Skip to main content

A flexible SDK for interacting with various models

Project description

A flexible SDK for interacting with various model types including BERT, Inkman, and BiasTPV.

Installation pip install modelsdk

Features Unified interface for different model types Easily extensible to support new models

Usage Basic Usage from modelsdk import ModelSDK

Create an Inkman model instance

inkman = ModelSDK("inkman")

Get model run id

run_id = inkman.get_run_id()

Get features

features = inkman.get_features()

Get factors

factors = inkman.get_factors()

Get model users data (requires a pid)

pid = datetime.now().strftime("%Y%m%dT%H%M%S") source_data = inkman.get_users_df(pid=pid)

Available Models

  • inkman

Environment Variables The SDK uses these environment variables: GOOGLE_CLOUD_PROJECT MLFLOW_TRACKING_URI MLFLOW_TRACKING_USERNAME MLFLOW_TRACKING_PASSWORD

License

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

modelsdk-0.0.1.tar.gz (1.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

modelsdk-0.0.1-py3-none-any.whl (1.6 kB view details)

Uploaded Python 3

File details

Details for the file modelsdk-0.0.1.tar.gz.

File metadata

  • Download URL: modelsdk-0.0.1.tar.gz
  • Upload date:
  • Size: 1.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.8.19

File hashes

Hashes for modelsdk-0.0.1.tar.gz
Algorithm Hash digest
SHA256 6283a69a12d1363af423c69ebab4f7bda485248849cb562195d6dd39bd2b8403
MD5 f148026fcb8a2a6233a768a93ad74762
BLAKE2b-256 b1d377897d610a1cb6e7daef79f811af8e275f94ea338568fc141bf81ff58fac

See more details on using hashes here.

File details

Details for the file modelsdk-0.0.1-py3-none-any.whl.

File metadata

  • Download URL: modelsdk-0.0.1-py3-none-any.whl
  • Upload date:
  • Size: 1.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.8.19

File hashes

Hashes for modelsdk-0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 4224d7b87a743914dcf674337941b4819f29dfdfba1cee4a8497bd833d51a5b8
MD5 ae484da6904c8935984957a12b39ae48
BLAKE2b-256 aa3d93fd937ad43bffea073a50f98aad62faed1b544767de0e53c9cae4a240c9

See more details on using hashes here.

Supported by

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