Neo4j Aura Graph Analytics Skill

pip install "graphdatascience>=2.1"     # 2.1 is the current stable release

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

# Per-algorithm + config — preferred
memory = sessions.estimate(
    node_count=1_000_000,
    relationship_count=5_000_000,
    algorithms=["wcc", "louvain", "fast_rp"],
)
# or with config:
memory = sessions.estimate(
    node_count=1_000_000,
    relationship_count=5_000_000,
    algorithms={"fast_rp": {"embedding_dimension": 128}},
)
# Coarse category estimate — 1.x style, still available
memory = sessions.estimate(
    node_count=1_000_000,
    relationship_count=5_000_000,
    algorithm_categories=[
        AlgorithmCategory.CENTRALITY,
        AlgorithmCategory.NODE_EMBEDDING,
        AlgorithmCategory.COMMUNITY_DETECTION,
    ],
)
# Returns SessionMemory tier, e.g. SessionMemory.m_8GB
# Fixed tiers: m_2GB … m_512GB — see references/limitations.md

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

# Reads: AURA_INSTANCEID (takes precedence) or NEO4J_URI, plus NEO4J_USERNAME,
# NEO4J_PASSWORD, NEO4J_DATABASE
db_connection = DbmsConnectionInfo.from_env()
# Explicit: DbmsConnectionInfo(aura_instance_id=..., username=..., password=...)

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

# Same from_env() — set NEO4J_URI (e.g. "bolt://my-server:7687"), no AURA_INSTANCEID
gds = sessions.get_or_create(
    session_name="my-analysis-sm",
    memory=SessionMemory.m_8GB,
    db_connection=DbmsConnectionInfo.from_env(),
    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()

query = """
    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)
    })
"""

G, result = gds.graph.project.cypher(
    graph_name="my-graph",
    query=query,
    undirected_relationship_types=["KNOWS"],
)
print(f"Projected {G.node_count()} nodes, {G.relationship_count()} relationships")

G, result = gds.graph.project.native(
    "my-graph",
    ["Person"],                              # node_label_filter
    ["KNOWS"],                               # relationship_type_filter
    node_properties=["age", "score"],
    undirected_relationship_types=["KNOWS"],
)

CYPHER runtime=parallel
MATCH (source)
OPTIONAL MATCH (source)-->(target)
RETURN gds.graph.project(
  'my-graph',
  source,
  target,
  {},
  { memory: '2GB' }
)

CYPHER runtime=parallel
MATCH (source)
OPTIONAL MATCH (source)-->(target)
RETURN gds.graph.project(
  'my-graph',
  source,
  target,
  {},
  { sessionId: '00000000-11111111' }
)

CALL gds.session.getOrCreate('test-session', '2GB', duration({minutes: 30}))
YIELD id, name, status
RETURN id, name, status

CALL gds.session.list()
YIELD id, name, status, memory
RETURN id, name, status, memory

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])

# Mutate — chain results without writing to DB
gds.page_rank.mutate(G, mutate_property="pagerank", damping_factor=0.85)
gds.fast_rp.mutate(G,
    mutate_property="embedding",
    embedding_dimension=128,
    feature_properties=["pagerank"],
    random_seed=42,
)

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

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