Data
satimage

satimage

active ARFF Publicly available Visibility: public Uploaded 23-04-2014 by Jan van Rijn
0 likes downloaded by 0 people , 0 total downloads 0 issues 0 downvotes
  • Environment OpenML-CC18 OpenML100 Science study_1 study_123 study_14 study_34 study_37 study_41 study_52 study_7 study_70 study_76 study_98 study_99 Technology
Issue #Downvotes for this reason By


Loading wiki
Help us complete this description Edit
Author: Ashwin Srinivasan, Department of Statistics and Data Modeling, University of Strathclyde Source: [UCI](https://archive.ics.uci.edu/ml/datasets/Statlog+(Landsat+Satellite)) - 1993 Please cite: [UCI](https://archive.ics.uci.edu/ml/citation_policy.html) The database consists of the multi-spectral values of pixels in 3x3 neighbourhoods in a satellite image, and the classification associated with the central pixel in each neighbourhood. The aim is to predict this classification, given the multi-spectral values. In the sample database, the class of a pixel is coded as a number. One frame of Landsat MSS imagery consists of four digital images of the same scene in different spectral bands. Two of these are in the visible region (corresponding approximately to green and red regions of the visible spectrum) and two are in the (near) infra-red. Each pixel is a 8-bit binary word, with 0 corresponding to black and 255 to white. The spatial resolution of a pixel is about 80m x 80m. Each image contains 2340 x 3380 such pixels. The database is a (tiny) sub-area of a scene, consisting of 82 x 100 pixels. Each line of data corresponds to a 3x3 square neighbourhood of pixels completely contained within the 82x100 sub-area. Each line contains the pixel values in the four spectral bands (converted to ASCII) of each of the 9 pixels in the 3x3 neighbourhood and a number indicating the classification label of the central pixel. Each pixel is categorized as one of the following classes: 1 red soil 2 cotton crop 3 grey soil 4 damp grey soil 5 soil with vegetation stubble 6 mixture class (all types present) 7 very damp grey soil NB. There are no examples with class 6 in this dataset. The data is given in random order and certain lines of data have been removed so you cannot reconstruct the original image from this dataset. ### Attribute information There are 36 predictive attributes (= 4 spectral bands x 9 pixels in neighborhood). In each line of data the four spectral values for the top-left pixel are given first followed by the four spectral values for the top-middle pixel and then those for the top-right pixel, and so on with the pixels read out in sequence left-to-right and top-to-bottom. Thus, the four spectral values for the central pixel are given by attributes 17,18,19 and 20. If you like you can use only these four attributes, while ignoring the others. This avoids the problem which arises when a 3x3 neighbourhood straddles a boundary. In this version, the pixel values 0..255 are normalized around 0. Note: it is unclear why the attributes are named Aattr - Fattr in this version, since there are only 4 bands and 9 pixels, naming them A1, B1, C1, D1, A2, B2, C2, D2, ... would have made more sense.

37 features

class (target)nominal6 unique values
0 missing
Aattrnumeric51 unique values
0 missing
Battrnumeric84 unique values
0 missing
Cattrnumeric76 unique values
0 missing
Dattrnumeric102 unique values
0 missing
Eattrnumeric51 unique values
0 missing
Fattrnumeric82 unique values
0 missing
A1attrnumeric76 unique values
0 missing
B2attrnumeric103 unique values
0 missing
C3attrnumeric50 unique values
0 missing
D4attrnumeric81 unique values
0 missing
E5attrnumeric78 unique values
0 missing
F6attrnumeric104 unique values
0 missing
A7attrnumeric51 unique values
0 missing
B8attrnumeric83 unique values
0 missing
C9attrnumeric78 unique values
0 missing
D10attrnumeric101 unique values
0 missing
E11attrnumeric50 unique values
0 missing
F12attrnumeric80 unique values
0 missing
A13attrnumeric77 unique values
0 missing
B14attrnumeric104 unique values
0 missing
C15attrnumeric50 unique values
0 missing
D16attrnumeric80 unique values
0 missing
E17attrnumeric78 unique values
0 missing
F18attrnumeric104 unique values
0 missing
A19attrnumeric51 unique values
0 missing
B20attrnumeric82 unique values
0 missing
C21attrnumeric75 unique values
0 missing
D22attrnumeric102 unique values
0 missing
E23attrnumeric50 unique values
0 missing
F24attrnumeric81 unique values
0 missing
A25attrnumeric77 unique values
0 missing
B26attrnumeric103 unique values
0 missing
C27attrnumeric50 unique values
0 missing
D28attrnumeric80 unique values
0 missing
E29attrnumeric77 unique values
0 missing
F30attrnumeric104 unique values
0 missing
Show all 37 features

