CTString CCurrencyField::GetAsString()
{
////assert( m_pValue && *m_pValue == fvValid ); //指示字节必须为1
CTString strRetValue;
CTString strFormat ;
//strFormat.Format("%%%d.%df",m_nWidth,m_nDecimals);
strFormat.Format("%%%d.%df",0,m_nDecimals);
strRetValue.Format(strFormat,*((FieldNUM *)m_pValue));
strRetValue.TrimLeft();
/*
if (m_nWidth >m_nTempBufLength)//#_修改 2002-12-12 $ 14:04:21 zlq
SetTempBufLength(m_nWidth);//如果空间不够，则扩大临时缓冲区
gcvt( ((FieldCurrency *)m_pValue)->dwValue, m_nWidth, m_pTempBuf );
strRetValue = _T(m_pTempBuf);
*/
return strRetValue;
}
/************************************************************************************
函数名称：
CField* CFields::NewFieldType(CFieldType chType)
功能说明：根据传入的字段类型生成相应的字段类型.
详细解释：1.返回新生成的字段.
2.如果传入的chType无效,则返回NULL.
出入参数：
[in]: 1.chType:传入的字段类型.
[out]:无.
返回类型：CField*
制作：YTLI 2002/07/15
修改:
***********************************************************************************/
CField* CFields::NewFieldType(CFields* pOwner ,CFieldType chType)
{
CField* pField = NULL;//如果传入的chType无效,则返回NULL.
switch(chType)
{
case fString :
pField = new CStringField(this);
break;
case fDouble :
pField = new CDoubleField(this);
break;
case fInt :
pField = new CIntField(this);
break;
case fBoolean :
pField = new CBooleanField(this);
break;
case fDate :
pField = new CDateField(this);
break;
case fCurrency :
pField = new CCurrencyField(this);
break;
}
CTString str;//###_Mod 2002-9-24 zlq 缺省字段名
int nCount = m_FieldVersion.GetAbsoluteFieldCount();
do
{//#_S 2003-5-28 $ 9 zlq 确保生成时,就唯一
str.Format("%d",nCount+1);
while (str.GetLength()<4)
{//#_修改 2002-11-15 $ 9:15:44 zlq
str = "0"+str;
}
str = "变量" +str;
nCount++;
}while (FieldByName(str)!=NULL);
pField->SetFieldName(str);
pField->m_pFields = pOwner;
return pField ;
}
int CRsltElementText::GetStringRow(CTString string)
{
int index=0,
row=0;
CTString str;
str.Format("%s\n","");
while(index>=0)
{
index=string.Find(str,index);
if(index>=0)
{
row++;
index++;
}
else
break;
}
return row;
}
void CMarkovChain::DrawResult()
{
if (m_nTotalID > 1000 || m_bSaveData)
{
//在主界面输出聚类结果
int i;
CDataAccess DataAcc;
CField *pUserIdNum = DataAcc.m_pFieldList->CreateField(fInt);
CField *pCluster = DataAcc.m_pFieldList->CreateField(fInt);
pUserIdNum->SetFieldName("用户序号");
pCluster->SetFieldName("分类结果");
DataAcc.m_pFieldList->Add(pUserIdNum);
DataAcc.m_pFieldList->Add(pCluster);
for ( i=0; i<m_nTotalID; i++)
{
DataAcc.Append();
pUserIdNum->SetAsInteger(i+1);
pCluster->SetAsInteger(m_VecClus(i) );
}
BOOL bSucSave;//保存文件
CTString NoUse, FileName;
if (m_bSaveData)
{
bSucSave = DataAcc.SaveFile(m_DataFile, &NoUse);
FileName = m_DataFile;
}
else
{
CTString strOutNameTemp = "_马尔可夫链聚类结果";
CTString strOrgNameTemp = m_pDataInterface->m_DataAccess.GetFileName();
