public void TestI_ScalerTransformSerialize()
{
using (var host = EnvHelper.NewTestEnvironment())
{
var inputs = new[] {
new ExampleA()
{
X = new float[] { 1, 10, 100 }
},
new ExampleA()
{
X = new float[] { 2, 3, 5 }
}
};
IDataView loader = host.CreateStreamingDataView(inputs);
var data = host.CreateTransform("Scaler{col=X}", loader);
(data as ITrainableTransform).Estimate();
// We create a specific folder in build/UnitTest which will contain the output.
var methodName = System.Reflection.MethodBase.GetCurrentMethod().Name;
var outModelFilePath = FileHelper.GetOutputFile("outModelFilePath.zip", methodName);
var outData = FileHelper.GetOutputFile("outData.txt", methodName);
var outData2 = FileHelper.GetOutputFile("outData2.txt", methodName);
var nb = DataViewUtils.ComputeRowCount(data);
if (nb < 1)
{
throw new Exception("empty view");
}
// This function serializes the output data twice, once before saving the pipeline, once after loading the pipeline.
// It checks it gives the same result.
TestTransformHelper.SerializationTestTransform(host, outModelFilePath, data, loader, outData, outData2);
}
}
public void TestTagViewTransform()
{
using (var host = EnvHelper.NewTestEnvironment())
{
var inputs = new[] {
new ExampleA()
{
X = new float[] { 0, 1 }
},
new ExampleA()
{
X = new float[] { 2, 3 }
}
};
IDataView loader = host.CreateStreamingDataView(inputs);
var data = host.CreateTransform("Scaler{col=X1:X}", loader);
data = host.CreateTransform("tag{t=memory}", data);
var methodName = System.Reflection.MethodBase.GetCurrentMethod().Name;
var outModelFilePath = FileHelper.GetOutputFile("outModelFilePath.zip", methodName);
var outData = FileHelper.GetOutputFile("outData.txt", methodName);
var outData2 = FileHelper.GetOutputFile("outData2.txt", methodName);
TestTransformHelper.SerializationTestTransform(host, outModelFilePath, data, loader, outData, outData2);
}
}
public void TestI_PolynomialTransformSerialize()
{
using (var host = EnvHelper.NewTestEnvironment())
{
var inputs = new[] {
new ExampleA()
{
X = new float[] { 1, 10, 100 }
},
new ExampleA()
{
X = new float[] { 2, 3, 5 }
}
};
IDataView loader = host.CreateStreamingDataView(inputs);
var data = host.CreateTransform("poly{col=poly:X d=3}", loader);
// We create a specific folder in build/UnitTest which will contain the output.
var methodName = System.Reflection.MethodBase.GetCurrentMethod().Name;
var outModelFilePath = FileHelper.GetOutputFile("outModelFilePath.zip", methodName);
var outData = FileHelper.GetOutputFile("outData.txt", methodName);
var outData2 = FileHelper.GetOutputFile("outData2.txt", methodName);
// This function serializes the output data twice, once before saving the pipeline, once after loading the pipeline.
// It checks it gives the same result.
TestTransformHelper.SerializationTestTransform(host, outModelFilePath, data, loader, outData, outData2);
}
}
public void TestChainTransformSerialize()
{
using (var host = EnvHelper.NewTestEnvironment())
{
var inputs = new[] {
new ExampleA()
{
X = new float[] { 1, 10, 100 }
},
new ExampleA()
{
X = new float[] { 2, 3, 5 }
}
};
IDataView loader = host.CreateStreamingDataView(inputs);
IDataTransform data = host.CreateTransform("Scaler{col=X4:X}", loader);
data = host.CreateTransform("ChainTrans{ xf1=Scaler{col=X2:X} xf2=Poly{col=X3:X2} }", data);
// We create a specific folder in build/UnitTest which will contain the output.
