Feature performance overview

Overview of Feature Values

The following measures were taken for the results of each feature:

obs (number of observations within the feature set)
NAs (number of NAs, i.e., missing values, within the feature set)
min (minimum), mean (arithmetic mean), max (maximum), std_dev (standard deviation)
1st_qu (1st quartile = lower quartile = 25%-quantile)
median (median = 50%-quantile)
3rd_qu (3rd quartile = upper quartile = 75%-quantile)
co_var (coefficient of variation = standard deviation / arithmetic mean)

Instance Feature Values

	obs	nas	min	qu_1st	med	mean	qu_3rd	max	sd	coeff_var
MeanAttributeEntropy	105	0	-1	-1	-1	-0.021	1.2	4.9	1.5	-70
NaiveBayesAdwin.warnings	105	0	0	0	0	0	0	0	0
NoiseToSignalRatio	105	68	-1	5.8	22	94	65	1.1e+03	2.1e+02	2.2
NumberOfNumericFeatures	105	0	0	7	21	1.3e+03	72	1.1e+04	3.4e+03	2.6
NumberOfBinaryFeatures	105	0	0	0	1	2	1	35	4.8	2.4
DecisionStumpKappa	105	0	-0.00017	0	0.13	0.27	0.45	0.92	0.29	1.1
Quartile3SkewnessOfNumericAtts	105	0	-0.0012	0.78	2.2	4.3	4.1	1.2e+02	12	2.8
NumberOfMissingValues	105	0	0	0	0	1.1e+03	0	6.8e+04	7e+03	6.6
J48.001.ErrRate	105	0	0	0.057	0.15	0.2	0.28	0.81	0.19	0.98
HoeffdingAdwin.changes	105	0	0	0	1	5.8	4	67	13	2.3
PercentageOfNumericFeatures	105	0	0	77	95	77	98	1e+02	33	0.43
MeanSkewnessOfNumericAtts	105	0	-0.12	0.27	2	3.4	3.5	72	7.5	2.2
MinStdDevOfNumericAtts	105	0	0	0	0.0027	30	0.24	4.8e+02	1.1e+02	3.7
NaiveBayesErrRate	105	0	0	0.091	0.2	0.25	0.33	0.83	0.2	0.81
MinMutualInformation	105	68	0	9.8e-06	0.0025	0.18	0.0082	4.2	0.71	4
MajorityClassPercentage	105	0	1	19	54	49	75	95	29	0.59
NumberOfSymbolicFeatures	105	0	1	1	1	7.3	4	2.4e+02	25	3.4
J48.00001.ErrRate	105	0	0	0.057	0.16	0.2	0.28	0.81	0.2	0.98
MaxNominalAttDistinctValues	105	0	-1	-1	-1	15	4	1.1e+03	1.1e+02	7.1
PercentageOfMissingValues	105	0	0	0	0	1.7	0	70	9.3	5.5
MinKurtosisOfNumericAtts	105	0	-2	-1.8	-1.5	18	-0.75	2.1e+03	2e+02	11
MaxKurtosisOfNumericAtts	105	0	-1.2	8.4	4.5e+02	4.5e+03	2.8e+03	1.9e+05	1.9e+04	4.3
EquivalentNumberOfAtts	105	68	-1	7.5	19	85	60	5.3e+02	1.4e+02	1.7
DecisionStumpErrRate	105	0	0.027	0.14	0.3	0.4	0.71	0.98	0.29	0.73
RandomTreeDepth3ErrRate	105	0	-1	0.11	0.22	0.28	0.39	0.93	0.27	0.95
MaxStdDevOfNumericAtts	105	0	0	3.7	1.6e+03	2.1e+06	6.1e+04	2.1e+07	6.2e+06	2.9
NaiveBayesAdwin.changes	105	0	0	0	1	5.8	5	88	14	2.4
Quartile3AttributeEntropy	105	68	0.24	1.4	1.8	2.3	2.9	7.8	1.6	0.68
