Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

File-scoped namespaces in files under Data (Microsoft.ML.Core) #6789

Merged
merged 2 commits into from
Aug 31, 2023
Merged

File-scoped namespaces in files under Data (Microsoft.ML.Core) #6789

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7d3e3df
File-scoped namespaces in files under `Data` (`Microsoft.ML.Core`)
Aug 10, 2023
9e980a3
Merge branch 'dotnet:main' into improvement3
Lehonti Aug 26, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
45 changes: 22 additions & 23 deletions src/Microsoft.ML.Core/Data/AnnotationBuilderExtensions.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,29 +4,28 @@

using System;

namespace Microsoft.ML.Data
namespace Microsoft.ML.Data;

[BestFriend]
internal static class AnnotationBuilderExtensions
{
[BestFriend]
internal static class AnnotationBuilderExtensions
{
/// <summary>
/// Add slot names annotation.
/// </summary>
/// <param name="builder">The <see cref="DataViewSchema.Annotations.Builder"/> to which to add the slot names.</param>
/// <param name="size">The size of the slot names vector.</param>
/// <param name="getter">The getter delegate for the slot names.</param>
public static void AddSlotNames(this DataViewSchema.Annotations.Builder builder, int size, ValueGetter<VBuffer<ReadOnlyMemory<char>>> getter)
=> builder.Add(AnnotationUtils.Kinds.SlotNames, new VectorDataViewType(TextDataViewType.Instance, size), getter);
/// <summary>
/// Add slot names annotation.
/// </summary>
/// <param name="builder">The <see cref="DataViewSchema.Annotations.Builder"/> to which to add the slot names.</param>
/// <param name="size">The size of the slot names vector.</param>
/// <param name="getter">The getter delegate for the slot names.</param>
public static void AddSlotNames(this DataViewSchema.Annotations.Builder builder, int size, ValueGetter<VBuffer<ReadOnlyMemory<char>>> getter)
=> builder.Add(AnnotationUtils.Kinds.SlotNames, new VectorDataViewType(TextDataViewType.Instance, size), getter);

/// <summary>
/// Add key values annotation.
/// </summary>
/// <typeparam name="TValue">The value type of key values.</typeparam>
/// <param name="builder">The <see cref="DataViewSchema.Annotations.Builder"/> to which to add the key values.</param>
/// <param name="size">The size of key values vector.</param>
/// <param name="valueType">The value type of key values. Its raw type must match <typeparamref name="TValue"/>.</param>
/// <param name="getter">The getter delegate for the key values.</param>
public static void AddKeyValues<TValue>(this DataViewSchema.Annotations.Builder builder, int size, PrimitiveDataViewType valueType, ValueGetter<VBuffer<TValue>> getter)
=> builder.Add(AnnotationUtils.Kinds.KeyValues, new VectorDataViewType(valueType, size), getter);
}
/// <summary>
/// Add key values annotation.
/// </summary>
/// <typeparam name="TValue">The value type of key values.</typeparam>
/// <param name="builder">The <see cref="DataViewSchema.Annotations.Builder"/> to which to add the key values.</param>
/// <param name="size">The size of key values vector.</param>
/// <param name="valueType">The value type of key values. Its raw type must match <typeparamref name="TValue"/>.</param>
/// <param name="getter">The getter delegate for the key values.</param>
public static void AddKeyValues<TValue>(this DataViewSchema.Annotations.Builder builder, int size, PrimitiveDataViewType valueType, ValueGetter<VBuffer<TValue>> getter)
=> builder.Add(AnnotationUtils.Kinds.KeyValues, new VectorDataViewType(valueType, size), getter);
}
805 changes: 402 additions & 403 deletions src/Microsoft.ML.Core/Data/AnnotationUtils.cs
View file
Open in desktop

Large diffs are not rendered by default.

