public static SchemaImpl Create(ModelLoadContext ctx, IExceptionContext ectx, ISchema inputSchema)
{
Contracts.AssertValueOrNull(ectx);
ectx.AssertValue(ctx);
ectx.AssertValue(inputSchema);
// *** Binary format ***
// int: ungroup mode
// int: K - number of pivot columns
// int[K]: ids of pivot column names
int modeIndex = ctx.Reader.ReadInt32();
ectx.CheckDecode(Enum.IsDefined(typeof(UngroupMode), modeIndex));
UngroupMode mode = (UngroupMode)modeIndex;
int k = ctx.Reader.ReadInt32();
ectx.CheckDecode(k > 0);
var pivotColumns = new string[k];
for (int i = 0; i < k; i++)
{
pivotColumns[i] = ctx.LoadNonEmptyString();
}
return(new SchemaImpl(ectx, inputSchema, mode, pivotColumns));
}
public UngroupBinding(IExceptionContext ectx, Schema inputSchema, UngroupMode mode, string[] pivotColumns)
{
Contracts.AssertValueOrNull(ectx);
_ectx = ectx;
_ectx.AssertValue(inputSchema);
_ectx.AssertNonEmpty(pivotColumns);
_inputSchema = inputSchema; // This also makes InputColumnCount valid.
Mode = mode;
Bind(_ectx, inputSchema, pivotColumns, out _infos);
_pivotIndex = Utils.CreateArray(InputColumnCount, -1);
for (int i = 0; i < _infos.Length; i++)
{
var info = _infos[i];
_ectx.Assert(_pivotIndex[info.Index] == -1);
_pivotIndex[info.Index] = i;
}
var schemaBuilder = new SchemaBuilder();
// Iterate through input columns. Input columns which are not pivot columns will be copied to output schema with the same column index unchanged.
// Input columns which are pivot columns would also be copied but with different data types and different metadata.
for (int i = 0; i < InputColumnCount; ++i)
{
if (_pivotIndex[i] < 0)
{
// i-th input column is not a pivot column. Let's do a naive copy.
schemaBuilder.AddColumn(inputSchema[i].Name, inputSchema[i].Type, inputSchema[i].Metadata);
}
else
{
// i-th input column is a pivot column. Let's calculate proper type and metadata for it.
var metadataBuilder = new MetadataBuilder();
metadataBuilder.Add(inputSchema[i].Metadata, metadataName => ShouldPreserveMetadata(metadataName));
// To explain the output type of pivot columns, let's consider a row
// Age UserID
// 18 {"Amy", "Willy"}
// where "Age" and "UserID" are column names and 18/{"Amy", "Willy"} is "Age"/"UserID" column in this example row.
// If the only pivot column is "UserID", the ungroup may produce
// Age UserID
// 18 "Amy"
// 18 "Willy"
// One can see that "UserID" column (in output data) has a type identical to the element's type of the "UserID" column in input data.
schemaBuilder.AddColumn(inputSchema[i].Name, inputSchema[i].Type.GetItemType(), metadataBuilder.GetMetadata());
}
}
OutputSchema = schemaBuilder.GetSchema();
}
public SchemaImpl(IExceptionContext ectx, ISchema inputSchema, UngroupMode mode, string[] pivotColumns)
{
Contracts.AssertValueOrNull(ectx);
_ectx = ectx;
_ectx.AssertValue(inputSchema);
_ectx.AssertNonEmpty(pivotColumns);
_inputSchema = inputSchema;
Mode = mode;
CheckAndBind(_ectx, inputSchema, pivotColumns, out _infos);
_pivotColMap = new Dictionary <string, int>();
_pivotIndex = Utils.CreateArray(_inputSchema.ColumnCount, -1);
for (int i = 0; i < _infos.Length; i++)
{
var info = _infos[i];
_pivotColMap[info.Name] = info.Index;
_ectx.Assert(_pivotIndex[info.Index] == -1);
_pivotIndex[info.Index] = i;
}
}
/// <summary>
/// Convenience constructor for public facing API.
/// </summary>
/// <param name="env">Host Environment.</param>
/// <param name="input">Input <see cref="IDataView"/>. This is the output from previous transform or loader.</param>
/// <param name="mode">Specifies how to unroll multiple pivot columns of different size.</param>
/// <param name="columns">Columns to unroll, or 'pivot'</param>
public UngroupTransform(IHostEnvironment env, IDataView input, UngroupMode mode, params string[] columns)
: this(env, new Arguments() { Column = columns, Mode = mode }, input)
{
}
