private void CompareInstances(TlcTextInstances instances1, TlcTextInstances instances2)
{
Assert.IsTrue(instances1.Schema.NumFeatures == instances2.Schema.NumFeatures, "mismatch on schema features");
using (var e1 = instances1.GetEnumerator())
using (var e2 = instances2.GetEnumerator())
{
for (; ;)
{
bool b1 = e1.MoveNext();
bool b2 = e2.MoveNext();
Assert.IsTrue(b1 == b2, "different number of instances");
if (!b1)
{
break;
}
var inst1 = e1.Current;
var inst2 = e2.Current;
Assert.IsTrue(inst1.Label == inst2.Label, "mismatch on instance label");
Assert.IsTrue(inst1.NumFeatures == inst2.NumFeatures, "mismatch on number of features");
Assert.IsTrue(inst1.NumFeatures == instances1.Schema.NumFeatures, "mismatch on number of instance vs. schema features");
Assert.IsTrue(Utils.AreEqual(inst1.Features.Values, inst2.Features.Values), "mismatch on feature values");
Assert.IsTrue(Utils.AreEqual(inst1.Features.Indices, inst2.Features.Indices), "mismatch on feature indices");
}
}
}
public void TestCreateTextInstancesWithNormalization()
{
TestDataset dataset = TestDatasets.mnistTiny28;
string trainData = GetDataPath(dataset.trainFilename);
string testData = GetDataPath(dataset.testFilename);
var prefix = TestContext.TestName + "-";
string outFile1 = DeleteOutputPath(Dir, prefix + "Norm-Separate-Train.txt");
string outTestFile1 = DeleteOutputPath(Dir, prefix + "Norm-Separate-Test.txt");
string outFile2 = DeleteOutputPath(Dir, prefix + "Norm-Trans-Train.txt");
string outTestFile2 = DeleteOutputPath(Dir, prefix + "Norm-Trans-Test.txt");
string transArgs = "inst=Trans{trans=RFF {rng=1}}";
var argsStr1 = string.Format(
"/c=CreateInstances {0} /test={1} /norm=MinMaxNormalizer /{2} /cifile={3} /citestfile={4}",
trainData, testData, transArgs, outFile1, outTestFile1);
var args1 = new TLCArguments();
Assert.IsTrue(CmdParser.ParseArguments(argsStr1, args1));
RunExperiments.Run(args1);
var argsStr2 = string.Format(
"/c=CreateInstances {0} /test={1} /inst Trans{{trans=MinMaxNormalizer {2}}} /cifile={3} /citestfile={4}",
trainData, testData, transArgs, outFile2, outTestFile2);
var args2 = new TLCArguments();
Assert.IsTrue(CmdParser.ParseArguments(argsStr2, args2));
RunExperiments.Run(args2);
var instances1 = new TlcTextInstances(new TlcTextInstances.Arguments(), outFile1);
var instances2 = new TlcTextInstances(new TlcTextInstances.Arguments(), outFile2);
CompareInstances(instances1, instances2);
var testInstances1 = new TlcTextInstances(new TlcTextInstances.Arguments(), outTestFile1);
var testInstances2 = new TlcTextInstances(new TlcTextInstances.Arguments(), outTestFile2);
CompareInstances(testInstances1, testInstances2);
Done();
}
public void TestPcaTransform()
{
// Force Microsoft.ML.Runtime.PCA assembly to be loaded into the AppDomain so
// ReflectionUtils.FindClassCore does not return null when called by ReflectionUtils.CreateInstance
Assert.AreEqual(typeof(PCAPredictor).Name, "PCAPredictor");
string trainData = GetDataPath(TestDatasets.mnistTiny28.trainFilename);
string fileName = TestContext.TestName + "-Train.txt";
string outFile = DeleteOutputPath(Dir, fileName);
const int rank = 3;
string pcaTransformArgs = string.Format("/inst Trans{{trans=pca {{k={0} seed=1}}}}", rank);
var argsStr1 = string.Format(
"/c CreateInstances {0} {1} /rs=1 /cifile={2}",
trainData,
pcaTransformArgs,
outFile);
var args1 = new TLCArguments();
Assert.IsTrue(CmdParser.ParseArguments(argsStr1, args1));
RunExperiments.Run(args1);
CheckEquality(Dir, fileName);
// Verify the scales of the transformed features decrease with respect to the feature index
TlcTextInstances outputInstances = new TlcTextInstances(new TlcTextInstances.Arguments(), outFile);
Double[] l1norms = new Double[rank];
foreach (Instance instance in outputInstances)
{
Assert.IsTrue(instance.Features.Count == rank);
for (int i = 0; i < instance.Features.Values.Length; i++)
{
l1norms[i] += (instance.Features.Values[i] < 0 ? -instance.Features.Values[i] : instance.Features.Values[i]);
}
}
for (int i = 0; i < l1norms.Length - 1; i++)
{
Assert.IsTrue(l1norms[i] > l1norms[i + 1]);
}
Done();
}
