入门 (SDK for Python (Boto3))

使用以下代码创建 Amazon Personalize 架构。将 getting-started-schema 替换为架构的名称。

import json
schema = {
  "type": "record",
  "name": "Interactions",
  "namespace": "com.amazonaws.personalize.schema",
  "fields": [
      {
          "name": "USER_ID",
          "type": "string"
      },
      {
          "name": "ITEM_ID",
          "type": "string"
      },
      {
          "name": "TIMESTAMP",
          "type": "long"
      }
  ],
  "version": "1.0"
}

create_interactions_schema_response = personalize.create_schema(
    name='getting-started-schema',
    schema=json.dumps(schema)
)

interactions_schema_arn = create_interactions_schema_response['schemaArn']
print(json.dumps(create_interactions_schema_response, indent=2))

使用以下代码创建数据集组。将 dataset group name 替换为数据集组的名称。

response = personalize.create_dataset_group(name = 'dataset group name')
dataset_group_arn = response['datasetGroupArn']

description = personalize.describe_dataset_group(datasetGroupArn = dataset_group_arn)['datasetGroup']

print('Name: ' + description['name'])
print('ARN: ' + description['datasetGroupArn'])
print('Status: ' + description['status'])

使用以下代码在新数据集组中创建物品交互数据集。为数据集命名，并提供前面步骤中的schema_arn和dataset_group_arn。

response = personalize.create_dataset(
    name = 'datase_name',
    schemaArn = 'schema_arn',
    datasetGroupArn = 'dataset_group_arn',
    datasetType = 'Interactions'
)

dataset_arn = response['datasetArn']

使用以下代码通过数据集导入作业导入数据。代码使用 describe_dataset_import_job 方法来跟踪作业的状态。

将以下内容作为参数传递：作业名称、上一步中的 dataset_arn、存储训练数据的 Amazon S3 存储桶路径 (s3://bucket name/folder name/ratings.csv) 以及您的 IAM 服务角色的 ARN。您在入门先决条件期间创建了此角色。Amazon Personalize 需要权限才能访问存储桶。请参阅 向 Amazon Personalize 授予访问 Amazon S3 资源的权限。

import time
response = personalize.create_dataset_import_job(
    jobName = 'JobName',
    datasetArn = 'dataset_arn',
    dataSource = {'dataLocation':'s3://bucket/file.csv'},
    roleArn = 'role_arn',
    importMode = 'FULL'
)

dataset_interactions_import_job_arn = response['datasetImportJobArn']

description = personalize.describe_dataset_import_job(
    datasetImportJobArn = dataset_interactions_import_job_arn)['datasetImportJob']

print('Name: ' + description['jobName'])
print('ARN: ' + description['datasetImportJobArn'])
print('Status: ' + description['status'])

max_time = time.time() + 3*60*60 # 3 hours
while time.time() < max_time:
    describe_dataset_import_job_response = personalize.describe_dataset_import_job(
        datasetImportJobArn = dataset_interactions_import_job_arn
    )
    status = describe_dataset_import_job_response["datasetImportJob"]['status']
    print("Interactions DatasetImportJob: {}".format(status))
    
    if status == "ACTIVE" or status == "CREATE FAILED":
        break
        
    time.sleep(60)

使用以下代码创建新解决方案。将以下内容作为参数传递：dataset_group_arn来自之前的、解决方案的名称以及用户个性化-v2 配方的 ARN ()。arn:aws:personalize:::recipe/aws-user-personalization-v2存储新解决方案的 ARN 以备日后使用。

create_solution_response = personalize.create_solution(
  name='solution name', 
  recipeArn= 'arn:aws:personalize:::recipe/aws-user-personalization-v2', 
  datasetGroupArn = 'dataset group arn'
)
solution_arn = create_solution_response['solutionArn']
print('solution_arn: ', solution_arn)

使用以下代码创建解决方案版本。将上一步中的 solution_arn 作为参数传递。以下代码将创建解决方案版本。在训练期间，代码使用 DescribeSolutionVersion 操作来检索解决方案版本的状态。训练完成后，方法将返回新解决方案版本的 ARN。请将其存储以便将来使用。

import time
import json

create_solution_version_response = personalize.create_solution_version(
    solutionArn = solution_arn
)

solution_version_arn = create_solution_version_response['solutionVersionArn']
print(json.dumps(create_solution_version_response, indent=2))

max_time = time.time() + 3*60*60 # 3 hours
while time.time() < max_time:
    describe_solution_version_response = personalize.describe_solution_version(
        solutionVersionArn = solution_version_arn
    )
    status = describe_solution_version_response["solutionVersion"]["status"]
    print("SolutionVersion: {}".format(status))
    
    if status == "ACTIVE" or status == "CREATE FAILED":
        break
        
    time.sleep(60)