ghl3/pymc_test.ipynb

## pymc_test.ipynb
{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "%matplotlib inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Couldn't import dot_parser, loading of dot files will not be possible.\n"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import pymc3 as pm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "from StringIO import StringIO\n",
    "\n",
    "data = \"\"\"Location,Tobacco,Alcohol\n",
    "North,6.47,4.03\n",
    "Yorkshire,6.13,3.76\n",
    "Northeast,6.19,3.77\n",
    "East Midlands,4.89,3.34\n",
    "West Midlands,5.63,3.47\n",
    "East Anglia,4.52,2.92\n",
    "Southeast,5.89,3.2\n",
    "Southwest,4.79,2.71\n",
    "Wales,5.27,3.53\n",
    "Scotland,6.08,4.51\"\"\"\n",
    "\n",
    "df = pd.read_csv(StringIO(data))\n",
    "df['Eins'] = 1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Location</th>\n",
       "      <th>Tobacco</th>\n",
       "      <th>Alcohol</th>\n",
       "      <th>Eins</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>North</td>\n",
       "      <td>6.47</td>\n",
       "      <td>4.03</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Yorkshire</td>\n",
       "      <td>6.13</td>\n",
       "      <td>3.76</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Northeast</td>\n",
       "      <td>6.19</td>\n",
       "      <td>3.77</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>East Midlands</td>\n",
       "      <td>4.89</td>\n",
       "      <td>3.34</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>West Midlands</td>\n",
       "      <td>5.63</td>\n",
       "      <td>3.47</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>East Anglia</td>\n",
       "      <td>4.52</td>\n",
       "      <td>2.92</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Southeast</td>\n",
       "      <td>5.89</td>\n",
       "      <td>3.20</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Southwest</td>\n",
       "      <td>4.79</td>\n",
       "      <td>2.71</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Wales</td>\n",
       "      <td>5.27</td>\n",
       "      <td>3.53</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>Scotland</td>\n",
       "      <td>6.08</td>\n",
       "      <td>4.51</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        Location  Tobacco  Alcohol  Eins\n",
       "0          North     6.47     4.03     1\n",
       "1      Yorkshire     6.13     3.76     1\n",
       "2      Northeast     6.19     3.77     1\n",
       "3  East Midlands     4.89     3.34     1\n",
       "4  West Midlands     5.63     3.47     1\n",
       "5    East Anglia     4.52     2.92     1\n",
       "6      Southeast     5.89     3.20     1\n",
       "7      Southwest     4.79     2.71     1\n",
       "8          Wales     5.27     3.53     1\n",
       "9       Scotland     6.08     4.51     1"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false,
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "ERROR (theano.gof.opt): SeqOptimizer apply <theano.tensor.opt.FusionOptimizer object at 0x10a551f50>\n",
      "ERROR:theano.gof.opt:SeqOptimizer apply <theano.tensor.opt.FusionOptimizer object at 0x10a551f50>\n",
      "ERROR (theano.gof.opt): Traceback:\n",
      "ERROR:theano.gof.opt:Traceback:\n",
      "ERROR (theano.gof.opt): Traceback (most recent call last):\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/gof/opt.py\", line 195, in apply\n",
      "    sub_prof = optimizer.optimize(fgraph)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/gof/opt.py\", line 81, in optimize\n",
      "    ret = self.apply(fgraph, *args, **kwargs)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/opt.py\", line 5498, in apply\n",
      "    new_outputs = self.optimizer(node)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/opt.py\", line 5433, in local_fuse\n",
      "    n = OP(C)(*inputs).owner\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/elemwise.py\", line 496, in __init__\n",
      "    scalar_op.nout)\n",
      "ValueError: Cannot construct a ufunc with more than 32 operands (requested number were: inputs = 51 and outputs = 1)\n",
      "\n",
      "ERROR:theano.gof.opt:Traceback (most recent call last):\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/gof/opt.py\", line 195, in apply\n",
