weka源码下载

㈠ 求助 weka 的ID3算法java源码

/*
*    This program is free software; you can redistribute it and/or modify
*    it under the terms of the GNU General Public License as published by
*    the Free Software Foundation; either version 2 of the License, or
*    (at your option) any later version.
*
*    This program is distributed in the hope that it will be useful,
*    but WITHOUT ANY WARRANTY; without even the implied warranty of
*    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
*    GNU General Public License for more details.
*
*    You should have received a  of the GNU General Public License
*    along with this program; if not, write to the Free Software
*    Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
/*
*    Id3.java
*    Copyright (C) 1999 University of Waikato, Hamilton, New Zealand
*
*/
package weka.classifiers.trees;
import weka.classifiers.Classifier;
import weka.classifiers.Sourcable;
import weka.core.Attribute;
import weka.core.Capabilities;
import weka.core.Instance;
import weka.core.Instances;
import weka.core.;
import weka.core.RevisionUtils;
import weka.core.TechnicalInformation;
import weka.core.TechnicalInformationHandler;
import weka.core.Utils;
import weka.core.Capabilities.Capability;
import weka.core.TechnicalInformation.Field;
import weka.core.TechnicalInformation.Type;
import java.util.Enumeration;
/**
<!-- globalinfo-start -->
* Class for constructing an unpruned decision tree based on the ID3 algorithm. Can only deal with nominal attributes. No missing values allowed. Empty leaves may result in unclassified instances. For more information see: <br/>
* <br/>
* R. Quinlan (1986). Inction of decision trees. Machine Learning. 1(1):81-106.
* <p/>
<!-- globalinfo-end -->
*
<!-- technical-bibtex-start -->
* BibTeX:
* <pre>
* &#64;article{Quinlan1986,
*    author = {R. Quinlan},
*    journal = {Machine Learning},
*    number = {1},
*    pages = {81-106},
*    title = {Inction of decision trees},
*    volume = {1},
*    year = {1986}
* }
* </pre>
* <p/>
<!-- technical-bibtex-end -->
*
<!-- options-start -->
* Valid options are: <p/>
*
* <pre> -D
*  If set, classifier is run in debug mode and
*  may output additional info to the console</pre>
*
<!-- options-end -->
*
* @author Eibe Frank ([email protected])
* @version $Revision: 6404 $
*/
public class Id3
extends Classifier
implements TechnicalInformationHandler, Sourcable {
/** for serialization */
static final long serialVersionUID = -2693678647096322561L;
/** The node's successors. */
private Id3[] m_Successors;
/** Attribute used for splitting. */
private Attribute m_Attribute;
/** Class value if node is leaf. */
private double m_ClassValue;
/** Class distribution if node is leaf. */
private double[] m_Distribution;
/** Class attribute of dataset. */
private Attribute m_ClassAttribute;
/**
* Returns a string describing the classifier.
* @return a description suitable for the GUI.
*/
public String globalInfo() {
return  "Class for constructing an unpruned decision tree based on the ID3 "
+ "algorithm. Can only deal with nominal attributes. No missing values "
+ "allowed. Empty leaves may result in unclassified instances. For more "
+ "information see: 

