gleeb

import boto3

sm_client = boto3.client('sagemaker', region_name='us-east-1')
sagemaker_runtime = boto3.client("sagemaker-runtime", region_name='us-east-1')

# Specify the location of the input.
input_location = "<Path to your csv file in S3>"

# The name of the endpoint. The name must be unique within an AWS Region in your AWS account.
endpoint_name='titanic-survival-async-endpoint'

gleeb

import boto3

sm_client = boto3.client('sagemaker', region_name='us-east-1')

endpoint_config_name = 'titanic-survival-async-endpoint-config'
print(endpoint_config_name)

create_endpoint_config_response = sm_client.create_endpoint_config(
    EndpointConfigName=endpoint_config_name, # You will specify this name in a CreateEndpoint request.
    # List of ProductionVariant objects, one for each model that you want to host at this endpoint.

gleeb

import boto3

sm_client = boto3.client('sagemaker', region_name='us-east-1')

endpoint_config_name = 'titanic-survival-serverless-endpoint-config'
print(endpoint_config_name)
create_endpoint_config_response = sm_client.create_endpoint_config(
    EndpointConfigName = endpoint_config_name,
    ProductionVariants=[        {
            "ModelName": "titanic-survival-v1",

gleeb

import boto3

sm_client = boto3.client('sagemaker', region_name='us-east-1')
sagemaker_runtime = boto3.client("sagemaker-runtime", region_name='us-east-1')

# The name of the endpoint. The name must be unique within an AWS Region in your AWS account.
endpoint_name='titanic-survival-endpoint1'

# After you deploy a model into production using SageMaker hosting
# services, your client applications use this API to get inferences

gleeb

import boto3
sm_client = boto3.client('sagemaker', region_name='us-east-1')

endpoint_name = 'titanic-survival-endpoint'
endpoint_config_name = 'titanic-survival-endpoint-config'

print("EndpointName={}".format(endpoint_name))
create_endpoint_response = sm_client.create_endpoint(
    EndpointName=endpoint_name,
    EndpointConfigName=endpoint_config_name)

gleeb

import boto3
sm_client = boto3.client('sagemaker', region_name='us-east-1')

endpoint_config_name = 'titanic-survival-endpoint-config'
print(endpoint_config_name)
create_endpoint_config_response = sm_client.create_endpoint_config(
    EndpointConfigName = endpoint_config_name,
    ProductionVariants=[{
        'InstanceType':'ml.m4.xlarge',
        'InitialVariantWeight':1,

gleeb

import boto3
from datetime import datetime


sm_client = boto3.client('sagemaker', region_name='us-east-1')

model_name = 'titanic-survival-v1'
print("Model name : {}".format(model_name))
container_list = [{'ModelPackageName': 'arn:aws:sagemaker:us-east-1:...:model-package/titanic-survival/3'}]

gleeb

import boto3


sm_client = boto3.client('sagemaker', region_name='us-east-1')

model_url = "s3://sagemaker-us-east-1-.../sagemaker-scikit-learn-.../output/model.tar.gz"

modelpackage_inference_specification =  {
    "InferenceSpecification": {
      "Containers": [

gleeb

import os
import sagemaker
import boto3

iam_client = boto3.client('iam')
role = iam_client.get_role(RoleName='AmazonSageMaker-ExecutionRole-xyz')['Role']['Arn']
sm_client = boto3.client('sagemaker', region_name="us-east-1")

model_package_group_name = "Titanic-survival"
model_package_group_input_dict = {

gleeb