Data
optdigits

optdigits

active ARFF Publicly available Visibility: public Uploaded 06-04-2014 by Jan van Rijn
0 likes downloaded by 0 people , 0 total downloads 0 issues 0 downvotes
  • Images Machine Learning OpenML-CC18 OpenML100 study_1 study_123 study_14 study_34 study_37 study_41 study_50 study_52 study_7 study_70 study_76 study_98 study_99 uci
Issue #Downvotes for this reason By


Loading wiki
Help us complete this description Edit
Author: E. Alpaydin, C. Kaynak Source: [UCI](http://archive.ics.uci.edu/ml/datasets/optical+recognition+of+handwritten+digits) Please cite: [UCI citation policy](https://archive.ics.uci.edu/ml/citation_policy.html) 1. Title of Database: Optical Recognition of Handwritten Digits 2. Source: E. Alpaydin, C. Kaynak Department of Computer Engineering Bogazici University, 80815 Istanbul Turkey alpaydin@boun.edu.tr July 1998 3. Past Usage: C. Kaynak (1995) Methods of Combining Multiple Classifiers and Their Applications to Handwritten Digit Recognition, MSc Thesis, Institute of Graduate Studies in Science and Engineering, Bogazici University. E. Alpaydin, C. Kaynak (1998) Cascading Classifiers, Kybernetika, to appear. ftp://ftp.icsi.berkeley.edu/pub/ai/ethem/kyb.ps.Z 4. Relevant Information: We used preprocessing programs made available by NIST to extract normalized bitmaps of handwritten digits from a preprinted form. From a total of 43 people, 30 contributed to the training set and different 13 to the test set. 32x32 bitmaps are divided into nonoverlapping blocks of 4x4 and the number of on pixels are counted in each block. This generates an input matrix of 8x8 where each element is an integer in the range 0..16. This reduces dimensionality and gives invariance to small distortions. For info on NIST preprocessing routines, see M. D. Garris, J. L. Blue, G. T. Candela, D. L. Dimmick, J. Geist, P. J. Grother, S. A. Janet, and C. L. Wilson, NIST Form-Based Handprint Recognition System, NISTIR 5469, 1994. 5. Number of Instances optdigits.tra Training 3823 optdigits.tes Testing 1797 The way we used the dataset was to use half of training for actual training, one-fourth for validation and one-fourth for writer-dependent testing. The test set was used for writer-independent testing and is the actual quality measure. 6. Number of Attributes 64 input+1 class attribute 7. For Each Attribute: All input attributes are integers in the range 0..16. The last attribute is the class code 0..9 8. Missing Attribute Values None 9. Class Distribution Class: No of examples in training set 0: 376 1: 389 2: 380 3: 389 4: 387 5: 376 6: 377 7: 387 8: 380 9: 382 Class: No of examples in testing set 0: 178 1: 182 2: 177 3: 183 4: 181 5: 182 6: 181 7: 179 8: 174 9: 180 Accuracy on the testing set with k-nn using Euclidean distance as the metric k = 1 : 98.00 k = 2 : 97.38 k = 3 : 97.83 k = 4 : 97.61 k = 5 : 97.89 k = 6 : 97.77 k = 7 : 97.66 k = 8 : 97.66 k = 9 : 97.72 k = 10 : 97.55 k = 11 : 97.89

