Implementation:Sdv dev SDV BaseSynthesizer Save Load
Appearance
| Knowledge Sources | |
|---|---|
| Domains | Serialization, Synthetic_Data |
| Last Updated | 2026-02-14 00:00 GMT |
Overview
Concrete tools for saving and loading fitted single-table synthesizers to/from disk, provided by the SDV library.
Description
BaseSynthesizer.save serializes the entire synthesizer to a file using cloudpickle. BaseSynthesizer.load deserializes from a file, validates the synthesizer type, checks version compatibility, and returns the restored instance.
Usage
Call save on a fitted synthesizer to persist it. Call load as a class method to restore.
Code Reference
Source Location
- Repository: SDV
- File: sdv/single_table/base.py
- Lines: L712-775
Signature
def save(self, filepath):
"""Save this model instance to the given path using cloudpickle.
Args:
filepath (str): Path where the synthesizer will be serialized.
"""
@classmethod
def load(cls, filepath):
"""Load a single-table synthesizer from a given path.
Args:
filepath (str): Filepath of saved synthesizer.
Returns:
SingleTableSynthesizer: The loaded synthesizer.
"""
Import
from sdv.single_table import GaussianCopulaSynthesizer
# save: synthesizer.save('model.pkl')
# load: synthesizer = GaussianCopulaSynthesizer.load('model.pkl')
I/O Contract
Inputs (save)
| Name | Type | Required | Description |
|---|---|---|---|
| filepath | str | Yes | Path for serialized file |
Inputs (load)
| Name | Type | Required | Description |
|---|---|---|---|
| filepath | str | Yes | Path to saved synthesizer file |
Outputs
| Name | Type | Description |
|---|---|---|
| save returns | None | Writes .pkl file to filepath |
| load returns | BaseSynthesizer | Restored synthesizer instance |
Usage Examples
# Save after fitting
synthesizer.save('my_synthesizer.pkl')
# Load later
from sdv.single_table import GaussianCopulaSynthesizer
loaded = GaussianCopulaSynthesizer.load('my_synthesizer.pkl')
new_data = loaded.sample(num_rows=100)
Related Pages
Implements Principle
Requires Environment
Uses Heuristic
Page Connections
Double-click a node to navigate. Hold to expand connections.
Principle
Implementation
Heuristic
Environment