gSkeletonClu: Revealing Density-Based Clustering Structure from the Core-Connected Tree of a Network

完成的主要是将一个文件的格式转换到另一格式，然后用gSkeletonClu的程序运行后，再讲结果转换到这种格式，并填写运行的结果。

所给的格式是：

Source;Target;Type;Id;Label;Weight

所要用的数据是source和target，weight

但是在这个格式里source和target均是字符串型，所以需要转换为整型

且所需的格式里，应该是id从0或1开始，且连续

即，先按照source排序，相同source的，按照target排序；

最后需要的格式是：id，id，weight

其中id需要转换到原source或者target的值

public class ReadgSkeletonClu是主要方法实现；

public class GenerateNeedDataTest 产生所需数据

public class ReBuildCSVTest 从运行结果产生最后的数据

包含类class Subgraph

class Point

class FinalData

class PointToCluster

public class ReadgSkeletonClu

package gSkeletonCluTest;

import java.io.BufferedReader;
import java.io.File;
import java.io.FileInputStream;
import java.io.FileOutputStream;
import java.io.FileReader;
import java.io.FileWriter;
import java.io.IOException;
import java.io.InputStreamReader;
import java.io.PrintWriter;
import java.io.RandomAccessFile;
import java.util.ArrayList;
import java.util.Collections;
import java.util.Comparator;
import java.util.Iterator;
import java.util.List;

/**
* @author zhaodeng
*
*/
public class ReadgSkeletonClu {

List<String> sourceList = new ArrayList<String>();
List<Subgraph> graphDataList = new ArrayList<Subgraph>();
List<Subgraph> neededGraphDataList = new ArrayList<Subgraph>();
List<Point> pointList = new ArrayList<Point>();
List<FinalData> finalDatas = new ArrayList<FinalData>();

List<PointToCluster> pointToClusters = new ArrayList<PointToCluster>();

/**
* @param fileName
*            读取最开始的csv文件，产生List<Subgraph> graphDataList
*/
public List<Subgraph> readFileByLines(String fileName) {
File file = new File(fileName);
BufferedReader reader = null;
try {
reader = new BufferedReader(new FileReader(file));
String tempString = null;
int line = 1;
while ((tempString = reader.readLine()) != null) {
// System.out.println(tempString);
if (line != 1) {
String tempSplitString[] = tempString.split(";");
Subgraph subgraph = new Subgraph(tempSplitString[0],
tempSplitString[1], tempSplitString[2],
Integer.valueOf(tempSplitString[3]),
tempSplitString[4],
Integer.valueOf(tempSplitString[5]));
graphDataList.add(subgraph);
}

// System.out.println("line " + line + ": " + tempString);
line++;
}
// System.out.println("line's number: " + line);
reader.close();
} catch (IOException e) {
e.printStackTrace();
} finally {
if (reader != null) {
try {
reader.close();
} catch (IOException e1) {
}
}
}
return graphDataList;
}

/*
* 根据读取文件产生的List<Subgraph> graphDataList，进行source和target的转换，
* 重新生成新的List<Subgraph> neededGraphDataList
*/
public List<Subgraph> generateNeededGraph(List<Subgraph> graphDataList) {

int id = 1;
for (Subgraph subgraph : graphDataList) {
Subgraph tmpSubgraph = subgraph;
boolean ifSourceExist = false; // 不存在
boolean ifTargetExist = false;
for (Point point : pointList) {
if (subgraph.getSource().equals(point.getName())) {
ifSourceExist = true;
tmpSubgraph.setSource(String.valueOf(point.getId()));

}
if (subgraph.getTarget().equals(point.getName())) {
ifTargetExist = true;
tmpSubgraph.setTarget(String.valueOf(point.getId()));
}
}
if (!ifSourceExist) {
Point point = new Point(subgraph.getSource(), id++);
pointList.add(point);
tmpSubgraph.setSource(String.valueOf(point.getId()));
}
if (!ifTargetExist) {
Point point = new Point(subgraph.getTarget(), id++);
pointList.add(point);
tmpSubgraph.setTarget(String.valueOf(point.getId()));
}
neededGraphDataList.add(tmpSubgraph);
// System.out.println(tmpSubgraph.getSource() + ";"+
// tmpSubgraph.getTarget());
}// for
return neededGraphDataList;
}

