File Exchange > DataAnalysis >    Bayesian Ridge Regression

Author:
OriginLab Technical Support
Date Added:
7/2/2020
Last Update:
4/6/2021
Downloads (90 Days):
160
Total Ratings:
0
File Size:
69 KB
Average Rating:
File Name:
BRR.opx
File Version:
1.01
Minimum Versions:
License:
Free
Summary:

Perform bayesian ridge regression with Python.

Screen Shot and Video:
Description:

Purpose

This App provides a tool for fitting data with Bayesian Ridge Regression model. It fits a dataset with one dependent variable and multiple independent variables. You can further use it to predict response of independent variables. 

Notes:

  • It needs Embedded Python and scikit-learn library. Other dependent libraries include numpy

Installation

  1. Download the BRR.opx file, then drag-and-drop onto the Origin workspace.
  2. The App will start downloading dependent Python libraries. Wait a few minutes until the download is completed and restart Origin.

Operation

  1. Activate a worksheet. Click the App icon to bring up the dialog.
  2. On Input Data tab, select single or multiple worksheet columns for Independent Variables and specify Dependent Variable by selecting a single worksheet column.
  3. On Options tab, change settings to fit the model
    • Maximum Iterations: Maximum number of iterations. The solver iterates until convergence or this number of iterations.
    • Tolerance: Stop the algorithm if fitting parameter has converged.
    • Alpha1: Shape parameter for the Gamma distribution prior over the alpha parameter.
    • Alpha2: Inverse scale parameter (rate parameter) for the Gamma distribution prior over the alpha parameter.
    • Lambda1: Shape parameter for the Gamma distribution prior over the lambda parameter.
    • Lambda2: Inverse scale parameter (rate parameter) for the Gamma distribution prior over the lambda parameter.
    • Alpha Initial: Initial value for alpha (precision of the noise). If not set, alpha_init is 1/Var(y).
    • Lambda Initial: Initial value for lambda (precision of the weights). If not set, lambda_init is 1.
    • Include Intercept: Whether to calculate the intercept for this model. 
    • Normalize: Whether to nomralize the dataset before regression.
  4. On Quantities tab: choose which quantities and plots to output.
  5. On Plot tab: choose plots to output. 
    • Score Plot:  Plot the log marginal likelihood as a function of iteration number. 
  6. On Prediction tab, you can select a range of independent data to predict the response with the fitted neural network.
  7. Click OK to output reports.

Updates:

v 1.01 Minor bug fix

Reviews and Comments:

Be the first to review this File Exchange submission.