＊ DayZSynthesizer

＊SDV Enterprise Feature. This feature is only available for licensed, enterprise users. For more information, visit our page to Compare SDV Features.

The Day Z Synthesizer produces synthetic data from scratch using the metadata. This allows you start generating synthetic data from day zero: no machine learning required!

from sdv.multi_table import DayZSynthesizer

synthesizer = DayZSynthesizer(metadata)
synthetic_data = synthesizer.sample(num_rows=1000)

Estimate parameters

For more realistic data, we recommend estimating some basic DayZ parameters using the real data. This includes information such as the min/max range of numerical columns and the possible category values in categorical columns.

SDV Community users can complete this step. You may be asked share the DayZ parameters file to the SDV team for help in performance testing or debugging.

Create Parameters

Use the create_parameters function to estimate the parameters and save them as a JSON file.

from sdv.multi_table import DayZSynthesizer

my_parameters = DayZSynthesizer.create_parameters(
  data=my_data,
  metadata=my_metadata,
  output_filename='dayz_parameters.json'
)

Parameters:

• (required) data: A dictionary mapping each table name to a pandas DataFrame containing the real data that the machine learning model will learn from

• (required) metadata: A SDV Metadata object that describes the data

• output_filepath: A string with the name of the file in which to save the parameters. This should end in a .json suffix.

Returns: A Python dictionary representation of the parameters (that are also saved in the JSON).

Validate Parameters

Use the validate_parameters to validate that the parameters accurately reflect the metadata. This is important if you've modified any of the parameters in the file.

DayZSynthesizer.validate_parameters(
    metadata=my_metadata,
    parameters=my_parameters
)

Parameters:

• (required) metadata: An SDV Metadata object that describes the data

• (required) parameters: The parameters dictionary

Returns: (None) If there are any issues with the parameters, you'll see an error.

Creating a synthesizer

When creating your synthesizer, you are required to pass in a Metadata object as the first argument. We also recommend setting the parameters at this time.

synthesizer = DayZSynthesizer(
    metadata,
    parameters=my_parameters,
    locales=['en_US', 'en_CA', 'fr_CA']
)

Parameter Reference

locales: A list of locale strings. Any PII columns will correspond to the locales that you provide.

(default) ['en_US']	Generate PII values in English corresponding to US-based concepts (eg. addresses, phone numbers, etc.)
<list>	Create data from the list of locales. Each locale string consists of a 2-character code for the language and 2-character code for the country, separated by an underscore. For example ["en_US", "fr_CA"]. For all options, see the Faker docs.

parameters: A dictionary of DayZ parameters. Use this to set all the parameters that DayZ needs to create realistic data. Use the create_parameters function described above and instantiate your DayZ synthesizer with it.

from sdv.single_table import DayZSynthesizer

my_parameters = DayZSynthesizer.create_parameters(
  data=my_data,
  metadata=my_metadata,
  output_filename='dayz_parameters.json'
)

synthesizer = DayZSynthesizer(
    metadata,
    parameters=my_parameters,
    locales=['en_US', 'en_CA', 'fr_CA']
)

Programmatic Parameters API

We recommend setting the parameters all at once. However, we also offer a programmatic, Python API to set the parameters one column at a time. Expand the sections below to learn more.

set_numerical_bounds

Use this method to set lower and upper bounds for numerical columns

Parameters

• (required) table_name: A string with the name of the table

• (required) column_name: A string with the name of the column. This must be a numerical column referenced in your metadata.

• (required) min_value: A float or int representing the minimum value.

• (required) max_value: A float or int representing the max value

Output (None) The sampled synthetic data will follow the min and max bounds

synthesizer.set_numerical_bounds(
    table_name='guests',
    column_name='room_rate',
    min_value=30.00,
    max_value=5000.00
)

set_rounding_scheme

Use this method to set the rounding scheme (# of decimal digits) for a numerical column.

Parameters:

• (required) table_name: A string with the name of the table

• (required) column_name: A string with the name of the column. This must be a numerical column referenced in your metadata.

• (required) num_decimal_digits: An integer that is >= 0, that specifies how to round the generated values

  • 0 means that the generated values should be whole numbers

  • Any higher number describes the # of digits to round. So 2 would mean rounding to 2 decimal digits (eg. 12.23)

set_datetime_bounds

Use this method to set lower and upper bounds for datetime columns

Parameters

• (required) table_name: A string with the name of the table

• (required) column_name: A string with the name of the column. This must be a datetime column referenced in your metadata.

• (required) start_timestamp: A string representing the earliest allowed datetime. The string must be in the same datetime format as referenced in your metadata.

• (required) end_timestamp: A string representing the latest allowed datetime. The string must be in the same datetime format as referenced in your metadata.

Output (None) The sampled synthetic data will follow start and end bounds

synthesizer.set_datetime_bounds(
    table_name='guests',
    column_name='checkin_date',
    start_timestamp='01 Jan 2020',
    end_timestamp='31 Dec 2020'
)

set_category_values

Use this method to set the different values that are possible for categorical columns.