293 changes: 146 additions & 147 deletions src/Microsoft.ML.Core/Data/ColumnTypeExtensions.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,165 +5,164 @@
using System;
using Microsoft.ML.Runtime;

namespace Microsoft.ML.Data
namespace Microsoft.ML.Data;

/// <summary>
/// Extension methods related to the ColumnType class.
/// </summary>
[BestFriend]
internal static class ColumnTypeExtensions
{
/// <summary>
/// Extension methods related to the ColumnType class.
/// Whether this type is a standard scalar type completely determined by its <see cref="DataViewType.RawType"/>
/// (not a <see cref="KeyDataViewType"/> or <see cref="StructuredDataViewType"/>, etc).
/// </summary>
public static bool IsStandardScalar(this DataViewType columnType) =>
(columnType is NumberDataViewType) || (columnType is TextDataViewType) || (columnType is BooleanDataViewType) ||
(columnType is RowIdDataViewType) || (columnType is TimeSpanDataViewType) ||
(columnType is DateTimeDataViewType) || (columnType is DateTimeOffsetDataViewType);

/// <summary>
/// Zero return means it's not a key type.
/// </summary>
public static ulong GetKeyCount(this DataViewType columnType) => (columnType as KeyDataViewType)?.Count ?? 0;

/// <summary>
/// Sometimes it is necessary to cast the Count to an int. This performs overflow check.
/// Zero return means it's not a key type.
/// </summary>
[BestFriend]
internal static class ColumnTypeExtensions
public static int GetKeyCountAsInt32(this DataViewType columnType, IExceptionContext ectx = null)
{
/// <summary>
/// Whether this type is a standard scalar type completely determined by its <see cref="DataViewType.RawType"/>
/// (not a <see cref="KeyDataViewType"/> or <see cref="StructuredDataViewType"/>, etc).
/// </summary>
public static bool IsStandardScalar(this DataViewType columnType) =>
(columnType is NumberDataViewType) || (columnType is TextDataViewType) || (columnType is BooleanDataViewType) ||
(columnType is RowIdDataViewType) || (columnType is TimeSpanDataViewType) ||
(columnType is DateTimeDataViewType) || (columnType is DateTimeOffsetDataViewType);

/// <summary>
/// Zero return means it's not a key type.
/// </summary>
public static ulong GetKeyCount(this DataViewType columnType) => (columnType as KeyDataViewType)?.Count ?? 0;

/// <summary>
/// Sometimes it is necessary to cast the Count to an int. This performs overflow check.
/// Zero return means it's not a key type.
/// </summary>
public static int GetKeyCountAsInt32(this DataViewType columnType, IExceptionContext ectx = null)
{
ulong count = columnType.GetKeyCount();
ectx.Check(count <= int.MaxValue, nameof(KeyDataViewType) + "." + nameof(KeyDataViewType.Count) + " exceeds int.MaxValue.");
return (int)count;
}
ulong count = columnType.GetKeyCount();
ectx.Check(count <= int.MaxValue, nameof(KeyDataViewType) + "." + nameof(KeyDataViewType.Count) + " exceeds int.MaxValue.");
return (int)count;
}

/// <summary>
/// For non-vector types, this returns the column type itself (i.e., return <paramref name="columnType"/>).
/// For vector types, this returns the type of the items stored as values in vector.
/// </summary>
public static DataViewType GetItemType(this DataViewType columnType) => (columnType as VectorDataViewType)?.ItemType ?? columnType;

/// <summary>
/// Zero return means either it's not a vector or the size is unknown.
/// </summary>
public static int GetVectorSize(this DataViewType columnType) => (columnType as VectorDataViewType)?.Size ?? 0;

/// <summary>
/// For non-vectors, this returns one. For unknown size vectors, it returns zero.
/// For known sized vectors, it returns size.
/// </summary>
public static int GetValueCount(this DataViewType columnType) => (columnType as VectorDataViewType)?.Size ?? 1;

/// <summary>
/// Whether this is a vector type with known size. Returns false for non-vector types.
/// Equivalent to <c><see cref="GetVectorSize"/> &gt; 0</c>.
/// </summary>
public static bool IsKnownSizeVector(this DataViewType columnType) => columnType.GetVectorSize() > 0;

