feat: example cypher querries in jupyter notebook

Author: vancauwe

src/neo4j-quickstart/quickstart.ipynb

@@ -12,19 +12,18 @@
   },
   {
    "cell_type": "markdown",
-   "id": "14bf5bb2",
+   "id": "21ad21b2",
    "metadata": {},
    "source": [
-    "## Downloading data from Neo4j \n",
+    "## Connecting to Neo4J \n",
     "\n",
-    "Here is an example of using the Neo4JDownloader to retrieve all nodes from the graph. \n",
-    "Adapt the Neo4JDownloader class as you see fit for retrieving information. "
+    "Here are some settings that allow to connect to Neo4J. Do not edit unless you know what you are doing. "
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "ea28c628",
+   "id": "4545c948",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -53,7 +52,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "id": "1a349b96",
+   "id": "d799a464",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -71,8 +70,101 @@
     "\n",
     "    return Neo4JDownloader(NEO4J_URI, NEO4J_USERNAME, NEO4J_PASSWORD, NEO4J_DATABASE)\n",
     "\n",
-    "def extract_data(nodes, relationships):\n",
+    "def connect_neo4j(): \n",
     "    downloader = get_downloader()\n",
+    "    return downloader"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d3707369",
+   "metadata": {},
+   "source": [
+    "## Neo4J Querrying: Examples of CYPHER Querries\n",
+    "\n",
+    "Here is an example of using the Neo4J Downloader to run some custom querries on the graph."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "02f8b4a2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "downloader = connect_neo4j()\n",
+    "\n",
+    "# QUERY: Get all nodes that have the EPFL string in their name (whether they are user, repository or org)\n",
+    "\n",
+    "epfl_query =\"\"\"\n",
+    "MATCH (n)\n",
+    "WHERE toLower(n.name) CONTAINS 'epfl'\n",
+    "RETURN n.name AS name, labels(n) AS node_type;\n",
+    "\"\"\"\n",
+    "\n",
+    "epfl_nodes = downloader.run_custom_query(epfl_query)\n",
+    "print(\"RESULTS: all nodes that match the epfl string: \",epfl_nodes)\n",
+    "\n",
+    "# QUERY: Get all organizations\n",
+    "\n",
+    "orgs_query = \"\"\"\n",
+    "MATCH (o:org)\n",
+    "RETURN o.name AS organization;\n",
+    "\"\"\"\n",
+    "organizations = downloader.run_custom_query(orgs_query)\n",
+    "print(\"RESULTS: all organizations in the graph: \",organizations)\n",
+    "\n",
+    "# QUERY : Get all users for an organization \n",
+    "\n",
+    "users_of_org_query = \"\"\"\n",
+    "MATCH (u:user)-[:member_of]->(o:org)\n",
+    "WHERE o.name = $org_name\n",
+    "RETURN u.name AS user\n",
+    "ORDER BY user;\n",
+    "\"\"\"\n",
+    "parameters = {\n",
+    "    \"org_name\": \"SwissDataScienceCenter\"\n",
+    "}\n",
+    "users_in_org = downloader.run_custom_query(users_of_org_query, parameters)\n",
+    "print(\"RESULTS: users inside the organization: \", users_in_org)\n",
+    "\n",
+    "# QUERY: For a list of users get all their repositories\n",
+    "\n",
+    "# Here we base the query on the Contributor of edge.\n",
+    "repos_of_users_query= \"\"\"\n",
+    "MATCH (u:user)-[:contributor_of]->(repo:repo)\n",
+    "WHERE u.name IN $user_list\n",
+    "RETURN u.name AS user,\n",
+    "       repo.name AS repository\n",
+    "ORDER BY user, repository;\n",
+    "\"\"\"\n",
+    "parameters = {\n",
+    "    \"user_list\": [\"yousra-elbachir\", \"Victor2175\", \"williamaeberhard\"]\n",
+    "}\n",
+    "users_and_their_repos = downloader.run_custom_query(repos_of_users_query, parameters)\n",
+    "print(\"RESULTS: users and their repositories: \", users_and_their_repos)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "14bf5bb2",
+   "metadata": {},
+   "source": [
+    "## Downloading data from Neo4j \n",
+    "\n",
+    "Here is an example of using the Neo4JDownloader to retrieve all nodes from the graph. \n",
+    "Adapt the Neo4JDownloader class as you see fit for retrieving information. "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1a349b96",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def extract_data(nodes, relationships):\n",
+    "    downloader = connect_neo4j()\n",
     "\n",
     "    try:\n",
     "        nodes_ids, nodes_features = downloader.retrieve_nodes(nodes)\n",