/// <summary>
/// Returns the max value for the specified metadata kind.
/// The metadata type should be a KeyType with raw type U4.
/// colMax will be set to the first column that has the max value for the specified metadata.
/// If no column has the specified metadata, colMax is set to -1 and the method returns zero.
/// The filter function is called for each column, passing in the schema and the column index, and returns
/// true if the column should be considered, false if the column should be skipped.
/// </summary>
public static uint GetMaxMetadataKind(this Schema schema, out int colMax, string metadataKind, Func <Schema, int, bool> filterFunc = null)
{
uint max = 0;
colMax = -1;
for (int col = 0; col < schema.Count; col++)
{
var columnType = schema.GetMetadataTypeOrNull(metadataKind, col);
if (columnType == null || !columnType.IsKey || columnType.RawKind != DataKind.U4)
{
continue;
}
if (filterFunc != null && !filterFunc(schema, col))
{
continue;
}
uint value = 0;
schema.GetMetadata(metadataKind, col, ref value);
if (max < value)
{
max = value;
colMax = col;
}
}
return(max);
}
internal static bool TryGetCategoricalFeatureIndices(Schema schema, int colIndex, out int[] categoricalFeatures)
{
Contracts.CheckValue(schema, nameof(schema));
Contracts.Check(colIndex >= 0, nameof(colIndex));
bool isValid = false;
categoricalFeatures = null;
if (!(schema.GetColumnType(colIndex) is VectorType vecType && vecType.Size > 0))
{
return(isValid);
}
var type = schema.GetMetadataTypeOrNull(MetadataUtils.Kinds.CategoricalSlotRanges, colIndex);
if (type?.RawType == typeof(VBuffer <int>))
{
VBuffer <int> catIndices = default(VBuffer <int>);
schema.GetMetadata(MetadataUtils.Kinds.CategoricalSlotRanges, colIndex, ref catIndices);
VBufferUtils.Densify(ref catIndices);
int columnSlotsCount = vecType.Size;
if (catIndices.Length > 0 && catIndices.Length % 2 == 0 && catIndices.Length <= columnSlotsCount * 2)
{
int previousEndIndex = -1;
isValid = true;
var catIndicesValues = catIndices.GetValues();
for (int i = 0; i < catIndicesValues.Length; i += 2)
{
if (catIndicesValues[i] > catIndicesValues[i + 1] ||
catIndicesValues[i] <= previousEndIndex ||
catIndicesValues[i] >= columnSlotsCount ||
catIndicesValues[i + 1] >= columnSlotsCount)
{
isValid = false;
break;
}
previousEndIndex = catIndicesValues[i + 1];
}
if (isValid)
{
categoricalFeatures = catIndicesValues.ToArray();
}
}
}
return(isValid);
}
internal static IEnumerable <int> GetColumnSet(this Schema schema, string metadataKind, string value)
{
for (int col = 0; col < schema.Count; col++)
{
var columnType = schema.GetMetadataTypeOrNull(metadataKind, col);
if (columnType != null && columnType.IsText)
{
ReadOnlyMemory <char> val = default;
schema.GetMetadata(metadataKind, col, ref val);
if (ReadOnlyMemoryUtils.EqualsStr(value, val))
{
yield return(col);
}
}
}
}
internal static IEnumerable <int> GetColumnSet(this Schema schema, string metadataKind, uint value)
{
for (int col = 0; col < schema.Count; col++)
{
var columnType = schema.GetMetadataTypeOrNull(metadataKind, col);
if (columnType != null && columnType.IsKey && columnType.RawKind == DataKind.U4)
{
uint val = 0;
schema.GetMetadata(metadataKind, col, ref val);
if (val == value)
{
yield return(col);
}
}
}
}
