Implementation:Sdv dev SDV BaseMultiTableSynthesizer Fit

Knowledge Sources	SDV SDV Documentation
Domains	Machine_Learning, Synthetic_Data
Last Updated	2026-02-14 00:00 GMT

Overview

Concrete tool for fitting a multi-table synthesizer on relational data, provided by the SDV library.

Description

The BaseMultiTableSynthesizer.fit method is the training entry point for multi-table synthesizers. It validates input data, preprocesses each table, then calls fit_processed_data which triggers table augmentation and per-table model fitting.

Usage

Call this method on an HMASynthesizer with a dictionary of DataFrames.

Code Reference

Source Location

• Repository: SDV
• File: sdv/multi_table/base.py
• Lines: L641-677

Signature

def fit(self, data):
    """Fit this model to the original data.

    Args:
        data (dict):
            Dictionary mapping each table name to a pandas.DataFrame.
    """

Import

from sdv.multi_table import HMASynthesizer
# fit is called as: synthesizer.fit(data)

I/O Contract

Inputs

Name	Type	Required	Description
data	dict[str, pd.DataFrame]	Yes	Dictionary mapping table names to DataFrames

Outputs

Name	Type	Description
(mutates self)	None	Sets self._fitted = True; augments and fits per-table models

Usage Examples

from sdv.datasets.demo import download_demo
from sdv.multi_table import HMASynthesizer

data, metadata = download_demo(modality='multi_table', dataset_name='fake_hotels')
synthesizer = HMASynthesizer(metadata)
synthesizer.fit(data)

Related Pages

Implements Principle

• Principle:Sdv_dev_SDV_Multi_Table_Model_Fitting

Requires Environment

• Environment:Sdv_dev_SDV_Python_Runtime