A Decision Tree

D-Tree:

A decision tree is formed by loading the preprocess ie: training data. Then using the training data, execute the classifier section of weka to get the % accuracy. We can modify the % accuracy by adjusting the confidence factor, numFolds, and minNumObj. Their range vary from 0-0.5, 1,2….20, 2,3…25 respectively. Before using the test data, a .model version of the training data is saved and then loaded again to the WEKA tool. Then the test data is incorporated, and WEKA again runs the entire operation to calculate the accuracy of data. We can improve the result by adjusting the confidence factor, numFolds, and minNumObj. All of WEKA's techniques (preprocessing, classification, regressions etc), are predicated on the assumption that the data which is available for accuracy checking is available on a single flat file, where each data point is described by a fixed number of attributes.

D-Tree:

A decision tree is formed by loading the preprocess ie: training data. Then using the training data, execute the classifier section of weka to get the % accuracy. We can modify the % accuracy by adjusting the confidence factor, numFolds, and minNumObj. Their range vary from 0-0.5, 1,2….20, 2,3…25 respectively. Before using the test data, a .model version of the training data is saved and then loaded again to the WEKA tool. Then the test data is incorporated, and WEKA again runs the entire operation to calculate the accuracy of data. We can improve the result by adjusting the confidence factor, numFolds, and minNumObj. All of WEKA's techniques (preprocessing, classification, regressions etc), are predicated on the assumption that the data which is available for accuracy checking is available on a single flat file, where each data point is described by a fixed number of attributes.