/// <summary>
/// Constructs an entrypoint graph from the current pipeline.
/// </summary>
public AutoInference.EntryPointGraphDef ToEntryPointGraph(Experiment experiment = null)
{
_env.CheckValue(Learner.PipelineNode, nameof(Learner.PipelineNode));
var subGraph = experiment ?? _env.CreateExperiment();
// Insert first node
Var <IDataView> lastOutput = new Var <IDataView>();
// Chain transforms
var transformsModels = new List <Var <ITransformModel> >();
var viableTransforms = Transforms.ToList().Where(transform => transform.PipelineNode != null);
foreach (var transform in viableTransforms)
{
transform.PipelineNode.SetInputData(lastOutput);
var returnedDataAndModel1 = transform.PipelineNode.Add(subGraph);
transformsModels.Add(returnedDataAndModel1.Model);
lastOutput = returnedDataAndModel1.OutData;
}
// Add learner
Learner.PipelineNode?.SetInputData(lastOutput);
var returnedDataAndModel2 = Learner.PipelineNode?.Add(subGraph);
// Create single model for featurizing and scoring data,
// if transforms present.
if (Transforms.Length > 0)
{
var modelCombine = new Legacy.Transforms.ManyHeterogeneousModelCombiner
{
TransformModels = new ArrayVar <ITransformModel>(transformsModels.ToArray()),
PredictorModel = returnedDataAndModel2?.Model
};
var modelCombineOutput = subGraph.Add(modelCombine);
return(new AutoInference.EntryPointGraphDef(subGraph, modelCombineOutput.PredictorModel, lastOutput));
}
// No transforms present, so just return predictor's model.
return(new AutoInference.EntryPointGraphDef(subGraph, returnedDataAndModel2?.Model, lastOutput));
}
public void TestCrossValidationMacroWithNonDefaultNames()
{
string dataPath = GetDataPath(@"adult.tiny.with-schema.txt");
var env = new MLContext(42);
var subGraph = env.CreateExperiment();
var textToKey = new Legacy.Transforms.TextToKeyConverter();
textToKey.Column = new[] { new Legacy.Transforms.ValueToKeyMappingTransformerColumn()
{
Name = "Label1", Source = "Label"
} };
var textToKeyOutput = subGraph.Add(textToKey);
var hash = new Legacy.Transforms.HashConverter();
hash.Column = new[] { new Legacy.Transforms.HashJoiningTransformColumn()
{
Name = "GroupId1", Source = "Workclass"
} };
hash.Data = textToKeyOutput.OutputData;
var hashOutput = subGraph.Add(hash);
var learnerInput = new Legacy.Trainers.FastTreeRanker
{
TrainingData = hashOutput.OutputData,
NumThreads = 1,
LabelColumn = "Label1",
GroupIdColumn = "GroupId1"
};
var learnerOutput = subGraph.Add(learnerInput);
var modelCombine = new Legacy.Transforms.ManyHeterogeneousModelCombiner
{
TransformModels = new ArrayVar <TransformModel>(textToKeyOutput.Model, hashOutput.Model),
PredictorModel = learnerOutput.PredictorModel
};
var modelCombineOutput = subGraph.Add(modelCombine);
var experiment = env.CreateExperiment();
var importInput = new Legacy.Data.TextLoader(dataPath);
importInput.Arguments.HasHeader = true;
importInput.Arguments.Column = new TextLoaderColumn[]
{
new TextLoaderColumn {
Name = "Label", Source = new[] { new TextLoaderRange(0) }
},
new TextLoaderColumn {
Name = "Workclass", Source = new[] { new TextLoaderRange(1) }, Type = Legacy.Data.DataKind.Text
},
new TextLoaderColumn {
Name = "Features", Source = new[] { new TextLoaderRange(9, 14) }
}
};
var importOutput = experiment.Add(importInput);
var crossValidate = new Legacy.Models.CrossValidator
{
Data = importOutput.Data,
Nodes = subGraph,
TransformModel = null,
LabelColumn = "Label1",
GroupColumn = "GroupId1",
NameColumn = "Workclass",
Kind = Legacy.Models.MacroUtilsTrainerKinds.SignatureRankerTrainer
};
crossValidate.Inputs.Data = textToKey.Data;
crossValidate.Outputs.PredictorModel = modelCombineOutput.PredictorModel;
var crossValidateOutput = experiment.Add(crossValidate);
experiment.Compile();
experiment.SetInput(importInput.InputFile, new SimpleFileHandle(env, dataPath, false, false));
experiment.Run();
var data = experiment.GetOutput(crossValidateOutput.OverallMetrics);
var schema = data.Schema;
var b = schema.TryGetColumnIndex("NDCG", out int metricCol);
Assert.True(b);
b = schema.TryGetColumnIndex("Fold Index", out int foldCol);
Assert.True(b);
using (var cursor = data.GetRowCursor(col => col == metricCol || col == foldCol))
{
var getter = cursor.GetGetter <VBuffer <double> >(metricCol);
var foldGetter = cursor.GetGetter <ReadOnlyMemory <char> >(foldCol);
ReadOnlyMemory <char> fold = default;
// Get the verage.
