search
githubEdit

H2O Java MoJo

  • Wrap a H2O model for use as a prediction microservice in seldon-core

    • Run locally on Docker to test

    • Deploy on seldon-core running on minikube

hashtag
Dependencies

pip install seldon-core
pip install sklearn

hashtag
Train locally

!mkdir -p experiment
import h2o

h2o.init()
from h2o.estimators.glm import H2OGeneralizedLinearEstimator

path = (
    "https://s3.amazonaws.com/h2o-public-test-data/smalldata/prostate/prostate.csv.zip"
)
h2o_df = h2o.import_file(path)
h2o_df["CAPSULE"] = h2o_df["CAPSULE"].asfactor()
model = H2OGeneralizedLinearEstimator(family="binomial")
model.train(y="CAPSULE", x=["AGE", "RACE", "PSA", "GLEASON"], training_frame=h2o_df)
modelfile = model.download_mojo(path="./experiment/", get_genmodel_jar=False)
print("Model saved to " + modelfile)
H2O cluster uptime:
01 secs

H2O cluster timezone:

Europe/London

H2O data parsing timezone:

UTC

H2O cluster version:

3.28.0.1

H2O cluster version age:

21 days, 15 hours and 52 minutes

H2O cluster name:

H2O_from_python_agm_ususoe

H2O cluster total nodes:

1

H2O cluster free memory:

6.896 Gb

H2O cluster total cores:

8

H2O cluster allowed cores:

8

H2O cluster status:

accepting new members, healthy

H2O connection url:

http://127.0.0.1:54321

H2O connection proxy:

{'http': None, 'https': None}

H2O internal security:

False

H2O API Extensions:

Amazon S3, XGBoost, Algos, AutoML, Core V3, TargetEncoder, Core V4

Python version:

3.6.9 final

Wrap model using s2i

Send some random features that conform to the contract

hashtag
Test using Minikube

Due to a minikube/s2i issuearrow-up-right you will need s2i >= 1.1.13arrow-up-right

hashtag
Setup Seldon Core

Use the notebook to Setup Cluster with Ambassador Ingress and Install Seldon Core. Instructions also online.

hashtag
Build model image and run predictions

Wait until ready (replicas == replicasAvailable)

PreviousKubeflow Seldon E2E PipelineNextOutlier Detection with Combiner

Last updated

Was this helpful?