向实时推理端点部署机器学习模型

%pip install --upgrade -q aiobotocore

复制

import pandas as pd
import numpy as np
import boto3
import sagemaker
import time
import json
import io
from io import StringIO
import base64
import pprint
import re

from sagemaker.image_uris import retrieve

sess = sagemaker.Session()
write_bucket = sess.default_bucket()
write_prefix = "fraud-detect-demo"

region = sess.boto_region_name
s3_client = boto3.client("s3", region_name=region)
sm_client = boto3.client("sagemaker", region_name=region)
sm_runtime_client = boto3.client("sagemaker-runtime")
sm_autoscaling_client = boto3.client("application-autoscaling")

sagemaker_role = sagemaker.get_execution_role()


# S3 locations used for parameterizing the notebook run
read_bucket = "sagemaker-sample-files"
read_prefix = "datasets/tabular/synthetic_automobile_claims" 
model_prefix = "models/xgb-fraud"

data_capture_key = f"{write_prefix}/data-capture"

# S3 location of trained model artifact
model_uri = f"s3://{read_bucket}/{model_prefix}/fraud-det-xgb-model.tar.gz"

# S3 path where data captured at endpoint will be stored
data_capture_uri = f"s3://{write_bucket}/{data_capture_key}"

# S3 location of test data
test_data_uri = f"s3://{read_bucket}/{read_prefix}/test.csv"

复制

# Retrieve the SageMaker managed XGBoost image
training_image = retrieve(framework="xgboost", region=region, version="1.3-1")

# Specify a unique model name that does not exist
model_name = "fraud-detect-xgb"
primary_container = {
                     "Image": training_image,
                     "ModelDataUrl": model_uri
                    }

model_matches = sm_client.list_models(NameContains=model_name)["Models"]
if not model_matches:
    model = sm_client.create_model(ModelName=model_name,
                                   PrimaryContainer=primary_container,
                                   ExecutionRoleArn=sagemaker_role)
else:
    print(f"Model with name {model_name} already exists! Change model name to create new")

复制

# Endpoint Config name
endpoint_config_name = f"{model_name}-endpoint-config"

# Endpoint config parameters
production_variant_dict = {
                           "VariantName": "Alltraffic",
                           "ModelName": model_name,
                           "InitialInstanceCount": 1,
                           "InstanceType": "ml.m5.xlarge",
                           "InitialVariantWeight": 1
                          }

# Data capture config parameters
data_capture_config_dict = {
                            "EnableCapture": True,
                            "InitialSamplingPercentage": 100,
                            "DestinationS3Uri": data_capture_uri,
                            "CaptureOptions": [{"CaptureMode" : "Input"}, {"CaptureMode" : "Output"}]
                           }


# Create endpoint config if one with the same name does not exist
endpoint_config_matches = sm_client.list_endpoint_configs(NameContains=endpoint_config_name)["EndpointConfigs"]
if not endpoint_config_matches:
    endpoint_config_response = sm_client.create_endpoint_config(
                                                                EndpointConfigName=endpoint_config_name,
                                                                ProductionVariants=[production_variant_dict],
                                                                DataCaptureConfig=data_capture_config_dict
                                                               )
else:
    print(f"Endpoint config with name {endpoint_config_name} already exists! Change endpoint config name to create new")

复制

endpoint_name = f"{model_name}-endpoint"

endpoint_matches = sm_client.list_endpoints(NameContains=endpoint_name)["Endpoints"]
if not endpoint_matches:
    endpoint_response = sm_client.create_endpoint(
                                                  EndpointName=endpoint_name,
                                                  EndpointConfigName=endpoint_config_name
                                                 )
else:
    print(f"Endpoint with name {endpoint_name} already exists! Change endpoint name to create new")

resp = sm_client.describe_endpoint(EndpointName=endpoint_name)
status = resp["EndpointStatus"]
while status == "Creating":
    print(f"Endpoint Status: {status}...")
    time.sleep(60)
    resp = sm_client.describe_endpoint(EndpointName=endpoint_name)
    status = resp["EndpointStatus"]
print(f"Endpoint Status: {status}")

复制

# Fetch test data to run predictions with the endpoint
test_df = pd.read_csv(test_data_uri)

# For content type text/csv, payload should be a string with commas separating the values for each feature
# This is the inference request serialization step
# CSV serialization
csv_file = io.StringIO()
test_sample = test_df.drop(["fraud"], axis=1).iloc[:5]
test_sample.to_csv(csv_file, sep=",", header=False, index=False)
payload = csv_file.getvalue()
response = sm_runtime_client.invoke_endpoint(
                                             EndpointName=endpoint_name,
                                             Body=payload,
                                             ContentType="text/csv",
                                             Accept="text/csv"
                                            )

# This is the inference response deserialization step
# This is a bytes object
result = response["Body"].read()
# Decoding bytes to a string
result = result.decode("utf-8")
# Converting to list of predictions
result = re.split(",|n",result)

prediction_df = pd.DataFrame()
prediction_df["Prediction"] = result[:5]
prediction_df["Label"] = test_df["fraud"].iloc[:5].values
prediction_df

