A Python package to monitor the drift in the machine learning models leveraging Snowflake ML Capabilities
Project description
Drift Package
Overview
The RefractMLMonitor Package is designed to monitor and detect data drift in machine learning models. It helps in identifying changes in the input data distribution over time, which can affect the performance of the model.
Features
- Feature Drift Detection: Detects changes in the input feature's data distribution.
- Label Drift Detection: Identifies changes in the distribution of the labels.
- Prediction Drift Detection: Monitors changes in the distribution of the model predictions.
- Performance Drift Detection: Tracks changes in the performance metrics of the model.
- Alert Generation: Generates alerts when significant drift is detected.
- Report Generation: Provides detailed reports on the detected drift.
- Integration with Snowflake: Stores drift data and alerts in Snowflake tables.
Installation
To install the Drift Package, use the following command:
pip install RefractMLMonitor
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
RefractMLMonitor-1.2.2.tar.gz
(34.5 kB
view hashes)
Built Distribution
Close
Hashes for RefractMLMonitor-1.2.2-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | d9672339e5fcc412a65455e148027f3eb54e34dfcc0d5d21886069c79323c706 |
|
MD5 | 7165661ae42d1b94d11df156afd3872c |
|
BLAKE2b-256 | 9eead06ddbd1a39c89dee94df064af9ad7f284dea56f57c8c46c6e732dd3ccd4 |