source: orange/Orange/testing/regression/results_reference/lasso-example.py.txt @ 10859:08a0a35c1687

Revision 10859:08a0a35c1687, 762 bytes checked in by Lan Zagar <lan.zagar@…>, 2 years ago (diff)

Reimplemented lasso. Breaks compatibility.

It now uses a proximal gradient method for optimization instead of using scipy.optimize (see #1118).
The formulation is slightly different so there are new parameters (mainly lasso_lambda instead of t/s).
Improved some other things as well.

Line 
1Actual: 24.00, predicted: 30.45
2Actual: 21.60, predicted: 25.60
3Actual: 34.70, predicted: 31.48
4Actual: 33.40, predicted: 30.18
5Actual: 36.20, predicted: 29.59
6  Variable  Coeff Est  Std Error          p
7 Intercept     22.533
8      CRIM     -0.023      0.024      0.050     .
9      CHAS      1.970      1.331      0.040     *
10       NOX     -4.226      2.944      0.010     *
11        RM      4.270      0.934      0.000   ***
12       DIS     -0.373      0.170      0.010     *
13   PTRATIO     -0.798      0.117      0.000   ***
14         B      0.007      0.003      0.020     *
15     LSTAT     -0.519      0.102      0.000   ***
16Signif. codes:  0 *** 0.001 ** 0.01 * 0.05 . 0.1 empty 1
17
18For 5 variables the regression coefficient equals 0:
19ZN, INDUS, AGE, RAD, TAX
Note: See TracBrowser for help on using the repository browser.