65 features

class (target)nominal10 unique values
0 missing
input1numeric1 unique values
0 missing
input2numeric9 unique values
0 missing
input3numeric17 unique values
0 missing
input4numeric17 unique values
0 missing
input5numeric17 unique values
0 missing
input6numeric17 unique values
0 missing
input7numeric17 unique values
0 missing
input8numeric17 unique values
0 missing
input9numeric4 unique values
0 missing
input10numeric17 unique values
0 missing
input11numeric17 unique values
0 missing
input12numeric17 unique values
0 missing
input13numeric17 unique values
0 missing
input14numeric17 unique values
0 missing
input15numeric17 unique values
0 missing
input16numeric15 unique values
0 missing
input17numeric5 unique values
0 missing
input18numeric17 unique values
0 missing
input19numeric17 unique values
0 missing
input20numeric17 unique values
0 missing
input21numeric17 unique values
0 missing
input22numeric17 unique values
0 missing
input23numeric17 unique values
0 missing
input24numeric9 unique values
0 missing
input25numeric2 unique values
0 missing
input26numeric17 unique values
0 missing
input27numeric17 unique values
0 missing
input28numeric17 unique values
0 missing
input29numeric17 unique values
0 missing
input30numeric17 unique values
0 missing
input31numeric17 unique values
0 missing
input32numeric3 unique values
0 missing
input33numeric2 unique values
0 missing
input34numeric16 unique values
0 missing
input35numeric17 unique values
0 missing
input36numeric17 unique values
0 missing
input37numeric17 unique values
0 missing
input38numeric17 unique values
0 missing
input39numeric15 unique values
0 missing
input40numeric1 unique values
0 missing
input41numeric8 unique values
0 missing
input42numeric17 unique values
0 missing
input43numeric17 unique values
0 missing
input44numeric17 unique values
0 missing
input45numeric17 unique values
0 missing
input46numeric17 unique values
0 missing
input47numeric17 unique values
0 missing
input48numeric7 unique values
0 missing
input49numeric9 unique values
0 missing
input50numeric17 unique values
0 missing
input51numeric17 unique values
0 missing
input52numeric17 unique values
0 missing
input53numeric17 unique values
0 missing
input54numeric17 unique values
0 missing
input55numeric17 unique values
0 missing
input56numeric13 unique values
0 missing
input57numeric2 unique values
0 missing
input58numeric11 unique values
0 missing
input59numeric17 unique values
0 missing
input60numeric17 unique values
0 missing
input61numeric17 unique values
0 missing
input62numeric17 unique values
0 missing
input63numeric17 unique values
0 missing
input64numeric17 unique values
0 missing