107 properties

NumberOfInstances
6430
Number of instances (rows) of the dataset.
NumberOfFeatures
37
Number of attributes (columns) of the dataset.
NumberOfClasses
6
Number of distinct values of the target attribute (if it is nominal).
NumberOfMissingValues
0
Number of missing values in the dataset.
NumberOfInstancesWithMissingValues
0
Number of instances with at least one value missing.
NumberOfNumericFeatures
36
Number of numeric attributes.
NumberOfSymbolicFeatures
1
Number of nominal attributes.
MaxStdDevOfNumericAtts
1
Maximum standard deviation of attributes of the numeric type.
MinorityClassPercentage
9.72
Percentage of instances belonging to the least frequent class.
PercentageOfNumericFeatures
97.3
Percentage of numeric attributes.
Quartile3MeansOfNumericAtts
-0
Third quartile of means among attributes of the numeric type.
CfsSubsetEval_DecisionStumpAUC
0.93
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
RandomTreeDepth2AUC
0.9
Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.RandomTree -depth 2
J48.00001.ErrRate
0.14
Error rate achieved by the landmarker weka.classifiers.trees.J48 -C .00001
MeanAttributeEntropy
Average entropy of the attributes.
MinorityClassSize
625
Number of instances belonging to the least frequent class.
PercentageOfSymbolicFeatures
2.7
Percentage of nominal attributes.
Quartile3MutualInformation
Third quartile of mutual information between the nominal attributes and the target attribute.
CfsSubsetEval_DecisionStumpErrRate
0.15
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
RandomTreeDepth2ErrRate
0.17
Error rate achieved by the landmarker weka.classifiers.trees.RandomTree -depth 2
J48.00001.Kappa
0.82
Kappa coefficient achieved by the landmarker weka.classifiers.trees.J48 -C .00001
MeanKurtosisOfNumericAtts
-0.15
Mean kurtosis among attributes of the numeric type.
NaiveBayesAUC
0.96
Area Under the ROC Curve achieved by the landmarker weka.classifiers.bayes.NaiveBayes
Quartile1AttributeEntropy
First quartile of entropy among attributes.
Quartile3SkewnessOfNumericAtts
0.67
Third quartile of skewness among attributes of the numeric type.
CfsSubsetEval_DecisionStumpKappa
0.82
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
RandomTreeDepth2Kappa
0.79
Kappa coefficient achieved by the landmarker weka.classifiers.trees.RandomTree -depth 2
J48.0001.AUC
0.92
Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.J48 -C .0001
MeanMeansOfNumericAtts
-0
Mean of means among attributes of the numeric type.
NaiveBayesErrRate
0.2
Error rate achieved by the landmarker weka.classifiers.bayes.NaiveBayes
Quartile1KurtosisOfNumericAtts
-0.84
First quartile of kurtosis among attributes of the numeric type.
Quartile3StdDevOfNumericAtts
1
Third quartile of standard deviation of attributes of the numeric type.
CfsSubsetEval_NaiveBayesAUC
0.93
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
RandomTreeDepth3AUC
0.9
Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.RandomTree -depth 3
J48.0001.ErrRate
0.14
Error rate achieved by the landmarker weka.classifiers.trees.J48 -C .0001
MeanMutualInformation
Average mutual information between the nominal attributes and the target attribute.
NaiveBayesKappa
0.75
Kappa coefficient achieved by the landmarker weka.classifiers.bayes.NaiveBayes
Quartile1MeansOfNumericAtts
-0
