Skip to main content

Scikit-Learn runtime for KozmoServer

Project description

Scikit-Learn runtime for KozmoServer

This package provides a KozmoServer runtime compatible with Scikit-Learn.

Usage

You can install the runtime, alongside kozmoserver, as:

pip install kozmoserver kozmoserver-sklearn

For further information on how to use KozmoServer with Scikit-Learn, you can check out this worked out example.

Content Types

If no content type is present on the request or metadata, the Scikit-Learn runtime will try to decode the payload as a NumPy Array. To avoid this, either send a different content type explicitly, or define the correct one as part of your model's metadata.

Model Outputs

The Scikit-Learn inference runtime exposes a number of outputs depending on the model type. These outputs match to the predict, predict_proba and transform methods of the Scikit-Learn model.

Output Returned By Default Availability
predict Available on most models, but not in Scikit-Learn pipelines.
predict_proba Only available on non-regressor models.
transform Only available on Scikit-Learn pipelines.

By default, the runtime will only return the output of predict. However, you are able to control which outputs you want back through the outputs field of your {class}InferenceRequest <kozmoserver.types.InferenceRequest> payload.

For example, to only return the model's predict_proba output, you could define a payload such as:

---
emphasize-lines: 10-12
---
{
  "inputs": [
    {
      "name": "my-input",
      "datatype": "INT32",
      "shape": [2, 2],
      "data": [1, 2, 3, 4]
    }
  ],
  "outputs": [
    { "name": "predict_proba" }
  ]
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

kozmoserver_sklearn-0.1.0.dev1.tar.gz (7.1 kB view hashes)

Uploaded Source

Built Distribution

kozmoserver_sklearn-0.1.0.dev1-py3-none-any.whl (8.1 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page