87
1
moa.OzaBoostAdwin_HoeffdingTree
1
Moa_2014.03_1.0
Moa implementation of OzaBoostAdwin
2014-04-23T17:55:42
English
Moa_2014.03
a
option
0.002
deltaAdwin: Delta of Adwin change detection
e
flag
false
same: Use Samme Algorithm.
l
baselearner
trees.HoeffdingTree
baseLearner: Classifier to train.
o
flag
false
outputCodes: Use Output Codes to use binary classifiers.
p
flag
false
pureBoost: Boost with weights only; no poisson.
r
option
1
randomSeed: Seed for random behaviour of the classifier.
s
option
10
ensembleSize: The number of models to boost.
l
80
1
moa.HoeffdingTree
1
Moa_2014.03_1.0
A Hoeffding tree (VFDT) is an incremental, anytime decision tree induction algorithm
that is capable of learning from massive data streams, assuming that the distribution
generating examples does not change over time. Hoeffding trees exploit the fact that
a small sample can often be enough to choose an optimal splitting attribute. This idea
is supported mathematically by the Hoeffding bound, which quantifies the number
of observations (in our case, examples) needed to estimate some statistics within a
prescribed precision (in our case, the goodness of an attribute).
2014-04-04T14:52:04
English
Moa_2014.03
b
flag
false
binarySplits: Only allow binary splits.
c
option
1.0E-7
splitConfidence: The allowable error in split decision, values closer to 0 will take longer to decide.
d
baselearner
NominalAttributeClassObserver
nominalEstimator: Nominal estimator to use.
e
option
1000000
memoryEstimatePeriod: How many instances between memory consumption checks.
g
option
200
gracePeriod: The number of instances a leaf should observe between split attempts.
l
option
NBAdaptive
leafprediction: Leaf prediction to use.
m
option
33554432
maxByteSize: Maximum memory consumed by the tree.
n
baselearner
GaussianNumericAttributeClassObserver
numericEstimator: Numeric estimator to use.
p
flag
false
noPrePrune: Disable pre-pruning.
q
option
0
nbThreshold: The number of instances a leaf should observe before permitting Naive Bayes.
r
flag
false
removePoorAtts: Disable poor attributes.
s
baselearner
InfoGainSplitCriterion
splitCriterion: Split criterion to use.
t
option
0.05
tieThreshold: Threshold below which a split will be forced to break ties.
z
flag
false
stopMemManagement: Stop growing as soon as memory limit is hit.
study_11
Verified_Supervised_Data_Stream_Classification
Verified_Supervised_Data_Stream_Classification
https://www.openml.org/data/download/2399/moa_task_174918857601727875514.xml
xml
c46e16669944091766c42e4cee625c57