First quartile of means among attributes of the numeric type.
REPTreeDepth1AUC
0.96
Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.REPTree -L 1
CfsSubsetEval_NaiveBayesErrRate
0.15
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
RandomTreeDepth3ErrRate
0.17
Error rate achieved by the landmarker weka.classifiers.trees.RandomTree -depth 3
J48.0001.Kappa
0.82
Kappa coefficient achieved by the landmarker weka.classifiers.trees.J48 -C .0001
MeanNoiseToSignalRatio
An estimate of the amount of irrelevant information in the attributes regarding the class. Equals (MeanAttributeEntropy - MeanMutualInformation) divided by MeanMutualInformation.
NumberOfBinaryFeatures
0
Number of binary attributes.
Quartile1MutualInformation
First quartile of mutual information between the nominal attributes and the target attribute.
REPTreeDepth1ErrRate
0.15
Error rate achieved by the landmarker weka.classifiers.trees.REPTree -L 1
CfsSubsetEval_NaiveBayesKappa
0.82
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
RandomTreeDepth3Kappa
0.79
Kappa coefficient achieved by the landmarker weka.classifiers.trees.RandomTree -depth 3
J48.001.AUC
0.92
Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.J48 -C .001
MeanNominalAttDistinctValues
6
Average number of distinct values among the attributes of the nominal type.
Quartile1SkewnessOfNumericAtts
-0.52
First quartile of skewness among attributes of the numeric type.
REPTreeDepth1Kappa
0.81
Kappa coefficient achieved by the landmarker weka.classifiers.trees.REPTree -L 1
CfsSubsetEval_kNN1NAUC
0.93
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
StdvNominalAttDistinctValues
0
Standard deviation of the number of distinct values among attributes of the nominal type.
J48.001.ErrRate
0.14
Error rate achieved by the landmarker weka.classifiers.trees.J48 -C .001
MeanSkewnessOfNumericAtts
0.04
Mean skewness among attributes of the numeric type.
Quartile1StdDevOfNumericAtts
1
First quartile of standard deviation of attributes of the numeric type.
REPTreeDepth2AUC
0.96
Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.REPTree -L 2
CfsSubsetEval_kNN1NErrRate
0.15
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
kNN1NAUC
0.94
Area Under the ROC Curve achieved by the landmarker weka.classifiers.lazy.IBk
J48.001.Kappa
0.82
Kappa coefficient achieved by the landmarker weka.classifiers.trees.J48 -C .001
MeanStdDevOfNumericAtts
1
Mean standard deviation of attributes of the numeric type.
Quartile2AttributeEntropy
Second quartile (Median) of entropy among attributes.
REPTreeDepth2ErrRate
0.15
Error rate achieved by the landmarker weka.classifiers.trees.REPTree -L 2
CfsSubsetEval_kNN1NKappa
0.82
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
kNN1NErrRate
0.11
Error rate achieved by the landmarker weka.classifiers.lazy.IBk
MajorityClassPercentage
23.81
Percentage of instances belonging to the most frequent class.
MinAttributeEntropy
Minimal entropy among attributes.
Quartile2KurtosisOfNumericAtts
-0.48
Second quartile (Median) of kurtosis among attributes of the numeric type.
REPTreeDepth2Kappa
0.81
Kappa coefficient achieved by the landmarker weka.classifiers.trees.REPTree -L 2
ClassEntropy
2.48
Entropy of the target attribute values.
kNN1NKappa
0.87
Kappa coefficient achieved by the landmarker weka.classifiers.lazy.IBk
MajorityClassSize
1531
