C4.5--using the JAVA realization algorithm of decision tree
C4.5 is a series of classification problems in machine learning and data mining algorithms. Its goal is to monitor: given a set of data, where each tuple is a set of attribute values are used to describe each tuple is a mutually exclusive category of some kind. C4.5 's goal was to learn, find a mapping from the property value to a category, and this map can be used to classify the new category unknown entity.
Proposed on the basis of ID3, C4.5 J.Ross Quinlan. ID3 algorithm used to construct decision tree. A decision tree is a tree structure similar to flowcharts, with each inner node (non-leaf node) represents an attribute on the test, each branch represents a test output, each leaf node storing a class label. Once established the decision tree, not given a tuple of class label, tracking a root node to the leaf node of the path, the leaf node is to deposit the tuple's forecast. Decision tree has the advantage of not requiring any knowledge in the field or parameter settings, suitable for detection of knowledge discovery.
Derived from the ID3 algorithm C4.5, CART two algorithms, these two algorithms in data mining is very important. Below is a typical C4.5 decision tree algorithm on data sets.
File listTips: You can preview the content of files by clicking file names^_^
|.classpath||299.00 B||2014-09-09 10:44|
|.project||383.00 B||2014-09-09 10:44|
|org.eclipse.jdt.core.prefs||598.00 B||2014-09-09 10:44|
|DecimalCalculate.class||2.57 kB||2014-09-09 10:44|
|DecisionTree$TreeNode.class||2.18 kB||2014-09-09 10:44|
|DecisionTree.class||3.88 kB||2014-09-09 10:44|
|InfoGain.class||6.37 kB||2014-09-09 10:44|
|MainC45.class||2.60 kB||2014-09-09 10:44|
|MathUtils.class||1.58 kB||2014-09-09 10:44|
|DecimalCalculate.java||4.58 kB||2014-09-09 10:44|
|DecisionTree.java||5.07 kB||2014-09-09 10:44|
|InfoGain.java||6.38 kB||2014-09-09 10:44|
|MainC45.java||1.85 kB||2014-09-09 10:44|
|MathUtils.java||1.73 kB||2014-09-09 10:44|
- Page 1
- Total 1