Terjemahan disediakan oleh mesin penerjemah. Jika konten terjemahan yang diberikan bertentangan dengan versi bahasa Inggris aslinya, utamakan versi bahasa Inggris.

# SageMaker Python SDK version 2.x is required
import sagemaker
import sys

import boto3
import pandas as pd
import numpy as np
import io
from sagemaker.session import Session
from sagemaker import get_execution_role

prefix = 'sagemaker-featurestore-introduction'
role = get_execution_role()

sagemaker_session = sagemaker.Session()
region = sagemaker_session.boto_region_name
s3_bucket_name = sagemaker_session.default_bucket()

customer_data = pd.read_csv("data/feature_store_introduction_customer.csv")
orders_data = pd.read_csv("data/feature_store_introduction_orders.csv")

print(customer_data.head())
print(orders_data.head())

import time
from time import strftime, gmtime
customers_feature_group_name = 'customers-feature-group-' + strftime('%d-%H-%M-%S', gmtime())
orders_feature_group_name = 'orders-feature-group-' + strftime('%d-%H-%M-%S', gmtime())

from sagemaker.feature_store.feature_group import FeatureGroup

customers_feature_group = FeatureGroup(
    name=customers_feature_group_name, sagemaker_session=sagemaker_session
)
orders_feature_group = FeatureGroup(
    name=orders_feature_group_name, sagemaker_session=sagemaker_session
)

import time
current_time_sec = int(round(time.time()))
record_identifier_feature_name = "customer_id"

customer_data["EventTime"] = pd.Series([current_time_sec]*len(customer_data), dtype="float64")
orders_data["EventTime"] = pd.Series([current_time_sec]*len(orders_data), dtype="float64")

customers_feature_group.load_feature_definitions(data_frame=customer_data)
orders_feature_group.load_feature_definitions(data_frame=orders_data)

customers_feature_group.create(
    s3_uri=f"s3://{s3_bucket_name}/{prefix}",
    record_identifier_name=record_identifier_feature_name,
    event_time_feature_name="EventTime",
    role_arn=role,
    enable_online_store=True
)

orders_feature_group.create(
    s3_uri=f"s3://{s3_bucket_name}/{prefix}",
    record_identifier_name=record_identifier_feature_name,
    event_time_feature_name="EventTime",
    role_arn=role,
    enable_online_store=True
)

customers_feature_group.describe()

orders_feature_group.describe()

sagemaker_session.boto_session.client('sagemaker', region_name=region).list_feature_groups() # We use the boto client to list FeatureGroups

def check_feature_group_status(feature_group):
    status = feature_group.describe().get("FeatureGroupStatus")
    while status == "Creating":
        print("Waiting for Feature Group to be Created")
        time.sleep(5)
        status = feature_group.describe().get("FeatureGroupStatus")
    print(f"FeatureGroup {feature_group.name} successfully created.")

check_feature_group_status(customers_feature_group)
check_feature_group_status(orders_feature_group)

customers_feature_group.ingest(
    data_frame=customer_data, max_workers=3, wait=True
)

orders_feature_group.ingest(
    data_frame=orders_data, max_workers=3, wait=True
)

customer_id = 573291
sample_record = sagemaker_session.boto_session.client('sagemaker-featurestore-runtime', region_name=region).get_record(FeatureGroupName=customers_feature_group_name, RecordIdentifierValueAsString=str(customer_id))

print(sample_record)

all_records = sagemaker_session.boto_session.client(
    "sagemaker-featurestore-runtime", region_name=region
).batch_get_record(
    Identifiers=[
        {
            "FeatureGroupName": customers_feature_group_name,
            "RecordIdentifiersValueAsString": ["573291", "109382", "828400", "124013"],
        },
        {
            "FeatureGroupName": orders_feature_group_name,
            "RecordIdentifiersValueAsString": ["573291", "109382", "828400", "124013"],
        },
    ]
)

print(all_records)

Langkah 5: Bersihkan

customers_feature_group.delete()
orders_feature_group.delete()

Langkah 6: Langkah selanjutnya

describe()
ingest()
delete()
create()
load_feature_definitions()

list_feature_groups()
get_record()