public void TestSimpleTrainExperiment()
{
var dataPath = GetDataPath("adult.tiny.with-schema.txt");
var env = new MLContext();
var experiment = env.CreateExperiment();
var importInput = new Legacy.Data.TextLoader(dataPath);
var importOutput = experiment.Add(importInput);
var catInput = new Legacy.Transforms.CategoricalOneHotVectorizer
{
Data = importOutput.Data
};
catInput.AddColumn("Categories");
var catOutput = experiment.Add(catInput);
var concatInput = new Legacy.Transforms.ColumnConcatenator
{
Data = catOutput.OutputData
};
concatInput.AddColumn("Features", "Categories", "NumericFeatures");
var concatOutput = experiment.Add(concatInput);
var sdcaInput = new Legacy.Trainers.StochasticDualCoordinateAscentBinaryClassifier
{
TrainingData = concatOutput.OutputData,
LossFunction = new HingeLossSDCAClassificationLossFunction()
{
Margin = 1.1f
},
NumThreads = 1,
Shuffle = false
};
var sdcaOutput = experiment.Add(sdcaInput);
var scoreInput = new Legacy.Transforms.DatasetScorer
{
Data = concatOutput.OutputData,
PredictorModel = sdcaOutput.PredictorModel
};
var scoreOutput = experiment.Add(scoreInput);
var evalInput = new Legacy.Models.BinaryClassificationEvaluator
{
Data = scoreOutput.ScoredData
};
var evalOutput = experiment.Add(evalInput);
experiment.Compile();
experiment.SetInput(importInput.InputFile, new SimpleFileHandle(env, dataPath, false, false));
experiment.Run();
var data = experiment.GetOutput(evalOutput.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);
}
}
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);
}
}
}
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);
}
}
}
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));
}