Flow
moa.ORTO

moa.ORTO

Visibility: public Uploaded 11-11-2014 by Jan van Rijn Moa_2014.03 101 runs
0 likes downloaded by 2 people 0 issues 0 downvotes , 2 total downloads
  • Verified_Supervised_Data_Stream_Classification
Issue #Downvotes for this reason By


Loading wiki
Help us complete this description Edit
Moa implementation of ORTO

Parameters

aPageHinckleyAlpha: The alpha value to use in the Page Hinckley change detection tests.default: 0.005
csplitConfidence: The allowable error in split decision, values closer to 0 will take longer to decide.default: 1.0E-7
dOptionDecayFactor: The option decay factor that determines how many options can be selected at a given level.default: 0.9
fAlternateTreeFadingFactor: The fading factor to use when deciding if an alternate tree should replace an original.default: 0.995
ggracePeriod: The number of instances a leaf should observe between split attempts.default: 200
hPageHinckleyThreshold: The threshold value to be used in the Page Hinckley change detection tests.default: 50
jLearningRatioDecayOrConst: learning Ratio Decay or const parameter.default: false
lMaxOptionLevel: The maximal depth at which option nodes can be created.default: 10
mMaxTrees: The maximum number of trees contained in the option tree.default: 10
nnumericEstimator: Numeric estimator to use.default: FIMTDDNumericAttributeClassObserver
oOptionNodeAggregation: The aggregation method used to combine predictions in option nodes.default: average
premovePoorAtts: Disable poor attributes.default: false
qOptionFadingFactor: The fading factor used for comparing subtrees of an option node.default: 0.9995
rrandomSeed: Seed for random behaviour of the classifier.default: 1
ssplitCriterion: Split criterion to use.default: VarianceReductionSplitCriterion
ttieThreshold: Threshold below which a split will be forced to break ties.default: 0.05
uAlternateTreeTime: The 'time' (in terms of number of instances) value to use when deciding if an alternate tree should be discarded.default: 1500
wLearningRatio: Learning ratio to use for training the Perceptrons in the leaves.default: 0.01
yAlternateTreeTMin: The Tmin value to use when deciding if an alternate tree should replace an original.default: 150

0
Runs

List all runs
Parameter:
Rendering chart
Rendering table