管理组件和管道的输入和输出

$schema: https://azuremlschemas.azureedge.net/latest/pipelineJob.schema.json
type: pipeline
display_name: 1b_e2e_registered_components
description: E2E dummy train-score-eval pipeline with registered components

inputs:
  pipeline_job_training_max_epocs: 20
  pipeline_job_training_learning_rate: 1.8
  pipeline_job_learning_rate_schedule: 'time-based'

outputs: 
  pipeline_job_trained_model:
    mode: upload
  pipeline_job_scored_data:
    mode: upload
  pipeline_job_evaluation_report:
    mode: upload

settings:
 default_compute: azureml:cpu-cluster

jobs:
  train_job:
    type: command
    component: azureml:my_train@latest
    inputs:
      training_data: 
        type: uri_folder 
        path: ./data      
      max_epocs: ${{parent.inputs.pipeline_job_training_max_epocs}}
      learning_rate: ${{parent.inputs.pipeline_job_training_learning_rate}}
      learning_rate_schedule: ${{parent.inputs.pipeline_job_learning_rate_schedule}}
    outputs:
      model_output: ${{parent.outputs.pipeline_job_trained_model}}
    services:
      my_vscode:
        type: vs_code
      my_jupyter_lab:
        type: jupyter_lab
      my_tensorboard:
        type: tensor_board
        log_dir: "outputs/tblogs"
    #  my_ssh:
    #    type: tensor_board
    #    ssh_public_keys: <paste the entire pub key content>
    #    nodes: all # Use the `nodes` property to pick which node you want to enable interactive services on. If `nodes` are not selected, by default, interactive applications are only enabled on the head node.

  score_job:
    type: command
    component: azureml:my_score@latest
    inputs:
      model_input: ${{parent.jobs.train_job.outputs.model_output}}
      test_data: 
        type: uri_folder 
        path: ./data
    outputs:
      score_output: ${{parent.outputs.pipeline_job_scored_data}}

  evaluate_job:
    type: command
    component: azureml:my_eval@latest
    inputs:
      scoring_result: ${{parent.jobs.score_job.outputs.score_output}}
    outputs:
      eval_output: ${{parent.outputs.pipeline_job_evaluation_report}}

可以在包含已注册组件的 train-score-eval 管道中找到该完整示例。 此管道将三个输入和三个输出提升到管道级别。 我们以 pipeline_job_training_max_epocs 为例。 它在根级别的 inputs 部分下声明，这意味着它属于管道级别输入。 在 jobs -> train_job 部分下，名为 max_epocs 的输入引用为 ${{parent.inputs.pipeline_job_training_max_epocs}}，这指示 train_job 的输入 max_epocs 引用了管道级别输入 pipeline_job_training_max_epocs。 同样，可以使用同一架构提升管道输出。

# import required libraries
from azure.identity import DefaultAzureCredential

from azure.ai.ml import MLClient, Input
from azure.ai.ml.dsl import pipeline
from azure.ai.ml import load_component

# Set your subscription, resource group and workspace name:
subscription_id = "<SUBSCRIPTION_ID>"
resource_group = "<RESOURCE_GROUP>"
workspace = "<AML_WORKSPACE_NAME>"

# connect to the AzureML workspace
ml_client = MLClient(
    DefaultAzureCredential(), subscription_id, resource_group, workspace
)

# define the dirtory that stores the input data 
parent_dir = ""

# Load components
prepare_data = load_component(source=parent_dir + "./prep.yml")
transform_data = load_component(source=parent_dir + "./transform.yml")
train_model = load_component(source=parent_dir + "./train.yml")
predict_result = load_component(source=parent_dir + "./predict.yml")
score_data = load_component(source=parent_dir + "./score.yml")

