Skip to main content

A ML model training automation tool

Project description

ML Workflow Automation Tool

The main goal is to simplify the machine learning workflow for users with different levels of expertise, through a CLI app. We ask the user for certain inputs like the dataset file or folder, and the type of ML problem and target variable (if necessary). We then perform standard data preprocessing (not dataset specific) and feature selection (if necessary), and train relevant models for the data and present a comparative analysis of the models trained, along with downloadable model weight files in the joblib format.

built with Python3 PyPI version

Key Features

  • Compare various machine learning algorithms
  • Performance comparison
  • Model training result comparison through CLI
  • All model files stored as a zip of joblib files

Preview

curdrice

Deployment

Find out which ML model suits your needs by installing our package from pypi

pip install curdrice

Usage

Use the following command for help -

curdrice --help

Template code

curdrice -p <db_path> -d <zip_name> <type> <target>

Acknowledgements

Authors

@hrishitb - @pranayobla - @shriharik - @ankitthomas

Project details


Release history Release notifications | RSS feed

This version

0.1

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

curdrice_v2-0.1.tar.gz (8.7 kB view details)

Uploaded Source

Built Distribution

curdrice_v2-0.1-py3-none-any.whl (9.1 kB view details)

Uploaded Python 3

File details

Details for the file curdrice_v2-0.1.tar.gz.

File metadata

  • Download URL: curdrice_v2-0.1.tar.gz
  • Upload date:
  • Size: 8.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.4

File hashes

Hashes for curdrice_v2-0.1.tar.gz
Algorithm Hash digest
SHA256 9354b032b37c473bdc8301107f20d825ff59df252788b70c5504db6164c12058
MD5 fed91b8597f3bd432f13ef8adccb8747
BLAKE2b-256 4d4b0e60b25506ef92b1b84d657f4fbdbca1bd089efc7a7ed0d18385074fb023

See more details on using hashes here.

File details

Details for the file curdrice_v2-0.1-py3-none-any.whl.

File metadata

  • Download URL: curdrice_v2-0.1-py3-none-any.whl
  • Upload date:
  • Size: 9.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.12.4

File hashes

Hashes for curdrice_v2-0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 bf4ccfa91d9dffc31a426bae15ec5e9352dda15d5e7a5997186e8b16e79fcfb9
MD5 1304dab4a816bd9fc97536061df2e609
BLAKE2b-256 408a60404011de15c65d087d752c56f86317979fccb3dfebf3b7afe5190bf2c5

See more details on using hashes here.

Supported by

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