/*
* 根据转换后的List<Subgraph> neededGraphDataList，来提取程序运行所需的格式 int source;int
* target;int weight; 生成List<FinalData> finalDatas
*/
public List<FinalData> generateFinalData(List<Subgraph> neededGraphDataList) {
for (Subgraph subgraph : neededGraphDataList) {
FinalData finalData = null;
if (Integer.valueOf(subgraph.getSource()) < Integer
.valueOf(subgraph.getTarget())) {
finalData = new FinalData(
Integer.valueOf(subgraph.getSource()),
Integer.valueOf(subgraph.getTarget()),
subgraph.getWeight());
finalDatas.add(finalData);
} else if (Integer.valueOf(subgraph.getSource()) > Integer
.valueOf(subgraph.getTarget())) {
finalData = new FinalData(
Integer.valueOf(subgraph.getTarget()),
Integer.valueOf(subgraph.getSource()),
subgraph.getWeight());
finalDatas.add(finalData);
}
}

// 排序
ComparatorFinalData comparator = new ComparatorFinalData();
Collections.sort(finalDatas, comparator);
return finalDatas;
}

/*
* 以最后产生的List<FinalData> finalDatas， 写入fileName.txt文件，去运行结果
*/
public void generatefinalDatasFile(List<FinalData> finalDatas,
String fileName) throws IOException {
File myFilePath = new File(fileName.toString());
if (myFilePath.exists()) { // 如果该文件存在,则删除
myFilePath.delete();
} else {
myFilePath.createNewFile();
}

for (FinalData finalData : finalDatas) {
String addFileContent = finalData.getSource() + " "
+ finalData.getTarget() + " " + finalData.getWeight();
addToFile(fileName, addFileContent);
}
}

/*
* 以运行结果1.txt文件来重新生成
*/
public void generateNewBiggestSubGraphFile(List<Subgraph> subgraphs,
String fileName) {
File myFilePath = new File(fileName.toString());
if (myFilePath.exists()) { // 如果该文件存在,则删除
myFilePath.delete();
}
for (Subgraph subgraph : subgraphs) {
String subgraphString = subgraph.getSource() + ";"
+ subgraph.getTarget() + ";" + subgraph.getType() + ";"
+ String.valueOf(subgraph.getId()) + ";"
+ subgraph.getLable() + ";"
+ String.valueOf(subgraph.getWeight());
addToFile(fileName, subgraphString);
}
}

public static void addToFile(String filePathAndName, String fileContent) {
try {
File myFilePath = new File(filePathAndName.toString());
// if (!myFilePath.exists()) { // 如果该文件不存在,则创建
// myFilePath.createNewFile();
// }
// FileWriter(myFilePath, true); //实现不覆盖追加到文件里

// FileWriter(myFilePath); 覆盖掉原来的内容
FileWriter resultFile = new FileWriter(myFilePath, true);
PrintWriter myFile = new PrintWriter(resultFile);
// 给文件里面写内容,原来的会覆盖掉
myFile.println(fileContent);
resultFile.close();
} catch (Exception e) {
e.printStackTrace();
}
}

public List<PointToCluster> ReadFileByLines(String fileName) {
File file = new File(fileName);
BufferedReader reader = null;
try {
reader = new BufferedReader(new FileReader(file));
String tempString = null;
// int line = 1;
while ((tempString = reader.readLine()) != null) {
// System.out.println("line " + line + ": " + tempString);
// line++;
String tmpSplitString[] = tempString.split(" ", 2);
PointToCluster pointToCluster = new PointToCluster(
Integer.valueOf(tmpSplitString[0].trim()),
Integer.valueOf(tmpSplitString[1].trim()));
pointToClusters.add(pointToCluster);
}
reader.close();
} catch (IOException e) {
e.printStackTrace();
} finally {
if (reader != null) {
try {
reader.close();
} catch (IOException e1) {
}
}
}
return pointToClusters;
}

