3287
939
weka.AttributeSelectedClassifier_CfsSubsetEval_BestFirst_SGD
1
Weka_3.7.13_11461
Weka implementation of AttributeSelectedClassifier
2016-03-18T13:45:24
English
Weka_3.7.13
-do-not-check-capabilities
flag
If set, classifier capabilities are not checked before classifier is built
(use with caution).
-doNotMakeSplitPointActualValue
flag
Do not make split point actual value.
A
flag
Laplace smoothing for predicted probabilities.
B
flag
Use binary splits only.
C
option
Set confidence threshold for pruning.
(default 0.25)
D
flag
Output debugging info.
E
kernel
weka.attributeSelection.CfsSubsetEval
Full class name of attribute evaluator, followed
by its options.
eg: "weka.attributeSelection.CfsSubsetEval -L"
(default weka.attributeSelection.CfsSubsetEval)
J
flag
Do not use MDL correction for info gain on numeric attributes.
L
flag
Do not clean up after the tree has been built.
M
option
Set minimum number of instances per leaf.
(default 2)
N
option
Set number of folds for reduced error
pruning. One fold is used as pruning set.
(default 3)
O
flag
Do not collapse tree.
P
option
The size of the thread pool, for example, the number of cores in the CPU. (default 1)
Q
option
Seed for random data shuffling (default 1).
R
flag
Use reduced error pruning.
S
kernel
weka.attributeSelection.BestFirst
Full class name of search method, followed
by its options.
eg: "weka.attributeSelection.BestFirst -D 1"
(default weka.attributeSelection.BestFirst)
U
flag
Use unpruned tree.
W
baselearner
weka.classifiers.functions.SGD
Full name of base classifier.
(default: weka.classifiers.trees.J48)
Z
flag
Precompute the full correlation matrix at the outset, rather than compute correlations lazily (as needed) during the search. Use this in conjuction with parallel processing in order to speed up a backward search.
num-decimal-places
option
The number of decimal places for the output of numbers in the model (default 2).
output-debug-info
flag
If set, classifier is run in debug mode and
may output additional info to the console
W
1944
818
weka.SGD
4
Weka_3.7.13_11468
Weka implementation of SGD
2015-11-30T23:10:25
English
Weka_3.7.13
-do-not-check-capabilities
flag
If set, classifier capabilities are not checked before classifier is built
(use with caution).
C
option
0.001
The epsilon threshold (epsilon-insenstive and Huber loss only, default = 1e-3)
E
option
500
The number of epochs to perform (batch learning only, default = 500)
F
option
0
Set the loss function to minimize.
0 = hinge loss (SVM), 1 = log loss (logistic regression),
2 = squared loss (regression), 3 = epsilon insensitive loss (regression),
4 = Huber loss (regression).
(default = 0)
L
option
0.01
The learning rate. If normalization is
turned off (as it is automatically for streaming data), then the
default learning rate will need to be reduced (try 0.0001).
(default = 0.01).
M
flag
Don't replace missing values
N
flag
Don't normalize the data
R
option
1.0E-4
The lambda regularization constant (default = 0.0001)
S
option
1
Random number seed.
(default 1)
num-decimal-places
option
The number of decimal places for the output of numbers in the model (default 2).
output-debug-info
flag
If set, classifier is run in debug mode and
may output additional info to the console
study_15
study_20
Verified_Learning_Curve,Verified_Supervised_Classification
weka
weka_3.7.13
https://api.openml.org/data/download/1687727/weka.classifiers.functions.SGD4950430537509506920.class
class
a8220c187f13fa59696a69da9418b199
E
2049
824
weka.CfsSubsetEval
5
Weka_3.7.13_11852
M. A. Hall (1998). Correlation-based Feature Subset Selection for Machine Learning. Hamilton, New Zealand.
2015-12-03T12:02:12
English
Weka_3.7.13
D
flag
Output debugging info.
E
option
1
The number of threads to use, which should be >= size of thread pool. (default 1)
L
flag
Don't include locally predictive attributes.
M
flag
Treat missing values as a separate value.
P
option
1
The size of the thread pool, for example, the number of cores in the CPU. (default 1)
Z
flag
Precompute the full correlation matrix at the outset, rather than compute correlations lazily (as needed) during the search. Use this in conjuction with parallel processing in order to speed up a backward search.
weka
weka_3.7.13
S
2050
824
weka.BestFirst
4
Weka_3.7.13_10396
Weka implementation of BestFirst
2015-12-03T12:02:12
English
Weka_3.7.13
D
option
1
Direction of search. (default = 1).
N
option
5
Number of non-improving nodes to
consider before terminating search.
P
option
Specify a starting set of attributes.
Eg. 1,3,5-7.
S
option
Size of lookup cache for evaluated subsets.
Expressed as a multiple of the number of
attributes in the data set. (default = 1)
weka
weka_3.7.13
study_15
study_20
Verified_Supervised_Classification
weka
weka_3.7.13
https://api.openml.org/data/download/1836553/weka.classifiers.meta.AttributeSelectedClassifier9218818895155849678.class
class
e33297e05015e5c2e3533a8e686b98eb