Skip to main content

MonitorAI SDK

The Official Python SDK for Monitoring Machines Lab. MonitorAI is an observabiltiy framework designed for tabular ML to GenAI offering root cause analysis and decision intelligence allowing a linkup between ML and decision making for organizations that rely and use ML for solutions.

Getting started with monitorai sdk for feature drift :

  • Install the package:
pip install monitorai
import pandas as pd
from monitorai import MonitorAI
from monitorai.drift.feature import CategoricalFeatureDrift

client=MonitorAI(api_key="***")

ref_df=pd.DataFrame({
"color":["red","red","blue","blue","red","yellow","yellow","red","blue"],
"social":["twitter","twitter","facebook","facebook","twitter","insta","insta","insta","insta"]})
    
analysis_df=pd.DataFrame({
"color":["red","red","red","blue","blue","yellow"],
"social":["twitter","twitter","facebook","insta","insta","insta"]
})


## create feature drift variable:
feature_drift=CategoricalFeatureDrift(ref_data=ref_df,analysis_data=analysis_df)

## get the bhattacharrya coefficients
bhatta_coeff_social=feature_drift.bhatta_coeff(feature="social")
bhatta_coeff_color=feature_drift.bhatta_coeff(feature="color")

## cauchy schwartz distance:
cauchy_schwartz_social=feature_drift.cauchy_schwartz_dist(feature="social")
cauchy_schwartz_color=feature_drift.cauchy_schwartz_dist(feature="color")

## euclidean distance:
euclid_social=feature_drift.euclidean_dist(feature="social")
euclid_color=feature_drift.euclidean_dist(feature="color")

## hellinger distance:
hellinger_social=feature_drift.hellinger_dist(feature="social")
hellinger_color=feature_drift.hellinger_dist(feature="color")

## jensen-shannon divergence:
js_social=feature_drift.js_divergence(feature="social")
js_color=feature_drift.js_divergence(feature="social")

## kl-divergence:
kl_social=feature_drift.kl_divergence(feature="social")
kl_color=feature_drift.kl_divergence(feature="color")

##psi:
psi_social=feature_drift.psi(feature="social")
psi_color=feature_drift.psi(feature="color")

Citing monitorai

If you use monitorai in your research, please cite it:

@software{monitorai,
  title = {monitorai: A Root Cause and Decision Intelligence Kit For Machine Learning},
  author = {Monitoring Machines Lab},
  year = {2026},
  url = {https://github.com/MasemeneMatlakanaBenny/monitorai},
  doi = {10.5281/zenodo.19646175},
  license = {MIT},
}

Download files

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

Source Distribution

monitor_aii-0.1.48.tar.gz (6.7 kB view details)

Uploaded Source

Built Distribution

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

monitor_aii-0.1.48-py3-none-any.whl (11.6 kB view details)

Uploaded Python 3

File details

Details for the file monitor_aii-0.1.48.tar.gz.

File metadata

  • Download URL: monitor_aii-0.1.48.tar.gz
  • Upload date:
  • Size: 6.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.12.3

File hashes

Hashes for monitor_aii-0.1.48.tar.gz
Algorithm Hash digest
SHA256 df86fa3111c88a38a2ca9af8900d07c308e0e0279a72dc0f315a6e485a80e127
MD5 ed7b221d449cc938866ce956bcb8b17a
BLAKE2b-256 296eff1c393cbc58a7de0bf42bd9aef20f3a8bf985dc59632cf43eb624db61d6

See more details on using hashes here.

File details

Details for the file monitor_aii-0.1.48-py3-none-any.whl.

File metadata

  • Download URL: monitor_aii-0.1.48-py3-none-any.whl
  • Upload date:
  • Size: 11.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/7.0.0 CPython/3.12.3

File hashes

Hashes for monitor_aii-0.1.48-py3-none-any.whl
Algorithm Hash digest
SHA256 610d48966fa6e10e8f7f1f1f77ec1c7f9782a37c821171a82004d0841036e98e
MD5 607e288b6479d51733c3da0b50ae94c9
BLAKE2b-256 76733b5414bd70ce5b9d89dfebd60a46faf8ef63138fc3ad8611855096f0fc62

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 Sentry Error logging StatusPage Status page