neo4j-aura-graph-analytics-skill

pip install "graphdatascience>=1.15"

import os
from graphdatascience.session import AuraAPICredentials, GdsSessions

sessions = GdsSessions(api_credentials=AuraAPICredentials.from_env())
# Reads: AURA_CLIENT_ID, AURA_CLIENT_SECRET, AURA_PROJECT_ID (optional)
# Create API credentials in Aura Console → Account → API credentials

from graphdatascience.session import AlgorithmCategory, SessionMemory

memory = sessions.estimate(
    node_count=1_000_000,
    relationship_count=5_000_000,
    algorithm_categories=[
        AlgorithmCategory.CENTRALITY,
        AlgorithmCategory.NODE_EMBEDDING,
        AlgorithmCategory.COMMUNITY_DETECTION,
    ],
)
# Returns a SessionMemory tier, e.g. SessionMemory.m_8GB
# Fixed tiers: m_2GB … m_256GB — see references/limitations.md

from graphdatascience.session import DbmsConnectionInfo, SessionMemory, CloudLocation
from datetime import timedelta

db_connection = DbmsConnectionInfo(
    username=os.environ["NEO4J_USERNAME"],
    password=os.environ["NEO4J_PASSWORD"],
    aura_instance_id=os.environ["AURA_INSTANCEID"],  # from Aura Console URL
)

gds = sessions.get_or_create(
    session_name="my-analysis",
    memory=memory,
    db_connection=db_connection,
    ttl=timedelta(hours=2),
)
gds.verify_connectivity()

db_connection = DbmsConnectionInfo(
    uri=os.environ["NEO4J_URI"],          # e.g. "bolt://my-server:7687"
    username=os.environ["NEO4J_USERNAME"],
    password=os.environ["NEO4J_PASSWORD"],
)
gds = sessions.get_or_create(
    session_name="my-analysis-sm",
    memory=SessionMemory.m_8GB,
    db_connection=db_connection,
    ttl=timedelta(hours=2),
    cloud_location=CloudLocation("gcp", "europe-west1"),
)
gds.verify_connectivity()

gds = sessions.get_or_create(
    session_name="my-standalone",
    memory=SessionMemory.m_4GB,
    ttl=timedelta(hours=1),
    cloud_location=CloudLocation("gcp", "europe-west1"),
)
gds.verify_connectivity()

G, result = gds.graph.project(
    "my-graph",
    """
    CALL () {
        MATCH (p:Person)
        OPTIONAL MATCH (p)-[r:KNOWS]->(p2:Person)
        RETURN p AS source, r AS rel, p2 AS target,
               p {.age, .score} AS sourceNodeProperties,
               p2 {.age, .score} AS targetNodeProperties
    }
    RETURN gds.graph.project.remote(source, target, {
        sourceNodeLabels:     labels(source),
        targetNodeLabels:     labels(target),
        sourceNodeProperties: sourceNodeProperties,
        targetNodeProperties: targetNodeProperties,
        relationshipType:     type(rel)
    })
    """,
)
print(f"Projected {G.node_count()} nodes, {G.relationship_count()} relationships")

import pandas as pd

nodes_df = pd.DataFrame([
    {"nodeId": 0, "labels": "Person", "age": 30},
    {"nodeId": 1, "labels": "Person", "age": 25},
])
rels_df = pd.DataFrame([
    {"sourceNodeId": 0, "targetNodeId": 1, "relationshipType": "KNOWS"},
])

G = gds.graph.construct("my-graph", nodes_df, rels_df)
# Multiple DataFrames: gds.graph.construct("g", [nodes1, nodes2], [rels1, rels2])

# Mutate — chain results without writing to DB
gds.pageRank.mutate(G, mutateProperty="pagerank", dampingFactor=0.85)
gds.fastRP.mutate(G,
    mutateProperty="embedding",
    embeddingDimension=128,
    featureProperties=["pagerank"],
    randomSeed=42,
)

# Stream — inspect results as DataFrame
df = gds.pageRank.stream(G)
print(df.sort_values("score", ascending=False).head(10))

# Write — persist to connected Neo4j DB (connected modes only)
gds.louvain.write(G, writeProperty="community")

import time

job = gds.pageRank.mutate(G, mutateProperty="pagerank")

# If job object returned (async mode), poll explicitly:
if hasattr(job, "status"):
    while job.status() not in ("RUNNING_DONE", "FAILED", "CANCELLED"):
        time.sleep(5)
        print(f"Job status: {job.status()}")
    if job.status() != "RUNNING_DONE":
        raise RuntimeError(f"Algorithm job failed: {job.status()}")

# Stream node properties — one column per property
result_df = gds.graph.nodeProperties.stream(
    G,
    node_properties=["pagerank", "embedding"],
    separate_property_columns=True,
    db_node_properties=["name"],   # pull from connected DB for context (connected modes only)
)
result_df.head(10)

result_df = gds.graph.nodeProperties.stream(G, ["pagerank"], separate_property_columns=True)
result_df.merge(nodes_df[["nodeId", "name"]], how="left")

# Write multiple node properties to connected Neo4j
gds.graph.nodeProperties.write(G, ["pagerank", "embedding"])

# Write relationship properties
gds.graph.relationshipProperties.write(G, G.relationship_types(), ["score"])

# Run Cypher against connected DB from within session
gds.run_cypher("MATCH (n:Person) RETURN count(n)")

# Drop projected graph (frees session memory)
G.drop()

# Delete session — stops billing
sessions.delete(session_name="my-analysis")
# or: gds.delete()

# List active sessions
from pandas import DataFrame
DataFrame(sessions.list())

# Reconnect to existing session
gds = sessions.get_or_create(session_name="my-analysis", memory=..., db_connection=...)