Add files via upload

Author: Pushkr

MungeolHeo.ipynb

@@ -10,6 +10,7 @@
    "source": [
     "import random\n",
     "\n",
+    "# Prepare data\n",
     "data1 = [(1,'a'),(3,'a'),(5,'c')]\n",
     "df1 = sc.parallelize(data1) \n",
     "\n",
@@ -26,11 +27,12 @@
    },
    "outputs": [],
    "source": [
+    "\n",
     "def func1(vals):\n",
     "    output =[]\n",
-    "    uniqueId = random.random() # random ID for each list\n",
+    "    uniqueId = random.random()  # create token\n",
     "    for value in vals:\n",
-    "        output.append((value,uniqueId))\n",
+    "        output.append((value,uniqueId)) # assign same token element of same list\n",
     "        \n",
     "    return ([x for x in output])\n",
     "    \n",
@@ -151,6 +153,8 @@
     "            v.append(entry[1])\n",
     "    \n",
     "    return (k,set(v))\n",
+    "\n",
+    "# Final result\n",
     "lines.mapValues(unzip).values().collect()\n",
     "    "
    ]