107 properties

5620
Number of instances (rows) of the dataset.
65
Number of attributes (columns) of the dataset.
10
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.
64
Number of numeric attributes.
1
Number of nominal attributes.
Second quartile (Median) of entropy among attributes.
0.14
Error rate achieved by the landmarker weka.classifiers.trees.REPTree -L 2
0.87
Kappa coefficient achieved by the landmarker weka.classifiers.lazy.IBk -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W
0.02
Error rate achieved by the landmarker weka.classifiers.lazy.IBk
10.18
Percentage of instances belonging to the most frequent class.
3.69
Mean standard deviation of attributes of the numeric type.
0.08
Second quartile (Median) of kurtosis among attributes of the numeric type.
0.84
Kappa coefficient achieved by the landmarker weka.classifiers.trees.REPTree -L 2
3.32
Entropy of the target attribute values.
0.98
Kappa coefficient achieved by the landmarker weka.classifiers.lazy.IBk
572
Number of instances belonging to the most frequent class.
Minimal entropy among attributes.
4.57
Second quartile (Median) of means among attributes of the numeric type.
0.96
Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.REPTree -L 3
0.69
Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.DecisionStump
Maximum entropy among attributes.
-1.65
Minimum kurtosis among attributes of the numeric type.
Second quartile (Median) of mutual information between the nominal attributes and the target attribute.
0.14
Error rate achieved by the landmarker weka.classifiers.trees.REPTree -L 3
0.8
Error rate achieved by the landmarker weka.classifiers.trees.DecisionStump
2807.5
Maximum kurtosis among attributes of the numeric type.
0
Minimum of means among attributes of the numeric type.
0.56
Second quartile (Median) of skewness among attributes of the numeric type.
0.84
Kappa coefficient achieved by the landmarker weka.classifiers.trees.REPTree -L 3
0.11
Kappa coefficient achieved by the landmarker weka.classifiers.trees.DecisionStump
11.99
Maximum of means among attributes of the numeric type.
Minimal mutual information between the nominal attributes and the target attribute.
0
Percentage of binary attributes.
4.3
Second quartile (Median) of standard deviation of attributes of the numeric type.
0.91
Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.RandomTree -depth 1
0.01
Number of attributes divided by the number of instances.
Maximum mutual information between the nominal attributes and the target attribute.
10
The minimal number of distinct values among attributes of the nominal type.
0
Percentage of instances having missing values.
Third quartile of entropy among attributes.
0.16
Error rate achieved by the landmarker weka.classifiers.trees.RandomTree -depth 1
Number of attributes needed to optimally describe the class (under the assumption of independence among attributes). Equals ClassEntropy divided by MeanMutualInformation.
10
The maximum number of distinct values among attributes of the nominal type.
-1.3
Minimum skewness among attributes of the numeric type.
0
Percentage of missing values.
20.3
Third quartile of kurtosis among attributes of the numeric type.
0.09
Average class difference between consecutive instances.
0.82
Kappa coefficient achieved by the landmarker weka.classifiers.trees.RandomTree -depth 1
0.94
Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.J48 -C .00001
53
Maximum skewness among attributes of the numeric type.
0
Minimum standard deviation of attributes of the numeric type.
98.46
Percentage of numeric attributes.
9.05
Third quartile of means among attributes of the numeric type.
0.94
Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.DecisionStump -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W
0.91
Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.RandomTree -depth 2
0.12
Error rate achieved by the landmarker weka.classifiers.trees.J48 -C .00001
6.52
Maximum standard deviation of attributes of the numeric type.
9.86
Percentage of instances belonging to the least frequent class.
1.54
Percentage of nominal attributes.
Third quartile of mutual information between the nominal attributes and the target attribute.
0.12
Error rate achieved by the landmarker weka.classifiers.trees.DecisionStump -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W
0.16
Error rate achieved by the landmarker weka.classifiers.trees.RandomTree -depth 2
0.87
Kappa coefficient achieved by the landmarker weka.classifiers.trees.J48 -C .00001
Average entropy of the attributes.
554
Number of instances belonging to the least frequent class.
First quartile of entropy among attributes.
4.07
Third quartile of skewness among attributes of the numeric type.
0.87
Kappa coefficient achieved by the landmarker weka.classifiers.trees.DecisionStump -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W
0.82
Kappa coefficient achieved by the landmarker weka.classifiers.trees.RandomTree -depth 2
0.94
Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.J48 -C .0001
168.55
Mean kurtosis among attributes of the numeric type.
0.98
Area Under the ROC Curve achieved by the landmarker weka.classifiers.bayes.NaiveBayes
-1.37
First quartile of kurtosis among attributes of the numeric type.
5.87
Third quartile of standard deviation of attributes of the numeric type.
0.94
Area Under the ROC Curve achieved by the landmarker weka.classifiers.bayes.NaiveBayes -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W
0.91
Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.RandomTree -depth 3
0.12
Error rate achieved by the landmarker weka.classifiers.trees.J48 -C .0001
4.91
Mean of means among attributes of the numeric type.
0.09
Error rate achieved by the landmarker weka.classifiers.bayes.NaiveBayes
0.26
First quartile of means among attributes of the numeric type.
0.96
Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.REPTree -L 1
0.12
Error rate achieved by the landmarker weka.classifiers.bayes.NaiveBayes -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W
0.16
Error rate achieved by the landmarker weka.classifiers.trees.RandomTree -depth 3
0.87
Kappa coefficient achieved by the landmarker weka.classifiers.trees.J48 -C .0001
Average mutual information between the nominal attributes and the target attribute.
0.9
Kappa coefficient achieved by the landmarker weka.classifiers.bayes.NaiveBayes
First quartile of mutual information between the nominal attributes and the target attribute.
0.14
Error rate achieved by the landmarker weka.classifiers.trees.REPTree -L 1
0.87
Kappa coefficient achieved by the landmarker weka.classifiers.bayes.NaiveBayes -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W
0.82
Kappa coefficient achieved by the landmarker weka.classifiers.trees.RandomTree -depth 3
0.94
Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.J48 -C .001
An estimate of the amount of irrelevant information in the attributes regarding the class. Equals (MeanAttributeEntropy - MeanMutualInformation) divided by MeanMutualInformation.
0
Number of binary attributes.
-0.33
First quartile of skewness among attributes of the numeric type.
0.84
Kappa coefficient achieved by the landmarker weka.classifiers.trees.REPTree -L 1
0.94
Area Under the ROC Curve achieved by the landmarker weka.classifiers.lazy.IBk -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W
0
Standard deviation of the number of distinct values among attributes of the nominal type.
0.12
Error rate achieved by the landmarker weka.classifiers.trees.J48 -C .001
10
Average number of distinct values among the attributes of the nominal type.
0.97
First quartile of standard deviation of attributes of the numeric type.
0.96
Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.REPTree -L 2
0.12
Error rate achieved by the landmarker weka.classifiers.lazy.IBk -E "weka.attributeSelection.CfsSubsetEval -P 1 -E 1" -S "weka.attributeSelection.BestFirst -D 1 -N 5" -W
0.99
Area Under the ROC Curve achieved by the landmarker weka.classifiers.lazy.IBk
0.87
Kappa coefficient achieved by the landmarker weka.classifiers.trees.J48 -C .001
5.45
Mean skewness among attributes of the numeric type.

