h2o-mlops-scoring-client 0.0.5b1

A Python client library to simplify robust mini-batch scoring against an H2O MLOps scoring endpoint.

H2O MLOps Scoring Client

A Python client library to simplify robust mini-batch scoring against an H2O MLOps scoring endpoint. It can run on your local PC, a stand alone server, Databricks, or a Spark 3 cluster.

Using it is as easy as:

import h2o_mlops_scoring_client

h2o_mlops_scoring_client.score_source_sink(
    mlops_endpoint_url="https://.../model/score",
    id_column="ID",
    source_data="file:///.../input.csv",
    source_format=h2o_mlops_scoring_client.Format.CSV,
    sink_location="file:///.../output/",
    sink_format=h2o_mlops_scoring_client.Format.PARQUET,
    sink_write_mode=h2o_mlops_scoring_client.WriteMode.OVERWRITE
)

Or if you want to work with Pandas DataFrames:

scores_df = h2o_mlops_scoring_client.score_data_frame(
    mlops_endpoint_url="https://.../model/score",
    id_column="ID",
    data_frame=input_df,
)

Installation

Requirements

• Linux or Mac OS (Windows is not supported)
• Java
• Python 3.8 or greater

Install from PyPI

pip install h2o_mlops_scoring_client

FAQ

When should I use the MLOps Scoring Client?

Use when batch scoring processing (authenticating and connecting to source or sink, file/data processing or conversions, etc.) can happen external to H2O AI Cloud but you want to stay within the H2O MLOps workflow (projects, scoring, registry, monitoring, etc.).

What file types are supported?

The MLOps scoring client can read and write CSV, Parquet, ORC, BigQuery Tables, JDBC Tables, and JDBC queries. If there's a file type you would like to see supported, please let us know.

Is a Spark installation required?

No. If you're running locally and scoring local files or data frames, then no extra Spark install or configuration is needed. If you want to connect to an external source or sink, you'll need to do a small amount of configuration.