使用 Amazon Neptune 绘制图形关系

import json
import os

from gremlin_python.process.anonymous_traversal import traversal
from gremlin_python.driver.driver_remote_connection import DriverRemoteConnection

endpoint = os.environ["NEPTUNE_ENDPOINT"]

g = traversal().withRemote(
    DriverRemoteConnection(f"wss://{endpoint}:8182/gremlin", "g")
)

with open("scripts/vertices.json", "r") as f:
    for row in f:
        data = json.loads(row)
        if data["label"] == "User":
            g.addV("User").property("username", data["username"]).next()
        elif data["label"] == "Restaurant":
            g.addV("Restaurant").property("name", data["name"]).next()
        elif data["label"] == "IPAddress":
            g.addV("IPAddress").property("address", data["address"]).next()

with open("scripts/edges.json", "r") as f:
    for row in f:
        data = json.loads(row)
        if data["label"] == "Used":
            g.V().has("User", "username", data["username"]).as_("user").V().has(
                "IPAddress", "address", data["ip_address"]
            ).as_("ip_address").addE("Used").from_("user").to("ip_address").next()
        elif data["label"] == "Reviewed":
            g.V().has("User", "username", data["username"]).as_("user").V().has(
                "Restaurant", "name", data["restaurant"]
            ).as_("restaurant").addE("Reviewed").from_("user").to(
                "restaurant"
            ).property(
                "rating", data["rating"]
            ).property(
                "username", data["username"]
            ).property(
                "restaurant", data["restaurant"]
            ).next()

print("Loaded data successfully!")

import os

from gremlin_python.process.anonymous_traversal import traversal
from gremlin_python.driver.driver_remote_connection import DriverRemoteConnection
from gremlin_python import statics

statics.load_statics(globals())


endpoint = os.environ["NEPTUNE_ENDPOINT"]

g = traversal().withRemote(
    DriverRemoteConnection(f"wss://{endpoint}:8182/gremlin", "g")
)


def find_users_of_suspicious_ip_addresses(ip_address):
    results = (
        g.V()
        .has("IPAddress", "address", ip_address)
        .as_("ip_address")
        .in_("Used")
        .aggregate("ip_address_users")
        .outE("Reviewed")
        .has("rating", 1)
        .values("username")
        .groupCount()
        .order(local)
        .by(values, desc)
        .limit(local, 10)
        .toList()
    )

    return [
        {"username": k, "1-star reviews": v}
        for result in results
        for k, v in result.items()
    ]


suspicious_users = find_users_of_suspicious_ip_addresses("173.153.51.29")

for user in suspicious_users:
    print(
        f"User {user['username']} has written {user['1-star reviews']} one-star reviews."
    )

import os

from gremlin_python.process.anonymous_traversal import traversal
from gremlin_python.driver.driver_remote_connection import DriverRemoteConnection
from gremlin_python import statics

statics.load_statics(globals())


endpoint = os.environ["NEPTUNE_ENDPOINT"]

g = traversal().withRemote(
    DriverRemoteConnection(f"wss://{endpoint}:8182/gremlin", "g")
)


def find_related_suspicious_ip_addresses(ip_address):
    results = (
        g.V()
        .has("IPAddress", "address", ip_address)
        .as_("ip_address")
        .in_("Used")
        .aggregate("ip_address_users")
        .out("Used")
        .where(neq("ip_address"))
        .values("address")
        .groupCount()
        .order(local)
        .by(values, desc)
        .limit(local, 10)
        .toList()
    )

    return [
        {"ip_address": k, "user_overlap": v}
        for result in results
        for k, v in result.items()
    ]


suspicious_ip_addresses = find_related_suspicious_ip_addresses("173.153.51.29")

for user in suspicious_ip_addresses:
    print(
        f"IP address {user['ip_address']} has {user['user_overlap']} overlapping users."
    )