"
+ getTechnicalInformation().toString();
}
/**
* Returns an instance of a TechnicalInformation object, containing
* detailed information about the technical background of this class,
* e.g., paper reference or book this class is based on.
*
* @return the technical information about this class
*/
public TechnicalInformation getTechnicalInformation() {
TechnicalInformation    result;
result = new TechnicalInformation(Type.ARTICLE);
result.setValue(Field.AUTHOR, "R. Quinlan");
result.setValue(Field.YEAR, "1986");
result.setValue(Field.TITLE, "Inction of decision trees");
result.setValue(Field.JOURNAL, "Machine Learning");
result.setValue(Field.VOLUME, "1");
result.setValue(Field.NUMBER, "1");
result.setValue(Field.PAGES, "81-106");
return result;
}
/**
* Returns default capabilities of the classifier.
*
* @return      the capabilities of this classifier
*/
public Capabilities getCapabilities() {
Capabilities result = super.getCapabilities();
result.disableAll();
// attributes
result.enable(Capability.NOMINAL_ATTRIBUTES);
// class
result.enable(Capability.NOMINAL_CLASS);
result.enable(Capability.MISSING_CLASS_VALUES);
// instances
result.setMinimumNumberInstances(0);
return result;
}
/**
* Builds Id3 decision tree classifier.
*
* @param data the training data
* @exception Exception if classifier can't be built successfully
*/
public void buildClassifier(Instances data) throws Exception {
// can classifier handle the data?
getCapabilities().testWithFail(data);
// remove instances with missing class
data = new Instances(data);
data.deleteWithMissingClass();
makeTree(data);
}
/**
* Method for building an Id3 tree.
*
* @param data the training data
* @exception Exception if decision tree can't be built successfully
*/
private void makeTree(Instances data) throws Exception {
// Check if no instances have reached this node.
if (data.numInstances() == 0) {
m_Attribute = null;
m_ClassValue = Instance.missingValue();
m_Distribution = new double[data.numClasses()];
return;
}
// Compute attribute with maximum information gain.
double[] infoGains = new double[data.numAttributes()];
Enumeration attEnum = data.enumerateAttributes();
while (attEnum.hasMoreElements()) {
Attribute att = (Attribute) attEnum.nextElement();
infoGains[att.index()] = computeInfoGain(data, att);
}
m_Attribute = data.attribute(Utils.maxIndex(infoGains));
// Make leaf if information gain is zero.
// Otherwise create successors.
if (Utils.eq(infoGains[m_Attribute.index()], 0)) {
m_Attribute = null;
m_Distribution = new double[data.numClasses()];
Enumeration instEnum = data.enumerateInstances();
while (instEnum.hasMoreElements()) {
Instance inst = (Instance) instEnum.nextElement();
m_Distribution[(int) inst.classValue()]++;
}
Utils.normalize(m_Distribution);
m_ClassValue = Utils.maxIndex(m_Distribution);
m_ClassAttribute = data.classAttribute();
} else {
Instances[] splitData = splitData(data, m_Attribute);
m_Successors = new Id3[m_Attribute.numValues()];
for (int j = 0; j < m_Attribute.numValues(); j++) {
m_Successors[j] = new Id3();
m_Successors[j].makeTree(splitData[j]);
}
}
}
/**
* Classifies a given test instance using the decision tree.
*
* @param instance the instance to be classified
* @return the classification
* @throws  if instance has missing values
*/
public double classifyInstance(Instance instance)
throws  {
if (instance.hasMissingValue()) {
throw new ("Id3: no missing values, "
+ "please.");
}
if (m_Attribute == null) {
return m_ClassValue;
} else {
return m_Successors[(int) instance.value(m_Attribute)].
classifyInstance(instance);
}
}
/**
* Computes class distribution for instance using decision tree.
*
* @param instance the instance for which distribution is to be computed
* @return the class distribution for the given instance
* @throws  if instance has missing values
*/
public double[] distributionForInstance(Instance instance)
throws  {
if (instance.hasMissingValue()) {
throw new ("Id3: no missing values, "
+ "please.");
}
if (m_Attribute == null) {
return m_Distribution;
} else {
return m_Successors[(int) instance.value(m_Attribute)].
distributionForInstance(instance);
}
}
/**
* Prints the decision tree using the private toString method from below.
*
* @return a textual description of the classifier
*/
public String toString() {
if ((m_Distribution == null) && (m_Successors == null)) {
return "Id3: No model built yet.";
}
return "Id3

