Datainsight 的核心组件介绍

kubectl get po -nkubeflow-user-example-com
NAME                                               READY   STATUS            RESTARTS   AGE
ml-pipeline-ui-artifact-6d7ffcc4b6-9kxkk           2/2     Running           0          48m
ml-pipeline-visualizationserver-84d577b989-5hl46   2/2     Running           0          48m
test-for-jupyter-0                                 0/2     PodInitializing   0          44s

apiVersion: "kubeflow.org/v1beta1"
kind: Experiment
metadata:
  namespace: kubeflow-user-example-com
  name: random-example
spec:
  objective:
    type: maximize
    goal: 0.99
    objectiveMetricName: Validation-accuracy
    additionalMetricNames:
      - Train-accuracy
  algorithm:
    algorithmName: random
  parallelTrialCount: 3
  maxTrialCount: 12
  maxFailedTrialCount: 3
  parameters:
    - name: lr
      parameterType: double
      feasibleSpace:
        min: "0.01"
        max: "0.03"
    - name: num-layers
      parameterType: int
      feasibleSpace:
        min: "2"
        max: "5"
    - name: optimizer
      parameterType: categorical
      feasibleSpace:
        list:
          - sgd
          - adam
          - ftrl
  trialTemplate:
    primaryContainerName: training-container
    trialParameters:
      - name: learningRate
        description: Learning rate for the training model
        reference: lr
      - name: numberLayers
        description: Number of training model layers
        reference: num-layers
      - name: optimizer
        description: Training model optimizer (sdg, adam or ftrl)
        reference: optimizer
    trialSpec:
      apiVersion: batch/v1
      kind: Job
      spec:
        template:
          spec:
            containers:
              - name: training-container
                image: docker.io/kubeflowkatib/mxnet-mnist:v1beta1-45c5727
                command:
                  - "python3"
                  - "/opt/mxnet-mnist/mnist.py"
                  - "--batch-size=64"
                  - "--lr=${trialParameters.learningRate}"
                  - "--num-layers=${trialParameters.numberLayers}"
                  - "--optimizer=${trialParameters.optimizer}"
            restartPolicy: Never

apiVersion: argoproj.io/v1alpha1
kind: Workflow
metadata:
  generateName: kubeflow-test-
spec:
  entrypoint: kubeflow-test
  templates:
  - name: kubeflow-test
    dag:
      tasks:
      - name: print-text
        template: print-text
        dependencies: [repeat-line]
      - {name: repeat-line, template: repeat-line}
  - name: repeat-line
    container:
      args: [--line, Hello, --count, '15', --output-text, /gotest/outputs/output_text/data]
      command:
      - sh
      - -ec
      - |
        program_path=$(mktemp)
        printf "%s" "$0" > "$program_path"
        python3 -u "$program_path" "$@"
      - |
        def _make_parent_dirs_and_return_path(file_path: str):
            import os
            os.makedirs(os.path.dirname(file_path), exist_ok=True)
            return file_path

        def repeat_line(line, output_text_path, count = 10):
            '''Repeat the line specified number of times'''
            with open(output_text_path, 'w') as writer:
                for i in range(count):
                    writer.write(line + '\n')

        import argparse
        _parser = argparse.ArgumentParser(prog='Repeat line', description='Repeat the line specified number of times')
        _parser.add_argument("--line", dest="line", type=str, required=True, default=argparse.SUPPRESS)
        _parser.add_argument("--count", dest="count", type=int, required=False, default=argparse.SUPPRESS)
        _parser.add_argument("--output-text", dest="output_text_path", type=_make_parent_dirs_and_return_path, required=True, default=argparse.SUPPRESS)
        _parsed_args = vars(_parser.parse_args())

        _outputs = repeat_line(**_parsed_args)
      image: python:3.7
      volumeMounts:
      - name: workdir
        mountPath: /gotest/outputs/output_text/
    volumes:
      - name: workdir
        persistentVolumeClaim:
          claimName: kubeflow-test-pv
    metadata:
      annotations: 
  - name: print-text
    container:
      args: [--text, /gotest/outputs/output_text/data]
      command:
      - sh
      - -ec
      - |
        program_path=$(mktemp)
        printf "%s" "$0" > "$program_path"
        python3 -u "$program_path" "$@"
      - |
        def print_text(text_path): # The "text" input is untyped so that any data can be printed
            '''Print text'''
            with open(text_path, 'r') as reader:
                for line in reader:
                    print(line, end = '')

        import argparse
        _parser = argparse.ArgumentParser(prog='Print text', description='Print text')
        _parser.add_argument("--text", dest="text_path", type=str, required=True, default=argparse.SUPPRESS)
        _parsed_args = vars(_parser.parse_args())

        _outputs = print_text(**_parsed_args)
      image: python:3.7
      volumeMounts:
      - name: workdir
        mountPath: /gotest/outputs/output_text/
    volumes:
      - name: workdir
        persistentVolumeClaim:
          claimName: kubeflow-test-pv
    metadata:
      annotations: 

apiVersion: v1
kind: PersistentVolumeClaim
metadata:
  name: kubeflow-test-pv
  namespace: kubeflow-user-example-com
spec:
  accessModes:
    - ReadWriteOnce
  resources:
    requests:
      storage: 128Mi