public static ColumnInferenceResults InferColumns(MLContext context, string path, ColumnInformation columnInfo, bool hasHeader,
TextFileContents.ColumnSplitResult splitInference, ColumnTypeInference.InferenceResult typeInference,
bool trimWhitespace, bool groupColumns)
{
var loaderColumns = ColumnTypeInference.GenerateLoaderColumns(typeInference.Columns);
var typedLoaderOptions = new TextLoader.Options
{
Columns = loaderColumns,
Separators = new[] { splitInference.Separator.Value },
AllowSparse = splitInference.AllowSparse,
AllowQuoting = splitInference.AllowQuote,
ReadMultilines = splitInference.ReadMultilines,
HasHeader = hasHeader,
TrimWhitespace = trimWhitespace
};
var textLoader = context.Data.CreateTextLoader(typedLoaderOptions);
var dataView = textLoader.Load(path);
// Validate all columns specified in column info exist in inferred data view
ColumnInferenceValidationUtil.ValidateSpecifiedColumnsExist(columnInfo, dataView);
var purposeInferenceResult = PurposeInference.InferPurposes(context, dataView, columnInfo);
// start building result objects
IEnumerable <TextLoader.Column> columnResults = null;
IEnumerable <(string, ColumnPurpose)> purposeResults = null;
// infer column grouping and generate column names
if (groupColumns)
{
var groupingResult = ColumnGroupingInference.InferGroupingAndNames(context, hasHeader,
typeInference.Columns, purposeInferenceResult);
columnResults = groupingResult.Select(c => c.GenerateTextLoaderColumn());
purposeResults = groupingResult.Select(c => (c.SuggestedName, c.Purpose));
}
else
{
columnResults = loaderColumns;
purposeResults = purposeInferenceResult.Select(p => (dataView.Schema[p.ColumnIndex].Name, p.Purpose));
}
var textLoaderOptions = new TextLoader.Options()
{
Columns = columnResults.ToArray(),
AllowQuoting = splitInference.AllowQuote,
AllowSparse = splitInference.AllowSparse,
Separators = new char[] { splitInference.Separator.Value },
ReadMultilines = splitInference.ReadMultilines,
HasHeader = hasHeader,
TrimWhitespace = trimWhitespace
};
return(new ColumnInferenceResults()
{
TextLoaderOptions = textLoaderOptions,
ColumnInformation = ColumnInformationUtil.BuildColumnInfo(purposeResults)
});
}
public static DatasetColumnInfo[] GetDatasetColumnInfo(MLContext context, IDataView data, ColumnInformation columnInfo)
{
var purposes = PurposeInference.InferPurposes(context, data, columnInfo);
var colDimensions = DatasetDimensionsApi.CalcColumnDimensions(context, data, purposes);
var cols = new DatasetColumnInfo[data.Schema.Count];
for (var i = 0; i < cols.Length; i++)
{
var schemaCol = data.Schema[i];
var col = new DatasetColumnInfo(schemaCol.Name, schemaCol.Type, purposes[i].Purpose, colDimensions[i]);
cols[i] = col;
}
return(cols);
}
/// <summary>
/// Create a single featurize pipeline according to <paramref name="columnInformation"/>. This function will collect all columns in <paramref name="columnInformation"/>,
/// featurizing them using <see cref="CatalogFeaturizer(string[], string[])"/>, <see cref="NumericFeaturizer(string[], string[])"/> or <see cref="TextFeaturizer(string, string)"/>. And combine
/// them into a single feature column as output.
/// </summary>
/// <param name="data">input data.</param>
/// <param name="columnInformation">column information.</param>
/// <param name="outputColumnName">output feature column.</param>
/// <returns>A <see cref="MultiModelPipeline"/> for featurization.</returns>
public MultiModelPipeline Featurizer(IDataView data, ColumnInformation columnInformation, string outputColumnName = "Features")
{
Contracts.CheckValue(data, nameof(data));
Contracts.CheckValue(columnInformation, nameof(columnInformation));
var columnPurposes = PurposeInference.InferPurposes(this._context, data, columnInformation);
var textFeatures = columnPurposes.Where(c => c.Purpose == ColumnPurpose.TextFeature);
var numericFeatures = columnPurposes.Where(c => c.Purpose == ColumnPurpose.NumericFeature);
var catalogFeatures = columnPurposes.Where(c => c.Purpose == ColumnPurpose.CategoricalFeature);
var textFeatureColumnNames = textFeatures.Select(c => data.Schema[c.ColumnIndex].Name).ToArray();
var numericFeatureColumnNames = numericFeatures.Select(c => data.Schema[c.ColumnIndex].Name).ToArray();
var catalogFeatureColumnNames = catalogFeatures.Select(c => data.Schema[c.ColumnIndex].Name).ToArray();
var pipeline = new MultiModelPipeline();
if (numericFeatureColumnNames.Length > 0)
{
pipeline = pipeline.Append(this.NumericFeaturizer(numericFeatureColumnNames, numericFeatureColumnNames));
}
if (catalogFeatureColumnNames.Length > 0)
{
pipeline = pipeline.Append(this.CatalogFeaturizer(catalogFeatureColumnNames, catalogFeatureColumnNames));
}
foreach (var textColumn in textFeatureColumnNames)
{
pipeline = pipeline.Append(this.TextFeaturizer(textColumn, textColumn));
}
var option = new ConcatOption
{
InputColumnNames = textFeatureColumnNames.Concat(numericFeatureColumnNames).Concat(catalogFeatureColumnNames).ToArray(),
OutputColumnName = outputColumnName,
};
if (option.InputColumnNames.Length > 0)
{
pipeline = pipeline.Append(SweepableEstimatorFactory.CreateConcatenate(option));
}
return(pipeline);
}