b = cursor.MoveNext();
Assert.True(b);
var avg = default(VBuffer <double>);
getter(ref avg);
foldGetter(ref fold);
Assert.True(ReadOnlyMemoryUtils.EqualsStr("Average", fold));
// Get the standard deviation.
b = cursor.MoveNext();
Assert.True(b);
var stdev = default(VBuffer <double>);
getter(ref stdev);
foldGetter(ref fold);
Assert.True(ReadOnlyMemoryUtils.EqualsStr("Standard Deviation", fold));
var stdevValues = stdev.GetValues();
Assert.Equal(2.462, stdevValues[0], 3);
Assert.Equal(2.763, stdevValues[1], 3);
Assert.Equal(3.273, stdevValues[2], 3);
var sumBldr = new BufferBuilder <double>(R8Adder.Instance);
sumBldr.Reset(avg.Length, true);
var val = default(VBuffer <double>);
for (int f = 0; f < 2; f++)
{
b = cursor.MoveNext();
Assert.True(b);
getter(ref val);
foldGetter(ref fold);
sumBldr.AddFeatures(0, in val);
Assert.True(ReadOnlyMemoryUtils.EqualsStr("Fold " + f, fold));
}
var sum = default(VBuffer <double>);
sumBldr.GetResult(ref sum);
var avgValues = avg.GetValues();
var sumValues = sum.GetValues();
for (int i = 0; i < avgValues.Length; i++)
{
Assert.Equal(avgValues[i], sumValues[i] / 2);
}
b = cursor.MoveNext();
Assert.False(b);
}
data = experiment.GetOutput(crossValidateOutput.PerInstanceMetrics);
Assert.True(data.Schema.TryGetColumnIndex("Instance", out int nameCol));
using (var cursor = data.GetRowCursor(col => col == nameCol))
{
var getter = cursor.GetGetter <ReadOnlyMemory <char> >(nameCol);
while (cursor.MoveNext())
{
ReadOnlyMemory <char> name = default;
getter(ref name);
Assert.Subset(new HashSet <string>()
{
"Private", "?", "Federal-gov"
}, new HashSet <string>()
{
name.ToString()
});
if (cursor.Position > 4)
{
break;
}
}
}
}
public void TestCrossValidationMacroWithStratification()
{
var dataPath = GetDataPath(@"breast-cancer.txt");
var env = new MLContext(42);
var subGraph = env.CreateExperiment();
var nop = new Legacy.Transforms.NoOperation();
var nopOutput = subGraph.Add(nop);
var learnerInput = new Legacy.Trainers.StochasticDualCoordinateAscentBinaryClassifier
{
TrainingData = nopOutput.OutputData,
NumThreads = 1
};
var learnerOutput = subGraph.Add(learnerInput);
var modelCombine = new Legacy.Transforms.ManyHeterogeneousModelCombiner
{
TransformModels = new ArrayVar <TransformModel>(nopOutput.Model),
PredictorModel = learnerOutput.PredictorModel
};
var modelCombineOutput = subGraph.Add(modelCombine);
var experiment = env.CreateExperiment();
var importInput = new Legacy.Data.TextLoader(dataPath);
importInput.Arguments.Column = new Legacy.Data.TextLoaderColumn[]
{
new Legacy.Data.TextLoaderColumn {
Name = "Label", Source = new[] { new Legacy.Data.TextLoaderRange(0) }
},
new Legacy.Data.TextLoaderColumn {
Name = "Strat", Source = new[] { new Legacy.Data.TextLoaderRange(1) }
},
new Legacy.Data.TextLoaderColumn {
Name = "Features", Source = new[] { new Legacy.Data.TextLoaderRange(2, 9) }
}
};
var importOutput = experiment.Add(importInput);
var crossValidate = new Legacy.Models.CrossValidator
{
Data = importOutput.Data,
Nodes = subGraph,
TransformModel = null,
StratificationColumn = "Strat"
};
crossValidate.Inputs.Data = nop.Data;
crossValidate.Outputs.PredictorModel = modelCombineOutput.PredictorModel;
