Plotly from matplotlib bars3.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "\n",
    "import math as m\n",
    "\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "import plotly.plotly as py\n",
    "import plotly.graph_objs as go\n",
    "\n",
    "# (*) Useful Python/Plotly tools\n",
    "import plotly.tools as tls\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "              A                  B         C         D         E\n",
      "0   foo foo foo        one one one    I1-one -1.292569 -0.843744\n",
      "1   bar bar bar        two two two    I2-two  0.136429  0.903531\n",
      "2   bar bar bar  three three three  I3-three -0.287419 -0.084308\n",
      "3   foo foo foo        two two two   I4-four -0.729803 -0.235186\n",
      "4   foo foo foo  three three three  I3-three -1.718906  0.002448\n",
      "5   bar bar bar        one one one   I4-four -0.190282 -0.929152\n",
      "6   bar bar bar        one one one    I1-one  1.078054  0.642704\n",
      "7   foo foo foo        two two two    I2-two -0.618334  0.705067\n",
      "8   foo foo foo  three three three    I1-one -0.151458  0.664500\n",
      "9   bar bar bar        two two two    I2-two -0.639363  1.505479\n",
      "10  bar bar bar  three three three  I3-three -1.136008 -1.214076\n",
      "11  foo foo foo        one one one   I4-four  0.717100  0.860251\n",
      "12  foo foo foo        one one one  I3-three  1.634142 -0.742396\n",
      "13  bar bar bar        two two two   I4-four  1.522161 -0.564526\n",
      "14  bar bar bar  three three three    I1-one -0.032455 -1.929642\n",
      "15  foo foo foo        two two two    I2-two -0.083564 -0.420016\n",
      "16  foo foo foo  three three three    I1-one  0.653361  1.317590\n",
      "17  bar bar bar        one one one    I2-two -0.764061 -1.004898\n",
      "18  bar bar bar        one one one  I3-three -0.261806 -1.198377\n",
      "19  foo foo foo        two two two   I4-four -0.640479  1.235738\n",
      "20  foo foo foo  three three three  I3-three  0.882835 -0.742760\n",
      "21  bar bar bar        two two two   I4-four  0.345015  1.393680\n",
      "22  bar bar bar  three three three    I1-one -0.767344  0.396372\n",
      "23  foo foo foo        one one one    I2-two  0.021742  1.438138\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>C</th>\n",
       "      <th>I1-one</th>\n",
       "      <th>I2-two</th>\n",
       "      <th>I3-three</th>\n",
       "      <th>I4-four</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>A</th>\n",
       "      <th>B</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th rowspan=\"3\" valign=\"top\">bar bar bar</th>\n",
       "      <th>one one one</th>\n",
       "      <td>1.078054</td>\n",
       "      <td>-0.764061</td>\n",
       "      <td>-0.261806</td>\n",
       "      <td>-0.190282</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>three three three</th>\n",
       "      <td>-0.399899</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-0.711714</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>two two two</th>\n",
       "      <td>NaN</td>\n",
       "      <td>-0.251467</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.933588</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th rowspan=\"3\" valign=\"top\">foo foo foo</th>\n",
       "      <th>one one one</th>\n",
       "      <td>-1.292569</td>\n",
       "      <td>0.021742</td>\n",
       "      <td>1.634142</td>\n",
       "      <td>0.717100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>three three three</th>\n",
       "      <td>0.250952</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-0.418035</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>two two two</th>\n",
       "      <td>NaN</td>\n",
       "      <td>-0.350949</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-0.685141</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "C                                I1-one    I2-two  I3-three   I4-four\n",
       "A           B                                                        \n",
       "bar bar bar one one one        1.078054 -0.764061 -0.261806 -0.190282\n",
       "            three three three -0.399899       NaN -0.711714       NaN\n",
       "            two two two             NaN -0.251467       NaN  0.933588\n",
