static void Main(string[] args)
{
string dataPath = "wikipedia-detox-250-line-data.tsv";
LearningPipeline pipeline = new LearningPipeline();
TextLoader testData = new TextLoader(dataPath).CreateFrom <SentimentData>(separator: '\t');
pipeline.Add(testData);
pipeline.Add(new TextFeaturizer("Features", "SentimentText"));
pipeline.Add(new FastTreeBinaryClassifier());
PredictionModel <SentimentData, SentimentPrediction> model = pipeline.Train <SentimentData, SentimentPrediction>();
Console.WriteLine(Environment.NewLine + Environment.NewLine);
while (true)
{
Console.WriteLine("Please enter some statement:" + Environment.NewLine);
// Positive: He is the best, and the article should say that.
// Negative: Please refrain from adding nonsense to Wikipedia.
var input = Console.ReadLine();
SentimentData data = new SentimentData
{
SentimentText = input
};
SentimentPrediction prediction = model.Predict(data);
string text = "Prediction: " + prediction.Sentiment + Environment.NewLine;
Console.WriteLine(text);
}
}
public void TestSimpleExperiment()
{
var dataPath = GetDataPath(@"adult.tiny.with-schema.txt");
using (var env = new TlcEnvironment())
{
var experiment = env.CreateExperiment();
var importInput = new ML.Data.TextLoader(dataPath);
var importOutput = experiment.Add(importInput);
var normalizeInput = new ML.Transforms.MinMaxNormalizer
{
Data = importOutput.Data
};
normalizeInput.AddColumn("NumericFeatures");
var normalizeOutput = experiment.Add(normalizeInput);
experiment.Compile();
experiment.SetInput(importInput.InputFile, new SimpleFileHandle(env, dataPath, false, false));
experiment.Run();
var data = experiment.GetOutput(normalizeOutput.OutputData);
var schema = data.Schema;
Assert.Equal(5, schema.ColumnCount);
var expected = new[] { "Label", "Workclass", "Categories", "NumericFeatures", "NumericFeatures" };
for (int i = 0; i < schema.ColumnCount; i++)
{
Assert.Equal(expected[i], schema.GetColumnName(i));
}
}
}
static void Evaluate(PredictionModel <WineData, WinePrediction> model)
{
var testData = new Microsoft.ML.Data.TextLoader(TestDataPath).CreateFrom <WineData>(useHeader: true, separator: ',', trimWhitespace: false);
var evaluator = new Microsoft.ML.Models.RegressionEvaluator();
var metrics = evaluator.Evaluate(model, testData);
Console.WriteLine("Rms=" + metrics.Rms);
Console.WriteLine("LossFn=" + metrics.LossFn);
Console.WriteLine("RSquared = " + metrics.RSquared);
}
private static void Evaluate(PredictionModel <DatosGenerales, Prediccion> model)
{
var testData = new Microsoft.ML.Data.TextLoader(testDataPath).CreateFrom <DatosGenerales>(useHeader: true, separator: ',');
var evaluator = new Microsoft.ML.Models.RegressionEvaluator();
RegressionMetrics regressionMetrics = evaluator.Evaluate(model, testData);
Console.WriteLine($"R Model Score: {regressionMetrics.Rms}");
Console.WriteLine($"R Squared: {regressionMetrics.RSquared}");
}
public void TestSimpleTrainExperiment()
{
var dataPath = GetDataPath(@"adult.tiny.with-schema.txt");
using (var env = new TlcEnvironment())
{
var experiment = env.CreateExperiment();
var importInput = new ML.Data.TextLoader(dataPath);
var importOutput = experiment.Add(importInput);
var catInput = new ML.Transforms.CategoricalOneHotVectorizer
{
Data = importOutput.Data
};
catInput.AddColumn("Categories");
var catOutput = experiment.Add(catInput);
var concatInput = new ML.Transforms.ColumnConcatenator
{
Data = catOutput.OutputData
};
concatInput.AddColumn("Features", "Categories", "NumericFeatures");
var concatOutput = experiment.Add(concatInput);
var sdcaInput = new ML.Trainers.StochasticDualCoordinateAscentBinaryClassifier
{
TrainingData = concatOutput.OutputData,
