Metadata-Version: 2.0
Name: ServeIt
Version: 0.0.1.dev2
Summary: Machine learning prediction serving
Home-page: https://github.com/rtlee9/serveit
Author: Ryan Lee
Author-email: ryantlee9@gmail.com
License: UNKNOWN
Description-Content-Type: UNKNOWN
Keywords: machine learning model deployment serving API RESTful
Platform: UNKNOWN
Classifier: Development Status :: 2 - Pre-Alpha
Classifier: Intended Audience :: Developers
Classifier: Topic :: Software Development :: Build Tools
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Internet :: WWW/HTTP :: WSGI :: Server
Classifier: License :: OSI Approved :: MIT License
Classifier: Programming Language :: Python :: 2.7
Classifier: Programming Language :: Python :: 3.6
Requires-Dist: flask
Requires-Dist: flask-restful
Provides-Extra: dev
Requires-Dist: check-manifest; extra == 'dev'
Provides-Extra: test
Requires-Dist: coverage; extra == 'test'

ServeIt
=======

ServeIt deploys your trained models to a RESTful API for prediction
serving. Current features include:

1. Model prediction serving
2. Model info endpoint creation
3. Logging

Supported libraries
-------------------

-  Scikit-Learn

.. code:: python

    from sklearn.datasets import load_iris
    from sklearn.linear_model import LogisticRegression
    from serveit.sklearn_server import SklearnServer

    # fit a model on the Iris dataset
    data = load_iris()
    reg = LogisticRegression()
    reg.fit(data.data, data.target)

    # deploy model to a SkLearnServer
    eds = SklearnServer(reg, reg.predict)

    # add informational endpoints
    eds.create_model_info_endpoint()
    eds.create_info_endpoint('features', data.feature_names)
    eds.create_info_endpoint('target_labels', data.target_names.tolist())

    # start API
    eds.serve()

Limited functionality
---------------------

-  TensorFlow
-  Keras
-  PyTorch