var crossValidateOutput = experiment.Add(crossValidate);
experiment.Compile();
experiment.SetInput(importInput.InputFile, new SimpleFileHandle(env, dataPath, false, false));
experiment.Run();
var data = experiment.GetOutput(crossValidateOutput.OverallMetrics);
var schema = data.Schema;
var b = schema.TryGetColumnIndex("AUC", out int metricCol);
Assert.True(b);
b = schema.TryGetColumnIndex("Fold Index", out int foldCol);
Assert.True(b);
using (var cursor = data.GetRowCursor(col => col == metricCol || col == foldCol))
{
var getter = cursor.GetGetter <double>(metricCol);
var foldGetter = cursor.GetGetter <ReadOnlyMemory <char> >(foldCol);
ReadOnlyMemory <char> fold = default;
// Get the verage.
b = cursor.MoveNext();
Assert.True(b);
double avg = 0;
getter(ref avg);
foldGetter(ref fold);
Assert.True(ReadOnlyMemoryUtils.EqualsStr("Average", fold));
// Get the standard deviation.
b = cursor.MoveNext();
Assert.True(b);
double stdev = 0;
getter(ref stdev);
foldGetter(ref fold);
Assert.True(ReadOnlyMemoryUtils.EqualsStr("Standard Deviation", fold));
Assert.Equal(0.00488, stdev, 5);
double sum = 0;
double val = 0;
for (int f = 0; f < 2; f++)
{
b = cursor.MoveNext();
Assert.True(b);
getter(ref val);
foldGetter(ref fold);
sum += val;
Assert.True(ReadOnlyMemoryUtils.EqualsStr("Fold " + f, fold));
}
Assert.Equal(avg, sum / 2);
b = cursor.MoveNext();
Assert.False(b);
}
}
public void TestCrossValidationMacroWithMultiClass()
{
var dataPath = GetDataPath(@"Train-Tiny-28x28.txt");
var env = new MLContext(42);
var subGraph = env.CreateExperiment();
var nop = new Legacy.Transforms.NoOperation();
var nopOutput = subGraph.Add(nop);
var learnerInput = new Legacy.Trainers.StochasticDualCoordinateAscentClassifier
{
TrainingData = nopOutput.OutputData,
NumThreads = 1
};
var learnerOutput = subGraph.Add(learnerInput);
var modelCombine = new Legacy.Transforms.ManyHeterogeneousModelCombiner
{
TransformModels = new ArrayVar <TransformModel>(nopOutput.Model),
PredictorModel = learnerOutput.PredictorModel
};
var modelCombineOutput = subGraph.Add(modelCombine);
var experiment = env.CreateExperiment();
var importInput = new Legacy.Data.TextLoader(dataPath);
var importOutput = experiment.Add(importInput);
var crossValidate = new Legacy.Models.CrossValidator
{
Data = importOutput.Data,
Nodes = subGraph,
Kind = Legacy.Models.MacroUtilsTrainerKinds.SignatureMultiClassClassifierTrainer,
TransformModel = null
};
crossValidate.Inputs.Data = nop.Data;
crossValidate.Outputs.PredictorModel = modelCombineOutput.PredictorModel;
var crossValidateOutput = experiment.Add(crossValidate);
experiment.Compile();
importInput.SetInput(env, experiment);
experiment.Run();
var data = experiment.GetOutput(crossValidateOutput.OverallMetrics);
var schema = data.Schema;
var b = schema.TryGetColumnIndex("Accuracy(micro-avg)", out int metricCol);
Assert.True(b);
b = schema.TryGetColumnIndex("Fold Index", out int foldCol);
Assert.True(b);
using (var cursor = data.GetRowCursor(col => col == metricCol || col == foldCol))
{
var getter = cursor.GetGetter <double>(metricCol);
var foldGetter = cursor.GetGetter <ReadOnlyMemory <char> >(foldCol);
ReadOnlyMemory <char> fold = default;
// Get the average.
