private void HashTestCore <T>(T val, PrimitiveDataViewType type, uint expected, uint expectedOrdered, uint expectedOrdered3, uint expectedCombined, uint expectedCombinedSparse)
{
const int bits = 10;
var builder = new DataViewSchema.Annotations.Builder();
builder.AddPrimitiveValue("Foo", type, val);
var inRow = AnnotationUtils.AnnotationsAsRow(builder.ToAnnotations());
//helper
ValueGetter <TType> hashGetter <TType>(HashingEstimator.ColumnOptions colInfo)
{
var xf = new HashingTransformer(Env, new[] { colInfo });
var mapper = ((ITransformer)xf).GetRowToRowMapper(inRow.Schema);
var col = mapper.OutputSchema["Bar"];
var outRow = mapper.GetRow(inRow, col);
return(outRow.GetGetter <TType>(col));
};
// First do an unordered hash.
var info = new HashingEstimator.ColumnOptions("Bar", "Foo", numberOfBits: bits);
var getter = hashGetter <uint>(info);
uint result = 0;
getter(ref result);
Assert.Equal(expected, result);
// Next do an ordered hash.
info = new HashingEstimator.ColumnOptions("Bar", "Foo", numberOfBits: bits, useOrderedHashing: true);
getter = hashGetter <uint>(info);
getter(ref result);
Assert.Equal(expectedOrdered, result);
// Next build up a vector to make sure that hashing is consistent between scalar values
// at least in the first position, and in the unordered case, the last position.
const int vecLen = 5;
var denseVec = new VBuffer <T>(vecLen, Utils.CreateArray(vecLen, val));
builder = new DataViewSchema.Annotations.Builder();
builder.Add("Foo", new VectorDataViewType(type, vecLen), (ref VBuffer <T> dst) => denseVec.CopyTo(ref dst));
inRow = AnnotationUtils.AnnotationsAsRow(builder.ToAnnotations());
info = new HashingEstimator.ColumnOptions("Bar", "Foo", numberOfBits: bits, useOrderedHashing: false);
var vecGetter = hashGetter <VBuffer <uint> >(info);
VBuffer <uint> vecResult = default;
vecGetter(ref vecResult);
Assert.Equal(vecLen, vecResult.Length);
// They all should equal this in this case.
Assert.All(vecResult.DenseValues(), v => Assert.Equal(expected, v));
// Now do ordered with the dense vector.
info = new HashingEstimator.ColumnOptions("Bar", "Foo", numberOfBits: bits, useOrderedHashing: true);
vecGetter = hashGetter <VBuffer <uint> >(info);
vecGetter(ref vecResult);
Assert.Equal(vecLen, vecResult.Length);
Assert.Equal(expectedOrdered, vecResult.GetItemOrDefault(0));
Assert.Equal(expectedOrdered3, vecResult.GetItemOrDefault(3));
Assert.All(vecResult.DenseValues(), v => Assert.True((v == 0) == (expectedOrdered == 0)));
// Now combine into one hash.
info = new HashingEstimator.ColumnOptions("Bar", "Foo", numberOfBits: bits, combine: true);
getter = hashGetter <uint>(info);
getter(ref result);
Assert.Equal(expectedCombined, result);
// Let's now do a sparse vector.
var sparseVec = new VBuffer <T>(10, 3, Utils.CreateArray(3, val), new[] { 0, 3, 7 });
builder = new DataViewSchema.Annotations.Builder();
builder.Add("Foo", new VectorDataViewType(type, vecLen), (ref VBuffer <T> dst) => sparseVec.CopyTo(ref dst));
inRow = AnnotationUtils.AnnotationsAsRow(builder.ToAnnotations());
info = new HashingEstimator.ColumnOptions("Bar", "Foo", numberOfBits: bits, useOrderedHashing: false);
vecGetter = hashGetter <VBuffer <uint> >(info);
vecGetter(ref vecResult);
Assert.Equal(10, vecResult.Length);
Assert.Equal(expected, vecResult.GetItemOrDefault(0));
Assert.Equal(expected, vecResult.GetItemOrDefault(3));
Assert.Equal(expected, vecResult.GetItemOrDefault(7));
info = new HashingEstimator.ColumnOptions("Bar", "Foo", numberOfBits: bits, useOrderedHashing: true);
vecGetter = hashGetter <VBuffer <uint> >(info);
vecGetter(ref vecResult);
Assert.Equal(10, vecResult.Length);
Assert.Equal(expectedOrdered, vecResult.GetItemOrDefault(0));
Assert.Equal(expectedOrdered3, vecResult.GetItemOrDefault(3));
info = new HashingEstimator.ColumnOptions("Bar", "Foo", numberOfBits: bits, combine: true);
getter = hashGetter <uint>(info);
getter(ref result);
Assert.Equal(expectedCombinedSparse, result);
}