     "outputs": [
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAfQAAAEsCAYAAAA1u0HIAAAEJGlDQ1BJQ0MgUHJvZmlsZQAAOBGF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\nKm0AAAAASUVORK5CYII=\n"
      }
     ],
     "prompt_number": 138
    },
    {
     "cell_type": "markdown",
     "metadata": {
      "slideshow": {
       "slide_type": "subslide"
      }
     },
     "source": [
      "**\u4e00\u4e2acell\u4e2d\u7684R\u4ee3\u7801\u9ed8\u8ba4\u4e0d\u4f1a\u548cpython\u8f93\u5165\u8f93\u51fa**"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%%R \n",
      "x = rnorm(100)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 139
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%%R\n",
      "summary(x)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "display_data",
       "text": [
        "    Min.  1st Qu.   Median     Mean  3rd Qu.     Max. \n",
        "-1.99400 -0.81550 -0.24020 -0.09816  0.70310  2.88200 \n"
       ]
      }
     ],
     "prompt_number": 140
    },
    {
     "cell_type": "markdown",
     "metadata": {
      "slideshow": {
       "slide_type": "subslide"
      }
     },
     "source": [
      "**\u548cpython\u4ea4\u4e92\u9700\u8981\u4f7f\u7528-i -o**"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%%R -o x,y\n",
      "x = rnorm(100)\n",
      "y = rnorm(100)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 141
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "x = np.array(x)\n",
      "y = np.array(y)\n",
      "z = np.random.choice(['r','b'], size=100, replace=True)\n",
      "plt.show(plt.scatter(x,y,s=80,c=z ,alpha=0.7))"
     ],
     "language": "python",
     "metadata": {
      "slideshow": {
       "slide_type": "subslide"
      }
     },
     "outputs": [
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAXAAAAEACAYAAACqOy3+AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nShX1/6Du2sN3OQRzAAAAAElFTkSuQmCC\n",
       "text": [
        "<matplotlib.figure.Figure at 0x10d302950>"
       ]
      }
     ],
     "prompt_number": 144
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import pandas as pd\n",
      "df = pd.DataFrame({'x':x, 'y':y, 'z':z})\n",
      "df.head()"
     ],
     "language": "python",
     "metadata": {
      "slideshow": {
       "slide_type": "subslide"
      }
     },
     "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>x</th>\n",
        "      <th>y</th>\n",
        "      <th>z</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td>-0.824222</td>\n",
        "      <td>-2.173650</td>\n",
        "      <td> b</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td>-1.929568</td>\n",
        "      <td>-0.550302</td>\n",
        "      <td> b</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td>-0.915369</td>\n",
        "      <td>-2.179241</td>\n",
        "      <td> b</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> 1.699432</td>\n",
        "      <td> 0.732482</td>\n",
        "      <td> b</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td>-0.215774</td>\n",
        "      <td>-0.523691</td>\n",
        "      <td> b</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 145,
       "text": [
        "          x         y  z\n",
        "0 -0.824222 -2.173650  b\n",
        "1 -1.929568 -0.550302  b\n",
        "2 -0.915369 -2.179241  b\n",
        "3  1.699432  0.732482  b\n",
        "4 -0.215774 -0.523691  b"
       ]
      }
     ],
     "prompt_number": 145
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%%R -i df -w 500 -h 300 \n",
      "library(ggplot2)\n",
      "p = ggplot(df,aes(x = x, y = y, color = z)) + geom_point(size=4)\n",
      "print(p)"
     ],
     "language": "python",
     "metadata": {
      "slideshow": {
       "slide_type": "subslide"
      }
     },
     "outputs": [
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAfQAAAEsCAYAAAA1u0HIAAAEJGlDQ1BJQ0MgUHJvZmlsZQAAOBGF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\nTkSuQmCC\n"
      }
     ],
     "prompt_number": 146
    },
    {
     "cell_type": "markdown",
     "metadata": {
      "slideshow": {
       "slide_type": "subslide"
      }
     },
     "source": [
      "**\u540c\u4e00\u4e2acell\u4e2d\u6df7\u7f16python\u548cR\u4ee3\u7801**"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%R -o coefs data(cars); model = lm(dist~speed, data=cars); coefs = model$coef \n",
