arminerdlg.cpp

Aprioriall的频繁序列发觉源码

// ARMinerDlg.cpp : implementation file
//

#include "stdafx.h"
#include "math.h"
#include "ARMiner.h"
#include "ARMinerDlg.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()

/////////////////////////////////////////////////////////////////////////////
// CARMinerDlg dialog

CARMinerDlg::CARMinerDlg(CWnd* pParent /*=NULL*/)
	: CDialog(CARMinerDlg::IDD, pParent)
{
	//{{AFX_DATA_INIT(CARMinerDlg)
	m_data = _T("data.txt");
	m_rule = _T("Result.txt");
	m_support = 0.2;
	m_confidence = 0.5;
	//}}AFX_DATA_INIT
	// Note that LoadIcon does not require a subsequent DestroyIcon in Win32
	m_hIcon = AfxGetApp()->LoadIcon(IDR_MAINFRAME);
}

void CARMinerDlg::DoDataExchange(CDataExchange* pDX)
{
	CDialog::DoDataExchange(pDX);
	//{{AFX_DATA_MAP(CARMinerDlg)
	DDX_Control(pDX, IDC_EDIT_DATA, m_dataEdit);
	DDX_Text(pDX, IDC_EDIT_DATA, m_data);
	DDX_Text(pDX, IDC_EDIT_RULE, m_rule);
	DDX_Text(pDX, IDC_EDIT_SUPPORT, m_support);
	DDX_Text(pDX, IDC_EDIT_CONFIDENCE, m_confidence);
	//}}AFX_DATA_MAP
}

BEGIN_MESSAGE_MAP(CARMinerDlg, CDialog)
	//{{AFX_MSG_MAP(CARMinerDlg)
	ON_WM_SYSCOMMAND()
	ON_WM_PAINT()
	ON_WM_QUERYDRAGICON()
	ON_BN_CLICKED(IDC_BUTTON_MINING, OnButtonMining)
	//}}AFX_MSG_MAP
END_MESSAGE_MAP()

/////////////////////////////////////////////////////////////////////////////
// CARMinerDlg message handlers

BOOL CARMinerDlg::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
	
	return TRUE;  // return TRUE  unless you set the focus to a control
}

void CARMinerDlg::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 CARMinerDlg::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 CARMinerDlg::OnQueryDragIcon()
{
	return (HCURSOR) m_hIcon;
}


#include "Apriori.h"
#include "Association.h"
#include "itemSet.h"
List * CARMinerDlg::loadItemSets(const char *datafile, int& max_pageno, bool keeporder)
{
    List *m_data;
    itemSet *pitemset;
    char line[20*4096];
    int pageno;
    char *t, *s;
    FILE *fp;

    // try to open the data file
    if((fp = fopen(datafile, "rt")) == NULL)
		return (List *)NULL;

    // this is the data structure that stores the input data
    m_data = (List *)new List();
    max_pageno = -1;

    // Read in each line, extract all the items within this line
    while(fgets(line, 20*4096, fp) != NULL)
    {
        if (strchr(line, ',') != NULL)
        {
            s = (char *) new char[strlen(line) + 1];
            strcpy(s, line);
            if ((t = strtok(s, ",")) == NULL)
            {
                delete s;
                break;
            }

            pitemset = (itemSet *)new itemSet();
			pitemset->keeporder(keeporder);
            pageno = atoi(t);
            if(max_pageno < pageno)
                max_pageno = pageno;
            pitemset->add(pageno);
            
            t = strtok((char *)NULL, ",");

            for ( ; t != NULL; t = strtok((char *)NULL, ","))
            {
                pageno = atoi(t);
                if(max_pageno < pageno)
                    max_pageno = pageno;
				
                pitemset->add(pageno);
            }

            // if the length of the session is greater than 1, then insert it into the session list
            if(pitemset->size() > 1)
            {
                pitemset->support(1);
                m_data->add(pitemset);
            }
			else
	            delete pitemset;

            delete s;
        }
    }

    fclose(fp);

    return(m_data);
}



void CARMinerDlg::OnButtonMining() 
{
	// TODO: Add your control notification handler code here
	UpdateData();
	//m_data;存放数据项集的文件名
	//m_rule;存放挖掘出的关联规则的文件名
	//m_support;最小支持度
	//m_confidence;最小信任度

	CString s,t;
	float tickCount=GetTickCount();

	CApriori *m_apriori;
	CAssociationRule *m_rules;//关联规则对象
    List *traindata;//训练数据链
    int pagenum;//属性个数
    double support = 0.2, confidence = 0.5;
	double m_ItemSupport;
    support=m_support;confidence=m_confidence;
	
    // Read in the structure of the web site from a map file
    if((traindata = loadItemSets(m_data, pagenum, false)) == NULL)
	{
		//从数据集文件m_data装裁项集到traindata链
		MessageBox("Cannot load data!");
		return;
	}
	
    m_apriori = new CApriori();
    m_apriori->setsupport(support);
	m_apriori->pagenum = pagenum + 1;

    // Finding large Itemsets from training data
	//以下函数从traindata中找出频繁集保存在m_apriori的m_Ls成员中，
	//训练集中项集总个数保存在m_sampleNum成员中
    m_apriori->FindLargeItemSets(traindata);
    
    // Association Rules from extracted large item sets
    m_rules = new CAssociationRule();
    m_rules->setconfidence(confidence);
    m_rules->m_LargeItemSets = m_apriori->m_Ls;//把频繁集保存到规则对象m_rules中
	
	//以下把频繁集保存到文件中
    FILE *fp;
	itemSet *current;
    fp=fopen(m_rule,"w");
	s.Format("频繁项集如下(最小支持度：%f，信任度：%f)\n\n",m_support,m_confidence);
	fprintf(fp,s);
    for(int i = 0; i < m_rules->m_LargeItemSets->size(); i++)
    {
		
        current = (itemSet *)m_rules->m_LargeItemSets->get(i);
        if(current->size() >0)
		{
			s="";
			for(int j=0;j<current->size();j++)
			{
				t.Format("%d,",current->get(j));
				s+=t;
			}
			m_ItemSupport=(double)current->support()/(double)m_apriori->m_sampleNum;
			s.Delete(strlen(s)-1,1);
			
			char tt[200];
			memcpy(tt, s.GetBuffer(0), s.GetLength());
			tt[s.GetLength()]=0;
			s.Format("%s   支持度为%d/%d=%.3f",tt,current->support(),m_apriori->m_sampleNum,m_ItemSupport);
			fprintf(fp,s);
			fprintf(fp,"\n");
			
		}
	}
	fflush(fp);
	fclose(fp);
			
//    m_rules->genrules();//由频繁集生成关联规则
//    m_rules->save(m_rule);//保存关联规则

    // Clear off
    delete m_apriori;
    delete m_rules;
    delete traindata;

    fp=fopen(m_rule,"a+");
	//取结束时间，保存执行时间
	tickCount=GetTickCount()-tickCount;
	s.Format("\n挖掘时间 %.3f秒",tickCount/1000);
	fprintf(fp,s);
	fflush(fp);
	fclose(fp);

	MessageBox("挖掘完成!");
}