vsmclassifydlg.cpp

用来文本分类的

// VSMClassifyDlg.cpp : implementation file
//

#include "stdafx.h"
#include "VSMClassify.h"
#include "VSMClassifyDlg.h"
#include "Shellapi.h"

#ifdef _DEBUG
#define new DEBUG_NEW
#undef THIS_FILE
static char THIS_FILE[] = __FILE__;
#endif

/////////////////////////////////////////////////////////////////////////////
// CAboutDlg dialog used for App About

class CAboutDlg : public CDialog
{
public:
	CAboutDlg();

// Dialog Data
	//{{AFX_DATA(CAboutDlg)
	enum { IDD = IDD_ABOUTBOX };
	//}}AFX_DATA

	// ClassWizard generated virtual function overrides
	//{{AFX_VIRTUAL(CAboutDlg)
	protected:
	virtual void DoDataExchange(CDataExchange* pDX);    // DDX/DDV support
	//}}AFX_VIRTUAL

// Implementation
protected:
	//{{AFX_MSG(CAboutDlg)
	//}}AFX_MSG
	DECLARE_MESSAGE_MAP()
};

CAboutDlg::CAboutDlg() : CDialog(CAboutDlg::IDD)
{
	//{{AFX_DATA_INIT(CAboutDlg)
	//}}AFX_DATA_INIT
}

void CAboutDlg::DoDataExchange(CDataExchange* pDX)
{
	CDialog::DoDataExchange(pDX);
	//{{AFX_DATA_MAP(CAboutDlg)
	//}}AFX_DATA_MAP
}

BEGIN_MESSAGE_MAP(CAboutDlg, CDialog)
	//{{AFX_MSG_MAP(CAboutDlg)
		// No message handlers
	//}}AFX_MSG_MAP
END_MESSAGE_MAP()

/////////////////////////////////////////////////////////////////////////////
// CVSMClassifyDlg dialog

CVSMClassifyDlg::CVSMClassifyDlg(CWnd* pParent /*=NULL*/)
	: CDialog(CVSMClassifyDlg::IDD, pParent)
{
	//{{AFX_DATA_INIT(CVSMClassifyDlg)
	m_fltWeight = 0.0f;
	m_nWordFrea = 1;
	m_fltCentral = 0.0f;
	m_strClassifyPath = _T("D:\\workshop\\VSMClassify\\resource\\testfile\\1.txt");
	m_strUpdatePath = _T("D:\\workshop\\VSMClassify\\resource\\Tree\\VSM.tree");
	m_strTrainPath = _T("D:\\workshop\\VSMClassify\\resource\\data");
	m_strTreePath = _T("D:\\workshop\\VSMClassify\\resource\\Tree\\VSM.tree");
	m_strResultPath = _T("D:\\workshop\\VSMClassify\\resource\\result\\result.txt");
	m_strIsTrainComplete = _T("");
	//}}AFX_DATA_INIT
	// Note that LoadIcon does not require a subsequent DestroyIcon in Win32
	m_hIcon = AfxGetApp()->LoadIcon(IDR_MAINFRAME);
	IsTrainOrUpdate=0;
}

void CVSMClassifyDlg::DoDataExchange(CDataExchange* pDX)
{
	CDialog::DoDataExchange(pDX);
	//{{AFX_DATA_MAP(CVSMClassifyDlg)
	DDX_Text(pDX, IDC_WEIGHT, m_fltWeight);
	DDX_Text(pDX, IDC_WORD_FREQ, m_nWordFrea);
	DDX_Text(pDX, IDC_CENTRAL, m_fltCentral);
	DDX_Text(pDX, IDC_CLASSIFYPATH, m_strClassifyPath);
	DDX_Text(pDX, IDC_UPDATEPATH, m_strUpdatePath);
	DDX_Text(pDX, IDC_TRAINPATH, m_strTrainPath);
	DDX_Text(pDX, IDC_SAVETREEPATH, m_strTreePath);
	DDX_Text(pDX, IDC_RESULTPATH, m_strResultPath);
	DDX_Text(pDX, IDC_ISCOMPLETETRAIN, m_strIsTrainComplete);
	//}}AFX_DATA_MAP
}

BEGIN_MESSAGE_MAP(CVSMClassifyDlg, CDialog)
	//{{AFX_MSG_MAP(CVSMClassifyDlg)
	ON_WM_SYSCOMMAND()
	ON_WM_PAINT()
	ON_WM_QUERYDRAGICON()
	ON_BN_CLICKED(IDC_CLASSIFY, OnClassify)
	ON_BN_CLICKED(IDC_TRAIN, OnTrain)
	ON_BN_CLICKED(IDC_UPDATE, OnUpdate)
	ON_BN_CLICKED(IDC_OPENCLASSIFY, OnOpenclassify)
	ON_BN_CLICKED(IDC_OPENUPDATE, OnOpenupdate)
	ON_BN_CLICKED(IDC_AUTOSLECTPARA, OnAutoslectpara)
	//}}AFX_MSG_MAP
END_MESSAGE_MAP()

/////////////////////////////////////////////////////////////////////////////
// CVSMClassifyDlg message handlers

BOOL CVSMClassifyDlg::OnInitDialog()
{
	CDialog::OnInitDialog();

	// Add "About..." menu item to system menu.