      "coefs = np.array(coefs).round(2)\n",
      "coefs"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 147,
       "text": [
        "array([-17.58,   3.93])"
       ]
      }
     ],
     "prompt_number": 147
    },
    {
     "cell_type": "markdown",
     "metadata": {
      "slideshow": {
       "slide_type": "subslide"
      }
     },
     "source": [
      "**\u5982\u4f55\u4e0d\u9700\u8981%\u5c31\u53ef\u4ee5\u4f7f\u7528notebook**\n",
      "\n",
      "- http://jupyter.org/ \u53ef\u4ee5\u89e3\u6790R\u8bed\u8a00\u7684notebook\n",
      "- http://blog.dominodatalab.com/r-notebooks/ \u4e00\u79cd\u53d6\u5de7\u7684\u505a\u6cd5\uff0c\u4ecd\u662f\u4f7f\u7528ipython notebook"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {
      "slideshow": {
       "slide_type": "slide"
      }
     },
     "source": [
      "## \u4e00\u4e2a\u6574\u5408R\u548cpython\u7684\u4f8b\u5b50\n",
      "- python\u6293\u53d6\u7f51\u9875\uff0c\u7ed3\u5408R\u7684\u53ef\u89c6\u5316"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import requests\n",
      "from bs4 import BeautifulSoup\n",
      "import re\n",
      "url = \"http://movie.douban.com/top250\"\n",
      "r = requests.get(url)\n",
      "soup_packtpage = BeautifulSoup(r.text)"
     ],
     "language": "python",
     "metadata": {
      "slideshow": {
       "slide_type": "subslide"
      }
     },
     "outputs": [],
     "prompt_number": 148
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "def namefunc(movie):\n",
      "    names = [x.findChild('span',attrs={'class':'title'}).string for x in movie]\n",
      "    return names\n",
      "def scorefunc(movie):\n",
      "    scores = [float(str(x.findChild('em').string)) for x in movie]\n",
      "    return scores\n",
      "def numfunc(movie):\n",
      "    num = [x.findChild('span',attrs=None).string for x in movie]\n",
      "    num = [int(str(re.sub('\\D', '', x))) for x in num]\n",
      "    return num\n",
      "url = \"http://movie.douban.com/top250\"\n",
      "def getinfo(url):\n",
      "    r = requests.get(url)\n",
      "    soup_packtpage = BeautifulSoup(r.text)\n",
      "    movie = soup_packtpage.findAll('div',attrs={'class':'info'})\n",
      "    names = namefunc(movie)\n",
      "    scores = scorefunc(movie)\n",
      "    num = numfunc(movie)\n",
      "    res = {'names': names, 'scores': scores, 'num': num}\n",
      "    return res"
     ],
     "language": "python",
     "metadata": {
      "slideshow": {
       "slide_type": "subslide"
      }
     },
     "outputs": [],
     "prompt_number": 149
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "urls = []\n",
      "index = range(0,250,25)\n",
      "for x in index:\n",
      "    urls.append('http://movie.douban.com/top250?start='+str(x)+'&filter=&type=')\n",
      "urls"
     ],
     "language": "python",
     "metadata": {
      "slideshow": {
       "slide_type": "subslide"
      }
     },
     "outputs": [
      {
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 150,
       "text": [
        "['http://movie.douban.com/top250?start=0&filter=&type=',\n",
        " 'http://movie.douban.com/top250?start=25&filter=&type=',\n",
        " 'http://movie.douban.com/top250?start=50&filter=&type=',\n",
        " 'http://movie.douban.com/top250?start=75&filter=&type=',\n",
        " 'http://movie.douban.com/top250?start=100&filter=&type=',\n",
        " 'http://movie.douban.com/top250?start=125&filter=&type=',\n",
        " 'http://movie.douban.com/top250?start=150&filter=&type=',\n",
        " 'http://movie.douban.com/top250?start=175&filter=&type=',\n",
        " 'http://movie.douban.com/top250?start=200&filter=&type=',\n",
        " 'http://movie.douban.com/top250?start=225&filter=&type=']"
       ]
      }
     ],
     "prompt_number": 150
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "res = {'names': [], 'scores': [], 'num': []}\n",
      "for url in urls:\n",
      "    new = getinfo(url)\n",
      "    res['names'].extend(new['names'])\n",
      "    res['scores'].extend(new['scores'])\n",
      "    res['num'].extend(new['num'])"
     ],
     "language": "python",
     "metadata": {
      "slideshow": {
       "slide_type": "subslide"
      }
     },
     "outputs": [],
     "prompt_number": 151
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import pandas as pd\n",
