comparison notebooks/test_music_segments.ipynb @ 7:46b2c713cc73 branch-tests

stats on speech/music duration

    "metadata": {
     "collapsed": true
    },
    "outputs": [],
    "source": [
-    "filenames = ['/import/c4dm-04/mariap/train_data_melodia_8.pickle', \n",
+    "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
-   },
+   "execution_count": 13,
+   "metadata": {},
    "outputs": [],
    "source": [
     "all_Yaudio = []\n",
+    "all_Y = []\n",
     "for filename in filenames:\n",
-    "    _, Y, Yaudio = pickle.load(open(filename), 'rb')\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"
-     ]
-    }
-   ],
+    "    all_Y.append(Y)\n",
+    "all_Yaudio = np.concatenate(all_Yaudio)\n",
+    "all_Y = np.concatenate(all_Y)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
    "source": [
     "uniq_audio, uniq_counts = np.unique(all_Yaudio, return_counts=True)"
    ]
   },
   {

     "## 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"
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "63 files out of 8200 have less than 10 frames\n"
      ]
     }
    ],
    "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)"
+    "short_files_idx = np.where(uniq_counts<min_n_frames)[0]\n",
+    "print '%d files out of %d have less than %d frames' % (len(short_files_idx), len(uniq_counts), min_n_frames)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Countries for tracks with less than 10 frames"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "{'Italy': 1, 'Peru': 1, 'Solomon Islands': 2, 'France': 2, 'Ethiopia': 1, 'Somalia': 1, 'Ireland': 1, 'Swaziland': 1, 'Argentina': 1, 'Norway': 1, 'Nigeria': 1, 'Algeria': 1, 'Germany': 1, 'Puerto Rico': 1, 'Dominican Republic': 1, 'Poland': 3, 'Spain': 2, 'Netherlands': 1, 'Uganda': 4, 'Western Sahara': 5, 'Gambia': 2, 'Philippines': 2, 'Trinidad and Tobago': 1, 'Latvia': 1, 'South Sudan': 3, 'Mali': 1, 'Russia': 1, 'Romania': 1, 'Portugal': 1, 'South Africa': 3, 'Egypt': 1, 'Sierra Leone': 1, 'United Kingdom': 4, 'Lesotho': 1, 'Senegal': 2, 'Colombia': 2, 'Japan': 2, 'Nicaragua': 1, 'Botswana': 1}\n"
+     ]
+    }
+   ],
+   "source": [
+    "countries = np.array([all_Y[np.where(all_Yaudio==uniq_audio[audio_idx])[0][0]][0] for audio_idx in short_files_idx])\n",
+    "unique, counts = np.unique(countries, return_counts=True)\n",
+    "print dict(zip(unique, counts))"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},

     "## 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"
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "mean 65.750000\n",
+      "median 44.000000\n",
+      "std 45.947865\n",
+      "mean duration 32.875000\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",

   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "## Stats on average duration of the music segments for the Smithsonian tracks"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "n tracks: 6132\n",
+      "mean 42.618885\n",
+      "median 44.000000\n",
+      "std 4.804534\n",
+      "mean duration 21.309442\n"
+     ]
+    }
+   ],
+   "source": [
+    "#British library tracks start with 'D:/Audio/...'\n",
+    "idx_SM_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 'n tracks: %d' % len(idx_SM_tracks)\n",
+    "print 'mean %f' % np.mean(uniq_counts[idx_SM_tracks])\n",
+    "print 'median %f' % np.median(uniq_counts[idx_SM_tracks])\n",
+    "print 'std %f' % np.std(uniq_counts[idx_SM_tracks])\n",
+    "print 'mean duration %f' % (np.mean(uniq_counts[idx_SM_tracks]) / 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"
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "n tracks: 2068\n",
+      "mean 134.338008\n",
+      "median 163.000000\n",
+      "std 44.855790\n",
+      "mean duration 67.169004\n"
      ]
     }
    ],
    "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 'n tracks: %d' % len(idx_BL_tracks)\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)"
    ]

    "pygments_lexer": "ipython2",
    "version": "2.7.12"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 0
+ "nbformat_minor": 1
 }