Data
CPMP-2015-runtime-classification

CPMP-2015-runtime-classification

active ARFF Publicly available Visibility: public Uploaded 19-06-2019 by Martin Hoang
0 likes downloaded by 0 people , 0 total downloads 0 issues 0 downvotes
  • Algorithm Selection Artificial Intelligence Data Science Machine Learning Optimization R
Issue #Downvotes for this reason By


Loading wiki
Help us complete this description Edit
source: An Algorithm Selection Benchmark for the Container Pre-Marshalling Problem (CPMP) authors: K. Tierney and Y. Malitsky (features) / K. Tierney and D. Pacino and S. Voss (algorithms) translator in coseal format: K. Tierney This is an extension of the 2013 premarshalling dataset that includes more features and a set of test instances. There are three sets of features: feature_values.arff contains the full set of features from iteration 2 of our latent feature analysis (LFA) process (see paper) feature_values_itr1.arff contains only the features after iteration 1 of LFA feature_values_orig.arff containers the features used in PREMARHSALLING-ASTAR-2013 We also provide test data with an identical naming scheme (see _test). The features for the pre-marshalling problem are all extremely easy and fast to compute, thus the feature_costs.arff file has been omitted, as it would be time 0 for every feature (regardless of using original, iteration 1 or iteration 2 features). The feature computation code is available at https://bitbucket.org/eusorpb/cpmp-as Note: previously the scenario was called PREMARSHALLING-ASTAR-2015. To save same space, we renamed the scenario.

23 features

algorithm (target)nominal4 unique values
0 missing
stacksnumeric10 unique values
0 missing
tiersnumeric4 unique values
0 missing
stack.tier.rationumeric17 unique values
0 missing
container.densitynumeric7 unique values
0 missing
empty.stack.pctnumeric15 unique values
0 missing
overstowing.stack.pctnumeric22 unique values
0 missing
overstowing.2cont.stack.pctnumeric34 unique values
0 missing
group.same.minnumeric2 unique values
0 missing
group.same.maxnumeric12 unique values
0 missing
group.same.meannumeric13 unique values
0 missing
group.same.stdevnumeric139 unique values
0 missing
top.good.minnumeric8 unique values
0 missing
top.good.maxnumeric31 unique values
0 missing
top.good.meannumeric281 unique values
0 missing
top.good.stdevnumeric484 unique values
0 missing
overstowage.pctnumeric69 unique values
0 missing
bflbnumeric49 unique values
0 missing
left.densitynumeric215 unique values
0 missing
tier.weighted.groupsnumeric522 unique values
0 missing
avg.l1.top.left.lg.groupnumeric218 unique values
0 missing
cont.empty.grt.estacknumeric62 unique values
0 missing
pct.bottom.pct.on.topnumeric22 unique values
0 missing
row_id (row identifier)string527 unique values
0 missing

62 properties

527
Number of instances (rows) of the dataset.
23
Number of attributes (columns) of the dataset.
4
Number of distinct values of the target attribute (if it is nominal).
0
Number of missing values in the dataset.
0
Number of instances with at least one value missing.
22
Number of numeric attributes.
1
Number of nominal attributes.
1.82
Maximum skewness among attributes of the numeric type.
0.05
Minimum standard deviation of attributes of the numeric type.
First quartile of entropy among attributes.
0.75
Third quartile of skewness among attributes of the numeric type.
13.81
Maximum standard deviation of attributes of the numeric type.
14.8
Percentage of instances belonging to the least frequent class.
-0.95
First quartile of kurtosis among attributes of the numeric type.
2.13
Third quartile of standard deviation of attributes of the numeric type.
Average entropy of the attributes.
78
Number of instances belonging to the least frequent class.
0.45
First quartile of means among attributes of the numeric type.
0
Standard deviation of the number of distinct values among attributes of the nominal type.
0.04
Mean kurtosis among attributes of the numeric type.
0
Number of binary attributes.
First quartile of mutual information between the nominal attributes and the target attribute.
4.07
Mean of means among attributes of the numeric type.
0.12
First quartile of skewness among attributes of the numeric type.
Average mutual information between the nominal attributes and the target attribute.
0.13
First quartile of standard deviation of attributes of the numeric type.
0.45
Average class difference between consecutive instances.
An estimate of the amount of irrelevant information in the attributes regarding the class. Equals (MeanAttributeEntropy - MeanMutualInformation) divided by MeanMutualInformation.
Second quartile (Median) of entropy among attributes.
1.88
Entropy of the target attribute values.
4
Average number of distinct values among the attributes of the nominal type.
-0.23
Second quartile (Median) of kurtosis among attributes of the numeric type.
0.04
Number of attributes divided by the number of instances.
0.46
Mean skewness among attributes of the numeric type.
0.79
Second quartile (Median) of means among attributes of the numeric type.
Number of attributes needed to optimally describe the class (under the assumption of independence among attributes). Equals ClassEntropy divided by MeanMutualInformation.
39.47
Percentage of instances belonging to the most frequent class.
1.81
Mean standard deviation of attributes of the numeric type.
Second quartile (Median) of mutual information between the nominal attributes and the target attribute.
208
Number of instances belonging to the most frequent class.
Minimal entropy among attributes.
0.59
Second quartile (Median) of skewness among attributes of the numeric type.
Maximum entropy among attributes.
-2.01
Minimum kurtosis among attributes of the numeric type.
0
Percentage of binary attributes.
0.49
Second quartile (Median) of standard deviation of attributes of the numeric type.
6.12
Maximum kurtosis among attributes of the numeric type.
0.07
Minimum of means among attributes of the numeric type.
0
Percentage of instances having missing values.
Third quartile of entropy among attributes.
30.2
Maximum of means among attributes of the numeric type.
Minimal mutual information between the nominal attributes and the target attribute.
0
Percentage of missing values.
0.43
Third quartile of kurtosis among attributes of the numeric type.
Maximum mutual information between the nominal attributes and the target attribute.
4
The minimal number of distinct values among attributes of the nominal type.
95.65
Percentage of numeric attributes.
4.76
Third quartile of means among attributes of the numeric type.
4
The maximum number of distinct values among attributes of the nominal type.
-1.68
Minimum skewness among attributes of the numeric type.
4.35
Percentage of nominal attributes.
Third quartile of mutual information between the nominal attributes and the target attribute.

9 tasks

14 runs - estimation_procedure: 10-fold Crossvalidation - evaluation_measure: average_cost - target_feature: algorithm
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
Define a new task