/*
* 根据最后运行的1.txt文件产生的List<PointToCluster>，来产生最后所需的graph文件 包含了lable，并且原点不变
*/
public List<Subgraph> writeToSubgraph(List<PointToCluster> pointToClusters) {
for (Subgraph subgraph : neededGraphDataList) {
String lable = "";
for (PointToCluster pointToCluster : pointToClusters) {
if (String.valueOf(pointToCluster.getId()).equals(
subgraph.getSource())) {
lable = String.valueOf(pointToCluster.getClusterId());
lable += "(p1)";
}
}
for (PointToCluster pointToCluster : pointToClusters) {
if (String.valueOf(pointToCluster.getId()).equals(
subgraph.getTarget())) {
lable += String.valueOf(pointToCluster.getClusterId());
lable += "(p2)";
}
}
subgraph.setLable(lable);
}
for (Subgraph subgraph : neededGraphDataList) {
for (Point point : pointList) {
if (subgraph.getSource().equals(String.valueOf(point.getId()))) {
subgraph.setSource(point.getName());
}
if (subgraph.getTarget().equals(String.valueOf(point.getId()))) {
subgraph.setTarget(point.getName());
}
}
}
return neededGraphDataList;
}

// 比较排序,因为程序运行时要求是：点连续，是指第一列的点连续，第二列的点从小到大
class ComparatorFinalData implements Comparator {
public int compare(Object arg0, Object arg1) {
FinalData data1 = (FinalData) arg0;
FinalData data2 = (FinalData) arg1;

int flag = Integer.valueOf(data1.getSource()).compareTo(
Integer.valueOf(data2.getSource()));
if (flag == 0) {
return Integer.valueOf(data1.getTarget()).compareTo(
Integer.valueOf(data2.getTarget()));
} else {
return flag;
}
}
}

// 产生最后的文件：id，点（原来的），clutster
public void newGeneratePointData(List<PointToCluster> pointToClusters,
String resultFileName, String read2fileName) {
File myFilePath = new File(resultFileName.toString());
if (myFilePath.exists()) { // 如果该文件存在,则删除
myFilePath.delete();
}
// maxcluster
int maxcluster = 0;
for (PointToCluster pointToCluster : pointToClusters) {
if (pointToCluster.getClusterId() > maxcluster) {
maxcluster = pointToCluster.getClusterId();
}
}

// 读取hubs和outliers
File file = new File(read2fileName);
BufferedReader reader = null;
try {
reader = new BufferedReader(new FileReader(file));
String tempString = null;
while ((tempString = reader.readLine()) != null) {
if (tempString.contains("hubs:")) {
maxcluster++;
String hubsString = tempString.substring(6);
String tempSplitString[] = hubsString.split("  ");
for (int i = 0; i < tempSplitString.length; i++) {
PointToCluster hub = new PointToCluster(
Integer.valueOf(tempSplitString[i].trim()),
maxcluster);
pointToClusters.add(hub);
}
}
if (tempString.contains("outliers:")) {
maxcluster++;
String outliersString = tempString.substring(10);
String tempSplitString[] = outliersString.split("  ");
for (int i = 0; i < tempSplitString.length; i++) {
PointToCluster outlier = new PointToCluster(
Integer.valueOf(tempSplitString[i].trim()),
maxcluster);
pointToClusters.add(outlier);
}
}
}
reader.close();
} catch (IOException e) {
e.printStackTrace();
} finally {
if (reader != null) {
try {
reader.close();
} catch (IOException e1) {
}
}
}

// 从cluster写入最后的格式
String title = "Id;Lable;Modularity Class";
addToFile(resultFileName, title);
for (PointToCluster pointToCluster : pointToClusters) {
for (Point point : pointList) {
if (point.getId() == pointToCluster.getId()) {
String addIdPointToCluster = point.getName() + ";"
+ point.getName() + ";"
+ pointToCluster.getClusterId();
addToFile(resultFileName, addIdPointToCluster);
}
}
}

}

}

public class GenerateNeedDataTest

package gSkeletonCluTest;

import gSkeletonCluTest.ReadgSkeletonClu.ComparatorFinalData;

import java.io.IOException;
import java.util.Collections;
import java.util.List;

/**
* @author zhaodeng
*
*/
public class GenerateNeedDataTest {

public static void main(String[] args) throws IOException {
// TODO Auto-generated method stub

ReadgSkeletonClu readgSkeletonClu = new ReadgSkeletonClu();
String fileName = "E:/gSkeletonClu_project/dataFile/Biggest_SubGraph_e.csv";
String finalFileName = "E:/gSkeletonClu_project/dataFile/karate.pairs";

List<Subgraph> graphDataList = readgSkeletonClu
.readFileByLines(fileName);
List<Subgraph> neededGraphDataList = readgSkeletonClu
.generateNeededGraph(graphDataList);
// 生成所需数据格式
List<FinalData> finalDatas = readgSkeletonClu
.generateFinalData(neededGraphDataList);

