m@6: {
m@6:  "cells": [
m@6:   {
m@6:    "cell_type": "code",
m@6:    "execution_count": 1,
m@6:    "metadata": {
m@6:     "collapsed": true
m@6:    },
m@6:    "outputs": [],
m@6:    "source": [
m@6:     "import numpy as np\n",
m@6:     "import pickle"
m@6:    ]
m@6:   },
m@6:   {
m@6:    "cell_type": "code",
m@6:    "execution_count": 2,
m@6:    "metadata": {
m@6:     "collapsed": true
m@6:    },
m@6:    "outputs": [],
m@6:    "source": [
m@6:     "filenames = ['/import/c4dm-04/mariap/train_data_melodia_8.pickle', \n",
m@6:     "             '/import/c4dm-04/mariap/val_data_melodia_8.pickle', \n",
m@6:     "             '/import/c4dm-04/mariap/test_data_melodia_8.pickle']"
m@6:    ]
m@6:   },
m@6:   {
m@6:    "cell_type": "code",
m@6:    "execution_count": null,
m@6:    "metadata": {
m@6:     "collapsed": true
m@6:    },
m@6:    "outputs": [],
m@6:    "source": [
m@6:     "all_Yaudio = []\n",
m@6:     "for filename in filenames:\n",
m@6:     "    _, Y, Yaudio = pickle.load(open(filename), 'rb')\n",
m@6:     "    all_Yaudio.append(Yaudio)\n",
m@6:     "all_Yaudio = np.concatenate(all_Yaudio)"
m@6:    ]
m@6:   },
m@6:   {
m@6:    "cell_type": "code",
m@6:    "execution_count": 3,
m@6:    "metadata": {
m@6:     "collapsed": false
m@6:    },
m@6:    "outputs": [
m@6:     {
m@6:      "ename": "NameError",
m@6:      "evalue": "name 'all_Yaudio' is not defined",
m@6:      "output_type": "error",
m@6:      "traceback": [
m@6:       "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
m@6:       "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
m@6:       "\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",
m@6:       "\u001b[0;31mNameError\u001b[0m: name 'all_Yaudio' is not defined"
m@6:      ]
m@6:     }
m@6:    ],
m@6:    "source": [
m@6:     "uniq_audio, uniq_counts = np.unique(all_Yaudio, return_counts=True)"
m@6:    ]
m@6:   },
m@6:   {
m@6:    "cell_type": "markdown",
m@6:    "metadata": {},
m@6:    "source": [
m@6:     "## Stats on audio files with very few music frames (after the speech/music discrimination)"
m@6:    ]
m@6:   },
m@6:   {
m@6:    "cell_type": "code",
m@6:    "execution_count": 4,
m@6:    "metadata": {
m@6:     "collapsed": false
m@6:    },
m@6:    "outputs": [
m@6:     {
m@6:      "ename": "NameError",
m@6:      "evalue": "name 'uniq_counts' is not defined",
m@6:      "output_type": "error",
m@6:      "traceback": [
m@6:       "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
m@6:       "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
m@6:       "\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",
m@6:       "\u001b[0;31mNameError\u001b[0m: name 'uniq_counts' is not defined"
m@6:      ]
m@6:     }
m@6:    ],
m@6:    "source": [
m@6:     "min_n_frames = 10\n",
m@6:     "n_short_files = np.where(uniq_counts<min_n_frames)[0].shape\n",
m@6:     "print '%d files out of %d have less than %d frames' % (n_short_files, len(uniq_counts), min_n_frames)"
m@6:    ]
m@6:   },
m@6:   {
m@6:    "cell_type": "markdown",
m@6:    "metadata": {},
m@6:    "source": [
m@6:     "## Stats on average duration of the music segments for all tracks"
m@6:    ]
m@6:   },
m@6:   {
m@6:    "cell_type": "code",
m@6:    "execution_count": 5,
m@6:    "metadata": {
m@6:     "collapsed": false
m@6:    },
m@6:    "outputs": [
m@6:     {
m@6:      "ename": "SyntaxError",
m@6:      "evalue": "invalid syntax (<ipython-input-5-2c4ab0e943a6>, line 1)",
m@6:      "output_type": "error",
m@6:      "traceback": [
m@6:       "\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"
m@6:      ]
m@6:     }
m@6:    ],
m@6:    "source": [
m@6:     "sr = 2.0  # with 8-second window and 0.5-second hop size the sampling rate is 2 about 2 samples per second\n",
m@6:     "print 'mean %f' % np.mean(uniq_counts)\n",
m@6:     "print 'median %f' % np.median(uniq_counts)\n",
m@6:     "print 'std %f' % np.std(uniq_counts)\n",
m@6:     "print 'mean duration %f' % (np.mean(uniq_counts) / sr)"
m@6:    ]
m@6:   },
m@6:   {
m@6:    "cell_type": "markdown",
m@6:    "metadata": {},
m@6:    "source": [
m@6:     "## Stats on average duration of the music segments for the British Library tracks"
m@6:    ]
m@6:   },
m@6:   {
m@6:    "cell_type": "code",
m@6:    "execution_count": 7,
m@6:    "metadata": {
m@6:     "collapsed": false
m@6:    },
m@6:    "outputs": [
m@6:     {
m@6:      "ename": "NameError",
m@6:      "evalue": "name 'uniq_audio' is not defined",
m@6:      "output_type": "error",
m@6:      "traceback": [
m@6:       "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
m@6:       "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
m@6:       "\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",
m@6:       "\u001b[0;31mNameError\u001b[0m: name 'uniq_audio' is not defined"
m@6:      ]
m@6:     }
m@6:    ],
m@6:    "source": [
m@6:     "#British library tracks start with 'D:/Audio/...'\n",
m@6:     "idx_BL_tracks = np.array([i for i in range(len(uniq_audio)) if len(uniq_audio[i].split('D:/'))>1])\n",
m@6:     "sr = 2.0  # with 8-second window and 0.5-second hop size the sampling rate is 2 about 2 samples per second\n",
m@6:     "print 'mean %f' % np.mean(uniq_counts[idx_BL_tracks])\n",
m@6:     "print 'median %f' % np.median(uniq_counts[idx_BL_tracks])\n",
m@6:     "print 'std %f' % np.std(uniq_counts[idx_BL_tracks])\n",
m@6:     "print 'mean duration %f' % (np.mean(uniq_counts[idx_BL_tracks]) / sr)"
m@6:    ]
m@6:   },
m@6:   {
m@6:    "cell_type": "code",
m@6:    "execution_count": null,
m@6:    "metadata": {
m@6:     "collapsed": true
m@6:    },
m@6:    "outputs": [],
m@6:    "source": []
m@6:   }
m@6:  ],
m@6:  "metadata": {
m@6:   "kernelspec": {
m@6:    "display_name": "Python 2",
m@6:    "language": "python",
m@6:    "name": "python2"
m@6:   },
m@6:   "language_info": {
m@6:    "codemirror_mode": {
m@6:     "name": "ipython",
m@6:     "version": 2
m@6:    },
m@6:    "file_extension": ".py",
m@6:    "mimetype": "text/x-python",
m@6:    "name": "python",
m@6:    "nbconvert_exporter": "python",
m@6:    "pygments_lexer": "ipython2",
m@6:    "version": "2.7.12"
m@6:   }
m@6:  },
m@6:  "nbformat": 4,
m@6:  "nbformat_minor": 0
m@6: }