synthpop-example-1.json

{
    "enabled" : false,
    "dataset" : "generator-outputs/odi-nhs-ae/hospital_ae_data_deidentify",
    "synth-method" : "synthpop",
    "parameters": 
    {
        "enabled" : true,
        "num_samples_to_fit": -1,
        "num_samples_to_synthesize": -1,
        "num_datasets_to_synthesize": 5,
        "random_state": 12345,
        "vars_sequence": [1,2,3,4,5,6,7,8],
        "synthesis_methods": ["sample", "sample", "sample", "sample", "sample", "sample", "sample", "sample"],
        "proper": true,
        "tree_minbucket": 1,
        "smoothing": {}
    },
    "privacy_parameters_disclosure_risk":
    {
        "enabled": true,
        "num_samples_intruder": 100,
        "vars_intruder": ["Treatment", "Gender", "Age bracket"]
    },
    "utility_parameters_classifiers":
    {
        "enabled": true,
        "input_columns": ["Time in A&E (mins)"],
        "label_column": "Age bracket",
        "test_train_ratio": 0.2,
        "num_leaked_rows": 0,
        "classifier": {
            "LogisticRegression":  {"mode": "main",
                                    "params_main": {"max_iter": 1000}
                                   }
        }
    },
    "utility_parameters_correlations":
    {
        "enabled": true
    }
}