" + toString(0);
}
/**
* Computes information gain for an attribute.
*
* @param data the data for which info gain is to be computed
* @param att the attribute
* @return the information gain for the given attribute and data
* @throws Exception if computation fails
*/
private double computeInfoGain(Instances data, Attribute att)
throws Exception {
double infoGain = computeEntropy(data);
Instances[] splitData = splitData(data, att);
for (int j = 0; j < att.numValues(); j++) {
if (splitData[j].numInstances() > 0) {
infoGain -= ((double) splitData[j].numInstances() /
(double) data.numInstances()) *
computeEntropy(splitData[j]);
}
}
return infoGain;
}
/**
* Computes the entropy of a dataset.
*
* @param data the data for which entropy is to be computed
* @return the entropy of the data's class distribution
* @throws Exception if computation fails
*/
private double computeEntropy(Instances data) throws Exception {
double [] classCounts = new double[data.numClasses()];
Enumeration instEnum = data.enumerateInstances();
while (instEnum.hasMoreElements()) {
Instance inst = (Instance) instEnum.nextElement();
classCounts[(int) inst.classValue()]++;
}
double entropy = 0;
for (int j = 0; j < data.numClasses(); j++) {
if (classCounts[j] > 0) {
entropy -= classCounts[j] * Utils.log2(classCounts[j]);
}
}
entropy /= (double) data.numInstances();
return entropy + Utils.log2(data.numInstances());
}
/**
* Splits a dataset according to the values of a nominal attribute.
*
* @param data the data which is to be split
* @param att the attribute to be used for splitting
* @return the sets of instances proced by the split
*/
private Instances[] splitData(Instances data, Attribute att) {
Instances[] splitData = new Instances[att.numValues()];
for (int j = 0; j < att.numValues(); j++) {
splitData[j] = new Instances(data, data.numInstances());
}
Enumeration instEnum = data.enumerateInstances();
while (instEnum.hasMoreElements()) {
Instance inst = (Instance) instEnum.nextElement();
splitData[(int) inst.value(att)].add(inst);
}
for (int i = 0; i < splitData.length; i++) {
splitData[i].compactify();
}
return splitData;
}
/**
* Outputs a tree at a certain level.
*
* @param level the level at which the tree is to be printed
* @return the tree as string at the given level
*/
private String toString(int level) {
StringBuffer text = new StringBuffer();
if (m_Attribute == null) {
if (Instance.isMissingValue(m_ClassValue)) {
text.append(": null");
} else {
text.append(": " + m_ClassAttribute.value((int) m_ClassValue));
}
} else {
for (int j = 0; j < m_Attribute.numValues(); j++) {
text.append("
");
for (int i = 0; i < level; i++) {
text.append("|  ");
}
text.append(m_Attribute.name() + " = " + m_Attribute.value(j));
text.append(m_Successors[j].toString(level + 1));
}
}
return text.toString();
}
/**
* Adds this tree recursively to the buffer.
*
* @param id          the unqiue id for the method
* @param buffer      the buffer to add the source code to
* @return            the last ID being used
* @throws Exception  if something goes wrong
*/
protected int toSource(int id, StringBuffer buffer) throws Exception {
int                 result;
int                 i;
int                 newID;
StringBuffer[]      subBuffers;
buffer.append("
");
buffer.append("  protected static double node" + id + "(Object[] i) {
");
// leaf?
if (m_Attribute == null) {
result = id;
if (Double.isNaN(m_ClassValue)) {
buffer.append("    return Double.NaN;");
} else {
buffer.append("    return " + m_ClassValue + ";");
}
if (m_ClassAttribute != null) {
buffer.append(" // " + m_ClassAttribute.value((int) m_ClassValue));
}
buffer.append("
");
buffer.append("  }
");
} else {
buffer.append("    checkMissing(i, " + m_Attribute.index() + ");

");
buffer.append("    // " + m_Attribute.name() + "
");
// subtree calls
subBuffers = new StringBuffer[m_Attribute.numValues()];
newID = id;
for (i = 0; i < m_Attribute.numValues(); i++) {
newID++;
buffer.append("    ");
if (i > 0) {
buffer.append("else ");
}
buffer.append("if (((String) i[" + m_Attribute.index()
+ "]).equals("" + m_Attribute.value(i) + ""))
");
buffer.append("      return node" + newID + "(i);
");
subBuffers[i] = new StringBuffer();
newID = m_Successors[i].toSource(newID, subBuffers[i]);
}
buffer.append("    else
");
buffer.append("      throw new IllegalArgumentException("Value '" + i["
+ m_Attribute.index() + "] + "' is not allowed!");
");
buffer.append("  }
");
// output subtree code
for (i = 0; i < m_Attribute.numValues(); i++) {
buffer.append(subBuffers[i].toString());
}
subBuffers = null;
result = newID;
}
return result;
}
/**
* Returns a string that describes the classifier as source. The
* classifier will be contained in a class with the given name (there may
* be auxiliary classes),
* and will contain a method with the signature:
* <pre><code>
* public static double classify(Object[] i);
* </code></pre>
* where the array <code>i</code> contains elements that are either
* Double, String, with missing values represented as null. The generated
* code is public domain and comes with no warranty. <br/>
* Note: works only if class attribute is the last attribute in the dataset.
*
* @param className the name that should be given to the source class.
* @return the object source described by a string
* @throws Exception if the source can't be computed
*/
public String toSource(String className) throws Exception {
StringBuffer        result;
int                 id;
result = new StringBuffer();
result.append("class " + className + " {
");
result.append("  private static void checkMissing(Object[] i, int index) {
");
result.append("    if (i[index] == null)
");
result.append("      throw new IllegalArgumentException("Null values "
+ "are not allowed!");
");
result.append("  }

