public static ColumnInferenceResults InferColumns(MLContext context, string path, ColumnInformation columnInfo,
char?separatorChar, bool?allowQuotedStrings, bool?supportSparse, bool trimWhitespace, bool groupColumns)
{
var sample = TextFileSample.CreateFromFullFile(path);
var splitInference = InferSplit(context, sample, separatorChar, allowQuotedStrings, supportSparse);
var typeInference = InferColumnTypes(context, sample, splitInference, true, null, columnInfo.LabelColumnName);
return(InferColumns(context, path, columnInfo, true, splitInference, typeInference, trimWhitespace, groupColumns));
}
public static ColumnInferenceResults InferColumns(MLContext context, string path, uint labelColumnIndex,
bool hasHeader, char?separatorChar, bool?allowQuotedStrings, bool?supportSparse, bool trimWhitespace, bool groupColumns)
{
var sample = TextFileSample.CreateFromFullFile(path);
var splitInference = InferSplit(context, sample, separatorChar, allowQuotedStrings, supportSparse);
var typeInference = InferColumnTypes(context, sample, splitInference, hasHeader, labelColumnIndex, null);
// If no headers, suggest label column name as 'Label'
if (!hasHeader)
{
typeInference.Columns[labelColumnIndex].SuggestedName = DefaultColumnNames.Label;
}
var columnInfo = new ColumnInformation()
{
LabelColumnName = typeInference.Columns[labelColumnIndex].SuggestedName
};
return(InferColumns(context, path, columnInfo, hasHeader, splitInference, typeInference, trimWhitespace, groupColumns));
}
private static ColumnTypeInference.InferenceResult InferColumnTypes(MLContext context, TextFileSample sample,
TextFileContents.ColumnSplitResult splitInference, bool hasHeader, uint?labelColumnIndex, string label)
{
// infer column types
var typeInferenceResult = ColumnTypeInference.InferTextFileColumnTypes(context, sample,
new ColumnTypeInference.Arguments
{
ColumnCount = splitInference.ColumnCount,
Separator = splitInference.Separator.Value,
AllowSparse = splitInference.AllowSparse,
AllowQuote = splitInference.AllowQuote,
HasHeader = hasHeader,
LabelColumnIndex = labelColumnIndex,
Label = label
});
if (!typeInferenceResult.IsSuccess)
{
throw new InferenceException(InferenceExceptionType.ColumnDataType, "Unable to infer column types of the file provided.");
}
return(typeInferenceResult);
}
private static TextFileContents.ColumnSplitResult InferSplit(MLContext context, TextFileSample sample, char?separatorChar, bool?allowQuotedStrings, bool?supportSparse)
{
var separatorCandidates = separatorChar == null ? TextFileContents.DefaultSeparators : new char[] { separatorChar.Value };
var splitInference = TextFileContents.TrySplitColumns(context, sample, separatorCandidates);
// respect passed-in overrides
if (allowQuotedStrings != null)
{
splitInference.AllowQuote = allowQuotedStrings.Value;
}
if (supportSparse != null)
{
splitInference.AllowSparse = supportSparse.Value;
}
if (!splitInference.IsSuccess)
{
throw new InferenceException(InferenceExceptionType.ColumnSplit, "Unable to split the file provided into multiple, consistent columns.");
}
return(splitInference);
}