	// IDM_ABOUTBOX must be in the system command range.
	ASSERT((IDM_ABOUTBOX & 0xFFF0) == IDM_ABOUTBOX);
	ASSERT(IDM_ABOUTBOX < 0xF000);

	CMenu* pSysMenu = GetSystemMenu(FALSE);
	if (pSysMenu != NULL)
	{
		CString strAboutMenu;
		strAboutMenu.LoadString(IDS_ABOUTBOX);
		if (!strAboutMenu.IsEmpty())
		{
			pSysMenu->AppendMenu(MF_SEPARATOR);
			pSysMenu->AppendMenu(MF_STRING, IDM_ABOUTBOX, strAboutMenu);
		}
	}

	// Set the icon for this dialog.  The framework does this automatically
	//  when the application's main window is not a dialog
	SetIcon(m_hIcon, TRUE);			// Set big icon
	SetIcon(m_hIcon, FALSE);		// Set small icon
	
	// TODO: Add extra initialization here
	IntialTree();
	
	return TRUE;  // return TRUE  unless you set the focus to a control
}

void CVSMClassifyDlg::OnSysCommand(UINT nID, LPARAM lParam)
{
	if ((nID & 0xFFF0) == IDM_ABOUTBOX)
	{
		CAboutDlg dlgAbout;
		dlgAbout.DoModal();
	}
	else
	{
		CDialog::OnSysCommand(nID, lParam);
	}
}

// If you add a minimize button to your dialog, you will need the code below
//  to draw the icon.  For MFC applications using the document/view model,
//  this is automatically done for you by the framework.

void CVSMClassifyDlg::OnPaint() 
{
	if (IsIconic())
	{
		CPaintDC dc(this); // device context for painting

		SendMessage(WM_ICONERASEBKGND, (WPARAM) dc.GetSafeHdc(), 0);

		// Center icon in client rectangle
		int cxIcon = GetSystemMetrics(SM_CXICON);
		int cyIcon = GetSystemMetrics(SM_CYICON);
		CRect rect;
		GetClientRect(&rect);
		int x = (rect.Width() - cxIcon + 1) / 2;
		int y = (rect.Height() - cyIcon + 1) / 2;

		// Draw the icon
		dc.DrawIcon(x, y, m_hIcon);
	}
	else
	{
		CDialog::OnPaint();
	}
}

// The system calls this to obtain the cursor to display while the user drags
//  the minimized window.
HCURSOR CVSMClassifyDlg::OnQueryDragIcon()
{
	return (HCURSOR) m_hIcon;
}
void CVSMClassifyDlg::FindDirectoryFile(CString strDirectory,CString &strResult)
{
	CFileFind finder;
	CString strTemp;
	BOOL bWorking=finder.FindFile(strDirectory.GetBuffer(0));
	if(!bWorking)
	{
		AfxMessageBox("The file is not existed.");
		return;
	}
	else
	{
		bWorking=finder.FindNextFile();
		strTemp=strDirectory;
		strTemp.MakeLower();
		if(strTemp.Find(_T(".txt"))!=-1)
		{
			txtClassify->Classify(strDirectory.GetBuffer(0),strTemp);
			strTemp=strDirectory+"====="+strTemp;
			strResult=strResult+strTemp+"\n";
			return;
		}
	}
	//if not ,is a directory
	strTemp=strDirectory+"\\*";
	bWorking=finder.FindFile(strTemp.GetBuffer(0));
	if(!bWorking)
	{
		AfxMessageBox("The file is not existed.");
		return;
	}
	while(bWorking)
	{
		bWorking = finder.FindNextFile();
		if(finder.IsDots())
			continue;
		strTemp=finder.GetFilePath();
		FindDirectoryFile(strTemp,strResult);
	}		
}
double CVSMClassifyDlg::OnClassify() 
{
	UpdateData(TRUE);
	if(!IsTrainOrUpdate)
	{
		AfxMessageBox("Train or update first!");
		return 0;
	}
	//if m_strClassifyPath is a folder,classify all files in this folder
	CString strResult;
	FindDirectoryFile(m_strClassifyPath,strResult);
//	AfxMessageBox(strResult);
	//save the result to file
	FILE *fp;
	if((fp=fopen(m_strResultPath.GetBuffer(0),"w+b"))==NULL)
	{
		AfxMessageBox("the result file can not be opened .");
		return 0;
	}
	int nLen=strResult.GetLength();
	fwrite(strResult.GetBufferSetLength(nLen),1,nLen,fp);
	fclose(fp);