var methodName = System.Reflection.MethodBase.GetCurrentMethod().Name;
var outModelFilePath = FileHelper.GetOutputFile("outModelFilePath.zip", methodName);
var outData = FileHelper.GetOutputFile("outData.txt", methodName);
var outData2 = FileHelper.GetOutputFile("outData2.txt", methodName);
TestTransformHelper.SerializationTestTransform(host, outModelFilePath, data, loader, outData, outData2);
}
}
public void TestDBScanTransform()
{
var methodName = System.Reflection.MethodBase.GetCurrentMethod().Name;
var dataFilePath = FileHelper.GetTestFile("three_classes_2d.txt");
var outputDataFilePath = FileHelper.GetOutputFile("outputDataFilePath.txt", methodName);
var outModelFilePath = FileHelper.GetOutputFile("outModelFilePath.zip", methodName);
using (var env = EnvHelper.NewTestEnvironment(conc: 1))
{
//var loader = env.CreateLoader("text{col=RowId:I4:0 col=Features:R4:1-2 header=+}", new MultiFileSource(dataFilePath));
var loader = TextLoader.Create(env, new TextLoader.Arguments()
{
HasHeader = true,
Column = new[] { TextLoader.Column.Parse("RowId:R4:0"),
TextLoader.Column.Parse("Features:R4:1-2") }
},
new MultiFileSource(dataFilePath));
var xf = env.CreateTransform("DBScan{col=Features}", loader);
string schema = SchemaHelper.ToString(xf.Schema);
if (string.IsNullOrEmpty(schema))
{
throw new Exception("Schema is null.");
}
if (!schema.Contains("Cluster"))
{
throw new Exception("Schema does not contain Cluster.");
}
if (!schema.Contains("Score"))
{
throw new Exception("Schema does not contain Score.");
}
StreamHelper.SaveModel(env, xf, outModelFilePath);
var saver = env.CreateSaver("Text{header=- schema=-}");
using (var fs2 = File.Create(outputDataFilePath))
saver.SaveData(fs2, TestTransformHelper.AddFlatteningTransform(env, xf),
StreamHelper.GetColumnsIndex(xf.Schema, new[] { "Features", "ClusterId", "Score" }));
// Checking the values.
var lines = File.ReadAllLines(outputDataFilePath).Select(c => c.Split('\t')).Where(c => c.Length == 4);
if (!lines.Any())
{
throw new Exception(string.Format("The output file is empty or not containing three columns '{0}'", outputDataFilePath));
}
var clusters = lines.Select(c => c[1]).Distinct();
if (clusters.Count() <= 1)
{
throw new Exception("Only one cluster, this is unexpected.");
}
// Serialization.
var outData = FileHelper.GetOutputFile("outData1.txt", methodName);
var outData2 = FileHelper.GetOutputFile("outData2.txt", methodName);
TestTransformHelper.SerializationTestTransform(env, outModelFilePath, xf, loader, outData, outData2);
}
}
public void TrainTestPipelinePredictTransform()
{
var methodName = System.Reflection.MethodBase.GetCurrentMethod().Name;
var dataFilePath = FileHelper.GetTestFile("mc_iris.txt");
var outModelFilePath = FileHelper.GetOutputFile("outModelFilePath.zip", methodName);
var outData = FileHelper.GetOutputFile("outData1.txt", methodName);
var outData2 = FileHelper.GetOutputFile("outData2.txt", methodName);
using (var env = EnvHelper.NewTestEnvironment(conc: 1))
{
var loader = env.CreateLoader("Text{col=Label:R4:0 col=Slength:R4:1 col=Swidth:R4:2 col=Plength:R4:3 col=Pwidth:R4:4 header=+}",
new MultiFileSource(dataFilePath));
var pipe = env.CreateTransform("Concat{col=Features:Slength,Swidth}", loader);
pipe = env.CreateTransform("SplitTrainTest{col=base tag=train tag=test}", pipe);
pipe = env.CreateTransform("SelectTag{tag=unused selectTag=train}", pipe);
pipe = env.CreateTransform(string.Format("TagTrainScore{{tag=trainP out={0} tr=mlr}}", outModelFilePath), pipe);
pipe = env.CreateTransform("SelectTag{tag=scoredTrain selectTag=test}", pipe);
pipe = env.CreateTransform("TagPredict{in=trainP}", pipe);
string schema = SchemaHelper.ToString(pipe.Schema);
var cursor = pipe.GetRowCursor(i => true);
string schema2 = SchemaHelper.ToString(cursor.Schema);
if (schema != schema2)
{
throw new Exception("Schema mismatch.");
}
long count = DataViewUtils.ComputeRowCount(pipe);
if (count != 49)
{
throw new Exception(string.Format("Unexpected number of rows {0}", count));
}
// Checks the outputs.