# Construct pipeline. 
# Below code snippet defines nyc_taxi_data_regression pipeline.
# The pipeline takes 1 input (pipeline_job_input) and generates 6 outputs as defined in return statement.
# The pipeline outputs are promoted from the child component using schema as <step_name.outputs.output_name>.
# for example `prepare_sample_data.outputs.prep_data`.  
@pipeline()
def nyc_taxi_data_regression(pipeline_job_input):
    """NYC taxi data regression example."""
    prepare_sample_data = prepare_data(raw_data=pipeline_job_input)
    transform_sample_data = transform_data(
        clean_data=prepare_sample_data.outputs.prep_data
    )
    train_with_sample_data = train_model(
        training_data=transform_sample_data.outputs.transformed_data
    )
    predict_with_sample_data = predict_result(
        model_input=train_with_sample_data.outputs.model_output,
        test_data=train_with_sample_data.outputs.test_data,
    )
    score_with_sample_data = score_data(
        predictions=predict_with_sample_data.outputs.predictions,
        model=train_with_sample_data.outputs.model_output,
    )
    return {
        "pipeline_job_prepped_data": prepare_sample_data.outputs.prep_data,
        "pipeline_job_transformed_data": transform_sample_data.outputs.transformed_data,
        "pipeline_job_trained_model": train_with_sample_data.outputs.model_output,
        "pipeline_job_test_data": train_with_sample_data.outputs.test_data,
        "pipeline_job_predictions": predict_with_sample_data.outputs.predictions,
        "pipeline_job_score_report": score_with_sample_data.outputs.score_report,
    }
# 
pipeline_job = nyc_taxi_data_regression(
    Input(type="uri_folder", path=parent_dir + "./data/")
)
# demo how to change pipeline output settings
pipeline_job.outputs.pipeline_job_prepped_data.mode = "rw_mount"

# set pipeline level compute
pipeline_job.settings.default_compute = "cpu-cluster"
# set pipeline level datastore
pipeline_job.settings.default_datastore = "workspaceblobstore"

azureml-example 存储库中的端到端笔记本示例

pipeline.yaml 定义了具有三个管道级别输出的管道。 可以在包含已注册组件实例的 train-score-eval 管道中找到该完整 YAML。 可以使用以下命令设置 pipeline_job_trained_model 输出的自定义输出路径。

# define the custom output path using datastore uri
# add relative path to your blob container after "azureml://datastores/<datastore_name>/paths"
output_path="azureml://datastores/{datastore_name}/paths/{relative_path_of_container}"  

# create job and define path using --outputs.<outputname>
az ml job create -f ./pipeline.yml --set outputs.pipeline_job_trained_model.path=$output_path  

cluster_name = "cpu-cluster"
custom_path = "azureml://datastores/workspaceblobstore/paths/custom_path/${{name}}/"

# define a pipeline with component
@pipeline(default_compute=cluster_name)
def pipeline_with_python_function_components(input_data, test_data, learning_rate):
    """E2E dummy train-score-eval pipeline with components defined via python function components"""

    # Call component obj as function: apply given inputs & parameters to create a node in pipeline
    train_with_sample_data = train_model(
        training_data=input_data, max_epochs=5, learning_rate=learning_rate
    )
    score_with_sample_data = score_data(
        model_input=train_with_sample_data.outputs.model_output, test_data=test_data
    )
    # example how to change path of output on step level,
    # please note if the output is promoted to pipeline level you need to change path in pipeline job level
    score_with_sample_data.outputs.score_output = Output(
        type="uri_folder", mode="rw_mount", path=custom_path
    )
    eval_with_sample_data = eval_model(
        scoring_result=score_with_sample_data.outputs.score_output
    )

    # Return: pipeline outputs
    return {
        "eval_output": eval_with_sample_data.outputs.eval_output,
        "model_output": train_with_sample_data.outputs.model_output,
    }


pipeline_job = pipeline_with_python_function_components(
    input_data=Input(
        path="wasbs://demo@dprepdata.blob.core.windows.net/Titanic.csv", type="uri_file"
    ),
    test_data=Input(
        path="wasbs://demo@dprepdata.blob.core.windows.net/Titanic.csv", type="uri_file"
    ),
    learning_rate=0.1,
)
# example how to change path of output on pipeline level
pipeline_job.outputs.model_output = Output(
    type="uri_folder", mode="rw_mount", path=custom_path
)