      "df = pd.DataFrame(res)\n",
      "df.head()"
     ],
     "language": "python",
     "metadata": {
      "slideshow": {
       "slide_type": "subslide"
      }
     },
     "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>names</th>\n",
        "      <th>num</th>\n",
        "      <th>scores</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td>  \u8096\u7533\u514b\u7684\u6551\u8d4e</td>\n",
        "      <td> 573624</td>\n",
        "      <td> 9.6</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> \u8fd9\u4e2a\u6740\u624b\u4e0d\u592a\u51b7</td>\n",
        "      <td> 543630</td>\n",
        "      <td> 9.4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td>    \u963f\u7518\u6b63\u4f20</td>\n",
        "      <td> 485031</td>\n",
        "      <td> 9.4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td>    \u9738\u738b\u522b\u59ec</td>\n",
        "      <td> 389513</td>\n",
        "      <td> 9.4</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td>    \u7f8e\u4e3d\u4eba\u751f</td>\n",
        "      <td> 265729</td>\n",
        "      <td> 9.4</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 158,
       "text": [
        "     names     num  scores\n",
        "0   \u8096\u7533\u514b\u7684\u6551\u8d4e  573624     9.6\n",
        "1  \u8fd9\u4e2a\u6740\u624b\u4e0d\u592a\u51b7  543630     9.4\n",
        "2     \u963f\u7518\u6b63\u4f20  485031     9.4\n",
        "3     \u9738\u738b\u522b\u59ec  389513     9.4\n",
        "4     \u7f8e\u4e3d\u4eba\u751f  265729     9.4"
       ]
      }
     ],
     "prompt_number": 158
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "%%R -i df -w 500 -h 300 \n",
      "library(ggplot2)\n",
      "p = ggplot(df,aes(x = num, y = scores)) + geom_point(size=4,alpha=0.5) + stat_smooth()\n",
      "print(p)"
     ],
     "language": "python",
     "metadata": {
      "slideshow": {
       "slide_type": "subslide"
      }
     },
     "outputs": [
      {
       "metadata": {},
       "output_type": "display_data",
       "text": [
        "geom_smooth: method=\"auto\" and size of largest group is <1000, so using loess. Use 'method = x' to change the smoothing method.\n"
       ]
      },
      {
       "metadata": {},
       "output_type": "display_data",
       "png": "iVBORw0KGgoAAAANSUhEUgAAAfQAAAEsCAYAAAA1u0HIAAAEJGlDQ1BJQ0MgUHJvZmlsZQAAOBGF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\n"
      }
     ],
     "prompt_number": 153
    },
    {
     "cell_type": "markdown",
     "metadata": {
      "slideshow": {
       "slide_type": "subslide"
      }
     },
     "source": [
      "**Thank You!**"
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "!ipython nbconvert r_and_python.ipynb --to slides --post serve"
     ],
     "language": "python",
     "metadata": {
      "slideshow": {
       "slide_type": "skip"
      }
     },
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "[NbConvertApp] Using existing profile dir: u'/Users/xiaokai/.ipython/profile_default'\r\n"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "[NbConvertApp] Converting notebook r_and_python.ipynb to slides\r\n",
        "[NbConvertApp] Support files will be in r_and_python_files/\r\n"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "[NbConvertApp] Loaded template slides_reveal.tpl\r\n"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "/Users/xiaokai/anaconda/lib/python2.7/site-packages/IPython/nbconvert/filters/markdown.py:78: UserWarning: Node.js 0.9.12 or later wasn't found.\r\n",
        "Nbconvert will try to use Pandoc instead.\r\n",
        "  \"Nbconvert will try to use Pandoc instead.\")\r\n"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "[NbConvertApp] Writing 392322 bytes to r_and_python.slides.html\r\n",
        "[NbConvertApp] Redirecting reveal.js requests to https://cdn.jsdelivr.net/reveal.js/2.5.0\r\n",
        "Serving your slides at http://127.0.0.1:8000/r_and_python.slides.html\r\n",
        "Use Control-C to stop this server\r\n"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "WARNING:tornado.access:404 GET /custom.css (127.0.0.1) 0.84ms\r\n"
       ]
      },
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "^C\r\n",
        "Interrupted\r\n",
        "\r\n"
       ]
      }
     ],
     "prompt_number": 159
    }
   ],
   "metadata": {}
  }
 ]
}