var saver = env.CreateSaver("Text");
var columns = new string[pipe.Schema.Count];
for (int i = 0; i < columns.Length; ++i)
{
columns[i] = pipe.Schema[i].Name;
}
using (var fs2 = File.Create(outData))
saver.SaveData(fs2, pipe, StreamHelper.GetColumnsIndex(pipe.Schema));
var lines = File.ReadAllLines(outData);
if (lines.Length < 40)
{
throw new Exception("Something is missing:" + string.Join("\n", lines));
}
if (lines.Length > 70)
{
throw new Exception("Too much data:" + string.Join("\n", lines));
}
TestTransformHelper.SerializationTestTransform(env, outModelFilePath, pipe, loader, outData, outData2);
}
}
public void TestOpticsOrderingTransform()
{
var methodName = System.Reflection.MethodBase.GetCurrentMethod().Name;
var dataFilePath = FileHelper.GetTestFile("three_classes_2d.txt");
var outputDataFilePath = FileHelper.GetOutputFile("outputDataFilePath.txt", methodName);
var outModelFilePath = FileHelper.GetOutputFile("outModelFilePath.zip", methodName);
/*using (*/ var env = EnvHelper.NewTestEnvironment();
{
var loader = env.CreateLoader("text{col=DataViewRowId:I4:0 col=Features:R4:1-2 header=+}",
new MultiFileSource(dataFilePath));
var xf = env.CreateTransform("OpticsOrd{col=Features epsilon=0.3 minPoints=6}", loader);
string schema = SchemaHelper.ToString(xf.Schema);
if (string.IsNullOrEmpty(schema))
{
throw new Exception("DataViewSchema is null.");
}
if (!schema.Contains("Ordering"))
{
throw new Exception("DataViewSchema does not contain Ordering.");
}
if (!schema.Contains("Reachability"))
{
throw new Exception("DataViewSchema does not contain Reachability.");
}
StreamHelper.SaveModel(env, xf, outModelFilePath);
var saver = env.CreateSaver("Text{header=- schema=-}");
using (var fs2 = File.Create(outputDataFilePath))
{
saver.SaveData(fs2, TestTransformHelper.AddFlatteningTransform(env, xf),
StreamHelper.GetColumnsIndex(xf.Schema, new[] { "Features", "Ordering", "Reachability" }));
}
// Checking the values.
var lines = File.ReadAllLines(outputDataFilePath).Select(c => c.Split('\t')).Where(c => c.Length == 4);
if (!lines.Any())
{
throw new Exception(string.Format("The output file is empty or not containing three columns '{0}'", outputDataFilePath));
}
var clusters = lines.Select(c => c[1]).Distinct();
if (clusters.Count() <= 1)
{
throw new Exception("Only one cluster, this is unexpected.");
}
// Serialization.
var outData = FileHelper.GetOutputFile("outData1.txt", methodName);
var outData2 = FileHelper.GetOutputFile("outData2.txt", methodName);
TestTransformHelper.SerializationTestTransform(env, outModelFilePath, xf, loader, outData, outData2);
}
}
public void TestTimeSeriesDeTrendSerialize()
{
using (var host = EnvHelper.NewTestEnvironment())
{
var inputs = new[] {
new InputOutput()
{
X = 7f, time = 0f
},
new InputOutput()
{
X = 7f, time = 1f
},
new InputOutput()
{
X = 9f, time = 2f
},
new InputOutput()
{
X = 9f, time = 3f
},
new InputOutput()
{
X = 8f, time = 4f
},
};
IDataView loader = host.CreateStreamingDataView(inputs);
var data = host.CreateTransform("detrend{col=Y:X time=time optim=sasdcar{iter=50}}", loader);
// To train the model.
