//Loading the contingency tables from the input file
//Implements the sampling techniques
private List <ContingencyTable> loadTables()
{
try
{
StreamReader sr = m_fiInput.OpenText();
ContingencyTable ctCurrent = null;
if (m_bReportProgress)
{
m_bContinue = m_prReport.reportPhase("Loading data");
m_bContinue = m_prReport.reportMessage("Loading data from file " + m_fiInput.Name, true);
}
string sLine = "";
List <ContingencyTable> actTables = new List <ContingencyTable>();
int cTables = 0;
long cCharacters = 0;
bool bUseTable = true;
double dSampleProbability = 0.0, dProb = 0.0;
Random rnd = new Random();
int iLineNumber = 0;
if (m_bHuge)
{
m_ctcTableCounts = new ContingencyTableCache();
}
else
{
m_ctcTableCounts = null;
}
//On the first iteration go through the file to check the number of rows (tables)
if (m_cTables == -1)
{
m_cTables = 0;
sLine = sr.ReadLine();
initColumnHeaders(sLine);
while (!sr.EndOfStream)
{
sLine = sr.ReadLine();
m_cTables++;
if (m_bReportProgress)
{
if (m_cTables % MAX_REPROT_POINT == 0)
{
m_bContinue = m_prReport.reportMessage(".", false);
}
}
}
if (m_bReportProgress)
{
m_bContinue = m_prReport.reportMessage("", true);
m_bContinue = m_prReport.reportMessage("Found " + m_cTables + " data rows.", true);
}
}
//Instead of enforcing a hard sample size, we sample the given the sample probability
dSampleProbability = m_iSampleSize / (double)m_cTables;
sr.Close();
sr = m_fiInput.OpenText();
if (m_bReportProgress)
{
if (m_bSampling)
{
m_bContinue = m_prReport.reportPhase("Sampling tables");
m_bContinue = m_prReport.reportMessage("Sampling " + m_iSampleSize + " tables.", true);
}
}
if (m_bHasColumnHeaders)
{
sr.ReadLine();
}
while (!sr.EndOfStream && m_bContinue)
{
sLine = sr.ReadLine().Trim();
iLineNumber++;
if (sLine.Length > 0)
{
bUseTable = true;//general use flag - sampling, validation, ...
if (m_bSampling)
{
dProb = rnd.NextDouble();
if (dProb > dSampleProbability)
{
bUseTable = false;
}
}
if (bUseTable)
{
ctCurrent = new ContingencyTable(sLine, m_cTableNamesColumns);
bUseTable = ctCurrent.validate();
}
if (bUseTable)
{
if (m_bHuge)//instead of maintaining all the tables try to see whether we already loaded a table with the same counts
{
double dCount = m_ctcTableCounts.getCachedValue(ctCurrent);
if (double.IsNaN(dCount))//First time table was observed
{
dCount = 0;
actTables.Add(ctCurrent);
}
m_ctcTableCounts.setCachedValue(ctCurrent, dCount + 1);//increment the table count
}
else//not huge - maintain all tables (including duplicates)
{
actTables.Add(ctCurrent);
}
}
cTables++;
}
if ((cTables > 0) && (cTables % MAX_REPROT_POINT == 0))
{
if (m_bReportProgress)
{
m_bContinue = m_prReport.reportProcessedTables(cTables, m_cTables);
m_bContinue = m_prReport.reportMessage("Loaded " + cTables + " tables.", false);
if (m_bHuge)
{
m_bContinue = m_prReport.reportMessage(" Found " + actTables.Count + " distinct tables.", false);
}
m_bContinue = m_prReport.reportMessage("", true);
}
}
cCharacters += sLine.Length + 2;
}
if (m_bReportProgress)
{
m_bContinue = m_prReport.reportMessage("Done loading data. Found " + actTables.Count + " distinct tables.", true);
}
sr.Close();
return(actTables);
}
catch (Exception e)
{
m_bContinue = m_prReport.reportError("Could not load data : " + e.Message);
}
return(null);
}