Number of instances belonging to the most frequent class.
MinKurtosisOfNumericAtts
-0.92
Minimum kurtosis among attributes of the numeric type.
Quartile2MeansOfNumericAtts
-0
Second quartile (Median) of means among attributes of the numeric type.
REPTreeDepth3AUC
0.96
Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.REPTree -L 3
DecisionStumpAUC
0.71
Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.DecisionStump
MaxAttributeEntropy
Maximum entropy among attributes.
MinMeansOfNumericAtts
-0
Minimum of means among attributes of the numeric type.
Quartile2MutualInformation
Second quartile (Median) of mutual information between the nominal attributes and the target attribute.
REPTreeDepth3ErrRate
0.15
Error rate achieved by the landmarker weka.classifiers.trees.REPTree -L 3
DecisionStumpErrRate
0.56
Error rate achieved by the landmarker weka.classifiers.trees.DecisionStump
MaxKurtosisOfNumericAtts
1.28
Maximum kurtosis among attributes of the numeric type.
MinMutualInformation
Minimal mutual information between the nominal attributes and the target attribute.
Quartile2SkewnessOfNumericAtts
-0.04
Second quartile (Median) of skewness among attributes of the numeric type.
REPTreeDepth3Kappa
0.81
Kappa coefficient achieved by the landmarker weka.classifiers.trees.REPTree -L 3
DecisionStumpKappa
0.27
Kappa coefficient achieved by the landmarker weka.classifiers.trees.DecisionStump
MaxMeansOfNumericAtts
-0
Maximum of means among attributes of the numeric type.
MinNominalAttDistinctValues
6
The minimal number of distinct values among attributes of the nominal type.
PercentageOfBinaryFeatures
0
Percentage of binary attributes.
Quartile2StdDevOfNumericAtts
1
Second quartile (Median) of standard deviation of attributes of the numeric type.
RandomTreeDepth1AUC
0.9
Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.RandomTree -depth 1
Dimensionality
0.01
Number of attributes divided by the number of instances.
MaxMutualInformation
Maximum mutual information between the nominal attributes and the target attribute.
MinSkewnessOfNumericAtts
-0.67
Minimum skewness among attributes of the numeric type.
PercentageOfInstancesWithMissingValues
0
Percentage of instances having missing values.
Quartile3AttributeEntropy
Third quartile of entropy among attributes.
RandomTreeDepth1ErrRate
0.17
Error rate achieved by the landmarker weka.classifiers.trees.RandomTree -depth 1
EquivalentNumberOfAtts
Number of attributes needed to optimally describe the class (under the assumption of independence among attributes). Equals ClassEntropy divided by MeanMutualInformation.
MaxNominalAttDistinctValues
6
The maximum number of distinct values among attributes of the nominal type.
MinStdDevOfNumericAtts
1
Minimum standard deviation of attributes of the numeric type.
PercentageOfMissingValues
0
Percentage of missing values.
Quartile3KurtosisOfNumericAtts
0.85
Third quartile of kurtosis among attributes of the numeric type.
AutoCorrelation
0.19
Average class difference between consecutive instances.
RandomTreeDepth1Kappa
0.79
Kappa coefficient achieved by the landmarker weka.classifiers.trees.RandomTree -depth 1
J48.00001.AUC
0.92
Area Under the ROC Curve achieved by the landmarker weka.classifiers.trees.J48 -C .00001
MaxSkewnessOfNumericAtts
0.92
Maximum skewness among attributes of the numeric type.
Show all 107 properties

