cli-responsibleaidashboard-programmer-regression.yml

$schema: https://azuremlschemas.azureedge.net/latest/pipelineJob.schema.json
experiment_name: programmers_dataset_analyze
type: pipeline

inputs:
  target_column_name: 'score'
  my_training_data:
    type: mltable
    path: ./data-programmer-regression/train
  my_test_data:
    type: mltable
    path: ./data-programmer-regression/test

outputs: 
  programmers_model:
    type: mlflow_model
    mode: rw_mount

compute: azureml:cpu-cluster

jobs:
  train_model:
    type: command
    component: file:./train_programmers.yml
    inputs:
      training_data: ${{parent.inputs.my_training_data}}
      target_column_name: ${{parent.inputs.target_column_name}}
      categorical_features: '["location", "style", "job title", "OS", "Employer", "IDE", "Programming language"]'
      continuous_features: '["YOE", "Number of github repos contributed to", "age"]'
      model_name: 'programmers_model'
    outputs:
      model_output: ${{parent.outputs.programmers_model}}

  create_rai_job:
    type: command
    component: azureml://registries/azureml/components/microsoft_azureml_rai_tabular_insight_constructor/versions/0.15.0
    limits:
      timeout: 3600
    inputs:
      title: Programmers Analysis
      task_type: regression
      model_info_path: ${{parent.jobs.train_model.outputs.model_output_json}}
      train_dataset: ${{parent.inputs.my_training_data}}
      test_dataset: ${{parent.inputs.my_test_data}}
      target_column_name: ${{parent.inputs.target_column_name}}
      categorical_column_names: '["location", "style", "job title", "OS", "Employer", "IDE", "Programming language"]'

  explain_01:
    type: command
    component: azureml://registries/azureml/components/microsoft_azureml_rai_tabular_explanation/versions/0.15.0
    limits:
      timeout: 7200
    inputs:
      comment: Some random string
      rai_insights_dashboard: ${{parent.jobs.create_rai_job.outputs.rai_insights_dashboard}}

  causal_01:
    type: command
    component: azureml://registries/azureml/components/microsoft_azureml_rai_tabular_causal/versions/0.15.0
    limits:
      timeout: 7200
    inputs:
      rai_insights_dashboard: ${{parent.jobs.create_rai_job.outputs.rai_insights_dashboard}}
      treatment_features: '["Number of github repos contributed to", "YOE"]'
      heterogeneity_features: '[]'
      nuisance_model: linear
      skip_cat_limit_checks: True

  counterfactual_01:
    type: command
    component: azureml://registries/azureml/components/microsoft_azureml_rai_tabular_counterfactual/versions/0.15.0
    limits:
      timeout: 7200
    inputs:
      rai_insights_dashboard: ${{parent.jobs.create_rai_job.outputs.rai_insights_dashboard}}
      total_CFs: 10
      desired_range: '[5, 10]'
      feature_importance: True

  error_analysis_01:
    limits:
      timeout: 7200
    type: command
    component: azureml://registries/azureml/components/microsoft_azureml_rai_tabular_erroranalysis/versions/0.15.0
    inputs:
      rai_insights_dashboard: ${{parent.jobs.create_rai_job.outputs.rai_insights_dashboard}}
      max_depth: 3
      filter_features: '["style", "Employer"]'

  gather_01:
    type: command
    component: azureml://registries/azureml/components/microsoft_azureml_rai_tabular_insight_gather/versions/0.15.0
    limits:
      timeout: 7200
    inputs:
      constructor: ${{parent.jobs.create_rai_job.outputs.rai_insights_dashboard}}
      insight_1: ${{parent.jobs.causal_01.outputs.causal}}
      insight_2: ${{parent.jobs.counterfactual_01.outputs.counterfactual}}
      insight_3: ${{parent.jobs.error_analysis_01.outputs.error_analysis}}
      insight_4: ${{parent.jobs.explain_01.outputs.explanation}}

  scorecard_01:
    type: command
    component: azureml://registries/azureml/components/microsoft_azureml_rai_tabular_score_card/versions/0.15.0
    inputs:
      dashboard: ${{parent.jobs.gather_01.outputs.dashboard}}
      pdf_generation_config:
        type: uri_file
        path: ./programmers_analyze_scorecard_config/pdf_gen.json
        mode: download