可以在具有 command_component 修饰的 python 函数笔记本的生成管道中找到端到端笔记本示例。

# Download all the outputs of the job
az ml job download --all -n <JOB_NAME> -g <RESOURCE_GROUP_NAME> -w <WORKSPACE_NAME> --subscription <SUBSCRIPTION_ID>

# Download specific output
az ml job download --output-name <OUTPUT_PORT_NAME> -n <JOB_NAME> -g <RESOURCE_GROUP_NAME> -w <WORKSPACE_NAME> --subscription <SUBSCRIPTION_ID>

在深入了解代码之前，需要一种方法来引用工作区。 你将为工作区句柄创建 ml_client。 请参阅创建工作区的句柄以初始化 ml_client。

# Download all the outputs of the job
output = client.jobs.download(name=job.name, download_path=tmp_path, all=True)

# Download specific output
output = client.jobs.download(name=job.name, download_path=tmp_path, output_name=output_port_name)

# List all child jobs in the job and print job details in table format
az ml job list --parent-job-name <JOB_NAME> -g <RESOURCE_GROUP_NAME> -w <WORKSPACE_NAME> --subscription <SUBSCRIPTION_ID> -o table

# Select needed child job name to download output
az ml job download --all -n <JOB_NAME> -g <RESOURCE_GROUP_NAME> -w <WORKSPACE_NAME> --subscription <SUBSCRIPTION_ID>

在深入了解代码之前，需要一种方法来引用工作区。 你将为工作区句柄创建 ml_client。 请参阅创建工作区的句柄以初始化 ml_client。

# List all child jobs in the job
child_jobs = client.jobs.list(parent_job_name=job.name)
# Traverse and download all the outputs of child job
for child_job in child_jobs:
    client.jobs.download(name=child_job.name, all=True)

display_name: register_pipeline_output
type: pipeline
jobs:
  node:
    type: command
    inputs:
      component_in_path:
        type: uri_file
        path: https://dprepdata.blob.core.chinacloudapi.cn/demo/Titanic.csv
    component: ../components/helloworld_component.yml
    outputs:
      component_out_path: ${{parent.outputs.component_out_path}}
outputs:
  component_out_path:
    type: mltable
    name: pipeline_output  # Define name and version to register pipeline output
    version: '1'
settings:
  default_compute: azureml:cpu-cluster

from azure.ai.ml import dsl, Output

# Load component functions
components_dir = "./components/"
helloworld_component = load_component(source=f"{components_dir}/helloworld_component.yml")

@pipeline()
def register_pipeline_output():
  # Call component obj as function: apply given inputs & parameters to create a node in pipeline
  node = helloworld_component(component_in_path=Input(
    type='uri_file', path='https://dprepdata.blob.core.chinacloudapi.cn/demo/Titanic.csv'))

  return {
      'component_out_path': node.outputs.component_out_path
  }

pipeline = register_pipeline_output()
# Define name and version to register pipeline output
pipeline.settings.default_compute = "azureml:cpu-cluster"
pipeline.outputs.component_out_path.name = 'pipeline_output'
pipeline.outputs.component_out_path.version = '1'

display_name: register_node_output
type: pipeline
jobs:
  node:
    type: command
    component: ../components/helloworld_component.yml
    inputs:
      component_in_path:
        type: uri_file
        path: 'https://dprepdata.blob.core.chinacloudapi.cn/demo/Titanic.csv'
    outputs:
      component_out_path:
        type: uri_folder
        name: 'node_output'  # Define name and version to register a child job's output
        version: '1'
settings:
  default_compute: azureml:cpu-cluster

from azure.ai.ml import dsl, Output

# Load component functions
components_dir = "./components/"
helloworld_component = load_component(source=f"{components_dir}/helloworld_component.yml")

@pipeline()
def register_node_output():
  # Call component obj as function: apply given inputs & parameters to create a node in pipeline
  node = helloworld_component(component_in_path=Input(
    type='uri_file', path='https://dprepdata.blob.core.chinacloudapi.cn/demo/Titanic.csv'))

  # Define name and version to register node output
  node.outputs.component_out_path.name = 'node_output'
  node.outputs.component_out_path.version = '1'

pipeline = register_node_output()
pipeline.settings.default_compute = "azureml:cpu-cluster"