public void KeyToBinaryVectorStatic()
{
string dataPath = GetDataPath("breast-cancer.txt");
var reader = TextLoader.CreateReader(Env, ctx => (
ScalarString: ctx.LoadText(1),
VectorString: ctx.LoadText(1, 4)
));
var data = reader.Read(dataPath);
// Non-pigsty Term.
var dynamicData = new TermEstimator(Env, new[] {
new TermTransform.ColumnInfo("ScalarString", "A"),
new TermTransform.ColumnInfo("VectorString", "B")
})
.Fit(data.AsDynamic).Transform(data.AsDynamic);
var data2 = dynamicData.AssertStatic(Env, ctx => (
A: ctx.KeyU4.TextValues.Scalar,
B: ctx.KeyU4.TextValues.Vector));
var est = data2.MakeNewEstimator()
.Append(row => (
ScalarString: row.A.ToBinaryVector(),
VectorString: row.B.ToBinaryVector()));
TestEstimatorCore(est.AsDynamic, data2.AsDynamic, invalidInput: data.AsDynamic);
Done();
}
public void KeyToValuePigsty()
{
string dataPath = GetDataPath("breast-cancer.txt");
var reader = TextLoader.CreateReader(Env, ctx => (
ScalarString: ctx.LoadText(1),
VectorString: ctx.LoadText(1, 4)
));
var data = reader.Read(new MultiFileSource(dataPath));
// Non-pigsty Term.
var dynamicData = new TermEstimator(Env,
new TermTransform.ColumnInfo("ScalarString", "A"),
new TermTransform.ColumnInfo("VectorString", "B"))
.Fit(data.AsDynamic).Transform(data.AsDynamic);
var data2 = dynamicData.AssertStatic(Env, ctx => (
A: ctx.KeyU4.TextValues.Scalar,
B: ctx.KeyU4.TextValues.Vector));
var est = data2.MakeNewEstimator()
.Append(row => (
ScalarString: row.A.ToValue(),
VectorString: row.B.ToValue()));
TestEstimatorCore(est.AsDynamic, data2.AsDynamic, invalidInput: data.AsDynamic);
// Check that term and ToValue are round-trippable.
var dataLeft = new ChooseColumnsTransform(Env, data.AsDynamic, "ScalarString", "VectorString");
var dataRight = new ChooseColumnsTransform(Env, est.Fit(data2).Transform(data2).AsDynamic, "ScalarString", "VectorString");
CheckSameSchemas(dataLeft.Schema, dataRight.Schema);
CheckSameValues(dataLeft, dataRight);
Done();
}