MeanKurtosisOfNumericAtts	105	0	-1.7	0.34	28	1.7e+02	78	8.9e+03	9.2e+02	5.6
MinorityClassPerentage	105	0	0	7.9	14	20	33	50	15	0.77
J48.00001.Kappa	105	0	0	0.33	0.67	0.59	0.87	1	0.32	0.54
REPTreeDepth2ErrRate	105	0	-1	0.075	0.17	0.25	0.33	0.96	0.28	1.1
Quartile2KurtosisOfNumericAtts	105	0	-2	0	0.71	99	10	9.3e+03	9.1e+02	9.2
REPTreeDepth3AUC	105	0	-1	0.72	0.87	0.81	0.94	1	0.23	0.29
RandomTreeDepth2ErrRate	105	0	-1	0.12	0.24	0.3	0.41	0.96	0.28	0.94
Quartile1AttributeEntropy	105	68	-0	0.63	1	1.2	1.6	4.9	1.1	0.91
MeanMeansOfNumericAtts	105	0	-9.4e+03	0.0013	39	2.1e+04	4.7e+02	2e+06	2e+05	9.5
MeanStdDevOfNumericAtts	105	0	0	1	40	1.2e+04	1.6e+03	1e+06	1e+05	8.3
REPTreeDepth1Kappa	105	0	-1	0.093	0.5	0.45	0.81	1	0.39	0.87
Dimensionality	105	0	8.7e-05	0.008	0.02	1.3	0.055	20	4	3
REPTreeDepth2AUC	105	0	-1	0.7	0.86	0.79	0.94	1	0.23	0.3
MinAttributeEntropy	105	68	-0	0.26	0.96	1.1	1	4.9	1.2	1.1
NaiveBayesDdm.changes	105	0	0	0	1	6.3	6	1.4e+02	18	2.9
MinNominalAttDistinctValues	105	0	-1	-1	-1	1.6	2	1e+02	11	6.4
MinorityClassSize	105	0	0	1.2e+02	2.6e+02	1.1e+03	6.2e+02	1.9e+04	2.6e+03	2.5
Quartile2AttributeEntropy	105	68	0	1	1.5	1.7	2	4.9	1.1	0.67
Quartile1SkewnessOfNumericAtts	105	0	-0.86	-0.086	0.0076	0.81	1	22	2.8	3.4
Quartile3StdDevOfNumericAtts	105	0	0	0.5	20	4.7e+03	81	4.3e+05	4.2e+04	8.9
Quartile1MutualInformation	105	68	0	0.0012	0.0054	0.19	0.034	4.2	0.71	3.7
Quartile2SkewnessOfNumericAtts	105	0	-0.27	0.077	0.68	2.3	2.4	85	8.5	3.7
MajorityClassSize	105	0	16	2.8e+02	6.8e+02	2.7e+03	1.8e+03	3.7e+04	6.2e+03	2.3
REPTreeDepth3ErrRate	105	0	-1	0.074	0.16	0.24	0.32	0.94	0.27	1.1
MaxAttributeEntropy	105	68	0.76	1.6	2.5	2.8	3.5	10	1.8	0.62
RandomTreeDepth2Kappa	105	0	-1	0.16	0.38	0.4	0.66	1	0.34	0.83
HoeffdingDDM.changes	105	0	0	0	1	6.4	6	1.7e+02	18	2.9
Quartile3KurtosisOfNumericAtts	105	0	-1.8	0.85	8	1.7e+02	31	1.5e+04	1.5e+03	8.4
NaiveBayesKappa	105	0	-0.082	0.3	0.53	0.55	0.82	1	0.3	0.54
HoeffdingDDM.warnings	105	0	0	1	4	15	10	4.6e+02	50	3.3
Quartile2StdDevOfNumericAtts	105	0	0	0.36	1	6.8e+02	9.8	5.6e+04	5.5e+03	8.1
MeanNominalAttDistinctValues	105	0	-1	-1	-1	5.2	2.8	2.7e+02	28	5.5
REPTreeDepth1ErrRate	105	0	-1	0.08	0.19	0.27	0.38	0.98	0.29	1.1
MaxMeansOfNumericAtts	105	0	-0.00013	3.4	3.3e+03	2.7e+06	1.2e+05	2.6e+07	7.8e+06	2.9
NumberOfInstances	105	0	5e+02	8e+02	1.6e+03	5.1e+03	4.6e+03	4.9e+04	9.5e+03	1.9
RandomTreeDepth1Kappa	105	0	-1	0.088	0.33	0.37	0.65	1	0.35	0.94
J48.001.AUC	105	0	0.5	0.71	0.87	0.82	0.94	1	0.16	0.19
