#
source:
orange/docs/widgets/rst/classify/naivebayes.rst
@
11778:ecd4beec2099

Revision 11778:ecd4beec2099, 3.1 KB checked in by Ales Erjavec <ales.erjavec@…>, 5 months ago (diff) |
---|

Line | |
---|---|

1 | .. _Naive Bayes: |

2 | |

3 | Naive Bayesian Learner |

4 | ====================== |

5 | |

6 | .. image:: ../../../../Orange/OrangeWidgets/Classify/icons/NaiveBayes.svg |

7 | |

8 | Naive Bayesian Learner |

9 | |

10 | Signals |

11 | ------- |

12 | |

13 | Inputs: |

14 | |

15 | |

16 | - Examples (ExampleTable) |

17 | A table with training examples |

18 | |

19 | |

20 | Outputs: |

21 | |

22 | - Learner |

23 | The naive Bayesian learning algorithm with settings as specified in |

24 | the dialog. |

25 | |

26 | - Naive Bayesian Classifier |

27 | Trained classifier (a subtype of Classifier) |

28 | |

29 | |

30 | Signal :obj:`Naive Bayesian Classifier` sends data only if the learning |

31 | data (signal :obj:`Examples` is present. |

32 | |

33 | Description |

34 | ----------- |

35 | |

36 | This widget provides a graphical interface to the Naive Bayesian classifier. |

37 | |

38 | As all widgets for classification, this widget provides a learner and |

39 | classifier on the output. Learner is a learning algorithm with settings |

40 | as specified by the user. It can be fed into widgets for testing learners, |

41 | for instance :ref:`Test Learners`. Classifier is a Naive Bayesian Classifier |

42 | (a subtype of a general classifier), built from the training examples on the |

43 | input. If examples are not given, there is no classifier on the output. |

44 | |

45 | .. image:: images/NaiveBayes.png |

46 | :alt: NaiveBayes Widget |

47 | |

48 | Learner can be given a name under which it will appear in, say, |

49 | :ref:`Test Learners`. The default name is "Naive Bayes". |

50 | |

51 | Next come the probability estimators. :obj:`Prior` sets the method used for |

52 | estimating prior class probabilities from the data. You can use either |

53 | :obj:`Relative frequency` or the :obj:`Laplace estimate`. |

54 | :obj:`Conditional (for discrete)` sets the method for estimating conditional |

55 | probabilities, besides the above two, conditional probabilities can be |

56 | estimated using the :obj:`m-estimate`; in this case the value of m should be |

57 | given as the :obj:`Parameter for m-estimate`. By setting it to |

58 | :obj:`<same as above>` the classifier will use the same method as for |

59 | estimating prior probabilities. |

60 | |

61 | Conditional probabilities for continuous attributes are estimated using |

62 | LOESS. :obj:`Size of LOESS window` sets the proportion of points in the |

63 | window; higher numbers mean more smoothing. |

64 | :obj:`LOESS sample points` sets the number of points in which the function |

65 | is sampled. |

66 | |

67 | If the class is binary, the classification accuracy may be increased |

68 | considerably by letting the learner find the optimal classification |

69 | threshold (option :obj:`Adjust threshold`). The threshold is computed from |

70 | the training data. If left unchecked, the usual threshold of 0.5 is used. |

71 | |

72 | When you change one or more settings, you need to push :obj:`Apply`; |

73 | this will put the new learner on the output and, if the training examples |

74 | are given, construct a new classifier and output it as well. |

75 | |

76 | |

77 | Examples |

78 | -------- |

79 | |

80 | There are two typical uses of this widget. First, you may want to induce |

81 | the model and check what it looks like in a :ref:`Nomogram`. |

82 | |

83 | .. image:: images/NaiveBayes-SchemaClassifier.png |

84 | :alt: Naive Bayesian Classifier - Schema with a Classifier |

85 | |

86 | The second schema compares the results of Naive Bayesian learner with |

87 | another learner, a C4.5 tree. |

88 | |

89 | .. image:: images/C4.5-SchemaLearner.png |

90 | :alt: Naive Bayesian Classifier - Schema with a Learner |

**Note:**See TracBrowser for help on using the repository browser.