housing_metadata.yaml

global:                                 # In this section you can specify training and inference settings which will be set for all tables
  train_settings:
    epochs: 2
    drop_null: true
    row_limit: 1800
    print_report: true

  infer_settings:
    size: 100
    run_parallel: false
    random_seed: 10
    print_report: true

housing_properties:                       # Use table name here
  train_settings:                         # Settings for training process
    source: "./examples/example-data/housing_properties.csv" # The path to the original data. Supported formats include local files in CSV, Avro formats. Required parameter
    epochs: 8                             # Number of epochs
    drop_null: true                       # Drop rows with NULL values
    row_limit: 1800                       # Limit of rows for training process
    print_report: true                    # Turn on or turn off generation of the report

  infer_settings:                         # Settings for infer process
    destination: "./examples/generated-data/housing_properties_generated.csv" # The path where the generated data will be stored. Supported formats include local files in CSV, Avro formats. Required parameter
    size: 90                              # Size for generated data
    run_parallel: false                   # Turn on or turn off parallel training process
    random_seed: 10                       # Ensure reproducible tables generation
    print_report: true                    # Turn on or turn off generation of the report

  keys:                                   # Keys of the table
    households_pk:                        # Name of a key
      type: "PK"                          # Type of key
      columns:                            # Columns related to key
        - households

housing_conditions:
  train_settings:
    source: "./examples/example-data/housing_conditions.csv"
    epochs: 5
    drop_null: true
    row_limit: 1800
    print_report: true
    column_types:
      categorical:                        # Force listed columns to have categorical type (use dictionary of values)
        - housing_median_age

  infer_settings:
    destination: "./examples/generated-data/housing_conditions_generated.csv"
    size: 90
    run_parallel: false
    random_seed: 10
    print_report: true

  keys:
    households_fk:
      type: "FK"
      columns:
        - households
      references:
        table: housing_properties
        columns:
          - households