public static CommonOutputs.TransformOutput Apply(IHostEnvironment env, HashJoinTransform.Arguments input)
{
Contracts.CheckValue(env, nameof(env));
env.CheckValue(input, nameof(input));
var h = EntryPointUtils.CheckArgsAndCreateHost(env, "HashJoin", input);
var view = new HashJoinTransform(h, input, input.Data);
return(new CommonOutputs.TransformOutput()
{
Model = new TransformModel(h, view, input.Data),
OutputData = view
});
}
public static string CreateStratificationColumn(IHost host, ref IDataView data, string stratificationColumn = null)
{
host.CheckValue(data, nameof(data));
host.CheckValueOrNull(stratificationColumn);
// Pick a unique name for the stratificationColumn.
const string stratColName = "StratificationKey";
string stratCol = stratColName;
int col;
int j = 0;
while (data.Schema.TryGetColumnIndex(stratCol, out col))
{
stratCol = string.Format("{0}_{1:000}", stratColName, j++);
}
// Construct the stratification column. If user-provided stratification column exists, use HashJoin
// of it to construct the strat column, otherwise generate a random number and use it.
if (stratificationColumn == null)
{
data = new GenerateNumberTransform(host,
new GenerateNumberTransform.Arguments
{
Column = new[] { new GenerateNumberTransform.Column {
Name = stratCol
} }
}, data);
}
else
{
data = new HashJoinTransform(host,
new HashJoinTransform.Arguments
{
Column = new[] { new HashJoinTransform.Column {
Name = stratCol, Source = stratificationColumn
} },
Join = true,
HashBits = 30
}, data);
}
return(stratCol);
}