");
result.append("  public static double classify(Object[] i) {
");
id = 0;
result.append("    return node" + id + "(i);
");
result.append("  }
");
toSource(id, result);
result.append("}
");
return result.toString();
}
/**
* Returns the revision string.
*
* @return        the revision
*/
public String getRevision() {
return RevisionUtils.extract("$Revision: 6404 $");
}
/**
* Main method.
*
* @param args the options for the classifier
*/
public static void main(String[] args) {
runClassifier(new Id3(), args);
}
}

㈡ 哪里可以下载weka软件啊

http://www.cs.waikato.ac.nz/ml/weka/

㈢ C4.5算法,请问哪里可以下载到C4.5的windows版本源代码多谢多谢~~

是的,weka是开源的. 记得我用过的那个版本在安装目录的bin文件夹里有一个weka.jar, 解压后得到的就是源码. c4.5在weka里的实现是j48, 大致是这个路径吧:weka.classifiers.trees.j48

您可以把整个weka.jar作为外部library导入类似Eclipse这样的开发环境, 这样看源码或者用weka的api进行二次开发都很方便的.

㈣ weka的聚类（clusterers）的那个可视化界面，它的源代码在weka具体的哪个包里面

我能给你的帮助仅限于这个路径： weka.gui.explorer 包下面的 clustererPanel.class，至于怎么抽取出来，你就把这个包的explorer.class设置一下debug调试的开始程序，然后自己摸索一下吧。

㈤ 数据挖掘用什么软件，求软件名称加下载地址！

weka是一个不错的开源的基于java写的数据挖掘软件，里面很多的算法直接可以使用，同时你也可以利用这些java包进行二次开发。http://www.cs.waikato.ac.nz/ml/weka/是其官方网站，里面可以下载最新的weka供你使用。
sql server也是一个不错的数据挖掘软件，但是貌似只有开发版的才有这个功能。所以要去找开发版进行下载，verycd上面很多资源可供下载。希望能帮到你。

㈥ 我装的是WEKA3.6.8和JDK1.7，运行WEKA的时候提示 class not found program will exit

配置：
先下载weka开发包，在安装目录下有个weka-src.jar包（源代码）和weka.jar包（可执行文件），将weka-src.jar包解压，然后把\weka-src\src\main\java\weka文件夹拖入到waka工程的src目录下.将weka.jar文件解压后，将\weka\weka文件夹拷贝到weka工程磁盘目录下的bin文件夹下。然后在所建工程的Build Path中把weka_javacodes.jar导入。最后在myeclipse或eclipse中编写代码运行即可。

㈦ 最近想学习数据挖掘，请问有基于weka的聚类算法的源码实现吗

我最近刚开始接触数据挖掘，在学习kmeans，由于随着kmeans中心的随机改动，聚类结果有些不合理的变化，所以正在试图将初始中心定下来

㈧ weka能否进行实例过滤

这个肯定是有的。不知道你是用weka作编程开发还是只用GUI作数据挖掘

如果是用GUI的话如图就是选择一种FILTER实现过滤实例（对原始数据进行预处理），可以看到filter有监督的和非监督的，你可以根据需求选择对应的filter，选好后点击那个filter的框就可以设置具体参数和规则什么的

如果你是用weka作开发，http://weka.sourceforge.net/doc.stable/这个是weka的API可以看到weka.filters的包然后具体的应用你自己看API就可以了

如果用GUI选择filter选晕了不知道用哪个那也去看看API吧解释的还是可以的是在不行去下载一个weka的源码看看注释不过全是E文

㈨ Weka搭建过程中向安装好的Eclipse导入源代码怎么老是失败

你先把weka-src解压缩，
在里面
找到一个名为weka的
文件夹
，(有好几个，注意一下)找到那个包含所有运行文件的那个，直接拖到所建工程的src下就可以了

㈩ 你在哪下载的weka啊用的怎么样

在weka的官方网站啊 weka源代码开放 纯java的 适合搞科研 实验什么的 挺实用的 不用自己编算法了 直接调用里面的函数