Difference between revisions of "Orange: Linear Regression"

From OnnoWiki
Jump to navigation Jump to search
(Created page with "Sumber: https://docs.biolab.si//3/visual-programming/widgets/model/linearregression.html A linear regression algorithm with optional L1 (LASSO), L2 (ridge) or L1L2 (elastic...")
 
Line 7: Line 7:
  
 
     Data: input dataset
 
     Data: input dataset
 
 
     Preprocessor: preprocessing method(s)
 
     Preprocessor: preprocessing method(s)
  
Line 13: Line 12:
  
 
     Learner: linear regression learning algorithm
 
     Learner: linear regression learning algorithm
 
 
     Model: trained model
 
     Model: trained model
 
 
     Coefficients: linear regression coefficients
 
     Coefficients: linear regression coefficients
  
Line 22: Line 19:
 
Linear regression works only on regression tasks.
 
Linear regression works only on regression tasks.
  
../../_images/LinearRegression-stamped.png
+
[[File:LinearRegression-stamped.png|center|200px|thumb]]
  
 
     The learner/predictor name
 
     The learner/predictor name
 
 
     Choose a model to train:
 
     Choose a model to train:
 
 
         no regularization
 
         no regularization
 
 
         a Ridge regularization (L2-norm penalty)
 
         a Ridge regularization (L2-norm penalty)
 
 
         a Lasso bound (L1-norm penalty)
 
         a Lasso bound (L1-norm penalty)
 
 
         an Elastic net regularization
 
         an Elastic net regularization
 
 
     Produce a report.
 
     Produce a report.
 
 
     Press Apply to commit changes. If Apply Automatically is ticked, changes are committed automatically.
 
     Press Apply to commit changes. If Apply Automatically is ticked, changes are committed automatically.
  
Example
+
==Contoh==
  
 
Below, is a simple workflow with housing dataset. We trained Linear Regression and Random Forest and evaluated their performance in Test & Score.
 
Below, is a simple workflow with housing dataset. We trained Linear Regression and Random Forest and evaluated their performance in Test & Score.
  
../../_images/LinearRegression-regression.png
+
[[File:LinearRegression-regression.png|center|200px|thumb]]
  
  

Revision as of 09:44, 23 January 2020

Sumber: https://docs.biolab.si//3/visual-programming/widgets/model/linearregression.html


A linear regression algorithm with optional L1 (LASSO), L2 (ridge) or L1L2 (elastic net) regularization.

Inputs

   Data: input dataset
   Preprocessor: preprocessing method(s)

Outputs

   Learner: linear regression learning algorithm
   Model: trained model
   Coefficients: linear regression coefficients

The Linear Regression widget constructs a learner/predictor that learns a linear function from its input data. The model can identify the relationship between a predictor xi and the response variable y. Additionally, Lasso and Ridge regularization parameters can be specified. Lasso regression minimizes a penalized version of the least squares loss function with L1-norm penalty and Ridge regularization with L2-norm penalty.

Linear regression works only on regression tasks.

LinearRegression-stamped.png
   The learner/predictor name
   Choose a model to train:
       no regularization
       a Ridge regularization (L2-norm penalty)
       a Lasso bound (L1-norm penalty)
       an Elastic net regularization
   Produce a report.
   Press Apply to commit changes. If Apply Automatically is ticked, changes are committed automatically.

Contoh

Below, is a simple workflow with housing dataset. We trained Linear Regression and Random Forest and evaluated their performance in Test & Score.

LinearRegression-regression.png


Referensi

Pranala Menarik