package?algorithm;

import?java.io.IOException;
import?java.util.HashMap;
import?java.util.Iterator;
import?java.util.List;
import?java.util.Map;

import?script.FileHandler;
import?script.StringHandler;
import?util.Conf;
import?util.Tool;
import?word2vec.main.java.com.ansj.vec.Word2VEC;

public?class?Model?{

	/**
	?*?input:docList1docList2?主方法入口及控制器
	?*/
	public?void?run（List?docList1?List?docList2?Word2VEC?w）?{
		int?i?j?n1?n2;
		double[]?similarArr;
		int[]?locArr;
		double?max?temp;
		int?loc;
		n1?=?docList1.size（）;
		n2?=?docList2.size（）;
		similarArr?=?new?double[n1];
		locArr?=?new?int[n1];
		for?（i?=?0;?i?			max?=?0.0;
			temp?=?0.0;
			loc?=?0;
			for?（j?=?0;?j?				try?{
					temp?=?getSimilar（docList1.get（i）?docList2.get（j）?w）;
				}?catch?（IOException?e）?{
					temp?=?0.0;
					e.printStackTrace（）;
				}
				if?（temp?>?max）?{
					max?=?temp;
					loc?=?j;
				}
			}
			similarArr[i]?=?max;
			locArr[i]?=?loc;
		}
		Tool.output（docList1?docList2?locArr?similarArr）;
	}

	/**
	?*?input:str1str2?計算2個字符串之間的相似度
	?*/
	public?double?getSimilar（String?str1?String?str2?Word2VEC?w）?throws?IOException?{

		double?ret?=?0.0;
		//?創(chuàng)建向量空間模型，使用map實現(xiàn)，主鍵為詞項，值為長度為2的數(shù)組，存放著對應(yīng)詞項在字符串中的出現(xiàn)次數(shù)
		Map?vectorSpace?=?new?HashMap（）;
		int[]?itemCountArray?=?null;//?為了避免頻繁產(chǎn)生局部變量，所以將itemCountArray聲明在此
		Iterator?iter;
		double?vector1Modulo?=?0.00;//?向量1的模
		double?vector2Modulo?=?0.00;//?向量2的模
		double?vectorProduct?=?0.00;?//?向量積
		List?list1list1_templist2list2_temptemp1temp2;
		
		StringHandler?sh?=?new?StringHandler（）;
		
		list1_temp?=?sh.stringToArray（str1）;
		list2_temp?=?sh.stringToArray（str2）;
		
		/*
		//使用word2vec擴充語義
		temp1?=?sh.stringToArray（str1）;
		temp2?=?sh.stringToArray（str2）;
		list1?=?sh.extendWord（w?temp1）;
		list2?=?sh.extendWord（w?temp2）;
		*/
		list1?=?sh.deleteStopWords（list1_temp?Conf.stopWordsPath）;
		list2?=?sh.deleteStopWords（list2_temp?Conf.stopWordsPath）;
		
		int?in;
		n?=?list1.size（）;
		for?（i?=?0;?i?			if?（vectorSpace.containsKey（list1.get（i）））
				++（vectorSpace.get（list1.get（i））[0]）;
			else?{
				itemCountArray?=?new?int[2];
				itemCountArray[0]?=?1;
				itemCountArray[1]?=?0;
				vectorSpace.put（list1.get（i）?itemCountArray）;
			}
		}
		
		//?對str2處理

		n?=?list2.size（）;
		for?（i?=?0;?i?			if?（vectorSpace.containsKey（list2.get（i）））
				++（vectorSpace.get（list2.get（i））[1]）;
			else?{
				itemCountArray?=?new?int[2];
				itemCountArray[0]?=?0;
				itemCountArray[1]?=?1;
				vectorSpace.put（list2.get（i）?itemCountArray）;
			}
		}

		//?計算相似度
		iter?=?vectorSpace.entrySet（）.iterator（）;
		while?（iter.hasNext（））?{
			Map.Entry?entry?=?（Map.Entry）?iter.next（）;
			itemCountArray?=?（int[]）?entry.getValue（）;
			vector1Modulo?+=?itemCountArray[0]?*?itemCountArray[0];
			vector2Modulo?+=?itemCountAr

?屬性????????????大小?????日期????時間???名稱
-----------?---------??----------?-----??----

?????文件????????395??2017-01-20?11:37??DocDistance\.classpath

?????文件????????387??2017-01-20?11:37??DocDistance\.project

?????文件????????138??2017-01-20?11:37??DocDistance\.settings\org.eclipse.core.resources.prefs

?????文件????????598??2017-01-20?11:37??DocDistance\.settings\org.eclipse.jdt.core.prefs

?????文件???????3807??2017-01-20?11:37??DocDistance\bin\algorithm\Model.class

?????文件???????2387??2017-01-20?11:37??DocDistance\bin\script\FileHandler.class

?????文件???????2497??2017-01-20?11:37??DocDistance\bin\script\runTest.class

?????文件???????3661??2017-01-20?11:37??DocDistance\bin\script\StringHandler.class

?????文件???????1173??2017-01-20?11:37??DocDistance\bin\script\test.class

?????文件????????431??2017-01-20?11:37??DocDistance\bin\util\Conf.class

?????文件???????3267??2017-01-20?11:37??DocDistance\bin\util\Tool.class

?????文件????????446??2017-01-20?11:37??DocDistance\bin\word2vec\main\java\com\ansj\vec\domain\HiddenNeuron.class

?????文件????????890??2017-01-20?11:37??DocDistance\bin\word2vec\main\java\com\ansj\vec\domain\Neuron.class

?????文件???????1283??2017-01-20?11:37??DocDistance\bin\word2vec\main\java\com\ansj\vec\domain\WordEntry.class

?????文件???????2063??2017-01-20?11:37??DocDistance\bin\word2vec\main\java\com\ansj\vec\domain\WordNeuron.class

?????文件??????13008??2017-01-20?11:37??DocDistance\bin\word2vec\main\java\com\ansj\vec\Learn.class

?????文件???????1688??2017-01-20?11:37??DocDistance\bin\word2vec\main\java\com\ansj\vec\util\Haffman.class

?????文件???????3036??2017-01-20?11:37??DocDistance\bin\word2vec\main\java\com\ansj\vec\util\MapCount.class

?????文件???????1630??2017-01-20?11:37??DocDistance\bin\word2vec\main\java\com\ansj\vec\util\WordKmeans$Classes$1.class

?????文件???????3392??2017-01-20?11:37??DocDistance\bin\word2vec\main\java\com\ansj\vec\util\WordKmeans$Classes.class

?????文件???????3680??2017-01-20?11:37??DocDistance\bin\word2vec\main\java\com\ansj\vec\util\WordKmeans.class

?????文件???????9617??2017-01-20?11:37??DocDistance\bin\word2vec\main\java\com\ansj\vec\Word2VEC.class

?????文件??????10721??2017-01-20?11:37??DocDistance\brand_ext.dic

?????文件???????1172??2017-01-20?11:37??DocDistance\color_ext.dic

?????文件??????19239??2017-01-20?11:04??DocDistance\data\result\out1_1.txt

?????文件??????17407??2017-01-20?11:05??DocDistance\data\result\out1_2.txt

?????文件??????15407??2017-01-20?11:09??DocDistance\data\result\out1_3.txt

?????文件??????10116??2017-01-20?11:13??DocDistance\data\result\out2_3.txt

?????文件??????80648??2017-01-20?11:29??DocDistance\data\result\out3_1.txt

?????文件??????73147??2017-01-20?11:26??DocDistance\data\result\out3_2.txt

............此處省略62個文件信息