// 生成所需数据karate.pairs
System.out.println("building the karate.pairs ... please wait ...");
readgSkeletonClu.generatefinalDatasFile(finalDatas, finalFileName);
System.out.println("build the karate.pairs successful! ");
}
}

public class ReBuildCSVTest

package gSkeletonCluTest;

import java.io.File;
import java.util.List;

/**
* @author zhaodeng
*
*/
public class ReBuildCSVTest {

/**
* @param args
*/
public static void main(String[] args) {
// TODO Auto-generated method stub

ReadgSkeletonClu readgSkeletonClu = new ReadgSkeletonClu();
String BiggestSubGraphPath = "E:/gSkeletonClu_project/dataFile/Biggest_SubGraph_e.csv";
String txt1 = "E:/gSkeletonClu_project/dataFile/1_new.txt";
String txt2 = "E:/gSkeletonClu_project/dataFile/2_new.txt";
String newBiggestSubGraphPath = "E:/gSkeletonClu_project/dataFile/Biggest_SubGraph_e_final.csv";

List<Subgraph> graphDataList = readgSkeletonClu
.readFileByLines(BiggestSubGraphPath);
List<Subgraph> neededGraphDataList = readgSkeletonClu
.generateNeededGraph(graphDataList);

List<PointToCluster> pointToClusters = readgSkeletonClu
.ReadFileByLines(txt1);

//		List<Subgraph> subgraphs = readgSkeletonClu
//				.writeToSubgraph(pointToClusters);

System.out
.println("building the Biggest_SubGraph_e_new.csv ... please wait ...");
readgSkeletonClu.newGeneratePointData(pointToClusters,
newBiggestSubGraphPath,txt2);
System.out.println("build the Biggest_SubGraph_e_new.csv successful!");
}

}

class Subgraph

package gSkeletonCluTest;
/**
* @author zhaodeng
*
*/
public class Subgraph {

String source;
String target;
String type;
int id;
String lable;
int weight;

public Subgraph() {
super();
}

public Subgraph(String source, String target, String type, int id,
String lable, int weight) {
super();
this.source = source;
this.target = target;
this.type = type;
this.id = id;
this.lable = lable;
this.weight = weight;
}

public String getSource() {
return source;
}
public void setSource(String source) {
this.source = source;
}
public String getTarget() {
return target;
}
public void setTarget(String target) {
this.target = target;
}
public String getType() {
return type;
}
public void setType(String type) {
this.type = type;
}
public int getId() {
return id;
}
public void setId(int id) {
this.id = id;
}
public String getLable() {
return lable;
}
public void setLable(String lable) {
this.lable = lable;
}
public int getWeight() {
return weight;
}
public void setWeight(int weight) {
this.weight = weight;
}

}

class Point

package gSkeletonCluTest;

/**
* @author zhaodeng
*
*/
public class Point {

String name;
int id;

public Point() {
super();
}

public Point(String name, int id) {
super();
this.name = name;
this.id = id;
}

public String getName() {
return name;
}

public void setName(String name) {
this.name = name;
}

public int getId() {
return id;
}

public void setId(int id) {
this.id = id;
}

}

class FinalData

package gSkeletonCluTest;

/**
* @author zhaodeng
*
*/
public class FinalData {

int source;
int target;
int weight;

public FinalData() {
super();
}

public FinalData(int source, int target, int weight) {
super();
this.source = source;
this.target = target;
this.weight = weight;
}

public int getSource() {
return source;
}

public void setSource(int source) {
this.source = source;
}

public int getTarget() {
return target;
}

public void setTarget(int target) {
this.target = target;
}

public int getWeight() {
return weight;
}

public void setWeight(int weight) {
this.weight = weight;
}

}

class PointToCluster

package gSkeletonCluTest;

/**
* @author zhaodeng
*
*/
public class PointToCluster {

int id;
int clusterId;

public PointToCluster() {
super();
}

public PointToCluster(int id, int clusterId) {
super();
this.id = id;
this.clusterId = clusterId;
}

public int getId() {
return id;
}

public void setId(int id) {
this.id = id;
}

public int getClusterId() {
return clusterId;
}

public void setClusterId(int clusterId) {
this.clusterId = clusterId;
}

}