/// <summary>
/// Gets the equivalent <see cref="InternalDataKind"/> for the <paramref name="columnType"/>'s RawType.
/// This can return default(<see cref="InternalDataKind"/>) if the RawType doesn't have a corresponding
/// <see cref="InternalDataKind"/>.
/// </summary>
public static InternalDataKind GetRawKind(this DataViewType columnType)
{
columnType.RawType.TryGetDataKind(out InternalDataKind result);
return result;
}
/// <summary>
/// For non-vector types, this returns the column type itself (i.e., return <paramref name="columnType"/>).
/// For vector types, this returns the type of the items stored as values in vector.
/// </summary>
public static DataViewType GetItemType(this DataViewType columnType) => (columnType as VectorDataViewType)?.ItemType ?? columnType;

/// <summary>
/// Equivalent to calling Equals(ColumnType) for non-vector types. For vector type,
/// returns true if current and other vector types have the same size and item type.
/// </summary>
public static bool SameSizeAndItemType(this DataViewType columnType, DataViewType other)
{
if (other == null)
return false;

if (columnType.Equals(other))
return true;

// For vector types, we don't care about the factoring of the dimensions.
if (!(columnType is VectorDataViewType vectorType) || !(other is VectorDataViewType otherVectorType))
return false;
if (!vectorType.ItemType.Equals(otherVectorType.ItemType))
return false;
return vectorType.Size == otherVectorType.Size;
}
/// <summary>
/// Zero return means either it's not a vector or the size is unknown.
/// </summary>
public static int GetVectorSize(this DataViewType columnType) => (columnType as VectorDataViewType)?.Size ?? 0;

public static PrimitiveDataViewType PrimitiveTypeFromType(Type type)
{
if (type == typeof(ReadOnlyMemory<char>) || type == typeof(string))
return TextDataViewType.Instance;
if (type == typeof(bool))
return BooleanDataViewType.Instance;
if (type == typeof(TimeSpan))
return TimeSpanDataViewType.Instance;
if (type == typeof(DateTime))
return DateTimeDataViewType.Instance;
if (type == typeof(DateTimeOffset))
return DateTimeOffsetDataViewType.Instance;
if (type == typeof(DataViewRowId))
return RowIdDataViewType.Instance;
return NumberTypeFromType(type);
}
/// <summary>
/// For non-vectors, this returns one. For unknown size vectors, it returns zero.
/// For known sized vectors, it returns size.
/// </summary>
public static int GetValueCount(this DataViewType columnType) => (columnType as VectorDataViewType)?.Size ?? 1;

public static PrimitiveDataViewType PrimitiveTypeFromKind(InternalDataKind kind)
{
if (kind == InternalDataKind.TX)
return TextDataViewType.Instance;
if (kind == InternalDataKind.BL)
return BooleanDataViewType.Instance;
if (kind == InternalDataKind.TS)
return TimeSpanDataViewType.Instance;
if (kind == InternalDataKind.DT)
return DateTimeDataViewType.Instance;
if (kind == InternalDataKind.DZ)
return DateTimeOffsetDataViewType.Instance;
if (kind == InternalDataKind.UG)
return RowIdDataViewType.Instance;
return NumberTypeFromKind(kind);
}
/// <summary>
/// Whether this is a vector type with known size. Returns false for non-vector types.
/// Equivalent to <c><see cref="GetVectorSize"/> &gt; 0</c>.
/// </summary>
public static bool IsKnownSizeVector(this DataViewType columnType) => columnType.GetVectorSize() > 0;

public static NumberDataViewType NumberTypeFromType(Type type)
{
InternalDataKind kind;
if (type.TryGetDataKind(out kind))
return NumberTypeFromKind(kind);
/// <summary>
/// Gets the equivalent <see cref="InternalDataKind"/> for the <paramref name="columnType"/>'s RawType.
/// This can return default(<see cref="InternalDataKind"/>) if the RawType doesn't have a corresponding
/// <see cref="InternalDataKind"/>.
/// </summary>
public static InternalDataKind GetRawKind(this DataViewType columnType)
{
columnType.RawType.TryGetDataKind(out InternalDataKind result);
return result;
}

Contracts.Assert(false);
throw new InvalidOperationException($"Bad type in {nameof(ColumnTypeExtensions)}.{nameof(NumberTypeFromType)}: {type}");
}
/// <summary>
/// Equivalent to calling Equals(ColumnType) for non-vector types. For vector type,
/// returns true if current and other vector types have the same size and item type.
/// </summary>
public static bool SameSizeAndItemType(this DataViewType columnType, DataViewType other)
{
if (other == null)
return false;

if (columnType.Equals(other))
return true;

