triple_apply_problem.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[INFO] Using MetricMock instead of real metrics, mode is: QA\n"
     ]
    }
   ],
   "source": [
    "import sframe as gl"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'1.6'"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gl.version"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "[INFO] Start server at: ipc:///tmp/graphlab_server-8521 - Server binary: /Users/me/anaconda/lib/python2.7/site-packages/sframe/unity_server - Server log: /tmp/sframe_server_1453820022.log\n",
      "[INFO] GraphLab Server Version: 1.6\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "{'num_edges': 796, 'num_vertices': 749}"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gr = gl.load_sgraph('/Users/me/temp/my_graph')\n",
    "gr.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def sum_weight(src, edge, dst):\n",
    "        src['__total_weight'] += edge['weight']\n",
    "        return src, edge, dst\n",
    "\n",
    "def normalize_weight(src, edge, dst):\n",
    "    edge['weight'] /= src['__total_weight']\n",
    "    return src, edge, dst"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "gr.vertices['__total_weight'] = 0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "gr = gr.triple_apply(sum_weight, ['__total_weight'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "ename": "RuntimeError",
     "evalue": "Runtime Exception. Runtime Exception. Traceback (most recent call last):\n  File \"<ipython-input-4-aafa1c00c8df>\", line 6, in normalize_weight\nZeroDivisionError: float division by zero\n",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mRuntimeError\u001b[0m                              Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-7-9fb4c6a4478c>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mgr\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mgr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtriple_apply\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnormalize_weight\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m'weight'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;32m/Users/me/anaconda/lib/python2.7/site-packages/sframe/data_structures/sgraph.pyc\u001b[0m in \u001b[0;36mtriple_apply\u001b[0;34m(self, triple_apply_fn, mutated_fields, input_fields)\u001b[0m\n\u001b[1;32m   1019\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1020\u001b[0m             \u001b[0;32mwith\u001b[0m \u001b[0mcython_context\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1021\u001b[0;31m                 \u001b[0;32mreturn\u001b[0m \u001b[0mSGraph\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0m_proxy\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mg\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__proxy__\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlambda_triple_apply\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtriple_apply_fn\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmutated_fields\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1022\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1023\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0msave\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfilename\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mformat\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'auto'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/Users/me/anaconda/lib/python2.7/site-packages/sframe/cython/context.pyc\u001b[0m in \u001b[0;36m__exit__\u001b[0;34m(self, exc_type, exc_value, traceback)\u001b[0m\n\u001b[1;32m     47\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshow_cython_trace\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     48\u001b[0m                 \u001b[0;31m# To hide cython trace, we re-raise from here\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 49\u001b[0;31m                 \u001b[0;32mraise\u001b[0m \u001b[0mexc_type\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mexc_value\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     50\u001b[0m             \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     51\u001b[0m                 \u001b[0;31m# To show the full trace, we do nothing and let exception propagate\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mRuntimeError\u001b[0m: Runtime Exception. Runtime Exception. Traceback (most recent call last):\n  File \"<ipython-input-4-aafa1c00c8df>\", line 6, in normalize_weight\nZeroDivisionError: float division by zero\n"
     ]
    }
   ],
   "source": [
    "gr = gr.triple_apply(normalize_weight, ['weight'])"
   ]
  },
  {
   "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": "2.7.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}

The data file is located here th: https://www.dropbox.com/s/yr7h1z8s2uo1mw9/my_graph.tar.gz?dl=0 (gzipped)

This gist relates to the following discussion: forum.dato.com/discussion/1674/strange-behaviour-of-triple-apply

The problem was caused by self-links that resulted in unpredicted order vertex updates: turi-code/how-to#37