view notebooks/test_music_segments.ipynb @ 6:a35bd818d8e9 branch-tests

notebook to test music segments

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pickle"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "filenames = ['/import/c4dm-04/mariap/train_data_melodia_8.pickle', \n",
    "             '/import/c4dm-04/mariap/val_data_melodia_8.pickle', \n",
    "             '/import/c4dm-04/mariap/test_data_melodia_8.pickle']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "all_Yaudio = []\n",
    "for filename in filenames:\n",
    "    _, Y, Yaudio = pickle.load(open(filename), 'rb')\n",
    "    all_Yaudio.append(Yaudio)\n",
    "all_Yaudio = np.concatenate(all_Yaudio)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'all_Yaudio' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-3-4107ada442c0>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0muniq_audio\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0muniq_counts\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0munique\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mall_Yaudio\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mreturn_counts\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m: name 'all_Yaudio' is not defined"
     ]
    }
   ],
   "source": [
    "uniq_audio, uniq_counts = np.unique(all_Yaudio, return_counts=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Stats on audio files with very few music frames (after the speech/music discrimination)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'uniq_counts' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-4-700ed156399c>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0mmin_n_frames\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m10\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mn_short_files\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mwhere\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0muniq_counts\u001b[0m\u001b[0;34m<\u001b[0m\u001b[0mmin_n_frames\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      3\u001b[0m \u001b[0;32mprint\u001b[0m \u001b[0;34m'%d files out of %d have less than %d frames'\u001b[0m \u001b[0;34m%\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mn_short_files\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0muniq_counts\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmin_n_frames\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mNameError\u001b[0m: name 'uniq_counts' is not defined"
     ]
    }
   ],
   "source": [
    "min_n_frames = 10\n",
    "n_short_files = np.where(uniq_counts<min_n_frames)[0].shape\n",
    "print '%d files out of %d have less than %d frames' % (n_short_files, len(uniq_counts), min_n_frames)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Stats on average duration of the music segments for all tracks"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "ename": "SyntaxError",
     "evalue": "invalid syntax (<ipython-input-5-2c4ab0e943a6>, line 1)",
     "output_type": "error",
     "traceback": [
      "\u001b[0;36m  File \u001b[0;32m\"<ipython-input-5-2c4ab0e943a6>\"\u001b[0;36m, line \u001b[0;32m1\u001b[0m\n\u001b[0;31m    print 'mean %f' np.mean(uniq_counts)\u001b[0m\n\u001b[0m                     ^\u001b[0m\n\u001b[0;31mSyntaxError\u001b[0m\u001b[0;31m:\u001b[0m invalid syntax\n"
     ]
    }
   ],
   "source": [
    "sr = 2.0  # with 8-second window and 0.5-second hop size the sampling rate is 2 about 2 samples per second\n",
    "print 'mean %f' % np.mean(uniq_counts)\n",
    "print 'median %f' % np.median(uniq_counts)\n",
    "print 'std %f' % np.std(uniq_counts)\n",
    "print 'mean duration %f' % (np.mean(uniq_counts) / sr)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Stats on average duration of the music segments for the British Library tracks"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'uniq_audio' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-7-4ebf50436e4a>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0;31m#British library tracks start with 'D:/Audio/...'\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0midx_BL_tracks\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0marray\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mi\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mi\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mrange\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0muniq_audio\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0muniq_audio\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msplit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'D:/'\u001b[0m\u001b[0;34m)\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[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      3\u001b[0m \u001b[0msr\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;36m2.0\u001b[0m  \u001b[0;31m# with 8-second window and 0.5-second hop size the sampling rate is 2 about 2 samples per second\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0;32mprint\u001b[0m \u001b[0;34m'mean %f'\u001b[0m \u001b[0;34m%\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmean\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0muniq_counts\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0midx_BL_tracks\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m \u001b[0;32mprint\u001b[0m \u001b[0;34m'median %f'\u001b[0m \u001b[0;34m%\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmedian\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0muniq_counts\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0midx_BL_tracks\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mNameError\u001b[0m: name 'uniq_audio' is not defined"
     ]
    }
   ],
   "source": [
    "#British library tracks start with 'D:/Audio/...'\n",
    "idx_BL_tracks = np.array([i for i in range(len(uniq_audio)) if len(uniq_audio[i].split('D:/'))>1])\n",
    "sr = 2.0  # with 8-second window and 0.5-second hop size the sampling rate is 2 about 2 samples per second\n",
    "print 'mean %f' % np.mean(uniq_counts[idx_BL_tracks])\n",
    "print 'median %f' % np.median(uniq_counts[idx_BL_tracks])\n",
    "print 'std %f' % np.std(uniq_counts[idx_BL_tracks])\n",
    "print 'mean duration %f' % (np.mean(uniq_counts[idx_BL_tracks]) / sr)"
   ]
  },
  {
   "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": "2.7.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}