       "foo foo foo one one one       -1.292569  0.021742  1.634142  0.717100\n",
       "            three three three  0.250952       NaN -0.418035       NaN\n",
       "            two two two             NaN -0.350949       NaN -0.685141"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.DataFrame({'A' : ['foo foo foo', 'bar bar bar', 'bar bar bar', 'foo foo foo']*6,\n",
    "                   'B' : ['one one one', 'two two two', 'three three three', 'two two two', 'three three three', 'one one one']*4,\n",
    "                  'C' : ['I1-one', 'I2-two', 'I3-three', 'I4-four', 'I3-three', 'I4-four','I1-one', 'I2-two']*3,\n",
    "                  'D' : np.random.randn(24),\n",
    "                  'E' : np.random.randn(24)})\n",
    "\n",
    "# Transform strings into floats, i.e., words into numbers\n",
    "#df['D'] = df['D'].astype(float)\n",
    "#df['D']=round(df['D'], 2)\n",
    "print(df)\n",
    "\n",
    "e = pd.pivot_table(df, index=['A','B'], columns='C',values='E')\n",
    "p = pd.pivot_table(df, index=['A','B'], columns='C',values='D')\n",
    "p"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.text.Text at 0x8c5cf4390>"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYgAAAEKCAYAAAAIO8L1AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nCnAAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x8c5cde780>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.close('all')  # close all open figures\n",
    "fig, ax = plt.subplots()\n",
    "\n",
    "xv = np.random.randn(12)\n",
    "\n",
    "ax.bar(1. + np.arange(len(xv)), xv, align='center')\n",
    "# Annotate with text\n",
    "ax.set_xticks(1. + np.arange(len(xv)))\n",
    "for i, val in enumerate(xv):\n",
    "    ax.text(i+1, val/2, str(round(val, 2)*100)+'%', va='center',\n",
    "ha='center', color='black')\n",
    "ax.set_ylabel('%')\n",
    "ax.set_title('Relative Frequency Barchart')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<iframe id=\"igraph\" scrolling=\"no\" style=\"border:none;\"seamless=\"seamless\" src=\"https://plot.ly/~xpt/109.embed\" height=\"525px\" width=\"100%\"></iframe>"
      ],
      "text/plain": [
       "<plotly.tools.PlotlyDisplay object>"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Convert mpl figure object to Plotly plot \n",
    "# py.iplot_mpl(fig, strip_style=True, filename='test/bars_ann')\n",
    "# https://plot.ly/~xpt/109"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAg8AAAD7CAYAAADtuXeEAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nrkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x8c6061208>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.close('all')  # close all open figures\n",
    "fig, ax = plt.subplots()\n",
    "\n",
    "p.plot(kind='barh', xerr=e, ax = ax, width=0.85)\n",
    "ax.invert_yaxis()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "def autolabel(rects):\n",
    "    #if height constant: hbars, vbars otherwise\n",
    "    if (np.diff([plt.getp(item, 'width') for item in rects])==0).all():\n",
    "        x_pos = [rect.get_x() + rect.get_width()/2. for rect in rects]\n",
    "        y_pos = [rect.get_y() + 1.05*rect.get_height() for rect in rects]\n",
    "        scores = [plt.getp(item, 'height') for item in rects]\n",
    "    else:\n",
    "        x_pos = [rect.get_width()+.3 for rect in rects]\n",
    "        y_pos = [rect.get_y()+.3*rect.get_height() for rect in rects]\n",
    "        scores = [plt.getp(item, 'width') for item in rects]\n",
    "    # attach some text labels\n",
    "    for rect, x, y, s in zip(rects, x_pos, y_pos, scores):\n",
    "        ax.text(x, \n",
    "                y,\n",
    "                #'%s'%s,\n",
    "                str(round(s, 2)*100)+'%',\n",
    "                ha='center', va='bottom')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAg8AAAD7CAYAAADtuXeEAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nrkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x8c61b8898>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.close('all')  # close all open figures\n",
    "fig, ax = plt.subplots()\n",
    "\n",
    "p.plot(kind='barh', xerr=e, ax = ax, width=0.85)\n",
    "ax.invert_yaxis()\n",
    "\n",
    "autolabel(ax.patches)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.5.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}