      "    sub_prof = optimizer.optimize(fgraph)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/gof/opt.py\", line 81, in optimize\n",
      "    ret = self.apply(fgraph, *args, **kwargs)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/opt.py\", line 5498, in apply\n",
      "    new_outputs = self.optimizer(node)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/opt.py\", line 5433, in local_fuse\n",
      "    n = OP(C)(*inputs).owner\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/elemwise.py\", line 496, in __init__\n",
      "    scalar_op.nout)\n",
      "ValueError: Cannot construct a ufunc with more than 32 operands (requested number were: inputs = 51 and outputs = 1)\n",
      "\n",
      "ERROR (theano.gof.opt): SeqOptimizer apply <theano.tensor.opt.FusionOptimizer object at 0x10a551f50>\n",
      "ERROR:theano.gof.opt:SeqOptimizer apply <theano.tensor.opt.FusionOptimizer object at 0x10a551f50>\n",
      "ERROR (theano.gof.opt): Traceback:\n",
      "ERROR:theano.gof.opt:Traceback:\n",
      "ERROR (theano.gof.opt): Traceback (most recent call last):\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/gof/opt.py\", line 195, in apply\n",
      "    sub_prof = optimizer.optimize(fgraph)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/gof/opt.py\", line 81, in optimize\n",
      "    ret = self.apply(fgraph, *args, **kwargs)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/opt.py\", line 5498, in apply\n",
      "    new_outputs = self.optimizer(node)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/opt.py\", line 5433, in local_fuse\n",
      "    n = OP(C)(*inputs).owner\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/elemwise.py\", line 496, in __init__\n",
      "    scalar_op.nout)\n",
      "ValueError: Cannot construct a ufunc with more than 32 operands (requested number were: inputs = 47 and outputs = 1)\n",
      "\n",
      "ERROR:theano.gof.opt:Traceback (most recent call last):\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/gof/opt.py\", line 195, in apply\n",
      "    sub_prof = optimizer.optimize(fgraph)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/gof/opt.py\", line 81, in optimize\n",
      "    ret = self.apply(fgraph, *args, **kwargs)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/opt.py\", line 5498, in apply\n",
      "    new_outputs = self.optimizer(node)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/opt.py\", line 5433, in local_fuse\n",
      "    n = OP(C)(*inputs).owner\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/elemwise.py\", line 496, in __init__\n",
      "    scalar_op.nout)\n",
      "ValueError: Cannot construct a ufunc with more than 32 operands (requested number were: inputs = 47 and outputs = 1)\n",
      "\n",
      "ERROR (theano.gof.opt): SeqOptimizer apply <theano.tensor.opt.FusionOptimizer object at 0x10a551f50>\n",
      "ERROR:theano.gof.opt:SeqOptimizer apply <theano.tensor.opt.FusionOptimizer object at 0x10a551f50>\n",
      "ERROR (theano.gof.opt): Traceback:\n",
      "ERROR:theano.gof.opt:Traceback:\n",
      "ERROR (theano.gof.opt): Traceback (most recent call last):\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/gof/opt.py\", line 195, in apply\n",
      "    sub_prof = optimizer.optimize(fgraph)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/gof/opt.py\", line 81, in optimize\n",
      "    ret = self.apply(fgraph, *args, **kwargs)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/opt.py\", line 5498, in apply\n",
      "    new_outputs = self.optimizer(node)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/opt.py\", line 5433, in local_fuse\n",
      "    n = OP(C)(*inputs).owner\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/elemwise.py\", line 496, in __init__\n",
      "    scalar_op.nout)\n",
      "ValueError: Cannot construct a ufunc with more than 32 operands (requested number were: inputs = 47 and outputs = 1)\n",
      "\n",
      "ERROR:theano.gof.opt:Traceback (most recent call last):\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/gof/opt.py\", line 195, in apply\n",
      "    sub_prof = optimizer.optimize(fgraph)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/gof/opt.py\", line 81, in optimize\n",
      "    ret = self.apply(fgraph, *args, **kwargs)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/opt.py\", line 5498, in apply\n",