using (var cursor = data.GetRowCursor(i => true)) { }
var methodName = System.Reflection.MethodBase.GetCurrentMethod().Name;
var outModelFilePath = FileHelper.GetOutputFile("outModelFilePath.zip", methodName);
var outData = FileHelper.GetOutputFile("outData.txt", methodName);
var outData2 = FileHelper.GetOutputFile("outData2.txt", methodName);
TestTransformHelper.SerializationTestTransform(host, outModelFilePath, data, loader, outData, outData2);
}
}
public void TestI_PassThroughTransform()
{
var methodName = System.Reflection.MethodBase.GetCurrentMethod().Name;
var dataFilePath = FileHelper.GetTestFile("iris.txt");
var outModelFilePath = FileHelper.GetOutputFile("outModelFilePath.zip", methodName);
var outData = FileHelper.GetOutputFile("outData1.txt", methodName);
var outData2 = FileHelper.GetOutputFile("outData2.txt", methodName);
var tempFile = FileHelper.GetOutputFile("dump.idv", methodName);
using (var env = EnvHelper.NewTestEnvironment(conc: 1))
{
var loader = env.CreateLoader("Text{col=Label:R4:0 col=Slength:R4:1 col=Swidth:R4:2 col=Plength:R4:3 col=Pwidth:R4:4 col=Uid:TX:5 header=+}",
new MultiFileSource(dataFilePath));
var xf1 = env.CreateTransform("Concat{col=Feat:Slength,Swidth}", loader);
var xf2 = env.CreateTransform("Scaler{col=Feat}", xf1);
var xf3 = env.CreateTransform(string.Format("DumpView{{s=+ f={0}}}", tempFile), xf2);
TestTransformHelper.SerializationTestTransform(env, outModelFilePath, xf3, loader, outData, outData2, false);
if (!File.Exists(tempFile))
{
throw new FileNotFoundException(tempFile);
}
}
}
public static void TrainkNNTransformId(int k, NearestNeighborsWeights weight, int threads, string distance = "L2")
{
var methodName = string.Format("{0}-k{1}-W{2}-T{3}-D{4}", System.Reflection.MethodBase.GetCurrentMethod().Name, k, weight, threads, distance);
var dataFilePath = FileHelper.GetTestFile("iris_binary_id.txt");
var outModelFilePath = FileHelper.GetOutputFile("outModelFilePath.zip", methodName);
var outData = FileHelper.GetOutputFile("outData1.txt", methodName);
var outData2 = FileHelper.GetOutputFile("outData2.txt", methodName);
var env = k == 1 ? EnvHelper.NewTestEnvironment(conc: 1) : EnvHelper.NewTestEnvironment();
using (env)
{
var loader = env.CreateLoader("Text{col=Label:R4:0 col=Slength:R4:1 col=Swidth:R4:2 col=Plength:R4:3 col=Pwidth:R4:4 col=Uid:I8:5 header=+}",
new MultiFileSource(dataFilePath));
var concat = env.CreateTransform("Concat{col=Features:Slength,Swidth}", loader);
if (distance == "cosine")
{
concat = env.CreateTransform("Scaler{col=Features}", concat);
}
concat = env.CreateTransform("knntr{k=5 id=Uid}", concat);
long nb = DataViewUtils.ComputeRowCount(concat);
if (nb == 0)
{
throw new System.Exception("Empty pipeline.");
}
using (var cursor = concat.GetRowCursor(i => true))
{
var getdist = cursor.GetGetter <VBuffer <float> >(7);
var getid = cursor.GetGetter <VBuffer <long> >(8);
var ddist = new VBuffer <float>();
var did = new VBuffer <long>();
while (cursor.MoveNext())
{
getdist(ref ddist);
getid(ref did);
if (!ddist.IsDense || !did.IsDense)
{
throw new System.Exception("not dense");
}
if (ddist.Count != did.Count)
{
throw new System.Exception("not the same dimension");
}
for (int i = 1; i < ddist.Count; ++i)
{
if (ddist.Values[i - 1] > ddist.Values[i])
{
throw new System.Exception("not sorted");
}
if (did.Values[i] % 2 != 1)
{
throw new System.Exception("wrong id");
}
}
}
}
TestTransformHelper.SerializationTestTransform(env, outModelFilePath, concat, loader, outData, outData2, false);
}
}