b = cursor.MoveNext();
Assert.True(b);
double avg = 0;
getter(ref avg);
foldGetter(ref fold);
Assert.True(ReadOnlyMemoryUtils.EqualsStr("Average", fold));
// Get the standard deviation.
b = cursor.MoveNext();
Assert.True(b);
double stdev = 0;
getter(ref stdev);
foldGetter(ref fold);
Assert.True(ReadOnlyMemoryUtils.EqualsStr("Standard Deviation", fold));
Assert.Equal(0.015, stdev, 3);
double sum = 0;
double val = 0;
for (int f = 0; f < 2; f++)
{
b = cursor.MoveNext();
Assert.True(b);
getter(ref val);
foldGetter(ref fold);
sum += val;
Assert.True(ReadOnlyMemoryUtils.EqualsStr("Fold " + f, fold));
}
Assert.Equal(avg, sum / 2);
b = cursor.MoveNext();
Assert.False(b);
}
var confusion = experiment.GetOutput(crossValidateOutput.ConfusionMatrix);
schema = confusion.Schema;
b = schema.TryGetColumnIndex("Count", out int countCol);
Assert.True(b);
b = schema.TryGetColumnIndex("Fold Index", out foldCol);
Assert.True(b);
var type = schema[countCol].Metadata.Schema[MetadataUtils.Kinds.SlotNames].Type;
Assert.True(type is VectorType vecType && vecType.ItemType is TextType && vecType.Size == 10);
var slotNames = default(VBuffer <ReadOnlyMemory <char> >);
schema[countCol].GetSlotNames(ref slotNames);
var slotNameValues = slotNames.GetValues();
for (int i = 0; i < slotNameValues.Length; i++)
{
Assert.True(ReadOnlyMemoryUtils.EqualsStr(i.ToString(), slotNameValues[i]));
}
using (var curs = confusion.GetRowCursor(col => true))
{
var countGetter = curs.GetGetter <VBuffer <double> >(countCol);
var foldGetter = curs.GetGetter <ReadOnlyMemory <char> >(foldCol);
var confCount = default(VBuffer <double>);
var foldIndex = default(ReadOnlyMemory <char>);
int rowCount = 0;
var foldCur = "Fold 0";
while (curs.MoveNext())
{
countGetter(ref confCount);
foldGetter(ref foldIndex);
rowCount++;
Assert.True(ReadOnlyMemoryUtils.EqualsStr(foldCur, foldIndex));
if (rowCount == 10)
{
rowCount = 0;
foldCur = "Fold 1";
}
}
Assert.Equal(0, rowCount);
}
var warnings = experiment.GetOutput(crossValidateOutput.Warnings);
using (var cursor = warnings.GetRowCursor(col => true))
Assert.False(cursor.MoveNext());
}
[ConditionalFact(typeof(BaseTestBaseline), nameof(BaseTestBaseline.LessThanNetCore30OrNotNetCore))] // netcore3.0 output differs from Baseline
public void TestCrossValidationMacro()
{
var dataPath = GetDataPath(TestDatasets.generatedRegressionDatasetmacro.trainFilename);
var env = new MLContext(42);
var subGraph = env.CreateExperiment();
var nop = new Legacy.Transforms.NoOperation();
var nopOutput = subGraph.Add(nop);
var generate = new Legacy.Transforms.RandomNumberGenerator();
generate.Column = new[] { new Legacy.Transforms.GenerateNumberTransformColumn()