      "    new_outputs = self.optimizer(node)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/opt.py\", line 5433, in local_fuse\n",
      "    n = OP(C)(*inputs).owner\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/elemwise.py\", line 496, in __init__\n",
      "    scalar_op.nout)\n",
      "ValueError: Cannot construct a ufunc with more than 32 operands (requested number were: inputs = 47 and outputs = 1)\n",
      "\n",
      "ERROR (theano.gof.opt): SeqOptimizer apply <theano.tensor.opt.FusionOptimizer object at 0x10a551f50>\n",
      "ERROR:theano.gof.opt:SeqOptimizer apply <theano.tensor.opt.FusionOptimizer object at 0x10a551f50>\n",
      "ERROR (theano.gof.opt): Traceback:\n",
      "ERROR:theano.gof.opt:Traceback:\n",
      "ERROR (theano.gof.opt): Traceback (most recent call last):\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/gof/opt.py\", line 195, in apply\n",
      "    sub_prof = optimizer.optimize(fgraph)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/gof/opt.py\", line 81, in optimize\n",
      "    ret = self.apply(fgraph, *args, **kwargs)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/opt.py\", line 5498, in apply\n",
      "    new_outputs = self.optimizer(node)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/opt.py\", line 5445, in local_fuse\n",
      "    ret = local_fuse(n)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/opt.py\", line 5433, in local_fuse\n",
      "    n = OP(C)(*inputs).owner\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/elemwise.py\", line 496, in __init__\n",
      "    scalar_op.nout)\n",
      "ValueError: Cannot construct a ufunc with more than 32 operands (requested number were: inputs = 40 and outputs = 1)\n",
      "\n",
      "ERROR:theano.gof.opt:Traceback (most recent call last):\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/gof/opt.py\", line 195, in apply\n",
      "    sub_prof = optimizer.optimize(fgraph)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/gof/opt.py\", line 81, in optimize\n",
      "    ret = self.apply(fgraph, *args, **kwargs)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/opt.py\", line 5498, in apply\n",
      "    new_outputs = self.optimizer(node)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/opt.py\", line 5445, in local_fuse\n",
      "    ret = local_fuse(n)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/opt.py\", line 5433, in local_fuse\n",
      "    n = OP(C)(*inputs).owner\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/elemwise.py\", line 496, in __init__\n",
      "    scalar_op.nout)\n",
      "ValueError: Cannot construct a ufunc with more than 32 operands (requested number were: inputs = 40 and outputs = 1)\n",
      "\n",
      "ERROR (theano.gof.opt): SeqOptimizer apply <theano.tensor.opt.FusionOptimizer object at 0x10a551f50>\n",
      "ERROR:theano.gof.opt:SeqOptimizer apply <theano.tensor.opt.FusionOptimizer object at 0x10a551f50>\n",
      "ERROR (theano.gof.opt): Traceback:\n",
      "ERROR:theano.gof.opt:Traceback:\n",
      "ERROR (theano.gof.opt): Traceback (most recent call last):\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/gof/opt.py\", line 195, in apply\n",
      "    sub_prof = optimizer.optimize(fgraph)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/gof/opt.py\", line 81, in optimize\n",
      "    ret = self.apply(fgraph, *args, **kwargs)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/opt.py\", line 5498, in apply\n",
      "    new_outputs = self.optimizer(node)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/opt.py\", line 5445, in local_fuse\n",
      "    ret = local_fuse(n)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/opt.py\", line 5433, in local_fuse\n",
      "    n = OP(C)(*inputs).owner\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/elemwise.py\", line 496, in __init__\n",
      "    scalar_op.nout)\n",
      "ValueError: Cannot construct a ufunc with more than 32 operands (requested number were: inputs = 33 and outputs = 1)\n",
      "\n",
      "ERROR:theano.gof.opt:Traceback (most recent call last):\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/gof/opt.py\", line 195, in apply\n",
      "    sub_prof = optimizer.optimize(fgraph)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/gof/opt.py\", line 81, in optimize\n",
      "    ret = self.apply(fgraph, *args, **kwargs)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/opt.py\", line 5498, in apply\n",