MaxSkewnessOfNumericAtts	105	0	-0.0012	2.3	21	37	53	4.4e+02	56	1.5
J48.0001.AUC	105	0	0.5	0.71	0.87	0.82	0.94	1	0.16	0.2
RandomTreeDepth3AUC	105	0	-1	0.66	0.79	0.76	0.89	1	0.22	0.28
MeanMutualInformation	105	68	0	0.019	0.052	0.34	0.23	4.2	0.79	2.3
RandomTreeDepth1ErrRate	105	0	-1	0.13	0.24	0.31	0.46	0.98	0.29	0.93
RandomTreeDepth2AUC	105	0	-1	0.64	0.77	0.74	0.87	1	0.21	0.29
MinMeansOfNumericAtts	105	0	-9.2e+07	-11	0	-8.7e+06	0.14	4e+03	2.7e+07	-3.1
PercentageOfBinaryFeatures	105	0	0	0	0.81	8.6	10	95	16	1.9
NumberOfFeatures	105	0	4	13	36	1.3e+03	82	1.1e+04	3.4e+03	2.5
NaiveBayesAUC	105	0	0.5	0.79	0.9	0.86	0.97	1	0.14	0.16
DefaultAccuracy	105	0	0.01	0.19	0.54	0.49	0.75	0.95	0.29	0.59
NaiveBayesDdm.warnings	105	0	0	1	5	15	9	3.9e+02	47	3.1
Quartile3MeansOfNumericAtts	105	0	-0.00036	0.42	28	2.5e+03	1.6e+02	1.6e+05	1.6e+04	6.4
REPTreeDepth1AUC	105	0	-1	0.62	0.8	0.76	0.94	1	0.25	0.32
MaxMutualInformation	105	68	0	0.06	0.22	0.6	0.5	4.2	1	1.7
HoeffdingAdwin.warnings	105	0	0	0	0	0	0	0	0
RandomTreeDepth1AUC	105	0	-1	0.64	0.71	0.72	0.83	1	0.22	0.3
J48.0001.Kappa	105	0	0	0.33	0.67	0.6	0.87	1	0.32	0.54
Quartile1MeansOfNumericAtts	105	0	-0.79	1.6e-08	0.36	1.5e+02	2.4	4.2e+03	4.9e+02	3.3
RandomTreeDepth3Kappa	105	0	-1	0.17	0.44	0.44	0.67	1	0.32	0.74
Quartile1StdDevOfNumericAtts	105	0	0	0.18	0.56	83	2.5	6.6e+02	2.1e+02	2.5
REPTreeDepth2Kappa	105	0	-1	0.17	0.54	0.49	0.81	1	0.37	0.74
Quartile2MeansOfNumericAtts	105	0	-0.046	0.04	1.1	5.3e+02	24	2.9e+04	2.9e+03	5.4
J48.00001.AUC	105	0	0.5	0.71	0.86	0.82	0.94	1	0.16	0.2
Quartile2MutualInformation	105	68	0	0.0042	0.03	0.31	0.23	4.2	0.77	2.5
J48.001.Kappa	105	0	0	0.34	0.67	0.6	0.86	1	0.32	0.53
PercentageOfInstancesWithMissingValues	105	0	0	0	0	5.5	0	1e+02	20	3.7
NumberOfClasses	105	0	2	2	2	7.8	8	1e+02	17	2.1
StdvNominalAttDistinctValues	105	0	-1	-1	-1	5.7	0.55	5.4e+02	53	9.2
ClassEntropy	105	0	0.29	0.83	1	1.8	2.9	6.6	1.4	0.79
Quartile1KurtosisOfNumericAtts	105	0	-2	-0.84	-0.092	29	2.1	2.7e+03	2.6e+02	9
Quartile3MutualInformation	105	68	0	0.018	0.072	0.49	0.31	4.2	1	2.1
MinSkewnessOfNumericAtts	105	0	-76	-3.8	-0.99	-11	-0.0033	1.8	22	-2.1
PercentageOfSymbolicFeatures	105	0	0.0091	1.5	5	23	23	1e+02	33	1.5
J48.0001.ErrRate	105	0	0	0.057	0.15	0.2	0.28	0.81	0.2	0.97
NumberOfInstancesWithMissingValues	105	0	0	0	0	1.5e+02	0	3.8e+03	6.3e+02	4.3
REPTreeDepth3Kappa	105	0	-1	0.19	0.62	0.51	0.82	1	0.36	0.7
DecisionStumpAUC	105	0	0.5	0.66	0.72	0.73	0.78	0.96	0.11	0.15

