example/recommenders/demo2-binary.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Binary Predictions with Negative Sampling\n",
    "Example of a recommender system making binary predictions instead of predicting a rating.\n",
    "Demonstrates use of `NegativeSamplingDataIter` to wrap an existing data iterator with `CosineLoss`.\n",
    "See [BlackOut by Shihao Ji et al](https://arxiv.org/abs/1511.06909) for more on negative sampling.\n",
    "\n",
    "You need to have python package pandas and bokeh installed (pip install pandas bokeh)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "import mxnet as mx\n",
    "from movielens_data import get_data_iter, max_id\n",
    "from matrix_fact import train\n",
    "import recotools"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# If MXNet is not compiled with GPU support (e.g. on OSX), set to [mx.cpu(0)]\n",
    "# Can be changed to [mx.gpu(0), mx.gpu(1), ..., mx.gpu(N-1)] if there are N GPUs\n",
    "ctx = [mx.gpu(0)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "pos_train_data, pos_test_data = get_data_iter(batch_size=100)\n",
    "max_user, max_item = max_id('./ml-100k/u.data')\n",
    "(max_user, max_item)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "train_data = recotools.NegativeSamplingDataIter(pos_train_data, sample_ratio=3, positive_label=0, negative_label=1)\n",
    "test_data = recotools.NegativeSamplingDataIter(pos_test_data, sample_ratio=3,   positive_label=0, negative_label=1)\n",
    "train_test_data = (train_data, test_data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "def plain_net(k):\n",
    "    # input\n",
    "    user = mx.symbol.Variable('user')\n",
    "    item = mx.symbol.Variable('item')\n",
    "    label = mx.symbol.Variable('score')\n",
    "    # user feature lookup\n",
    "    user = mx.symbol.Embedding(data = user, input_dim = max_user, output_dim = k)\n",
    "    # item feature lookup\n",
    "    item = mx.symbol.Embedding(data = item, input_dim = max_item, output_dim = k)\n",
    "    # loss layer\n",
    "    pred = recotools.CosineLoss(a=user, b=item, label=label)\n",
    "    return pred\n",
    "\n",
    "net1 = plain_net(64)\n",
    "mx.viz.plot_network(net1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false,
    "scrolled": false
   },
   "outputs": [],
   "source": [
    "results1 = train(net1, train_test_data, num_epoch=20, learning_rate=0.02, ctx=ctx)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "anaconda-cloud": {},
  "kernelspec": {
   "display_name": "Python [Root]",
   "language": "python",
   "name": "Python [Root]"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}