Data
Pen_global

Pen_global

in_preparation ARFF Publicly available Visibility: public Uploaded 22-09-2017 by Minh-Anh Le
0 likes downloaded by 0 people , 0 total downloads 0 issues 0 downvotes
Issue #Downvotes for this reason By


Loading wiki
Help us complete this description Edit
"This UCI dataset contains the hand- written digits 0–9 of 45 different writers. Here, in the “global” task, we only keep the digit 8 as the normal class and sample the 10 digits from all of the other classes as anomalies. This results in one big normal cluster and global anomalies sparsely distributed. The resulting pen-global dataset has 16 dimensions and 809 instances including a large amount of anomalies (11.1%)." (cite from Goldstein, Markus, and Seiichi Uchida. "A comparative evaluation of unsupervised anomaly detection algorithms for multivariate data." PloS one 11.4 (2016): e0152173). This dataset is not the original dataset. The target variable "Target" is relabeled into "Normal" and "Anomaly".

17 features

Target (target)nominal2 unique values
0 missing
V1numeric101 unique values
0 missing
V2numeric84 unique values
0 missing
V3numeric99 unique values
0 missing
V4numeric76 unique values
0 missing
V5numeric101 unique values
0 missing
V6numeric101 unique values
0 missing
V7numeric101 unique values
0 missing
V8numeric97 unique values
0 missing
V9numeric99 unique values
0 missing
V10numeric79 unique values
0 missing
V11numeric101 unique values
0 missing
V12numeric93 unique values
0 missing
V13numeric91 unique values
0 missing
V14numeric99 unique values
0 missing
V15numeric96 unique values
0 missing
V16numeric94 unique values
0 missing

62 properties

809
Number of instances (rows) of the dataset.
17
Number of attributes (columns) of the dataset.
2
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.
16
Number of numeric attributes.
1
Number of nominal attributes.
0.5
Entropy of the target attribute values.
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.
0.02
Number of attributes divided by the number of instances.
2
Average number of distinct values among the attributes of the nominal type.
-0.94
Second quartile (Median) of kurtosis 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.
-0.11
Mean skewness among attributes of the numeric type.
50.36
Second quartile (Median) of means among attributes of the numeric type.
88.88
Percentage of instances belonging to the most frequent class.
28.98
Mean standard deviation of attributes of the numeric type.
Second quartile (Median) of mutual information between the nominal attributes and the target attribute.
719
Number of instances belonging to the most frequent class.
Minimal entropy among attributes.
-0.07
Second quartile (Median) of skewness among attributes of the numeric type.
Maximum entropy among attributes.
-1.42
Minimum kurtosis among attributes of the numeric type.
5.88
Percentage of binary attributes.
29.54
Second quartile (Median) of standard deviation of attributes of the numeric type.
2.26
Maximum kurtosis among attributes of the numeric type.
20.91
Minimum of means among attributes of the numeric type.
0
Percentage of instances having missing values.
Third quartile of entropy among attributes.
80.64
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.
-0.56
Third quartile of kurtosis among attributes of the numeric type.
Maximum mutual information between the nominal attributes and the target attribute.
2
The minimal number of distinct values among attributes of the nominal type.
94.12
Percentage of numeric attributes.
65.46
Third quartile of means among attributes of the numeric type.
2
The maximum number of distinct values among attributes of the nominal type.
-1.32
Minimum skewness among attributes of the numeric type.
5.88
Percentage of nominal attributes.
Third quartile of mutual information between the nominal attributes and the target attribute.
0.89
Maximum skewness among attributes of the numeric type.
18.01
Minimum standard deviation of attributes of the numeric type.
First quartile of entropy among attributes.
0.37
Third quartile of skewness among attributes of the numeric type.
38.54
Maximum standard deviation of attributes of the numeric type.
11.12
Percentage of instances belonging to the least frequent class.
-1.16
First quartile of kurtosis among attributes of the numeric type.
31.87
Third quartile of standard deviation of attributes of the numeric type.
Average entropy of the attributes.
90
Number of instances belonging to the least frequent class.
38.08
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.
-0.63
Mean kurtosis among attributes of the numeric type.
1
Number of binary attributes.
First quartile of mutual information between the nominal attributes and the target attribute.
51.58
Mean of means among attributes of the numeric type.
-0.39
First quartile of skewness among attributes of the numeric type.
0.97
Average class difference between consecutive instances.
Average mutual information between the nominal attributes and the target attribute.
27.06
First quartile of standard deviation of attributes of the numeric type.

10 tasks

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
0 runs - estimation_procedure: 50 times Clustering
Define a new task