{
Name = "Weight1"
} };
generate.Data = nopOutput.OutputData;
var generateOutput = subGraph.Add(generate);
var learnerInput = new Legacy.Trainers.PoissonRegressor
{
TrainingData = generateOutput.OutputData,
NumThreads = 1,
WeightColumn = "Weight1"
};
var learnerOutput = subGraph.Add(learnerInput);
var modelCombine = new Legacy.Transforms.ManyHeterogeneousModelCombiner
{
TransformModels = new ArrayVar <TransformModel>(nopOutput.Model, generateOutput.Model),
PredictorModel = learnerOutput.PredictorModel
};
var modelCombineOutput = subGraph.Add(modelCombine);
var experiment = env.CreateExperiment();
var importInput = new Legacy.Data.TextLoader(dataPath)
{
Arguments = new Legacy.Data.TextLoaderArguments
{
Separator = new[] { ';' },
HasHeader = true,
Column = new[]
{
new TextLoaderColumn()
{
Name = "Label",
Source = new [] { new TextLoaderRange(11) },
Type = Legacy.Data.DataKind.Num
},
new TextLoaderColumn()
{
Name = "Features",
Source = new [] { new TextLoaderRange(0, 10) },
Type = Legacy.Data.DataKind.Num
}
}
}
};
var importOutput = experiment.Add(importInput);
var crossValidate = new Legacy.Models.CrossValidator
{
Data = importOutput.Data,
Nodes = subGraph,
Kind = Legacy.Models.MacroUtilsTrainerKinds.SignatureRegressorTrainer,
TransformModel = null,
WeightColumn = "Weight1"
};
crossValidate.Inputs.Data = nop.Data;
crossValidate.Outputs.PredictorModel = modelCombineOutput.PredictorModel;
var crossValidateOutput = experiment.Add(crossValidate);
experiment.Compile();
importInput.SetInput(env, experiment);
experiment.Run();
var data = experiment.GetOutput(crossValidateOutput.OverallMetrics);
var schema = data.Schema;
var b = schema.TryGetColumnIndex("L1(avg)", out int metricCol);
Assert.True(b);
b = schema.TryGetColumnIndex("Fold Index", out int foldCol);
Assert.True(b);
b = schema.TryGetColumnIndex("IsWeighted", out int isWeightedCol);
using (var cursor = data.GetRowCursor(col => col == metricCol || col == foldCol || col == isWeightedCol))
{
var getter = cursor.GetGetter <double>(metricCol);
var foldGetter = cursor.GetGetter <ReadOnlyMemory <char> >(foldCol);
ReadOnlyMemory <char> fold = default;
var isWeightedGetter = cursor.GetGetter <bool>(isWeightedCol);
bool isWeighted = default;
double avg = 0;
double weightedAvg = 0;
for (int w = 0; w < 2; w++)
{
// Get the average.
b = cursor.MoveNext();
Assert.True(b);
if (w == 1)
{
getter(ref weightedAvg);
}
else
{
getter(ref avg);
}
foldGetter(ref fold);
Assert.True(ReadOnlyMemoryUtils.EqualsStr("Average", fold));
isWeightedGetter(ref isWeighted);
Assert.True(isWeighted == (w == 1));
// Get the standard deviation.
b = cursor.MoveNext();
Assert.True(b);
double stdev = 0;
getter(ref stdev);
foldGetter(ref fold);
Assert.True(ReadOnlyMemoryUtils.EqualsStr("Standard Deviation", fold));
if (w == 1)
{
Assert.Equal(1.585, stdev, 3);
}
else
{
Assert.Equal(1.39, stdev, 2);
}
isWeightedGetter(ref isWeighted);
Assert.True(isWeighted == (w == 1));
}
double sum = 0;
double weightedSum = 0;
for (int f = 0; f < 2; f++)
{
for (int w = 0; w < 2; w++)
{
b = cursor.MoveNext();
Assert.True(b);
double val = 0;
getter(ref val);
foldGetter(ref fold);
if (w == 1)
{
weightedSum += val;
}
else
{
sum += val;
}
Assert.True(ReadOnlyMemoryUtils.EqualsStr("Fold " + f, fold));
isWeightedGetter(ref isWeighted);
Assert.True(isWeighted == (w == 1));
}
}
Assert.Equal(weightedAvg, weightedSum / 2);
Assert.Equal(avg, sum / 2);
b = cursor.MoveNext();
Assert.False(b);
}
}
public void TestCrossValidationBinaryMacro()
{
var dataPath = GetDataPath("adult.tiny.with-schema.txt");
using (var env = new ConsoleEnvironment())
{
var subGraph = env.CreateExperiment();
var catInput = new Legacy.Transforms.CategoricalOneHotVectorizer();
catInput.AddColumn("Categories");
var catOutput = subGraph.Add(catInput);
var concatInput = new Legacy.Transforms.ColumnConcatenator
{
Data = catOutput.OutputData
};
concatInput.AddColumn("Features", "Categories", "NumericFeatures");
var concatOutput = subGraph.Add(concatInput);
var lrInput = new Legacy.Trainers.LogisticRegressionBinaryClassifier
{
TrainingData = concatOutput.OutputData,
NumThreads = 1
};
var lrOutput = subGraph.Add(lrInput);
var modelCombine = new Legacy.Transforms.ManyHeterogeneousModelCombiner
{
TransformModels = new ArrayVar <ITransformModel>(catOutput.Model, concatOutput.Model),
PredictorModel = lrOutput.PredictorModel
};
var modelCombineOutput = subGraph.Add(modelCombine);
var experiment = env.CreateExperiment();
var importInput = new Legacy.Data.TextLoader(dataPath);
var importOutput = experiment.Add(importInput);
var crossValidateBinary = new Legacy.Models.BinaryCrossValidator
{
Data = importOutput.Data,
Nodes = subGraph
};
crossValidateBinary.Inputs.Data = catInput.Data;
crossValidateBinary.Outputs.Model = modelCombineOutput.PredictorModel;
var crossValidateOutput = experiment.Add(crossValidateBinary);
experiment.Compile();
importInput.SetInput(env, experiment);
experiment.Run();
var data = experiment.GetOutput(crossValidateOutput.OverallMetrics[0]);
var schema = data.Schema;
var b = schema.TryGetColumnIndex("AUC", out int aucCol);
Assert.True(b);
using (var cursor = data.GetRowCursor(col => col == aucCol))
{
var getter = cursor.GetGetter <double>(aucCol);
b = cursor.MoveNext();
Assert.True(b);
double auc = 0;
getter(ref auc);
Assert.Equal(0.87, auc, 1);
b = cursor.MoveNext();
Assert.False(b);
}
}
}
public void TestTrainTestMacro()
{
var dataPath = GetDataPath("adult.tiny.with-schema.txt");
using (var env = new ConsoleEnvironment())
{
var subGraph = env.CreateExperiment();
var catInput = new Legacy.Transforms.CategoricalOneHotVectorizer();
catInput.AddColumn("Categories");
var catOutput = subGraph.Add(catInput);
var concatInput = new Legacy.Transforms.ColumnConcatenator
{
Data = catOutput.OutputData
};
concatInput.AddColumn("Features", "Categories", "NumericFeatures");
var concatOutput = subGraph.Add(concatInput);
var sdcaInput = new Legacy.Trainers.StochasticDualCoordinateAscentBinaryClassifier
{
TrainingData = concatOutput.OutputData,
LossFunction = new HingeLossSDCAClassificationLossFunction()
{
Margin = 1.1f
},
NumThreads = 1,
Shuffle = false
};
var sdcaOutput = subGraph.Add(sdcaInput);
var modelCombine = new Legacy.Transforms.ManyHeterogeneousModelCombiner
{
TransformModels = new ArrayVar <ITransformModel>(catOutput.Model, concatOutput.Model),
PredictorModel = sdcaOutput.PredictorModel
};
var modelCombineOutput = subGraph.Add(modelCombine);
var experiment = env.CreateExperiment();
var importInput = new Legacy.Data.TextLoader(dataPath);
var importOutput = experiment.Add(importInput);
var trainTestInput = new Legacy.Models.TrainTestBinaryEvaluator
{
TrainingData = importOutput.Data,
TestingData = importOutput.Data,
Nodes = subGraph
};
trainTestInput.Inputs.Data = catInput.Data;
trainTestInput.Outputs.Model = modelCombineOutput.PredictorModel;
var trainTestOutput = experiment.Add(trainTestInput);
experiment.Compile();
experiment.SetInput(importInput.InputFile, new SimpleFileHandle(env, dataPath, false, false));
experiment.Run();
var data = experiment.GetOutput(trainTestOutput.OverallMetrics);
var schema = data.Schema;
var b = schema.TryGetColumnIndex("AUC", out int aucCol);
Assert.True(b);
using (var cursor = data.GetRowCursor(col => col == aucCol))
{
var getter = cursor.GetGetter <double>(aucCol);
b = cursor.MoveNext();
Assert.True(b);
double auc = 0;
getter(ref auc);
Assert.Equal(0.93, auc, 2);
b = cursor.MoveNext();
Assert.False(b);
}
}
}
private static ITransformModel CreateKcHousePricePredictorModel(string dataPath)
{
Experiment experiment = s_environment.CreateExperiment();
var importData = new Legacy.Data.TextLoader(dataPath)
{
Arguments = new TextLoaderArguments
{
Separator = new[] { ',' },
HasHeader = true,
Column = new[]
{
new TextLoaderColumn()
{
Name = "Id",
Source = new [] { new TextLoaderRange(0) },
Type = Legacy.Data.DataKind.Text
},
new TextLoaderColumn()
{
Name = "Date",
Source = new [] { new TextLoaderRange(1) },
Type = Legacy.Data.DataKind.Text
},
new TextLoaderColumn()
{
Name = "Label",
Source = new [] { new TextLoaderRange(2) },
Type = Legacy.Data.DataKind.Num
},
new TextLoaderColumn()
{
Name = "Bedrooms",
Source = new [] { new TextLoaderRange(3) },
Type = Legacy.Data.DataKind.Num
},
new TextLoaderColumn()
{
Name = "Bathrooms",
Source = new [] { new TextLoaderRange(4) },
Type = Legacy.Data.DataKind.Num
},
new TextLoaderColumn()
{
Name = "SqftLiving",
Source = new [] { new TextLoaderRange(5) },
Type = Legacy.Data.DataKind.Num
},
new TextLoaderColumn()
{
Name = "SqftLot",
Source = new [] { new TextLoaderRange(6) },
Type = Legacy.Data.DataKind.Num
},
new TextLoaderColumn()
{
Name = "Floors",
Source = new [] { new TextLoaderRange(7) },
Type = Legacy.Data.DataKind.Num
},
new TextLoaderColumn()
{
Name = "Waterfront",
Source = new [] { new TextLoaderRange(8) },
Type = Legacy.Data.DataKind.Num
},
new TextLoaderColumn()
{
Name = "View",
Source = new [] { new TextLoaderRange(9) },
Type = Legacy.Data.DataKind.Num
},
new TextLoaderColumn()
{
Name = "Condition",
Source = new [] { new TextLoaderRange(10) },
Type = Legacy.Data.DataKind.Num
},
new TextLoaderColumn()
{
Name = "Grade",
Source = new [] { new TextLoaderRange(11) },
Type = Legacy.Data.DataKind.Num
},
new TextLoaderColumn()
{
Name = "SqftAbove",
Source = new [] { new TextLoaderRange(12) },
Type = Legacy.Data.DataKind.Num
},
new TextLoaderColumn()
{
Name = "SqftBasement",
Source = new [] { new TextLoaderRange(13) },
