Metadata-Version: 2.2
Name: waylay-ml-adapter-numpy
Version: 0.0.9
Summary: ML_adapter for numpy.
Author-email: Waylay <info@waylay.io>
Requires-Python: >=3.11
Description-Content-Type: text/markdown
License-File: LICENCE.txt
Requires-Dist: numpy>=1.25.0
Requires-Dist: waylay-ml-adapter-base
Provides-Extra: dev
Requires-Dist: waylay-ml-adapter-devtools; extra == "dev"

# waylay-ml-adapter-numpy

This provides the `ml_adapter.numpy` module as [Waylay ML Adapter](https://docs.waylay.io/#/api/sdk/python?id=ml_adapter) for models that use numpy as data representation.

This `waylay-ml-adapter-numpy` module provides marshalling for (custom) models that use [numpy](https://numpy.org/) as native data representation.

```
pip install waylay-ml-adapter-numpy
```

## Exported classes

This module exports the following classes:

### `ml_adapter.numpy.V1NumpyModelAdapter`

> Adapts a callable with numpy arrays as input and output.

Supports dill, joblib or selfserializing model assets.



### `ml_adapter.numpy.V1NumpyMarshaller`

> Converts v1 payload from and to numpy arrays.


### `ml_adapter.numpy.V1NumpyNoLoadAdapter`

> Adapts a callable with numpy arrays as input and output.

This adapter does not manage the model as a standard asset.
Relies on the `model` or `model_class` constructor arguments
to define the model.
When `model` is not provided, any `model_path` is passed as a constructor
argument to `model_class` if the signature allows it.


