yamaguchiyuto/cpals_example.ipynb

## cpals_example.ipynb
{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "from cp_decomposition import CPALS\n",
    "%matplotlib inline "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "\"\"\" Define model \"\"\"\n",
    "model = CPALS(k=5,lamb=0.001,max_iter=30)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "\"\"\" Make test data \"\"\"\n",
    "true_k = 5\n",
    "true_U = np.random.normal(loc=0.0, scale=0.1, size=(10,true_k))\n",
    "true_V = np.random.normal(loc=0.0, scale=0.1, size=(15,true_k))\n",
    "true_W = np.random.normal(loc=0.0, scale=0.1, size=(20,true_k))\n",
    "X = {}\n",
    "for i in range(true_U.shape[0]):\n",
    "    for j in range(true_V.shape[0]):\n",
    "        for k in range(true_W.shape[0]):\n",
    "            X[(i,j,k)] = np.sum(true_U[i]*true_V[j]*true_W[k])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<cp_decomposition.CPALS instance at 0x105bb33f8>"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "model.fit(X)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false,
    "scrolled": true
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAa0AAAEdCAYAAAC/nDhCAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nOAAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x109a88350>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot(model._losses)\n",
    "plt.ylabel('Loss')\n",
    "plt.xlabel('# iters')\n",
    "plt.title('CPALS')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "-0.00125451349883\n",
      "-0.00119725917568\n"
     ]
    }
   ],
   "source": [
    "indices = (4,7,9)\n",
    "print X[indices]\n",
    "print model.predict(indices)"
   ]
  }
 ],
 "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
}
	{
	"cells": [
	{
	"cell_type": "code",
	"execution_count": 1,
	"metadata": {
	"collapsed": false
	},
	"outputs": [],
	"source": [
	"import numpy as np\n",
	"import matplotlib.pyplot as plt\n",
	"from cp_decomposition import CPALS\n",
	"%matplotlib inline "
	]
	},
	{
	"cell_type": "code",
	"execution_count": 2,
	"metadata": {
	"collapsed": false
	},
	"outputs": [],
	"source": [
	"\"\"\" Define model \"\"\"\n",
	"model = CPALS(k=5,lamb=0.001,max_iter=30)"
	]
	},
	{
	"cell_type": "code",
	"execution_count": 3,
	"metadata": {
	"collapsed": true
	},
	"outputs": [],
	"source": [
	"\"\"\" Make test data \"\"\"\n",
	"true_k = 5\n",
	"true_U = np.random.normal(loc=0.0, scale=0.1, size=(10,true_k))\n",
	"true_V = np.random.normal(loc=0.0, scale=0.1, size=(15,true_k))\n",
	"true_W = np.random.normal(loc=0.0, scale=0.1, size=(20,true_k))\n",
	"X = {}\n",
	"for i in range(true_U.shape[0]):\n",
	" for j in range(true_V.shape[0]):\n",
	" for k in range(true_W.shape[0]):\n",
	" X[(i,j,k)] = np.sum(true_U[i]true_V[j]true_W[k])"
	]
	},
	{
	"cell_type": "code",
	"execution_count": 4,
	"metadata": {
	"collapsed": false
	},
	"outputs": [
	{
	"data": {
	"text/plain": [
	"<cp_decomposition.CPALS instance at 0x105bb33f8>"
	]
	},
	"execution_count": 4,
	"metadata": {},
	"output_type": "execute_result"
	}
	],
	"source": [
	"model.fit(X)"
	]
	},
	{
	"cell_type": "code",
	"execution_count": 5,
	"metadata": {
	"collapsed": false,
	"scrolled": true
	},
	"outputs": [
	{
	"data": {
	"image/png": "iVBORw0KGgoAAAANSUhEUgAAAa0AAAEdCAYAAAC/nDhCAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nOAAAAABJRU5ErkJggg==\n",
	"text/plain": [
	"<matplotlib.figure.Figure at 0x109a88350>"
	]
	},
	"metadata": {},
	"output_type": "display_data"
	}
	],
	"source": [
	"plt.plot(model._losses)\n",
	"plt.ylabel('Loss')\n",
	"plt.xlabel('# iters')\n",
	"plt.title('CPALS')\n",
	"plt.show()"
	]
	},
	{
	"cell_type": "code",
	"execution_count": 6,
	"metadata": {
	"collapsed": false
	},
	"outputs": [
	{
	"name": "stdout",
	"output_type": "stream",
	"text": [
	"-0.00125451349883\n",
	"-0.00119725917568\n"
	]
	}
	],
	"source": [
	"indices = (4,7,9)\n",
	"print X[indices]\n",
	"print model.predict(indices)"
	]
	}
	],
	"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
	}