/// <summary>
/// Analyze the data. This counts the records and prepares the data to be
/// processed.
/// </summary>
///
/// <param name="theAnalyst">The analyst to use.</param>
/// <param name="inputFile">The input file to analyze.</param>
/// <param name="headers">True, if the input file has headers.</param>
/// <param name="format">The format of the input file.</param>
public void Analyze(EncogAnalyst theAnalyst,
FileInfo inputFile, bool headers, CSVFormat format)
{
InputFilename = inputFile;
ExpectInputHeaders = headers;
InputFormat = format;
Analyzed = true;
_analyst = theAnalyst;
if (OutputFormat == null)
{
OutputFormat = InputFormat;
}
_data = new BasicMLDataSet();
ResetStatus();
int recordCount = 0;
int outputLength = _analyst.DetermineTotalColumns();
var csv = new ReadCSV(InputFilename.ToString(),
ExpectInputHeaders, InputFormat);
ReadHeaders(csv);
_analystHeaders = new CSVHeaders(InputHeadings);
while (csv.Next() && !ShouldStop())
{
UpdateStatus(true);
var row = new LoadedRow(csv, 1);
double[] inputArray = AnalystNormalizeCSV.ExtractFields(
_analyst, _analystHeaders, csv, outputLength, true);
var input = new ClusterRow(inputArray, row);
_data.Add(input);
recordCount++;
}
RecordCount = recordCount;
Count = csv.ColumnCount;
ReadHeaders(csv);
csv.Close();
ReportDone(true);
}
/// <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, IMLMethod method)
{
var csv = new ReadCSV(InputFilename.ToString(),
ExpectInputHeaders, Format);
IMLData output;
foreach (AnalystField field in _analyst.Script.Normalize.NormalizedFields)
{
field.Init();
}
int outputLength = _analyst.DetermineTotalInputFieldCount();
StreamWriter tw = PrepareOutputFile(outputFile);
ResetStatus();
while (csv.Next())
{
UpdateStatus(false);
var row = new LoadedRow(csv, _outputColumns);
double[] inputArray = AnalystNormalizeCSV.ExtractFields(_analyst,
_analystHeaders, csv, outputLength, true);
if (_series.TotalDepth > 1)
{
inputArray = _series.Process(inputArray);
}
if (inputArray != null)
{
IMLData input = new BasicMLData(inputArray);
// evaluation data
if ((method is IMLClassification) &&
!(method is IMLRegression))
{
// classification only?
var tmp = new BasicMLData(1);
tmp[0] = ((IMLClassification)method).Classify(input);
output = tmp;
}
else
{
// regression
output = ((IMLRegression)method).Compute(input);
}
// skip file data
int index = _fileColumns;
int outputIndex = 0;
// display output
foreach (AnalystField field in _analyst.Script.Normalize.NormalizedFields)
{
if (_analystHeaders.Find(field.Name) != -1)
{
if (field.Output)
{
if (field.Classify)
{
// classification
ClassItem cls = field.DetermineClass(
outputIndex, output);
outputIndex += field.ColumnsNeeded;
if (cls == null)
{
row.Data[index++] = "?Unknown?";
}
else
{
row.Data[index++] = cls.Name;
}
}
else
{
// regression
double n = output[outputIndex++];
n = field.DeNormalize(n);
row.Data[index++] = Format
.Format(n, Precision);
}
}
}
}
}
WriteRow(tw, row);
}
ReportDone(false);
tw.Close();
csv.Close();
}