Parameters

• (required) table_name: A string with the name of the table

• (required) column_name: A string with the name of the column. This must be a categorical column referenced in your metadata.

• (required) category_values: A list of strings representing the different unique category values that are possible. (If missing values are allowed, use the set_missing_values method instead of listing it here.)

Output (None) The sampled synthetic data will include the category values

synthesizer.set_category_values(
    table_name='guests',
    column_name='room_type',
    category_values=['BASIC', 'DELUXE', 'SUITE']
)

set_missing_values

Use this method to set the proportion of missing values to generate in a column

Parameters

• (required) table_name: A string representing the name of the table

• (required) column_name: A string representing the name of the column. This column cannot be a primary or foreign key.

• (required) missing_values_proportion: A float representing the proportion of missing values

  • Any float between 0.0 and 1.0: Randomly create this proportion of missing values in the column

synthesizer.set_missing_values(
    table_name='guests',
    column_name='room_type',
    missing_values_proportion=0.1
)

Output (None) Sets the proportion of the missing values

set_cardinality

Use this function to set the cardinality of a parent/child relationship. The cardinality refers to the number of children that each parent row is allowed to have. This can be anywhere from 0 to infinity.

This function can help you create realistic data for many relationship types such as 1-1, 1-to-many, etc.

# each hotel must have 1 or more guests
synthesizer.set_cardinality(
    parent_table_name='hotels',
    child_table_name='guests',
    parent_primary_key='hotel_id',
    child_foreign_key='hotel_id',
    min_cardinality=1,
    max_cardinality=None
)

Parameters

• (required) parent_table_name: The name of the parent table

• (required) child_table_name: The name of the child table

• (required) parent_primary_key: The name of the primary key in the parent

• (required) child_foreign_key: The name of the foreign key in the child that refers to the primary key of the parent

• min_cardinality: The minimum # of children each parent must have, must be an integer >=0

  • (default) 0: A parent row must have 0 or more children

  • <integer>: An integer representing the minimum # of children

• max_cardinality: The maximum # of children each parent must have, must be an integer >0

  • (default) None: Do not enforce a maximum (i.e. the maximum # of children can be infinite)

  • <integer>: An integer > min_cardinality representing the maximum # of children

  • Note that If min cardinality = max cardinality, then that means there is a fixed # of children for each parent.

Output (None) Sets the min and max cardinality of the parent/child relationship, or updates it if the cardinality was already set.

set_table_sizes

Use this function to set the (relative) table sizes of each table in the dataset. When sampling, you can scale the entire dataset up or down.

synthesizer = DayZSynthesizer(metadata)
synthesizer.set_table_sizes(
    num_rows_per_table={
        'hotels': 1000,
        'guests': 2500
    }
)

Parameters:

• (required) num_rows_per_table: A dictionary containing the number of rows to set per table. The keys are the names of the tables, and the values are integers representing the number of rows.

get_parameters

Use this function to access the all parameters your synthesizer uses -- those you have provided as well as the default ones.

Parameters

• output_filepath: A string representing the name of the file to write the parameters to. We recommend storing this as a JSON file. Defaults to None, meaning that no output filepath is written.

Output A dictionary with the table names and parameters for each table.

These parameters are only for the multi-table synthesizer. To get individual table-level parameters, use the get_table_parameters function.

The returned parameters are a copy. Changing them will not affect the synthesizer.

synthesizer.get_parameters()

{
    'locales': ['en_US', 'fr_CA'],
    ...
}

get_table_parameters

Use this function to access the all parameters a table synthesizer uses -- those you have provided as well as the default ones.

Parameters

• (required) table_name: A string describing the name of the table

Output A dictionary with the parameter names and the values

synthesizer.get_table_parameters(table_name='users')

{
    'synthesizer_name': 'DayZSynthesizer',
    'synthesizer_parameters': {
        'columns': {
            ...
        }
    }
}

Saving your synthesizer

Save your synthesizer for future use

save

Use this function to save your synthesizer as a Python pickle file.

Parameters

• (required) filepath: A string describing the filepath where you want to save your synthesizer. Make sure this ends in .pkl

Output (None) The file will be saved at the desired location

synthesizer.save(
    filepath='my_synthesizer.pkl'
)

load (utility function)

Use this utility function to load a trained synthesizer from a Python pickle file. After loading your synthesizer, you'll be able to sample synthetic data from it.

Parameters

• (required) filepath: A string describing the filepath of your saved synthesizer

Output Your synthesizer object

from sdv.utils import load_synthesizer

synthesizer = load_synthesizer(
    filepath='my_synthesizer.pkl'
)

This utility function works for any SDV synthesizer.

What's next?

After training your synthesizer, you can now sample synthetic data. See the Sampling section for more details. (This synthesizer does not yet offer support for conditional sampling.)

synthetic_data = synthesizer.sample(scale=1.0)

Want to improve your synthesizer? Input logical rules in the form of constraints. This synthesizer offers limited support for constraints (constraints within a single table only).

For more details, see Customizations.