// For vector types, we don't care about the factoring of the dimensions.
if (!(columnType is VectorDataViewType vectorType) || !(other is VectorDataViewType otherVectorType))
return false;
if (!vectorType.ItemType.Equals(otherVectorType.ItemType))
return false;
return vectorType.Size == otherVectorType.Size;
}

private static NumberDataViewType NumberTypeFromKind(InternalDataKind kind)
public static PrimitiveDataViewType PrimitiveTypeFromType(Type type)
{
if (type == typeof(ReadOnlyMemory<char>) || type == typeof(string))
return TextDataViewType.Instance;
if (type == typeof(bool))
return BooleanDataViewType.Instance;
if (type == typeof(TimeSpan))
return TimeSpanDataViewType.Instance;
if (type == typeof(DateTime))
return DateTimeDataViewType.Instance;
if (type == typeof(DateTimeOffset))
return DateTimeOffsetDataViewType.Instance;
if (type == typeof(DataViewRowId))
return RowIdDataViewType.Instance;
return NumberTypeFromType(type);
}

public static PrimitiveDataViewType PrimitiveTypeFromKind(InternalDataKind kind)
{
if (kind == InternalDataKind.TX)
return TextDataViewType.Instance;
if (kind == InternalDataKind.BL)
return BooleanDataViewType.Instance;
if (kind == InternalDataKind.TS)
return TimeSpanDataViewType.Instance;
if (kind == InternalDataKind.DT)
return DateTimeDataViewType.Instance;
if (kind == InternalDataKind.DZ)
return DateTimeOffsetDataViewType.Instance;
if (kind == InternalDataKind.UG)
return RowIdDataViewType.Instance;
return NumberTypeFromKind(kind);
}

public static NumberDataViewType NumberTypeFromType(Type type)
{
InternalDataKind kind;
if (type.TryGetDataKind(out kind))
return NumberTypeFromKind(kind);

Contracts.Assert(false);
throw new InvalidOperationException($"Bad type in {nameof(ColumnTypeExtensions)}.{nameof(NumberTypeFromType)}: {type}");
}

private static NumberDataViewType NumberTypeFromKind(InternalDataKind kind)
{
switch (kind)
{
switch (kind)
{
case InternalDataKind.I1:
return NumberDataViewType.SByte;
case InternalDataKind.U1:
return NumberDataViewType.Byte;
case InternalDataKind.I2:
return NumberDataViewType.Int16;
case InternalDataKind.U2:
return NumberDataViewType.UInt16;
case InternalDataKind.I4:
return NumberDataViewType.Int32;
case InternalDataKind.U4:
return NumberDataViewType.UInt32;
case InternalDataKind.I8:
return NumberDataViewType.Int64;
case InternalDataKind.U8:
return NumberDataViewType.UInt64;
case InternalDataKind.R4:
return NumberDataViewType.Single;
case InternalDataKind.R8:
return NumberDataViewType.Double;
}

Contracts.Assert(false);
throw new InvalidOperationException($"Bad data kind in {nameof(ColumnTypeExtensions)}.{nameof(NumberTypeFromKind)}: {kind}");
case InternalDataKind.I1:
return NumberDataViewType.SByte;
case InternalDataKind.U1:
return NumberDataViewType.Byte;
case InternalDataKind.I2:
return NumberDataViewType.Int16;
case InternalDataKind.U2:
return NumberDataViewType.UInt16;
case InternalDataKind.I4:
return NumberDataViewType.Int32;
case InternalDataKind.U4:
return NumberDataViewType.UInt32;
case InternalDataKind.I8:
return NumberDataViewType.Int64;
case InternalDataKind.U8:
return NumberDataViewType.UInt64;
case InternalDataKind.R4:
return NumberDataViewType.Single;
case InternalDataKind.R8:
return NumberDataViewType.Double;
}

Contracts.Assert(false);
throw new InvalidOperationException($"Bad data kind in {nameof(ColumnTypeExtensions)}.{nameof(NumberTypeFromKind)}: {kind}");
}
}
Loading
Loading