blackboard.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "\n",
    "\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pylab as plt\n",
    "import seaborn as sns\n",
    "from IPython.core.display import clear_output\n",
    "from shaolin import KungFu,Dashboard\n",
    "class DensityPlot(Dashboard):\n",
    "    def __init__(self,data):\n",
    "        d_kwargs= {'num_xbins':(1,40,2,10),\n",
    "                 'num_ybins':(1,40,2,10),\n",
    "                 'grid': True,\n",
    "                 'link_bins':True,\n",
    "                 'plot_density':True,\n",
    "                 'reg_order':(1,10,1,1),\n",
    "                 'ci':\"(1,100,1,95)$N=ci&d=Confidence intervals\",\n",
    "                 'robust':[False],\n",
    "                 'scatter':True,\n",
    "                 'regression':True,\n",
    "                 'marginals':(['None','Histogram','KDE','Both'],'Both'),\n",
    "                 'bw':(0.001,10,0.05,0.5),\n",
    "                 'Title':'#Combining plots$N=title&D=',\n",
    "                 'dataset':['ALL','I','II','III','IV'],\n",
    "                 'save':False,\n",
    "                 #'@kernel':['gau','cos','biw','epa','tri','triw']\n",
    "                }\n",
    "        #general\n",
    "        title = '#Exploratory plots$N=title&D='\n",
    "        marginals = \"@['Both','None','Histogram','KDE']$d=Marginals\"\n",
    "        \n",
    "        dset = \"@['ALL','I','II','III','IV']$D=Dataset\"\n",
    "        x_cols = '@dd$D=X column&o='+str(data.columns.values.tolist())\n",
    "        y_cols = '@dd$D=Y column&o='+str(data.columns.values.tolist())+'&v='+data.columns[1]\n",
    "        save = \"@[False]$D=Save plot&n=save\"\n",
    "        data_layout = ['c$N=data_layout',[title,dset,['r$N=sub_row',[x_cols,y_cols]],marginals,save]]\n",
    "        #histograms\n",
    "        h_title = '#Historam options$N=h_title&D='\n",
    "        num_xbins = '@(1,40,2,10)$D=Num xbins&n=num_xbins'\n",
    "        num_ybins = '@(1,40,2,10)$D=Num ybins&n=num_ybins'\n",
    "        lbins = '@True$D=link_bins'\n",
    "        hist_layout = ['c$N=hist_layout',[h_title,num_xbins,num_ybins,lbins]]\n",
    "        \n",
    "        #scatter\n",
    "        s_title = '#Scatterplot options$N=s_title&D='\n",
    "        scat = '@[True]$D=Plot Scatter&n=scatter' \n",
    "        grid = '@True$D=Grid'\n",
    "        scatter_layout = ['c$N=scatter_layout',[s_title,scat,grid]]\n",
    "        #regression\n",
    "        r_title = '#Regression options$N=r_title&D='\n",
    "        reg = '@[True]$D=Plot Regression&n=regression'\n",
    "        robust = '@True$D=Robust'\n",
    "        reg_order = \"@(1,10,1,1)$D=Reg order\"\n",
    "        ci = \"@(1,100,1,95)$N=ci&d=Confidence intervals\"\n",
    "        reg_layout = ['c$N=reg_layout',[r_title,reg,reg_order,ci,robust]]\n",
    "        #kde\n",
    "        k_title = '#KDE plot options$N=k_title&D='\n",
    "        kde = '@[True]$D=Plot KDE&n=plot_density'\n",
    "        bw =  \"@(0.001,10,0.05,0.5)$D=Bandwidth&n=bw\"\n",
    "        kde_layout = ['@c$N=kde_layout',[k_title,kde,bw]]\n",
    "        dash = ['ac$N=dae_plot&t=General,Histogram,Scatter,KDE,Regression',[data_layout,\n",
    "                                                                        hist_layout,\n",
    "                                                                        scatter_layout,\n",
    "                                                                        kde_layout,\n",
    "                                                                        reg_layout,\n",
    "                                                                       ]\n",
    "               ]\n",
    "        self.data = data\n",
    "        Dashboard.__init__(self,dash=dash,mode='interactive')\n",
    "        \n",
    "        self.num_xbins.widget.continuous_update=False\n",
    "        self.num_ybins.widget.continuous_update=False\n",
    "        self.density_plot()\n",
    "        \n",
    "        \n",
    "        self.plot_density.value = False\n",
    "        self.regression.value = False\n",
    "        self.marginals.value = 'None'\n",
    "        self.scatter.value = False\n",
    "        self.grid.value = False\n",
    "        \n",
    "        \n",
    "        self.link_bins.observe(self.link_sliders)\n",
    "        self.observe(self.density_plot)\n",
    "        self.link_sliders()\n",
    "        \"\"\"self.marginal_x.value = 'None'\n",
    "        self.scatter.value = False\n",
    "        self.grid.value = False\n",
    "        self.plot_density.value = False\"\"\"\n",
    "        #self.density_plot()\n",