53 tasks

Supervised Classification on satimage
21370 runs - estimation_procedure: 10-fold Crossvalidation - target_feature: class
Supervised Classification on satimage
308 runs - estimation_procedure: 33% Holdout set - evaluation_measure: predictive_accuracy - target_feature: class
Supervised Classification on satimage
203 runs - estimation_procedure: 10 times 10-fold Crossvalidation - evaluation_measure: predictive_accuracy - target_feature: class
Supervised Classification on satimage
31 runs - estimation_procedure: 10-fold Crossvalidation - evaluation_measure: precision - target_feature: class
Supervised Classification on satimage
1 runs - estimation_procedure: 5 times 2-fold Crossvalidation - target_feature: class
Supervised Classification on satimage
0 runs - estimation_procedure: 33% Holdout set - target_feature: class
Supervised Classification on satimage
0 runs - estimation_procedure: 4-fold Crossvalidation - target_feature: class
Learning Curve on satimage
368 runs - estimation_procedure: 10-fold Learning Curve - evaluation_measure: predictive_accuracy - target_feature: class
Learning Curve on satimage
0 runs - estimation_procedure: 10-fold Learning Curve - target_feature: class
Learning Curve on satimage
0 runs - estimation_procedure: 10-fold Learning Curve - target_feature: class
Learning Curve on satimage
0 runs - estimation_procedure: 10-fold Learning Curve - target_feature: class
Learning Curve on satimage
0 runs - estimation_procedure: 10-fold Learning Curve - target_feature: class
Learning Curve on satimage
0 runs - estimation_procedure: 10-fold Learning Curve - target_feature: class
Learning Curve on satimage
0 runs - estimation_procedure: 10-fold Learning Curve - target_feature: class
Learning Curve on satimage
0 runs - estimation_procedure: 10-fold Learning Curve - target_feature: class
Learning Curve on satimage
0 runs - estimation_procedure: 10-fold Learning Curve - target_feature: class
Supervised Data Stream Classification on satimage
25 runs - estimation_procedure: Interleaved Test then Train - target_feature: class
Clustering on satimage
0 runs - estimation_procedure: 50 times Clustering
Clustering on satimage
0 runs - estimation_procedure: 50 times Clustering
Clustering on satimage
0 runs - estimation_procedure: 50 times Clustering
Clustering on satimage
0 runs - estimation_procedure: 50 times Clustering
Clustering on satimage
0 runs - estimation_procedure: 50 times Clustering
Clustering on satimage
0 runs
Clustering on satimage
0 runs - estimation_procedure: 50 times Clustering
Clustering on satimage
0 runs - target_feature: class
Clustering on satimage
0 runs - estimation_procedure: 50 times Clustering
Clustering on satimage
0 runs - estimation_procedure: 50 times Clustering
Clustering on satimage
0 runs - estimation_procedure: 50 times Clustering
Clustering on satimage
0 runs - estimation_procedure: 50 times Clustering
Subgroup Discovery on satimage
1321 runs - target_feature: class
Subgroup Discovery on satimage
1316 runs - target_feature: class
Subgroup Discovery on satimage
1313 runs - target_feature: class
Subgroup Discovery on satimage
1311 runs - target_feature: class
Subgroup Discovery on satimage
1309 runs - target_feature: class
Subgroup Discovery on satimage
1306 runs - target_feature: class
Subgroup Discovery on satimage
0 runs - target_feature: class
Subgroup Discovery on satimage
0 runs - target_feature: class
Subgroup Discovery on satimage
0 runs - target_feature: class
Subgroup Discovery on satimage
0 runs - target_feature: class
Subgroup Discovery on satimage
0 runs - target_feature: class
Subgroup Discovery on satimage
0 runs - target_feature: class
Subgroup Discovery on satimage
0 runs - target_feature: class
Subgroup Discovery on satimage
0 runs - target_feature: class
Subgroup Discovery on satimage
0 runs - target_feature: class
Subgroup Discovery on satimage
0 runs - target_feature: class
Subgroup Discovery on satimage
0 runs - target_feature: class
Subgroup Discovery on satimage
0 runs - target_feature: class
Subgroup Discovery on satimage
0 runs - target_feature: class
Subgroup Discovery on satimage
0 runs - target_feature: class
Subgroup Discovery on satimage
0 runs - target_feature: class
Subgroup Discovery on satimage
0 runs - target_feature: class
Subgroup Discovery on satimage
0 runs - target_feature: class
Subgroup Discovery on satimage
0 runs - target_feature: class
Define a new task