复制

from sagemaker.s3 import S3Downloader
print("Waiting for captures to show up", end="")
for _ in range(90):
    capture_files = sorted(S3Downloader.list(f"{data_capture_uri}/{endpoint_name}"))
    if capture_files:
        capture_file = S3Downloader.read_file(capture_files[-1]).split("n")
        capture_record = json.loads(capture_file[0])
        if "inferenceId" in capture_record["eventMetadata"]:
            break
    print(".", end="", flush=True)
    time.sleep(1)
print()
print(f"Found {len(capture_files)} Data Capture Files:")

复制

capture_files = sorted(S3Downloader.list(f"{data_capture_uri}/{endpoint_name}"))
capture_file = S3Downloader.read_file(capture_files[0]).split("n")
capture_record = json.loads(capture_file[0])
capture_record

复制

input_data = capture_record["captureData"]["endpointInput"]["data"]
output_data = capture_record["captureData"]["endpointOutput"]["data"]
input_data_list = base64.b64decode(input_data).decode("utf-8").split("n")
print(input_data_list)
output_data_list = base64.b64decode(output_data).decode("utf-8").split("n")
print(output_data_list)

复制

resp = sm_client.describe_endpoint(EndpointName=endpoint_name)

# SageMaker expects resource id to be provided with the following structure
resource_id = f"endpoint/{endpoint_name}/variant/{resp['ProductionVariants'][0]['VariantName']}"

# Scaling configuration
scaling_config_response = sm_autoscaling_client.register_scalable_target(
                                                          ServiceNamespace="sagemaker",
                                                          ResourceId=resource_id,
                                                          ScalableDimension="sagemaker:variant:DesiredInstanceCount", 
                                                          MinCapacity=1,
                                                          MaxCapacity=2
                                                        )

复制

# Create Scaling Policy
policy_name = f"scaling-policy-{endpoint_name}"
scaling_policy_response = sm_autoscaling_client.put_scaling_policy(
                                                PolicyName=policy_name,
                                                ServiceNamespace="sagemaker",
                                                ResourceId=resource_id,
                                                ScalableDimension="sagemaker:variant:DesiredInstanceCount",
                                                PolicyType="TargetTrackingScaling",
                                                TargetTrackingScalingPolicyConfiguration={
                                                    "TargetValue": 5.0, # Target for avg invocations per minutes
                                                    "PredefinedMetricSpecification": {
                                                        "PredefinedMetricType": "SageMakerVariantInvocationsPerInstance",
                                                    },
                                                    "ScaleInCooldown": 600, # Duration in seconds until scale in
                                                    "ScaleOutCooldown": 60 # Duration in seconds between scale out
                                                }
                                            )

复制

response = sm_autoscaling_client.describe_scaling_policies(ServiceNamespace="sagemaker")

pp = pprint.PrettyPrinter(indent=4, depth=4)
for i in response["ScalingPolicies"]:
    pp.pprint(i["PolicyName"])
    print("")
    if("TargetTrackingScalingPolicyConfiguration" in i):
        pp.pprint(i["TargetTrackingScalingPolicyConfiguration"])

复制

request_duration = 250
end_time = time.time() + request_duration
print(f"Endpoint will be tested for {request_duration} seconds")
while time.time() < end_time:
    csv_file = io.StringIO()
    test_sample = test_df.drop(["fraud"], axis=1).iloc[[np.random.randint(0, test_df.shape[0])]]
    test_sample.to_csv(csv_file, sep=",", header=False, index=False)
    payload = csv_file.getvalue()
    response = sm_runtime_client.invoke_endpoint(
                                                 EndpointName=endpoint_name,
                                                 Body=payload,
                                                 ContentType="text/csv"
                                                )

复制

# Check the instance counts after the endpoint gets more load
response = sm_client.describe_endpoint(EndpointName=endpoint_name)
endpoint_status = response["EndpointStatus"]
request_duration = 250
end_time = time.time() + request_duration
print(f"Waiting for Instance count increase for a max of {request_duration} seconds. Please re run this cell in case the count does not change")
while time.time() < end_time:
    response = sm_client.describe_endpoint(EndpointName=endpoint_name)
    endpoint_status = response["EndpointStatus"]
    instance_count = response["ProductionVariants"][0]["CurrentInstanceCount"]
    print(f"Status: {endpoint_status}")
    print(f"Current Instance count: {instance_count}")
    if (endpoint_status=="InService") and (instance_count>1):
        break
    else:
        time.sleep(15)

复制

# Delete model
sm_client.delete_model(ModelName=model_name)

# Delete endpoint configuration
sm_client.delete_endpoint_config(EndpointConfigName=endpoint_config_name)

# Delete endpoint
sm_client.delete_endpoint(EndpointName=endpoint_name)

复制