Changeset 7324:5fff4f240fdc in orange


Ignore:
Timestamp:
02/03/11 13:42:53 (3 years ago)
Author:
Gregor Rot <gregor.rot@…>
Branch:
default
Convert:
c5bb7fd126488e6aeab4eb2ee18957fed6344b8b
Message:
 
File:
1 edited

Legend:

Unmodified
Added
Removed
  • orange/Orange/associate/__init__.py

    r7323 r7324  
    2525 
    2626    .. attribute:: support 
     27     
    2728    Minimal support for the rule. 
    2829     
    2930    .. attribute:: confidence 
     31     
    3032    Minimal confidence for the rule. 
    3133     
    3234    .. attribute:: storeExamples 
     35     
    3336    Tells the inducer to store the examples covered by each rule and those confirming it. 
    3437     
    3538    .. attribute:: maxItemSets 
     39     
    3640    The maximal number of itemsets. 
    3741 
     
    116120 
    117121    .. attribute:: support 
     122     
    118123    Minimal support for the rule. 
    119124     
    120125    .. attribute:: confidence 
     126     
    121127    Minimal confidence for the rule. 
    122128     
    123129    .. attribute:: classificationRules 
     130     
    124131    If 1 (default is 0), the algorithm constructs classification rules instead of general association rules. 
    125132     
    126133    .. attribute:: storeExamples 
     134     
    127135    Tells the inducer to store the examples covered by each rule and those confirming it 
    128136     
    129137    .. attribute:: maxItemSets 
     138     
    130139    The maximal number of itemsets. 
    131140 
     
    189198     
    190199    .. attribute:: nLeft, nRight 
     200     
    191201    The number of features (ie defined values) on the left and on the right side of the rule. 
    192202     
    193203    .. attribute:: nAppliesLeft, nAppliesRight, nAppliesBoth 
     204     
    194205    The number of (learning) examples that conform to the left, the right and to both sides of the rule. 
    195206     
    196207    .. attribute:: nExamples 
     208     
    197209    The total number of learning examples. 
    198210     
    199211    .. attribute:: support 
     212     
    200213    nAppliesBoth/nExamples. 
    201214 
    202215    .. attribute:: confidence 
     216     
    203217    nAppliesBoth/nAppliesLeft. 
    204218     
    205219    .. attribute:: coverage 
     220     
    206221    nAppliesLeft/nExamples. 
    207222 
    208223    .. attribute:: strength 
     224     
    209225    nAppliesRight/nAppliesLeft. 
    210226     
    211227    .. attribute:: lift 
     228     
    212229    nExamples * nAppliesBoth / (nAppliesLeft * nAppliesRight). 
    213230     
    214231    .. attribute:: leverage 
     232     
    215233    (nAppliesBoth * nExamples - nAppliesLeft * nAppliesRight). 
    216234     
    217235    .. attribute:: examples, matchLeft, matchBoth 
     236     
    218237    If storeExamples was True during induction, examples contains a copy of the example table used to induce the rules. Attributes matchLeft and matchBoth are lists of integers, representing the indices of examples which match the left-hand side of the rule and both sides, respectively. 
    219238 
    220239    .. method:: AssociationRule(left, right, nAppliesLeft, nAppliesRight, nAppliesBoth, nExamples) 
     240     
    221241    Constructs an association rule and computes all measures listed above. 
    222242     
    223243    .. method:: AssociationRule(left, right, support, confidence) 
     244     
    224245    Construct association rule and sets its support and confidence. If you intend to pass on such a rule you should set other attributes manually - AssociationRules's constructor cannot compute anything from arguments support and confidence. 
    225246     
    226247    .. method:: AssociationRule(rule) 
     248     
    227249    Given an association rule as the argument, constructor copies of the rule. 
    228250     
    229251    .. method:: appliesLeft(example), appliesRight(example), appliesBoth(example) 
     252     
    230253    Tells whether the example fits into the left, right or both sides of the rule, respectively. If the rule is represented by sparse examples, the given example must be sparse as well. 
    231254     
Note: See TracChangeset for help on using the changeset viewer.