      "    new_outputs = self.optimizer(node)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/opt.py\", line 5445, in local_fuse\n",
      "    ret = local_fuse(n)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/opt.py\", line 5433, in local_fuse\n",
      "    n = OP(C)(*inputs).owner\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/elemwise.py\", line 496, in __init__\n",
      "    scalar_op.nout)\n",
      "ValueError: Cannot construct a ufunc with more than 32 operands (requested number were: inputs = 33 and outputs = 1)\n",
      "\n",
      "ERROR (theano.gof.opt): SeqOptimizer apply <theano.tensor.opt.FusionOptimizer object at 0x10a551f50>\n",
      "ERROR:theano.gof.opt:SeqOptimizer apply <theano.tensor.opt.FusionOptimizer object at 0x10a551f50>\n",
      "ERROR (theano.gof.opt): Traceback:\n",
      "ERROR:theano.gof.opt:Traceback:\n",
      "ERROR (theano.gof.opt): Traceback (most recent call last):\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/gof/opt.py\", line 195, in apply\n",
      "    sub_prof = optimizer.optimize(fgraph)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/gof/opt.py\", line 81, in optimize\n",
      "    ret = self.apply(fgraph, *args, **kwargs)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/opt.py\", line 5498, in apply\n",
      "    new_outputs = self.optimizer(node)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/opt.py\", line 5445, in local_fuse\n",
      "    ret = local_fuse(n)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/opt.py\", line 5433, in local_fuse\n",
      "    n = OP(C)(*inputs).owner\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/elemwise.py\", line 496, in __init__\n",
      "    scalar_op.nout)\n",
      "ValueError: Cannot construct a ufunc with more than 32 operands (requested number were: inputs = 33 and outputs = 1)\n",
      "\n",
      "ERROR:theano.gof.opt:Traceback (most recent call last):\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/gof/opt.py\", line 195, in apply\n",
      "    sub_prof = optimizer.optimize(fgraph)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/gof/opt.py\", line 81, in optimize\n",
      "    ret = self.apply(fgraph, *args, **kwargs)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/opt.py\", line 5498, in apply\n",
      "    new_outputs = self.optimizer(node)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/opt.py\", line 5445, in local_fuse\n",
      "    ret = local_fuse(n)\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/opt.py\", line 5433, in local_fuse\n",
      "    n = OP(C)(*inputs).owner\n",
      "  File \"/Library/Frameworks/Python.framework/Versions/2.7/lib/python2.7/site-packages/Theano-0.7.0-py2.7.egg/theano/tensor/elemwise.py\", line 496, in __init__\n",
      "    scalar_op.nout)\n",
      "ValueError: Cannot construct a ufunc with more than 32 operands (requested number were: inputs = 33 and outputs = 1)\n",
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " [-----------------100%-----------------] 10000 of 10000 complete in 48.3 sec"
     ]
    }
   ],
   "source": [
    "with pm.Model() as model:\n",
    "    Eins = pm.Uniform('Eins', lower=-10, upper=10)\n",
    "    Tobacco = pm.Uniform('Tobacco', lower=-10, upper=10)\n",
    "    sigma = pm.Uniform('sigma', lower=0, upper=10)\n",
    "\n",
    "    alc_mean = Eins*df.Eins + Tobacco*df.Tobacco\n",
    "    \n",
    "    likelihood = pm.Normal('Alcohol', mu=alc_mean, sd=sigma, observed=df.Alcohol)\n",
    "    \n",
    "    start = pm.find_MAP()\n",
    "    step = pm.NUTS(state=start)\n",
    "    trace = pm.sample(10000, step, start=start, progressbar=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[<matplotlib.axes._subplots.AxesSubplot object at 0x10b07fc10>,\n",
       "        <matplotlib.axes._subplots.AxesSubplot object at 0x117777750>],\n",
       "       [<matplotlib.axes._subplots.AxesSubplot object at 0x1177a2c10>,\n",
       "        <matplotlib.axes._subplots.AxesSubplot object at 0x117900610>],\n",
       "       [<matplotlib.axes._subplots.AxesSubplot object at 0x117910bd0>,\n",
       "        <matplotlib.axes._subplots.AxesSubplot object at 0x117947a10>],\n",
       "       [<matplotlib.axes._subplots.AxesSubplot object at 0x117974190>,\n",
       "        <matplotlib.axes._subplots.AxesSubplot object at 0x117989210>],\n",
