{
 "metadata": {
  "name": "",
  "signature": "sha256:3f785632d8399faeb298103405c9f9b70f1240eca928b05d3549f7900d5465fb"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "Now, it's time to do some deep learning. Recall that a RBM (Restricted Boltzmann Machine) takes in a binary vector, and you can use it in the SKLearn Pipeline with a classifier. You'll want to read in Oscar's original data as an array of bitwise note vectors, and from there build the RBM to predict chords (the y's, perhaps build the chord bank and assign a unique number to each). After that, given a note vector (maybe plural?), you should be able to predict the chords for a note (notes?)."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "from collections import defaultdict\n",
      "from sklearn.neural_network import BernoulliRBM\n",
      "import pandas as pd\n",
      "import numpy as np"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 28
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Extract chords into unique ids, e.g. 1, 2, 3, 4, 5\n",
      "allchords = defaultdict()\n",
      "with open(\"oscar2chords_extract.txt\", 'rb') as f:\n",
      "    assert len(allchords) == len(set(allchords)) # ensure no duplicate chords\n",
      "    for ix, line in enumerate(f):\n",
      "        allchords[ix] = line.rstrip()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [],
     "prompt_number": 12
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Read in Oscar's data.\n",
      "vectors = []\n",
      "notedata = pd.read_csv(open(\"oscar2notes.txt\", 'rb'), skiprows=2)\n",
      "allnotes = []\n",
      "for note, octave in zip(notedata[\"Note/Rest\"], notedata[\"Octave\"]):\n",
      "    allnotes.append(\"%s%s\" % (note, octave))\n",
      "print allnotes[:10]\n",
      "notedata.head()"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "output_type": "stream",
       "stream": "stdout",
       "text": [
        "['B3', 'A5', 'F4', 'G4', 'F4', 'B-5', 'B3', 'B-5', 'C4', 'C5']\n"
       ]
      },
      {
       "html": [
        "<div style=\"max-height:1000px;max-width:1500px;overflow:auto;\">\n",
        "<table border=\"1\" class=\"dataframe\">\n",
        "  <thead>\n",
        "    <tr style=\"text-align: right;\">\n",
        "      <th></th>\n",
        "      <th>Note/Rest</th>\n",
        "      <th>Octave</th>\n",
        "      <th>Len</th>\n",
        "      <th>Offset</th>\n",
        "    </tr>\n",
        "  </thead>\n",
        "  <tbody>\n",
        "    <tr>\n",
        "      <th>0</th>\n",
        "      <td> B</td>\n",
        "      <td> 3</td>\n",
        "      <td> 0.500000</td>\n",
        "      <td> 12.625</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
        "      <td> A</td>\n",
        "      <td> 5</td>\n",
        "      <td> 0.250000</td>\n",
        "      <td> 15.000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
        "      <td> F</td>\n",
        "      <td> 4</td>\n",
        "      <td> 3.125000</td>\n",
        "      <td> 16.000</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
        "      <td> G</td>\n",
        "      <td> 4</td>\n",
        "      <td> 0.666667</td>\n",
        "      <td> 20.625</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
        "      <td> F</td>\n",
        "      <td> 4</td>\n",
        "      <td> 1.250000</td>\n",
        "      <td> 23.875</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
        "<p>5 rows \u00d7 4 columns</p>\n",
        "</div>"
       ],
       "metadata": {},
       "output_type": "pyout",
       "prompt_number": 23,
       "text": [
        "  Note/Rest  Octave       Len  Offset\n",
        "0         B       3  0.500000  12.625\n",
        "1         A       5  0.250000  15.000\n",
        "2         F       4  3.125000  16.000\n",
        "3         G       4  0.666667  20.625\n",
        "4         F       4  1.250000  23.875\n",
        "\n",
        "[5 rows x 4 columns]"
       ]
      }
     ],
     "prompt_number": 23
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "# Given a MUSIC21 note, such as C5 or D#7, convert it\n",
      "# into a note on the keyboard between 0 and 87 inclusive.\n",
      "# Don't convert it for mingus; try to use music21 note style\n",
      "# as much as possible for all this stuff.\n",
      "def quantify(note):\n",
      "    notevals = {\n",
      "        'C' : 0,\n",
      "        'D' : 2,\n",
      "        'E' : 4,\n",
      "        'F' : 5,\n",
      "        'G' : 7,\n",
      "        'A' : 9,\n",
      "        'B' : 11\n",
      "    }\n",
      "    quantized = 0\n",
      "    octave = int(note[-1]) - 1\n",
      "    for i in note[:-1]:\n",
      "        if i in notevals: quantized += notevals[i]\n",
      "        if i == '-': quantized -= 1\n",
      "        if i == '#': quantized += 1\n",
      "    quantized += 12 * octave\n",
      "    return quantized\n",
      "\n",
      "vect1 = np.array((1, 88)).reshape(88, -1)\n",
      "note1 = allnotes[0]\n",
      "print quantify(note1), note1\n",
      "vect1[quantify(note1)] = 1\n",
      "print vect1"
     ],
     "language": "python",
     "metadata": {},
     "outputs": [
      {
       "ename": "ValueError",
       "evalue": "total size of new array must be unchanged",
       "output_type": "pyerr",
       "traceback": [
        "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m\n\u001b[1;31mValueError\u001b[0m                                Traceback (most recent call last)",
        "\u001b[1;32m<ipython-input-35-21c7afe81a70>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[0;32m     22\u001b[0m     \u001b[1;32mreturn\u001b[0m \u001b[0mquantized\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     23\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 24\u001b[1;33m \u001b[0mvect1\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0marray\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;36m88\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mreshape\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;36m88\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m-\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     25\u001b[0m \u001b[0mnote1\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mallnotes\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     26\u001b[0m \u001b[1;32mprint\u001b[0m \u001b[0mquantify\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mnote1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnote1\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
        "\u001b[1;31mValueError\u001b[0m: total size of new array must be unchanged"
       ]
      }
     ],
     "prompt_number": 35
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [],
     "language": "python",
     "metadata": {},
     "outputs": []
    }
   ],
   "metadata": {}
  }
 ]
}