Feature extraction loop for audio processing

audio_preprocessing.ipynb

@@ -100,6 +100,42 @@
     "features = np.load(\"features.npy\", allow_pickle=True)\n",
     "labels   = np.load(\"labels.npy\", allow_pickle=True)"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# DONT RUN THIS IF YOU ALREADY LOADED THE NUMPY ARRAYS ^^^^\n",
+    "\n",
+    "metadata = pd.read_csv('./UrbanSound8k/metadata/UrbanSound8K.csv')\n",
+    "features = []\n",
+    "labels = []\n",
+    "i = 0\n",
+    "\n",
+    "# Iterate through each sound file and extract the features \n",
+    "for index, row in metadata.iterrows():\n",
+    "    \n",
+    "    i = i +1\n",
+    "    file_name = os.path.join(os.path.abspath('UrbanSound8k/audio/'),'fold'+str(row[\"fold\"])+'/',str(row[\"slice_file_name\"]))\n",
+    "    \n",
+    "    class_label = row[\"class\"]\n",
+    "    print(f'{i}: Processing {file_name}')\n",
+    "    data = extract_features(file_name)\n",
+    "    \n",
+    "    features.append(data)\n",
+    "    labels.append(class_label)\n",
+    "\n",
+    "# Convert into a Panda dataframe \n",
+    "#featuresdf = pd.DataFrame(features, columns=['feature','class_label'])\n",
+    "#np.save('features.npy', features)\n",
+    "\n",
+    "print('Finished feature extraction from ', len(features), ' files')\n",
+    "\n",
+    "np.save('features.npy', features)\n",
+    "np.save('labels.npy',   labels)"
+   ]
   }
  ],
  "metadata": {