FileName = CFileReadWrite::GetSaveFileName(strOrgNameTemp, strOutNameTemp);
bSucSave = DataAcc.SaveFile(FileName, &NoUse);
}
CRsltElementText * pWarningTextRslt = new CRsltElementText( "马尔可夫链分类结果" );
CTString strWarn;
if (bSucSave)
strWarn = "模型运行结束，结果已经成功输出到"+FileName+"文件里。";
else
strWarn = "模型运行结束，结果已经成功输出到"+NoUse+"文件里。";
pWarningTextRslt->AddString(strWarn);
m_pResult->Add( pWarningTextRslt );
return;
}
else
{
CTLTable * pTable = new CTLTable;
CRsltElementTable * pETable = new CRsltElementTable("马尔可夫链分类结果",pTable);//申请一个表对象类的对象
pTable->CreateTable(2, 2);
pTable->SetTitle("马尔可夫链分类情况");
pTable->SetCols(2);
pTable->SetRows(m_nTotalID+1);
pTable->InsertColumn(0,"用户序号");
pTable->InsertColumn(1,"分类结果");
CTString str;
for(int i=0;i<m_nTotalID;i++)
{
str.Format("%d",i+1);
pTable->InsertItem(i,str);
pTable->SetItemText(i, 1, m_VecClus(i) );
}
m_pResult->Add(pETable);
return;
}
}
BOOL CMarkovChain::Main()
{
int id = 0;
int L = 0;
int i = 0;
int j,k,l,t;
m_nPageNum = m_Path_vec.Max();
CDoubleVector start_vec(m_nRow);
CDoubleVector pairID_vec(m_nRow);
CDoubleVector length_vec(m_nRow, 0);
// (Preprocessing) begin
//
while (i < m_nRow)
{
L=0;
start_vec(id) = i;
pairID_vec(id) = m_ID_vec(i);
while (pairID_vec(id) == m_ID_vec(i))
{
length_vec(id)++;
i++;
if (i >= m_nRow)
{
break;
}
}
id++;
}
m_nTotalID = id;
start_vec.resize(m_nTotalID);
pairID_vec.resize(m_nTotalID);
length_vec.resize(m_nTotalID);
CDoubleVector score(28);
// (Preprocessing) end
//
// (Model selection) begin
//
if (m_bAutoCluster)//如果自动计算KClusters
{
int cutting = min(0.4 * m_nTotalID, 5000);
int KClusters;
for (KClusters=3; KClusters<15; KClusters++)
{
CDoubleMatrix responsibility(cutting, KClusters);
// (Initialization) begin
CDoubleVector Pi_vec(KClusters, 1.0/KClusters);
CDoubleMatrix Theta_Init_mx(KClusters, m_nPageNum);
srand(GetTickCount());
for (k=0; k<KClusters; k++)
{
for (j=0; j<m_nPageNum; j++)
{
Theta_Init_mx(k,j) = rand();
}
}
for (k=0; k<KClusters; k++)
{
double s = 0;
for (j=0; j<m_nPageNum; j++)
{
s += Theta_Init_mx(k,j);
}
for (j=0; j<m_nPageNum; j++)
{
Theta_Init_mx(k,j) = Theta_Init_mx(k,j)/s;
}
}
CDoubleMatrix * Theta_Trans= new CDoubleMatrix[KClusters];
for (k=0; k<KClusters; k++)
{
CDoubleMatrix Theta_Trans_mx(m_nPageNum, m_nPageNum);
for (i=0; i<m_nPageNum; i++)
{
for (j=0; j<m_nPageNum; j++)
{
Theta_Trans_mx(i, j) = rand();
}
}
Theta_Trans[k] = Theta_Trans_mx;
}
for (k=0; k<KClusters; k++)
{
for (j=0; j<m_nPageNum; j++)
{
double s = 0;
for (l=0; l<m_nPageNum; l++)
{
s += Theta_Trans[k](j,l);
}
for (l=0; l<m_nPageNum; l++)
{
Theta_Trans[k](j,l) = Theta_Trans[k](j,l)/s;
}
}
}
// (Initialization) end
EMalgorithm(Pi_vec, Theta_Init_mx, Theta_Trans, responsibility,
start_vec, length_vec, pairID_vec, KClusters, cutting);
