https://github.com/iskandr/censored_regression

Linear regression with lower-bound labels
https://github.com/iskandr/censored_regression

Last synced: 23 days ago
JSON representation

Linear regression with lower-bound labels

• Host: GitHub
• URL: https://github.com/iskandr/censored_regression
• Owner: iskandr
• License: apache-2.0
• Created: 2014-09-03T18:16:49.000Z (over 10 years ago)
• Default Branch: master
• Last Pushed: 2014-09-08T17:55:06.000Z (over 10 years ago)
• Last Synced: 2024-10-15T20:25:35.364Z (2 months ago)
• Language: Python
• Size: 140 KB
• Stars: 4
• Watchers: 2
• Forks: 3
• Open Issues: 0
• Metadata Files:
  • Readme: README
  • License: LICENSE

Awesome Lists containing this project

README

        
censored_regression

===================

Linear regression with inequality constraints on some of the target values. Useful when you don't care about the specific value predicted

for some samples, only that's they're above some given value. 

Implementations for ordinary least-squares regression, as well as L1-penalized (Lasso) and L2-penalized (Ridge). 

Example usage:

```

	model = censored_regression.Lasso()

	# C is a boolean mask indicating which targets are lower bounds

	model.fit(X,Y,C)

	model.predict(X_test)

```