Algorithm Feature Values

	obs	min	qu_1st	med	mean	qu_3rd	max	sd	coeff_var
Lines..Average.	21	7.4	12	15	15	18	24	4.5	0.31
Lines..Total.	21	1.8e+02	3.8e+02	6e+02	6.5e+02	9.6e+02	1.2e+03	3.3e+02	0.51
Size..Average.	21	1.2e+04	2.5e+04	3.2e+04	3.6e+04	4.9e+04	6.5e+04	1.6e+04	0.44
Size..Total.	21	1.2e+04	2.5e+04	3.2e+04	3.6e+04	4.9e+04	6.5e+04	1.6e+04	0.44
Number.of.files	21	1	1	1	1	1	1	0	0
Cyclomatic..Average.	21	0.42	2	2.4	2.3	2.9	4.3	1.1	0.46
Cyclomatic..Total.	21	13	50	80	98	1.5e+02	2.3e+02	64	0.65
Max.Indent..Average.	21	1.2	1.6	1.8	1.8	2	2.3	0.34	0.19
Max.Indent..Total.	21	25	42	68	73	93	1.5e+02	34	0.46
nb_nodes	21	4.4e+02	1.2e+03	1.9e+03	2.4e+03	3.9e+03	4.9e+03	1.5e+03	0.63
nb_edges	21	4.4e+02	1.2e+03	1.9e+03	2.4e+03	3.9e+03	4.8e+03	1.5e+03	0.63
degree_min	21	1	1	1	1	1	1	0	0
degree_max	21	8	8	8	8	8	8	0	0
degree_mean	21	2	2	2	2	2	2	0.0012	0.00058
degree_variance	21	0.84	0.88	0.9	0.91	0.93	1	0.052	0.057
degree_entropy	21	1.2	1.2	1.2	1.2	1.2	1.2	0.015	0.013
transitivity	21	0	0	0	0	0	0	0
clustering_min	21	0	0	0	0	0	0	0
clustering_max	21	0	0	0	0	0	0	0
clustering_mean	21	0	0	0	0	0	0	0
clustering_variance	21	0	0	0	0	0	0	0
path_min	21	3	3	3	3	3	3	0	0
paths_max	21	20	27	31	32	36	63	8.9	0.28
path_mean	21	12	16	18	18	20	23	2.7	0.15
path_variance	21	14	20	25	28	31	72	12	0.44
path_entropy	21	2.6	2.9	3	3	3.1	3.4	0.18	0.061

Summary of feature steps

The following table summarizes the feature steps over all instances.

size (percentage of features affected by this step)
ok, ..., other (percentage of run status)
cost_min, cost_mean, cost_max (range of costs for this step)
cost_na (percentage of missing values occuring in costs)

	size	ok	presolved
ALL	1	1e+02	0
code	1	1e+02
AST	1	1e+02

Duplicated Features

Underneath, you'll find blocks of duplicated instnace features, i.e., observations that have equal values over all features. Please note, that only a maximum of 5 duplicates per block are shown.

There were no duplicated features.