comparison notebooks/test_music_segments.ipynb @ 63:b0e194bfb71d branch-tests

minor edits on server

     "             '/import/c4dm-04/mariap/test_data_melodia_8.pickle']"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 25,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "# verify on the 30-second segments\n",
+    "filenames = ['/import/c4dm-04/mariap/train_data_melodia_8_30sec.pickle',\n",
+    "             '/import/c4dm-04/mariap/val_data_melodia_8_30sec.pickle', \n",
+    "             '/import/c4dm-04/mariap/test_data_melodia_8_30sec.pickle']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
    "metadata": {
     "collapsed": true
    },
    "outputs": [],
    "source": [

     "all_Y = np.concatenate(all_Y)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 27,
    "metadata": {
     "collapsed": true
    },
    "outputs": [],
    "source": [

     "## Stats on average duration of the music segments for the Smithsonian tracks"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 28,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",

     "## Stats on average duration of the music segments for the British Library tracks"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 29,
    "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"
+      "mean 42.459381\n",
+      "median 44.000000\n",
+      "std 6.567739\n",
+      "mean duration 21.229691\n"
      ]
     }
    ],
    "source": [
     "#British library tracks start with 'D:/Audio/...'\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)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "8089"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "6147+1942"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "8099"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "6119+1980"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "8200"
+      ]
+     },
+     "execution_count": 24,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "6132+2068"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,