    "        self._i_plot = 0\n",
    "        #time.sleep(1)\n",
    "        #self.grid.value = True\n",
    "        \n",
    "        \n",
    "    \n",
    "    def link_sliders(self,_=None):\n",
    "        if self.link_bins():\n",
    "            self.num_ybins.visible = False\n",
    "            self.link('num_xbins','num_ybins')\n",
    "        else:\n",
    "            self.unlink('num_xbins','num_ybins')\n",
    "            self.num_ybins.visible = True\n",
    "            \n",
    "    def density_plot(self,_=None):\n",
    "        clear_output()\n",
    "        #if len(self.columns())>1:\n",
    "        #    subdf = self.data[list(self.columns())]\n",
    "        if self.kwargs['dataset']=='ALL':\n",
    "            self.x_column.value = 'x'\n",
    "            self.y_column.value = 'y'\n",
    "            subdf = self.data.copy()\n",
    "        else:\n",
    "            subdf = self.data[self.data['dataset']==self.dataset()].copy()\n",
    "        x,y = subdf[self.x_column()],subdf[self.y_column()]\n",
    "        x_regions = 10\n",
    "        y_regions = 10\n",
    "        x_bins = np.linspace(x.min(),x.max(),num=self.kwargs['num_xbins'])\n",
    "        y_bins = np.linspace(y.min(),y.max(),num=self.kwargs['num_ybins'])\n",
    "        \n",
    "        g = sns.JointGrid(x=self.x_column(), y=self.y_column(), data=subdf)\n",
    "        \n",
    "        g.fig.set_figwidth(14)\n",
    "        g.fig.set_figheight(9)\n",
    "        if self.kwargs['plot_density']:\n",
    "            g = g.plot_joint(sns.kdeplot, shade=True,alpha=0.5,legend=True,bw=self.kwargs['bw'],\n",
    "                             gridsize=int((len(x_bins)+len(y_bins))/2),\n",
    "                             clip=((x.min()*0.95,x.max()*1.05),(y.min()*0.95,y.max()*1.05)))\n",
    "        \n",
    "        if self.kwargs['scatter']:# and not self.kwargs['regression']:\n",
    "            g = g.plot_joint(plt.scatter,s=80,alpha=0.8)\n",
    "            \n",
    "        \n",
    "        if self.kwargs['marginals'] in ['Histogram','Both']:\n",
    "            _ = g.ax_marg_x.hist(x, alpha=.6,\n",
    "                                  bins=x_bins,normed=True)\n",
    "            _ = g.ax_marg_y.hist(y, alpha=.6,\n",
    "                                   orientation=\"horizontal\",\n",
    "                                   bins=y_bins,normed=True)\n",
    "        if self.kwargs['marginals'] in ['KDE','Both']:\n",
    "            clip = ((x.values.min()*0.95,x.values.max()*1.05),(y.values.min()*0.95,y.values.max()*1.05))\n",
    "            g = g.plot_marginals(sns.kdeplot, shade=True,alpha=0.5,\n",
    "                             gridsize=int((len(x_bins)+len(y_bins))/2))\n",
    "                             #clip=clip)\n",
    "        if self.kwargs['regression']:\n",
    "            g = g.plot_joint(sns.regplot,\n",
    "                             robust=self.kwargs['robust'],\n",
    "                             ci=self.kwargs['ci'],\n",
    "                             order=self.kwargs['reg_order'],\n",
    "                             truncate=True,\n",
    "                             scatter_kws={\"s\": 0})\n",
    "        if self.kwargs['grid']:\n",
    "            plt.grid(linewidth=2) \n",
    "            plt.xticks(x_bins)\n",
    "            plt.yticks(y_bins)\n",
    "            \n",
    "        plt.xlim(x.values.min()*0.95,x.values.max()*1.05)\n",
    "        plt.ylim(y.values.min()*0.95,y.values.max()*1.05)\n",
    "         \n",
    "        \n",
    "        #_ = plt.show()\n",
    "        if self.kwargs['save']:\n",
    "            _ =plt.savefig(\"density_plot_{}.png\".format(self._i_plot), dpi=100)\n",
    "            self._i_plot += 1\n",
    "        #clear_output(True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "from IPython.core.display import display\n",
    "%matplotlib inline\n",
    "sns.set(style=\"ticks\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "df = sns.load_dataset(\"anscombe\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA44AAAJaCAYAAABgLxkZAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x7f53c991f4e0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "\n",
    "DensityPlot(df)[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 48,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2073600.0"
      ]
     },
     "execution_count": 48,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "1080*16/9*1080"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "32*32"
   ]
  }
 ],
 "metadata": {
  "anaconda-cloud": {},
  "kernelspec": {
   "display_name": "Python [default]",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}