// (Compute Score) begin
double LS2 = 0;
double total_length = 0;
for (i=cutting; i<m_nTotalID; i++)
{
double like = 0;
for (k=0; k<KClusters; k++)
{
L = length_vec(i);
double temp = 1;
for (t=start_vec(i); t<start_vec(i)+L-1; t++)
{
temp *= Theta_Trans[k](m_Path_vec(t)-1,m_Path_vec(t+1)-1);
}
like += temp * Pi_vec(k) * Theta_Init_mx(k,m_Path_vec(start_vec(i))-1);
}
LS2 += log(like)/log(2);
}
for (i=0; i<m_nTotalID; i++)
{
total_length += length_vec(i);
}
score(KClusters-3) = -(LS2/total_length)+(0.01*KClusters);
// (Compute Score) end
}
}
for (i=0; i<28; i++)
{
if (score(i) < score(m_nCluster-3))
{
m_nCluster = i+3;
}
}
// (Model selection) end
//
// (Training) begin
//
CDoubleMatrix responsibility(m_nTotalID, m_nCluster);
// (Initialization)
CDoubleVector Pi_vec(m_nCluster, 1.0/m_nCluster); // Pi
CDoubleMatrix Theta_Init_mx(m_nCluster, m_nPageNum); // Theta_Init
srand(GetTickCount());
for (k=0; k<m_nCluster; k++)
{
for (j=0; j<m_nPageNum; j++)
{
Theta_Init_mx(k,j) = rand();
}
}
for (k=0; k<m_nCluster; k++) // normalization
{
double s = 0;
for (j=0; j<m_nPageNum; j++)
{
s += Theta_Init_mx(k,j);
}
for (j=0; j<m_nPageNum; j++)
{
Theta_Init_mx(k,j) = Theta_Init_mx(k,j)/s;
}
}
CDoubleMatrix * Theta_Trans= new CDoubleMatrix[m_nCluster]; // Theta_Trans
for (k=0; k<m_nCluster; k++)
{
CDoubleMatrix Theta_Trans_mx(m_nPageNum, m_nPageNum);
for (i=0; i<m_nPageNum; i++)
{
for (j=0; j<m_nPageNum; j++)
{
Theta_Trans_mx(i, j) = rand();
}
}
Theta_Trans[k] = Theta_Trans_mx;
}
for (k=0; k<m_nCluster; k++) // normalization
{
for (j=0; j<m_nPageNum; j++)
{
double s = 0;
for (l=0; l<m_nPageNum; l++)
{
s += Theta_Trans[k](j,l);
}
for (l=0; l<m_nPageNum; l++)
{
Theta_Trans[k](j,l) = Theta_Trans[k](j,l)/s;
}
}
}
// (hyperparameter)
double alpha_IT = 0.01 / m_nPageNum;
// EM training
EMalgorithm(Pi_vec, Theta_Init_mx, Theta_Trans, responsibility,
start_vec, length_vec, pairID_vec, m_nCluster, m_nTotalID);
// (Training) end
//
// (Hard assignment) begin
//
m_VecClus.create(m_nTotalID);
for (i=0; i<m_nTotalID; i++)
{
int which = 0;
for (k=0; k<m_nCluster; k++)
{
if (responsibility(i, which) > responsibility(i,k))
{
which = k;
}
}
m_VecClus(i) = which;
}
//输出模型信息到 m_strModel
CTString strTemp;
m_strModel = "";
strTemp.Format("%d", m_nCluster);
m_strModel += strTemp;
m_strModel += " ";
strTemp.Format("%d", m_nPageNum);
m_strModel += strTemp;
m_strModel += " ";
for (k=0; k<m_nCluster; k++)
{
for (j=0; j<m_nPageNum; j++)
{
for (i=0; i<m_nPageNum; i++)
{
strTemp.Format("%.9f", Theta_Trans[k](i,j));
m_strModel += strTemp;
m_strModel += " ";
}
}
} //输出模型信息到 m_strModel 完成
if (m_bSaveModel)//保存模型
CFileReadWrite::WriteStrToFile(m_ModelFile, m_strModel);
// (Hard assignment) end
//
return TRUE;
}
