Botany Data Characterization for Machine Learning
From hpcwiki
Contents |
Archivo ARFF
El archivo arff se compone de 3 partes
- @ relation
- @ attributes
- @ data
@Relation
Se define como la cabecera del archivo arff y nos permitirá establecer que se esta clasificando
@ Attributes
Son los atributos que poseen los datos (El significado), este tipo de datos tambien puede contener la clase a la que pertenece
@ Data
Contiene los datos que representan el modelo
Data del proyecto
Resultados
Run information
Scheme:weka.classifiers.lazy.IBk -K 1 -W 0 -A "weka.core.neighboursearch.LinearNNSearch -A \"weka.core.EuclideanDistance -R first-last\"" Relation: plantas Instances: 40 Attributes: 46
Y1 Y2 Y3 Y4 Y5 Y6 Y7 Y8 Y9 Y10 Y11 Y12 Y13 Y14 Y15 Cr1 Cr2 Cr3 Cr4 Cr5 Cr6 Cr7 Cr8 Cr9 Cr10 Cr11 Cr12 Cr13 Cr14 Cr15 Cb1 Cb2 Cb3 Cb4 Cb5 Cb6 Cb7 Cb8 Cb9 Cb10 Cb11 Cb12 Cb13 Cb14 Cb15 class
Test mode:10-fold cross-validation
Classifier model (full training set)
IB1 instance-based classifier using 1 nearest neighbour(s) for classification
Time taken to build model: 0 seconds
Stratified cross-validation
Summary
Correctly Classified Instances 29 72.5 % Incorrectly Classified Instances 11 27.5 % Kappa statistic 0.45 Mean absolute error 0.2868 Root mean squared error 0.5111 Relative absolute error 57.3684 % Root relative squared error 102.2191 % Total Number of Instances 40
Detailed Accuracy By Class
TP Rate FP Rate Precision Recall F-Measure ROC Area Class 0.45 0 1 0.45 0.621 0.725 Alternaria 1 0.55 0.645 1 0.784 0.725 Sana
Weighted Avg. 0.725 0.275 0.823 0.725 0.703 0.725
Confusion Matrix
a b <-- classified as 9 11 | a = Alternaria 0 20 | b = Sana