Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Exploration - Getting Started with Evidently #6

Open
manisnesan opened this issue Aug 13, 2021 · 1 comment · May be fixed by #7
Open

Exploration - Getting Started with Evidently #6

manisnesan opened this issue Aug 13, 2021 · 1 comment · May be fixed by #7

Comments

@manisnesan
Copy link
Owner

manisnesan commented Aug 13, 2021

Expected Outcomes

  • Follow the Getting Started and Run through the tutorial step by step guide for iris datasets
@manisnesan
Copy link
Owner Author

manisnesan commented Aug 13, 2021

Notes

Functionality

  • Model Health
  • Data Drift
  • Target Drift

Requirements
Reference Data - Most likely the test data set
Current Production Data

img

What should be used as reference & current???

In practice, you can use it in different combinations:

  • Training vs Test : To compare the model performance on a hold-out Test to the Training. Pass the training data as "Reference", and test data as "Current".
  • Production vs Training : To compare the Production model performance to the Training period. Pass the training data as "Reference", and production data as "Current".
  • Current perfromance vs Past: To compare the Current production performance to an Earlier period. For example, to compare the last week to the previous week or month. Pass the earlier data as "Reference", and newer data as "Current".
  • Compare any two models or datasets: For example, to estimate the historical drift for different windows in your training data or to compare how two models perform in the test. Pass the first dataset as "Reference", and the second as "Current".

For Data Drift report, include the input features only.
For Target Drift reports, include the column with Target and/or Prediction.
For Model Performance reports, include the columns with Target and Prediction.

Generates a dashboard with HTML report or json profiles

@manisnesan manisnesan linked a pull request Aug 15, 2021 that will close this issue
@manisnesan manisnesan linked a pull request Aug 15, 2021 that will close this issue
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging a pull request may close this issue.

1 participant