/// <summary>
/// Process the file.
/// </summary>
///
/// <param name="outputFile">The output file.</param>
/// <param name="method">The method to use.</param>
public void Process(FileInfo outputFile, IMLRegression method)
{
var csv = new ReadCSV(InputFilename.ToString(),
ExpectInputHeaders, InputFormat);
if (method.InputCount > _inputCount)
{
throw new AnalystError("This machine learning method has "
+ method.InputCount
+ " inputs, however, the data has " + _inputCount
+ " inputs.");
}
IMLData input = new BasicMLData(method.InputCount);
StreamWriter tw = AnalystPrepareOutputFile(outputFile);
ResetStatus();
while (csv.Next())
{
UpdateStatus(false);
var row = new LoadedRow(csv, _idealCount);
int dataIndex = 0;
// load the input data
for (int i = 0; i < _inputCount; i++)
{
String str = row.Data[i];
double d = InputFormat.Parse(str);
input[i] = d;
dataIndex++;
}
// do we need to skip the ideal values?
dataIndex += _idealCount;
// compute the result
IMLData output = method.Compute(input);
// display the computed result
for (int i = 0; i < _outputCount; i++)
{
double d = output[i];
row.Data[dataIndex++] = InputFormat.Format(d, Precision);
}
WriteRow(tw, row);
}
ReportDone(false);
tw.Close();
csv.Close();
}
/// <summary>
/// Read the CSV file.
/// </summary>
///
private void ReadFile()
{
ReadCSV csv = null;
try
{
csv = new ReadCSV(InputFilename.ToString(),
ExpectInputHeaders, InputFormat);
ResetStatus();
int row = 0;
while (csv.Next() && !ShouldStop())
{
UpdateStatus("Reading data");
foreach (BaseCachedColumn column in Columns)
{
if (column is FileData)
{
if (column.Input)
{
var fd = (FileData)column;
String str = csv.Get(fd.Index);
double d = InputFormat.Parse(str);
fd.Data[row] = d;
}
}
}
row++;
}
}
finally
{
ReportDone("Reading data");
if (csv != null)
{
csv.Close();
}
}
}
/// <summary>
/// Write the sorted output file.
/// </summary>
///
/// <param name="outputFile">The name of the output file.</param>
private void WriteOutputFile(FileInfo outputFile)
{
StreamWriter tw = PrepareOutputFile(outputFile);
var nonNumeric = new bool[Count];
bool first = true;
ResetStatus();
// write the file
foreach (LoadedRow row in _data)
{
UpdateStatus("Writing output");
// for the first row, determine types
if (first)
{
for (int i = 0; i < Count; i++)
{
try
{
String str = row.Data[i];
InputFormat.Parse(str);
nonNumeric[i] = false;
}
catch (Exception)
{
nonNumeric[i] = true;
}
}
first = false;
}
// write the row
var line = new StringBuilder();
for (int i = 0; i < Count; i++)
{
if (i > 0)
{
line.Append(",");
}
if (nonNumeric[i])
{
line.Append("\"");
line.Append(row.Data[i]);
line.Append("\"");
}
else
{
line.Append(row.Data[i]);
}
}
tw.WriteLine(line.ToString());
}
ReportDone("Writing output");
// close the file
tw.Close();
}
