Line | |
---|

1 | .. _Linear Regression: |
---|

2 | |
---|

3 | Linear Regression Learner |
---|

4 | ========================= |
---|

5 | |
---|

6 | .. image:: ../../../../Orange/OrangeWidgets/icons/Unknown.png |
---|

7 | :alt: Linear Regression |
---|

8 | |
---|

9 | Learns a linear function of its input data. |
---|

10 | |
---|

11 | Channels |
---|

12 | -------- |
---|

13 | |
---|

14 | Input |
---|

15 | - Data (Table) |
---|

16 | Input data table |
---|

17 | |
---|

18 | Output |
---|

19 | - Learner |
---|

20 | The learning algorithm with the supplied parameters |
---|

21 | |
---|

22 | - Predictor |
---|

23 | Trained regressor |
---|

24 | |
---|

25 | - Model Statisics |
---|

26 | A data table containing trained model statistics |
---|

27 | |
---|

28 | |
---|

29 | Signal ``Predictor`` and ``Model Statistics`` send the output |
---|

30 | signal only if input signal ``Data`` is present. |
---|

31 | |
---|

32 | Description |
---|

33 | ----------- |
---|

34 | |
---|

35 | Linear Regression widget construct a learner/predictor that learns a |
---|

36 | linear function from its input data. Furthermore `Lasso`_ and `Ridge`_ |
---|

37 | regularization parameters can be specified. |
---|

38 | |
---|

39 | .. image:: images/LinearRegression.png |
---|

40 | :alt: Linear Regression interface |
---|

41 | |
---|

42 | .. rst-class:: stamp-list |
---|

43 | |
---|

44 | 1. The learner/predictor name |
---|

45 | 2. Train an ordinary least squares or ridge regression model |
---|

46 | 3. If ``Ridge lambda`` is checked the learner will build a ridge regression model |
---|

47 | with 4 as the ``lambda`` parameter. |
---|

48 | 4. Ridge lambda parameter. |
---|

49 | 5. Use `Lasso`_ regularization. |
---|

50 | 6. The Lasso bound (bound on the beta vector L1 norm) |
---|

51 | 7. Tolerance (any beta value lower then this will be forced to 0) |
---|

52 | |
---|

53 | .. _`Lasso`: http://en.wikipedia.org/wiki/Least_squares#LASSO_method |
---|

54 | |
---|

55 | .. _`Ridge`: http://en.wikipedia.org/wiki/Ridge_regression |
---|

**Note:** See

TracBrowser
for help on using the repository browser.