ml_experiment_demo.dig

timezone: Asia/Tokyo
#timezone: PST

_export:
  !include : config/params.yaml
  td:
    engine: presto
    database: ${output_database}

+create_db_tbl_if_not_exists:
  td_ddl>:
  create_databases: ["${output_database}"]
  create_tables: ["${expr_tracking_table}"]

+load_datasets:
  ipynb>:
    notebook: ml_datasets
    output_database: ${input_database}
    input_table: ${input_database}.dummy
#   datasets: gluon, bank_marketing
    datasets: gluon

+gluon_train:
  ml_train>:
    notebook: gluon_train
    model_name: gluon_model_${session_id}
    input_table: ${input_database}.gluon_train # expect database_name.table_name
    target_column: class
    # The following options are optional ones
    #problem_type: binary                # ‘binary’, ‘multiclass’, ‘regression’, or ‘quantile’. autolugon automatically detect problem types
    #eval_metric: roc_auc                # autolugon automatically select a right eval_metric for a given setting if not specified.
    ignore_columns: time,rowid           # Note time column is ignored by the default.
    time_limit: 60 * 3                   # fit timeout. 3 min just for training time. Default: 60 * 60 (1hr). 1hr or more is recommended for production purposes (Note 24 hours at max). Note this is a soft limit, not hard limit.
    # timeout: 60 * 3                    # timeout for notebook cell-level execution. This is a hard limit. Note it's cell-level timeout. No timeout if not specified.
    export_leaderboard: ${output_database}.leaderboard_gluon_train
    export_feature_importance: ${output_database}.feature_importance_gluon_train
    # hide_table_contents: true

+print_train_result:
  echo>: "executed ${automl.last_executed_notebook}.ipynb"

+track_experiment:
  td>: queries/track_experiment.sql
  insert_into: automl_experiments
  last_executed_notebook: ${automl.last_executed_notebook}
  user_id: ${automl.last_executed_user_id}
  user_email: ${automl.last_executed_user_email}
  model_name: gluon_model_${session_id}
  task_attempt_id: ${attempt_id}
  session_time: ${session_local_time}
  engine: presto

+gluon_predict:
  ml_predict>:
    notebook: gluon_predict
    model_name: gluon_model_${session_id}
    input_table: ${input_database}.gluon_test # expect database_name.table_name
    output_table: ${output_database}.gluon_predicted  # expect database_name.table_name. DB will be created if not exists. table is overwrite'd.
    # optional
    #rowid_column: rowid                # Note when rowid_column is specified, only rowid column + prediction result columns are resulted in the output table
    #ignore_columns: time               # target column should not be in test data
    export_leaderboard: ${output_database}.leaderboard_gluon_predict
    export_feature_importance: ${output_database}.feature_importance_gluon_predict
    # hide_table_contents: true

+print_predict_result:
  echo>: "executed ${automl.last_executed_notebook}.ipynb"