Difference between revisions of "Orange: Linear Regression"

From OnnoWiki
Jump to navigation Jump to search
Line 2: Line 2:
  
  
A linear regression algorithm with optional L1 (LASSO), L2 (ridge) or L1L2 (elastic net) regularization.
+
Sebuah algoritma linear regression dengan regularisasi optional L1 (LASSO), L2 (ridge) atau L1L2 (elastic net).
  
 
==Input==
 
==Input==
Line 15: Line 15:
 
  Coefficients: linear regression coefficients
 
  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.
+
Widget Linear Regression membangun learner/predictor yang akan learn fungsi linear function dari input data-nya. Model dapat mengidentifikasi hubungan antara predictor xi dan response variable y. Di samping itu, parameter regularisasi Lasso and Ridge dapat di spesifikasikan. Lasso regression meminimalisasi penalized version dari least squares loss function dengan L1-norm penalty sedangkan regularisai Ridge dengan L2-norm penalty.
  
Linear regression works only on regression tasks.
+
Linear regression hanya dapat berfungsi / bekerja pada task regression.
  
 
[[File:LinearRegression-stamped.png|center|200px|thumb]]
 
[[File:LinearRegression-stamped.png|center|200px|thumb]]
Line 33: Line 33:
 
==Contoh==
 
==Contoh==
  
Below, is a simple workflow with housing dataset. We trained Linear Regression and Random Forest and evaluated their performance in Test & Score.
+
Di bawah ini adalah workflow sederhana dengan housing dataset. Kita men-train Linear Regression dan Random Forest dan mengevaluasi performance-nya di Test & Score.
  
 
[[File:LinearRegression-regression.png|center|200px|thumb]]
 
[[File:LinearRegression-regression.png|center|200px|thumb]]

Revision as of 14:53, 6 March 2020

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


Sebuah algoritma linear regression dengan regularisasi optional L1 (LASSO), L2 (ridge) atau L1L2 (elastic net).

Input

Data: input dataset
Preprocessor: preprocessing method(s)

Output

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

Widget Linear Regression membangun learner/predictor yang akan learn fungsi linear function dari input data-nya. Model dapat mengidentifikasi hubungan antara predictor xi dan response variable y. Di samping itu, parameter regularisasi Lasso and Ridge dapat di spesifikasikan. Lasso regression meminimalisasi penalized version dari least squares loss function dengan L1-norm penalty sedangkan regularisai Ridge dengan L2-norm penalty.

Linear regression hanya dapat berfungsi / bekerja pada task regression.

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

Di bawah ini adalah workflow sederhana dengan housing dataset. Kita men-train Linear Regression dan Random Forest dan mengevaluasi performance-nya di Test & Score.

LinearRegression-regression.png


Referensi

Pranala Menarik