https://github.com/hydrospheredata/hydro-serving-python

Python runtime for the Hydrosphere.io project.
https://github.com/hydrospheredata/hydro-serving-python

hydrosphere python python-runtime

Last synced: 28 days ago
JSON representation

Python runtime for the Hydrosphere.io project.

• Host: GitHub
• URL: https://github.com/hydrospheredata/hydro-serving-python
• Owner: Hydrospheredata
• License: apache-2.0
• Created: 2017-12-18T14:25:31.000Z (about 7 years ago)
• Default Branch: master
• Last Pushed: 2022-12-09T05:55:08.000Z (about 2 years ago)
• Last Synced: 2024-04-14T07:52:50.980Z (9 months ago)
• Topics: hydrosphere, python, python-runtime
• Language: Python
• Homepage: http://docs.hydrosphere.io
• Size: 162 KB
• Stars: 3
• Watchers: 11
• Forks: 2
• Open Issues: 2
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# hydro-serving-python

Python runtime for [Hydrosphere Serving](https://github.com/Hydrospheredata/hydro-serving).

Provides a GRPC API for Python scripts.

Supported versions are: python-3.7 python-3.8 

## Build commands

- `make test`

- `make python-${VERSION}` - build docker runtime with python:${VERSION}-alpine base image

- `make clean` - clean repository from temp files

## Usage

This runtime uses `src/func_main.py` script as an entry point.

You may create any arbitrary Python application within,

just keep in mind that the entry point of your script has to be located in

   `src/func_main.py`.

 

Example of a `func_main.py`:

```python

import pandas as pd

from joblib import load

# Load an ML model during runtime initialisation

clf = load('/model/files/classification_model.joblib')

# This function is called on each request

# Input and output must comply with your model's signature 

def predict(**kwargs):

    # kwargs is a dict with Numpy arrays or scalars you've specified in a signature

    x = pd.DataFrame.from_dict({"request": kwargs}).T

    predicted = clf.predict(x)

    return {"income": int(predicted)}

```

or if you wish to work with proto messages:

```python

    return {"income": TensorProto(int_val=[int(predicted)],

                                  dtype=DT_INT32,

                                  tensor_shape=TensorShapeProto())}

```