diabetes_regression-variables-template.yml

# Pipeline template that defines common runtime environment variables.
variables:
  # Source Config
  # The directory containing the scripts for training, evaluating, and registering the model
  - name: SOURCES_DIR_TRAIN
    value: .
    # The path to the model training script under SOURCES_DIR_TRAIN
  - name: TRAIN_SCRIPT_PATH
    value: diabetes_regression/training/train_aml.py
    # The path to the model evaluation script under SOURCES_DIR_TRAIN
  - name: EVALUATE_SCRIPT_PATH
    value: diabetes_regression/evaluate/evaluate_model.py
    # The path to the model registration script under SOURCES_DIR_TRAIN
  - name: REGISTER_SCRIPT_PATH
    value: diabetes_regression/register/register_model.py
    # The path to the model scoring script relative to SOURCES_DIR_TRAIN
  - name: SCORE_SCRIPT
    value: diabetes_regression/scoring/score.py
    

  # Azure ML Variables
  - name: EXPERIMENT_NAME
    value: mlopspython
  - name: DATASET_NAME
    value: diabetes_ds
  # Uncomment DATASTORE_NAME if you have configured non default datastore to point to your data
  # - name: DATASTORE_NAME
  #   value: datablobstore
  - name: DATASET_VERSION
    value: latest
  - name: TRAINING_PIPELINE_NAME
    value: "diabetes-Training-Pipeline"
  - name: MODEL_NAME
    value: diabetes_regression_model.pkl

  # AML Compute Cluster Config
  - name: AML_ENV_NAME
    value: diabetes_regression_training_env
  - name: AML_ENV_TRAIN_CONDA_DEP_FILE
    value: "conda_dependencies.yml"
  - name: AML_COMPUTE_CLUSTER_CPU_SKU
    value: STANDARD_DS2_V2
  - name: AML_COMPUTE_CLUSTER_NAME
    value: train-cluster
  - name: AML_CLUSTER_MIN_NODES
    value: 0
  - name: AML_CLUSTER_MAX_NODES
    value: 4
  - name: AML_CLUSTER_PRIORITY
    value: lowpriority

  # The name for the (docker/webapp) scoring image
  - name: IMAGE_NAME
    value: "diabetestrained"

    # Optional. Used by a training pipeline with R on Databricks
  - name: DB_CLUSTER_ID
    value: ""

  # These are the default values set in ml_service\util\env_variables.py. Uncomment and override if desired.
  # Set to false to disable the evaluation step in the ML pipeline and register the newly trained model unconditionally.
  # - name: RUN_EVALUATION
  #   value: "true"
  # Set to false to register the model regardless of the outcome of the evaluation step in the ML pipeline.
  # - name: ALLOW_RUN_CANCEL
  #   value: "true"

  # Flag to allow rebuilding the AML Environment after it was built for the first time. This enables dependency updates from conda_dependencies.yaml.
#  - name: AML_REBUILD_ENVIRONMENT
#    value: "true"

  # Variables below are used for controlling various aspects of batch scoring
  - name: USE_GPU_FOR_SCORING
    value: False
  # Conda dependencies for the batch scoring step
  - name: AML_ENV_SCORE_CONDA_DEP_FILE
    value: "conda_dependencies_scoring.yml"
  # Conda dependencies for the score copying step
  - name: AML_ENV_SCORECOPY_CONDA_DEP_FILE
    value: "conda_dependencies_scorecopy.yml"
    # AML Compute Cluster Config for parallel batch scoring
  - name: AML_ENV_NAME_SCORING
    value: diabetes_regression_scoring_env
  - name: AML_ENV_NAME_SCORE_COPY
    value: diabetes_regression_score_copy_env
  - name: AML_COMPUTE_CLUSTER_CPU_SKU_SCORING
    value: STANDARD_DS2_V2
  - name: AML_COMPUTE_CLUSTER_NAME_SCORING
    value: score-cluster
  - name: AML_CLUSTER_MIN_NODES_SCORING
    value: 0
  - name: AML_CLUSTER_MAX_NODES_SCORING
    value: 4
  - name: AML_CLUSTER_PRIORITY_SCORING
    value: lowpriority
  # The path to the batch scoring script relative to SOURCES_DIR_TRAIN
  - name: BATCHSCORE_SCRIPT_PATH
    value: diabetes_regression/scoring/parallel_batchscore.py
  - name: BATCHSCORE_COPY_SCRIPT_PATH
    value: diabetes_regression/scoring/parallel_batchscore_copyoutput.py
  # Flag to allow rebuilding the AML Environment after it was built for the first time. 
  # This enables dependency updates from the conda dependencies yaml for scoring activities.
  - name: AML_REBUILD_ENVIRONMENT_SCORING
    value: "true"

  # Datastore config for scoring
  # The storage account name and key are supplied as variables in a variable group 
  # in the Azure Pipelines library for this project. Please refer to repo docs for 
  # more details

  # Blob container where the input data for scoring can be found
  - name: SCORING_DATASTORE_INPUT_CONTAINER
    value: "input"
  # Blobname for the input data - include any applicable path in the string 
  - name: SCORING_DATASTORE_INPUT_FILENAME
    value: "diabetes_scoring_input.csv"
  # Blob container where the output data for scoring can be found
  - name: SCORING_DATASTORE_OUTPUT_CONTAINER
    value: "output"
  # Blobname for the output data - include any applicable path in the string 
  - name: SCORING_DATASTORE_OUTPUT_FILENAME
    value: "diabetes_scoring_output.csv"
  # Dataset name for input data for scoring
  - name: SCORING_DATASET_NAME
    value: "diabetes_scoring_ds"
  # Scoring pipeline name
  - name: SCORING_PIPELINE_NAME
    value: "diabetes-scoring-pipeline"

  #Observability
  - name: APP_INSIGHTS_CONNECTION_STRING
    value: ""