Type = Legacy.Data.DataKind.Num
},
new TextLoaderColumn()
{
Name = "YearBuilt",
Source = new [] { new TextLoaderRange(14) },
Type = Legacy.Data.DataKind.Num
},
new TextLoaderColumn()
{
Name = "YearRenovated",
Source = new [] { new TextLoaderRange(15) },
Type = Legacy.Data.DataKind.Num
},
new TextLoaderColumn()
{
Name = "Zipcode",
Source = new [] { new TextLoaderRange(16) },
Type = Legacy.Data.DataKind.Num
},
new TextLoaderColumn()
{
Name = "Lat",
Source = new [] { new TextLoaderRange(17) },
Type = Legacy.Data.DataKind.Num
},
new TextLoaderColumn()
{
Name = "Long",
Source = new [] { new TextLoaderRange(18) },
Type = Legacy.Data.DataKind.Num
},
new TextLoaderColumn()
{
Name = "SqftLiving15",
Source = new [] { new TextLoaderRange(19) },
Type = Legacy.Data.DataKind.Num
},
new TextLoaderColumn()
{
Name = "SqftLot15",
Source = new [] { new TextLoaderRange(20) },
Type = Legacy.Data.DataKind.Num
},
}
}
//new Data.CustomTextLoader();
// importData.CustomSchema = dataSchema;
//
};
Legacy.Data.TextLoader.Output imported = experiment.Add(importData);
var numericalConcatenate = new Legacy.Transforms.ColumnConcatenator();
numericalConcatenate.Data = imported.Data;
numericalConcatenate.AddColumn("NumericalFeatures", "SqftLiving", "SqftLot", "SqftAbove", "SqftBasement", "Lat", "Long", "SqftLiving15", "SqftLot15");
Legacy.Transforms.ColumnConcatenator.Output numericalConcatenated = experiment.Add(numericalConcatenate);
var categoryConcatenate = new Legacy.Transforms.ColumnConcatenator();
categoryConcatenate.Data = numericalConcatenated.OutputData;
categoryConcatenate.AddColumn("CategoryFeatures", "Bedrooms", "Bathrooms", "Floors", "Waterfront", "View", "Condition", "Grade", "YearBuilt", "YearRenovated", "Zipcode");
Legacy.Transforms.ColumnConcatenator.Output categoryConcatenated = experiment.Add(categoryConcatenate);
var categorize = new Legacy.Transforms.CategoricalOneHotVectorizer();
categorize.AddColumn("CategoryFeatures");
categorize.Data = categoryConcatenated.OutputData;
Legacy.Transforms.CategoricalOneHotVectorizer.Output categorized = experiment.Add(categorize);
var featuresConcatenate = new Legacy.Transforms.ColumnConcatenator();
featuresConcatenate.Data = categorized.OutputData;
featuresConcatenate.AddColumn("Features", "NumericalFeatures", "CategoryFeatures");
Legacy.Transforms.ColumnConcatenator.Output featuresConcatenated = experiment.Add(featuresConcatenate);
var learner = new Legacy.Trainers.StochasticDualCoordinateAscentRegressor();
learner.TrainingData = featuresConcatenated.OutputData;
learner.NumThreads = 1;
Legacy.Trainers.StochasticDualCoordinateAscentRegressor.Output learnerOutput = experiment.Add(learner);
var combineModels = new Legacy.Transforms.ManyHeterogeneousModelCombiner();
combineModels.TransformModels = new ArrayVar <ITransformModel>(numericalConcatenated.Model, categoryConcatenated.Model, categorized.Model, featuresConcatenated.Model);
combineModels.PredictorModel = learnerOutput.PredictorModel;
Legacy.Transforms.ManyHeterogeneousModelCombiner.Output combinedModels = experiment.Add(combineModels);
var scorer = new Legacy.Transforms.Scorer
{
PredictorModel = combinedModels.PredictorModel
};
var scorerOutput = experiment.Add(scorer);
experiment.Compile();
experiment.SetInput(importData.InputFile, new SimpleFileHandle(s_environment, dataPath, false, false));
experiment.Run();
return(experiment.GetOutput(scorerOutput.ScoringTransform));
}