	//display the reslut;
	/*
	SHELLEXECUTEINFO sei;
    ZeroMemory(&sei, sizeof(SHELLEXECUTEINFO));
    sei.cbSize = sizeof(SHELLEXECUTEINFO);
    sei.hwnd = m_hWnd;
    sei.lpFile = m_strResultPath.GetBuffer(0);
    sei.lpVerb = "open";
    sei.nShow = SW_SHOW;
    ShellExecuteEx(&sei);
	*/
	double resultScore;
	txtClassify->veracity(&resultScore,m_strResultPath);
	CString str;
	str.Format("right rate:%f",resultScore);
	AfxMessageBox(str);
	return resultScore;
	

}

void CVSMClassifyDlg::OnTrain() 
{
	UpdateData(TRUE);
	m_strIsTrainComplete="please wait";
	UpdateData(FALSE);
	txtClassify->TrainTree(m_strTrainPath,m_nWordFrea,m_fltWeight,m_fltCentral);
	txtClassify->SaveTree(m_strTreePath.GetBuffer(0));
	IsTrainOrUpdate=true;
	m_strIsTrainComplete="complete training";
	UpdateData(FALSE);
	AfxMessageBox("complete training");

	
}

void CVSMClassifyDlg::OnUpdate() 
{
	UpdateData(TRUE);
	if(!txtClassify->UpdateTree(m_strUpdatePath.GetBuffer(0)))
	{
		AfxMessageBox("Update tree error");
		return;
	}
	IsTrainOrUpdate=true;
	AfxMessageBox("updated");
	
}

void CVSMClassifyDlg::OnOpenclassify() 
{
	// TODO: Add your control notification handler code here
		// TODO: Add your control notification handler code here
	CFileDialog fileDlg(TRUE, NULL,  NULL, OFN_HIDEREADONLY | OFN_OVERWRITEPROMPT, "TXT File(*.txt)|*.txt||", NULL );
	fileDlg.DoModal();
	m_strClassifyPath=fileDlg.GetPathName();
	UpdateData(FALSE);
	
}


void CVSMClassifyDlg::OnOpenupdate() 
{
	// TODO: Add your control notification handler code here
	CFileDialog fileDlg(TRUE, NULL,  NULL, OFN_HIDEREADONLY | OFN_OVERWRITEPROMPT, "TreeFile(*.tree)|*.tree||", NULL );
	fileDlg.DoModal();
	m_strUpdatePath=fileDlg.GetPathName();
	UpdateData(FALSE);
	
}



BOOL CVSMClassifyDlg::DestroyWindow() 
{
	// TODO: Add your specialized code here and/or call the base class
	//free the txtClassify
	delete txtClassify;
	
	return CDialog::DestroyWindow();
}

void CVSMClassifyDlg::IntialTree()
{
	//create TextClassify
	char *strWordList="resource//wordlist_30k.txt";
	char *strStopWordList="resource//stopusing.txt";
	txtClassify=new TextClassify(strWordList,strStopWordList);//delete when destroy window
	if(!txtClassify->InitialTree())
		AfxMessageBox("Initial tree error");

	

}

void CVSMClassifyDlg::OnAutoslectpara() 
{
	double weight,central,frequence,final_weight,final_central,final_frequence;
	weight=0.0;
	central=0;
	frequence=1;
	double centralmax=1;
	double veracity=0;
	m_strClassifyPath=m_strTrainPath;
	//we just use training data as test data
//加循环
	for(weight=0;weight<1;weight+=0.01)
	{
		for(frequence=0;frequence<2;frequence++)
		{
			for(central=0;central<centralmax;central+=0.01)
		
			{
				txtClassify->clear(m_strResultPath);
				txtClassify->test(weight,central,frequence);
				UpdateData(FALSE);
				OnTrain();
				double temp=OnClassify();
			//	AfxMessageBox("ok");
				if(temp>veracity)
				{
					final_frequence=frequence;
					final_central=central;
					final_weight=weight;
					veracity=temp;
				}

			}
		}
	}
	m_nWordFrea=final_frequence;
	m_fltWeight=final_weight;
	m_fltCentral=final_central;
	UpdateData(TRUE);
}