From 36c7b5fd367a5bc633cfdd06b83516cab6b74413 Mon Sep 17 00:00:00 2001
From: yashshah035 <yashshah035@gmail.com>
Date: Tue, 25 Feb 2025 11:00:51 +0530
Subject: [PATCH] adding graph visual examples

---
 graph-visuals/graph_with_html.py  |  34 ++++++++
 graph-visuals/graph_with_neo4j.py | 126 ++++++++++++++++++++++++++++++
 2 files changed, 160 insertions(+)
 create mode 100644 graph-visuals/graph_with_html.py
 create mode 100644 graph-visuals/graph_with_neo4j.py

diff --git a/graph-visuals/graph_with_html.py b/graph-visuals/graph_with_html.py
new file mode 100644
index 0000000..dc9b87a
--- /dev/null
+++ b/graph-visuals/graph_with_html.py
@@ -0,0 +1,34 @@
+import pipmaster as pm
+
+if not pm.is_installed("pyvis"):
+    pm.install("pyvis")
+if not pm.is_installed("networkx"):
+    pm.install("networkx")
+
+import networkx as nx
+from pyvis.network import Network
+import random
+
+# Load the GraphML file
+G = nx.read_graphml("./LiHua-World/graph_chunk_entity_relation.graphml")
+
+# Create a Pyvis network
+net = Network(height="100vh", notebook=True)
+
+# Convert NetworkX graph to Pyvis network
+net.from_nx(G)
+
+
+# Add colors and title to nodes
+for node in net.nodes:
+    node["color"] = "#{:06x}".format(random.randint(0, 0xFFFFFF))
+    if "description" in node:
+        node["title"] = node["description"]
+
+# Add title to edges
+for edge in net.edges:
+    if "description" in edge:
+        edge["title"] = edge["description"]
+
+# Save and display the network
+net.show("knowledge_graph.html")
diff --git a/graph-visuals/graph_with_neo4j.py b/graph-visuals/graph_with_neo4j.py
new file mode 100644
index 0000000..e7441d1
--- /dev/null
+++ b/graph-visuals/graph_with_neo4j.py
@@ -0,0 +1,126 @@
+import os
+import json
+from minirag.utils import xml_to_json
+from neo4j import GraphDatabase
+
+# Constants
+WORKING_DIR = "./LiHua-World"
+BATCH_SIZE_NODES = 500
+BATCH_SIZE_EDGES = 100
+
+# Neo4j connection credentials
+NEO4J_URI = "bolt://localhost:7687"
+NEO4J_USERNAME = "neo4j"
+NEO4J_PASSWORD = "your_password"
+
+
+def convert_xml_to_json(xml_path, output_path):
+    """Converts XML file to JSON and saves the output."""
+    if not os.path.exists(xml_path):
+        print(f"Error: File not found - {xml_path}")
+        return None
+
+    json_data = xml_to_json(xml_path)
+    if json_data:
+        with open(output_path, "w", encoding="utf-8") as f:
+            json.dump(json_data, f, ensure_ascii=False, indent=2)
+        print(f"JSON file created: {output_path}")
+        return json_data
+    else:
+        print("Failed to create JSON data")
+        return None
+
+
+def process_in_batches(tx, query, data, batch_size):
+    """Process data in batches and execute the given query."""
+    for i in range(0, len(data), batch_size):
+        batch = data[i : i + batch_size]
+        tx.run(query, {"nodes": batch} if "nodes" in query else {"edges": batch})
+
+
+def main():
+    # Paths
+    xml_file = os.path.join(WORKING_DIR, "graph_chunk_entity_relation.graphml")
+    json_file = os.path.join(WORKING_DIR, "graph_data.json")
+
+    # Convert XML to JSON
+    json_data = convert_xml_to_json(xml_file, json_file)
+    if json_data is None:
+        return
+
+    # Load nodes and edges
+    nodes = json_data.get("nodes", [])
+    edges = json_data.get("edges", [])
+
+    # Neo4j queries
+    create_nodes_query = """
+    UNWIND $nodes AS node
+    MERGE (e:Entity {id: node.id})
+    SET e.entity_type = node.entity_type,
+        e.description = node.description,
+        e.source_id = node.source_id,
+        e.displayName = node.id
+    REMOVE e:Entity
+    WITH e, node
+    CALL apoc.create.addLabels(e, [node.id]) YIELD node AS labeledNode
+    RETURN count(*)
+    """
+
+    create_edges_query = """
+    UNWIND $edges AS edge
+    MATCH (source {id: edge.source})
+    MATCH (target {id: edge.target})
+    WITH source, target, edge,
+         CASE
+            WHEN edge.keywords CONTAINS 'lead' THEN 'lead'
+            WHEN edge.keywords CONTAINS 'participate' THEN 'participate'
+            WHEN edge.keywords CONTAINS 'uses' THEN 'uses'
+            WHEN edge.keywords CONTAINS 'located' THEN 'located'
+            WHEN edge.keywords CONTAINS 'occurs' THEN 'occurs'
+           ELSE REPLACE(SPLIT(edge.keywords, ',')[0], '\"', '')
+         END AS relType
+    CALL apoc.create.relationship(source, relType, {
+      weight: edge.weight,
+      description: edge.description,
+      keywords: edge.keywords,
+      source_id: edge.source_id
+    }, target) YIELD rel
+    RETURN count(*)
+    """
+
+    set_displayname_and_labels_query = """
+    MATCH (n)
+    SET n.displayName = n.id
+    WITH n
+    CALL apoc.create.setLabels(n, [n.entity_type]) YIELD node
+    RETURN count(*)
+    """
+
+    # Create a Neo4j driver
+    driver = GraphDatabase.driver(NEO4J_URI, auth=(NEO4J_USERNAME, NEO4J_PASSWORD))
+
+    try:
+        # Execute queries in batches
+        with driver.session() as session:
+            # Insert nodes in batches
+            session.execute_write(
+                process_in_batches, create_nodes_query, nodes, BATCH_SIZE_NODES
+            )
+
+            # Insert edges in batches
+            session.execute_write(
+                process_in_batches, create_edges_query, edges, BATCH_SIZE_EDGES
+            )
+
+            # Set displayName and labels
+            session.run(set_displayname_and_labels_query)
+
+    except Exception as e:
+        print(f"Error occurred: {e}")
+
+    finally:
+        driver.close()
+
+
+if __name__ == "__main__":
+    main()