update

Author: marlesson

.gitignore

@@ -1,2 +1,4 @@
 .ipynb_checkpoints/
-log/
+log/
+metastore_db/
+derby.log

README.md

@@ -5,7 +5,12 @@
 Tutorial que utiliza as bibliotecas Spark GraphX (https://spark.apache.org/graphx/
 ), GraphFrames (https://graphframes.github.io/) e D3 (https://d3js.org/) para criação, análise e visualização de Grafos no Spark.
 
-Ver **tutorial.ipynb**
+* **tutorial.ipynb**: Jupyter Notebook de Tutorial
+* **d3.html**: Visualização do Gráfo gerada pelo D3
+
+### Medium
+
+https://medium.com/@marlessonsantana/introdução-ao-spark-graphx-e-graphframes-9b10089f2e7f
 
 ![Alt Text](./img/graph.png) 
 

tutorial.ipynb

@@ -197,7 +197,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 52,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -206,12 +206,13 @@
     "    Return a list containing the most friends\n",
     "    '''\n",
     "    g_indegrees = g.inDegrees\n",
-    "    return g.vertices.join(g_indegrees, \"id\").orderBy(\"inDegree\", ascending=False).limit(topN)"
+    "    return g.vertices.join(g_indegrees, \"id\")\\\n",
+    "            .orderBy(\"inDegree\", ascending=False).limit(topN)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 67,
    "metadata": {},
    "outputs": [
     {
@@ -232,13 +233,12 @@
       "|5736|    Lemon|    1289|\n",
       "| 403|    Alvah|    1280|\n",
       "+----+---------+--------+\n",
-      "only showing top 10 rows\n",
       "\n"
      ]
     }
    ],
    "source": [
-    "most_connected = get_most_connected(g, 1000)\n",
+    "most_connected = get_most_connected(g, 10)\n",
     "most_connected.show(10)"
    ]
   },
@@ -255,7 +255,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 68,
    "metadata": {},
    "outputs": [
     {
@@ -282,7 +282,9 @@
     "    '''\n",
     "    Return a list of connected users\n",
     "    '''\n",
-    "    return g.find(\"(a)-[e]->(b)\").filter(\"b.id = %d\" % user_id).select(\"a.id\", \"a.NAME\")\n",
+    "    return g.find(\"(a)-[e]->(b)\")\\\n",
+    "            .filter(\"b.id = %d\" % user_id)\\\n",
+    "            .select(\"a.id\", \"a.NAME\")\n",
     "\n",
     "users = get_users_connected(g, 859)\n",
     "print(\"Total de usuários conectados a 'Hallie': \", users.count())\n",
@@ -302,23 +304,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 69,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Total de possíveis amigos:  56331\n",
-      "+----+--------+\n",
-      "|  id|    name|\n",
-      "+----+--------+\n",
-      "|4845|  Winnie|\n",
-      "|3219|    Juan|\n",
-      "|1310|Laurence|\n",
-      "| 177|Nicholas|\n",
-      "|1003|  George|\n",
-      "+----+--------+\n",
+      "Total de possíveis amigos:  15181\n",
+      "+----+-------+\n",
+      "|  id|   name|\n",
+      "+----+-------+\n",
+      "|1289|  Abram|\n",
+      "|1484|Wilburn|\n",
+      "|4040|  Ralph|\n",
+      "| 208|   Andy|\n",
+      "|3750| Emmitt|\n",
+      "+----+-------+\n",
       "only showing top 5 rows\n",
       "\n"
      ]
@@ -329,10 +331,11 @@
     "    '''\n",
     "    Returns a list of suggested friendships \"people you may know\"\n",
     "    '''\n",
-    "    users = g.find(\"(a)-[e]->(b); (b)-[e2]->(c); !(a)-[]->(c)\").filter(\"a.id = %d\" % user_id)\n",
+    "    users = g.find(\"(a)-[e]->(b); (b)-[e2]->(c); !(a)-[]->(c)\")\\\n",
+    "                .filter(\"a.id = %d\" % user_id)\n",
     "    return users.select(\"c.id\", \"c.name\")\n",
     "\n",
-    "users = get_friends_suggestion(g, 859).cache()\n",
+    "users = get_friends_suggestion(g, 1572).cache()\n",
     "print(\"Total de possíveis amigos: \", users.count())\n",
     "users.show(5)"
    ]
@@ -490,6 +493,27 @@
    "source": [
     "graph_to_file(g_users, \"graph.json\")"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {