{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "# Binary numbers as input\n",
    "\n",
    "This is based on [this question](https://stackoverflow.com/questions/46012622/check-divisibility-using-machine-learning/46016389#46016389) from Stackoverflow.\n",
    "\n",
    "It doesn't make any real-world sense, but it's easy introductory example, and more complex issues can be explained using this problem.\n",
    "\n",
    "The problem is to classify whether some numbers (from fixed range) are divisible by some fixed number M.\n",
    "\n",
    "The key idea is to not just encode numbers as ints, but use their binary representation."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "## Checking divisibility with machine learning"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "\n",
    "from sklearn.model_selection import train_test_split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [],
   "source": [
    "N = 1024\n",
    "logN = int(np.log2(N))\n",
    "M = 10 \n",
    "\n",
    "X_bin = [list(np.binary_repr(x, width=logN)) for x in range(N)]\n",
    "X = np.array(X_bin)\n",
    "y = np.arange(N) % M == 0\n",
    "\n",
    "X_train, X_test, y_train, y_test = train_test_split(X_bin, y, test_size=0.125, stratify=y, random_state=0)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "## SVM"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.8984375"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.svm import SVC\n",
    "\n",
    "svc = SVC(kernel='linear', C=1)\n",
    "svc.fit(X_train, y_train)\n",
    "\n",
    "svc.score(X_test, y_test)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "deletable": true,
    "editable": true
   },
   "source": [
    "## Decision tree "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false,
    "deletable": true,
    "editable": true
   },
   "outputs": [
    {
     "ename": "ValueError",
     "evalue": "Can't handle mix of binary and multilabel-indicator",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-10-b84c593cddc7>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0mtree\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX_train\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mvstack\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0my_train\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_train\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mT\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 6\u001b[0;31m \u001b[0mtree\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mscore\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX_test\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_test\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;32m/opt/anaconda3/lib/python3.5/site-packages/sklearn/base.py\u001b[0m in \u001b[0;36mscore\u001b[0;34m(self, X, y, sample_weight)\u001b[0m\n\u001b[1;32m    347\u001b[0m         \"\"\"\n\u001b[1;32m    348\u001b[0m         \u001b[0;32mfrom\u001b[0m \u001b[0;34m.\u001b[0m\u001b[0mmetrics\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0maccuracy_score\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 349\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0maccuracy_score\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0my\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpredict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0msample_weight\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0msample_weight\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    350\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    351\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/opt/anaconda3/lib/python3.5/site-packages/sklearn/metrics/classification.py\u001b[0m in \u001b[0;36maccuracy_score\u001b[0;34m(y_true, y_pred, normalize, sample_weight)\u001b[0m\n\u001b[1;32m    170\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    171\u001b[0m     \u001b[0;31m# Compute accuracy for each possible representation\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 172\u001b[0;31m     \u001b[0my_type\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_true\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_pred\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_check_targets\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0my_true\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_pred\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    173\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0my_type\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstartswith\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'multilabel'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    174\u001b[0m         \u001b[0mdiffering_labels\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcount_nonzero\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0my_true\u001b[0m \u001b[0;34m-\u001b[0m \u001b[0my_pred\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m/opt/anaconda3/lib/python3.5/site-packages/sklearn/metrics/classification.py\u001b[0m in \u001b[0;36m_check_targets\u001b[0;34m(y_true, y_pred)\u001b[0m\n\u001b[1;32m     80\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0my_type\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m>\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     81\u001b[0m         raise ValueError(\"Can't handle mix of {0} and {1}\"\n\u001b[0;32m---> 82\u001b[0;31m                          \"\".format(type_true, type_pred))\n\u001b[0m\u001b[1;32m     83\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     84\u001b[0m     \u001b[0;31m# We can't have more than one value on y_type => The set is no more needed\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mValueError\u001b[0m: Can't handle mix of binary and multilabel-indicator"
     ]
    }
   ],
   "source": [
    "from sklearn.tree import DecisionTreeClassifier \n",
    "\n",
    "tree = DecisionTreeClassifier(max_features='log2', max_depth=2)\n",
    "tree.fit(X_train, np.vstack([y_train, y_train]).T)\n",
    "\n",
    "tree.score(X_test, y_test)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(2, 896)"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "np.vstack([y_train, y_train]).shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "hide_input": false,
  "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": "3.5.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}