       "       [<matplotlib.axes._subplots.AxesSubplot object at 0x1179bbbd0>,\n",
       "        <matplotlib.axes._subplots.AxesSubplot object at 0x1179e7190>],\n",
       "       [<matplotlib.axes._subplots.AxesSubplot object at 0x117d02c90>,\n",
       "        <matplotlib.axes._subplots.AxesSubplot object at 0x117d2f8d0>]], dtype=object)"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA1kAAANaCAYAAAB7lYadAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nAAAAAElFTkSuQmCC\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x10b0735d0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "pm.traceplot(trace)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Eins_interval:\n",
      "\n",
      "  Mean             SD               MC Error         95% HPD interval\n",
      "  -------------------------------------------------------------------\n",
      "  \n",
      "  0.041            0.374            0.013            [-0.669, 0.751]\n",
      "\n",
      "  Posterior quantiles:\n",
      "  2.5            25             50             75             97.5\n",
      "  |--------------|==============|==============|--------------|\n",
      "  \n",
      "  -0.668         -0.145         0.030          0.211          0.754\n",
      "\n",
      "\n",
      "Tobacco_interval:\n",
      "\n",
      "  Mean             SD               MC Error         95% HPD interval\n",
      "  -------------------------------------------------------------------\n",
      "  \n",
      "  0.120            0.061            0.002            [-0.002, 0.242]\n",
      "\n",
      "  Posterior quantiles:\n",
      "  2.5            25             50             75             97.5\n",
      "  |--------------|==============|==============|--------------|\n",
      "  \n",
      "  -0.002         0.089          0.121          0.152          0.243\n",
      "\n",
      "\n",
      "sigma_interval:\n",
      "\n",
      "  Mean             SD               MC Error         95% HPD interval\n",
      "  -------------------------------------------------------------------\n",
      "  \n",
      "  -2.955           0.864            0.027            [-3.667, -2.209]\n",
      "\n",
      "  Posterior quantiles:\n",
      "  2.5            25             50             75             97.5\n",
      "  |--------------|==============|==============|--------------|\n",
      "  \n",
      "  -3.587         -3.287         -3.086         -2.838         -1.880\n",
      "\n",
      "\n",
      "Eins:\n",
      "\n",
      "  Mean             SD               MC Error         95% HPD interval\n",
      "  -------------------------------------------------------------------\n",
      "  \n",
      "  0.187            1.691            0.059            [-3.226, 3.590]\n",
      "\n",
      "  Posterior quantiles:\n",
      "  2.5            25             50             75             97.5\n",
      "  |--------------|==============|==============|--------------|\n",
      "  \n",
      "  -3.223         -0.723         0.148          1.052          3.601\n",
      "\n",
      "\n",
      "Tobacco:\n",
      "\n",
      "  Mean             SD               MC Error         95% HPD interval\n",
      "  -------------------------------------------------------------------\n",
      "  \n",
      "  0.598            0.306            0.010            [-0.011, 1.206]\n",
      "\n",
      "  Posterior quantiles:\n",
      "  2.5            25             50             75             97.5\n",
      "  |--------------|==============|==============|--------------|\n",
      "  \n",
      "  -0.008         0.446          0.604          0.758          1.210\n",
      "\n",
      "\n",
      "sigma:\n",
      "\n",
      "  Mean             SD               MC Error         95% HPD interval\n",
      "  -------------------------------------------------------------------\n",
      "  \n",
      "  0.591            0.915            0.029            [0.232, 0.962]\n",
      "\n",
      "  Posterior quantiles:\n",
      "  2.5            25             50             75             97.5\n",
      "  |--------------|==============|==============|--------------|\n",
      "  \n",
      "  0.269          0.360          0.437          0.553          1.324\n",
      "\n"
     ]
    }
   ],
   "source": [
    "pm.summary(trace)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}