71 tasks

21750 runs - estimation_procedure: 10-fold Crossvalidation - target_feature: class
305 runs - estimation_procedure: 5 times 2-fold Crossvalidation - evaluation_measure: predictive_accuracy - target_feature: class
301 runs - estimation_procedure: 33% Holdout set - evaluation_measure: predictive_accuracy - target_feature: class
167 runs - estimation_procedure: 10 times 10-fold Crossvalidation - evaluation_measure: predictive_accuracy - target_feature: class
31 runs - estimation_procedure: 10-fold Crossvalidation - evaluation_measure: precision - target_feature: class
1 runs - estimation_procedure: 5 times 2-fold Crossvalidation - target_feature: class
0 runs - estimation_procedure: 33% Holdout set - target_feature: class
0 runs - estimation_procedure: 4-fold Crossvalidation - target_feature: class
304 runs - estimation_procedure: 10-fold Learning Curve - evaluation_measure: predictive_accuracy - target_feature: class
174 runs - estimation_procedure: 10 times 10-fold Learning Curve - evaluation_measure: predictive_accuracy - target_feature: class
0 runs - estimation_procedure: 10-fold Learning Curve - target_feature: class
0 runs - estimation_procedure: 10-fold Learning Curve - target_feature: class
0 runs - estimation_procedure: 10-fold Learning Curve - target_feature: class
0 runs - estimation_procedure: 10-fold Learning Curve - target_feature: class
0 runs - estimation_procedure: 10-fold Learning Curve - target_feature: class
0 runs - estimation_procedure: 10-fold Learning Curve - target_feature: class
0 runs - estimation_procedure: 10-fold Learning Curve - target_feature: class
0 runs - estimation_procedure: 10-fold Learning Curve - target_feature: class
25 runs - estimation_procedure: Interleaved Test then Train - target_feature: class
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 - target_feature: class
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
1310 runs - target_feature: class
1309 runs - target_feature: class
1309 runs - target_feature: class
1308 runs - target_feature: class
1308 runs - target_feature: class
1307 runs - target_feature: class
1304 runs - target_feature: class
1304 runs - target_feature: class
1303 runs - target_feature: class
1299 runs - target_feature: class
0 runs - target_feature: class
0 runs - target_feature: class
0 runs - target_feature: class
0 runs - target_feature: class
0 runs - target_feature: class
0 runs - target_feature: class
0 runs - target_feature: class
0 runs - target_feature: class
0 runs - target_feature: class
0 runs - target_feature: class
0 runs - target_feature: class
0 runs - target_feature: class
0 runs - target_feature: class
0 runs - target_feature: class
0 runs - target_feature: class
0 runs - target_feature: class
0 runs - target_feature: class
0 runs - target_feature: class
0 runs - target_feature: class
0 runs - target_feature: class
0 runs - target_feature: class
0 runs - target_feature: class
0 runs - target_feature: class
0 runs - target_feature: class
0 runs - target_feature: class
0 runs - target_feature: class
0 runs - target_feature: class
0 runs - target_feature: class
0 runs - target_feature: class
0 runs - target_feature: class
Define a new task