/// <summary>
/// Extract fields from a file into a numeric array for machine learning.
/// </summary>
///
/// <param name="analyst">The analyst to use.</param>
/// <param name="headers">The headers for the input data.</param>
/// <param name="csv">The CSV that holds the input data.</param>
/// <param name="outputLength">The length of the returned array.</param>
/// <param name="skipOutput">True if the output should be skipped.</param>
/// <returns>The encoded data.</returns>
public static double[] ExtractFields(EncogAnalyst analyst,
CSVHeaders headers, ReadCSV csv,
int outputLength, bool skipOutput)
{
var output = new double[outputLength];
int outputIndex = 0;
foreach (AnalystField stat in analyst.Script.Normalize.NormalizedFields)
{
if (stat.Action == NormalizationAction.Ignore)
{
continue;
}
if (stat.Output && skipOutput)
{
continue;
}
int index = headers.Find(stat.Name);
String str = csv.Get(index);
// is this an unknown value?
if (str.Equals("?") || str.Length == 0)
{
IHandleMissingValues handler = analyst.Script.Normalize.MissingValues;
double[] d = handler.HandleMissing(analyst, stat);
// should we skip the entire row
if (d == null)
{
return(null);
}
// copy the returned values in place of the missing values
for (int i = 0; i < d.Length; i++)
{
output[outputIndex++] = d[i];
}
}
else
{
// known value
if (stat.Action == NormalizationAction.Normalize)
{
double d = csv.Format.Parse(str.Trim());
d = stat.Normalize(d);
output[outputIndex++] = d;
}
else
{
double[] d = stat.Encode(str.Trim());
foreach (double element in d)
{
output[outputIndex++] = element;
}
}
}
}
return(output);
}