LossFunction = new HingeLossSDCAClassificationLossFunction()
{
Margin = 1.1f
},
NumThreads = 1,
Shuffle = false
};
var sdcaOutput = experiment.Add(sdcaInput);
var scoreInput = new ML.Transforms.DatasetScorer
{
Data = concatOutput.OutputData,
PredictorModel = sdcaOutput.PredictorModel
};
var scoreOutput = experiment.Add(scoreInput);
var evalInput = new ML.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 TestCrossValidationMacro()
{
var dataPath = GetDataPath(@"housing.txt");
using (var env = new TlcEnvironment())
{
var subGraph = env.CreateExperiment();
var nop = new ML.Transforms.NoOperation();
var nopOutput = subGraph.Add(nop);
var learnerInput = new ML.Trainers.StochasticDualCoordinateAscentRegressor
{
TrainingData = nopOutput.OutputData,
NumThreads = 1
};
var learnerOutput = subGraph.Add(learnerInput);
var modelCombine = new ML.Transforms.ManyHeterogeneousModelCombiner
{
TransformModels = new ArrayVar <ITransformModel>(nopOutput.Model),
PredictorModel = learnerOutput.PredictorModel
};
var modelCombineOutput = subGraph.Add(modelCombine);
var experiment = env.CreateExperiment();
var importInput = new ML.Data.TextLoader(dataPath);
var importOutput = experiment.Add(importInput);
var crossValidate = new ML.Models.CrossValidator
{
Data = importOutput.Data,
Nodes = subGraph,
Kind = ML.Models.MacroUtilsTrainerKinds.SignatureRegressorTrainer,
TransformModel = null
};
crossValidate.Inputs.Data = nop.Data;
crossValidate.Outputs.Model = 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[0]);
var schema = data.Schema;
var b = schema.TryGetColumnIndex("L1(avg)", out int metricCol);
Assert.True(b);
using (var cursor = data.GetRowCursor(col => col == metricCol))
{
var getter = cursor.GetGetter <double>(metricCol);
b = cursor.MoveNext();
Assert.True(b);
double val = 0;
getter(ref val);
Assert.Equal(3.32, val, 1);
b = cursor.MoveNext();
Assert.False(b);
}
}
}
public void TestCrossValidationBinaryMacro()
{
var dataPath = GetDataPath(@"adult.tiny.with-schema.txt");
using (var env = new TlcEnvironment())
{
var subGraph = env.CreateExperiment();
var catInput = new ML.Transforms.CategoricalOneHotVectorizer();
catInput.AddColumn("Categories");
var catOutput = subGraph.Add(catInput);
var concatInput = new ML.Transforms.ColumnConcatenator
{
Data = catOutput.OutputData
};
concatInput.AddColumn("Features", "Categories", "NumericFeatures");
var concatOutput = subGraph.Add(concatInput);
var lrInput = new ML.Trainers.LogisticRegressionBinaryClassifier
{
TrainingData = concatOutput.OutputData,
NumThreads = 1
};
var lrOutput = subGraph.Add(lrInput);
var modelCombine = new ML.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 ML.Data.TextLoader(dataPath);
var importOutput = experiment.Add(importInput);
var crossValidateBinary = new ML.Models.BinaryCrossValidator
{
Data = importOutput.Data,
Nodes = subGraph
};
crossValidateBinary.Inputs.Data = catInput.Data;
crossValidateBinary.Outputs.Model = modelCombineOutput.PredictorModel;
var crossValidateOutput = experiment.Add(crossValidateBinary);
experiment.Compile();
experiment.SetInput(importInput.InputFile, new SimpleFileHandle(env, dataPath, false, false));
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 TestCrossValidationMacroWithStratification()
{
var dataPath = GetDataPath(@"breast-cancer.txt");
using (var env = new TlcEnvironment())
{
var subGraph = env.CreateExperiment();
var nop = new ML.Transforms.NoOperation();
var nopOutput = subGraph.Add(nop);
var learnerInput = new ML.Trainers.StochasticDualCoordinateAscentBinaryClassifier
{
TrainingData = nopOutput.OutputData,
NumThreads = 1
};
var learnerOutput = subGraph.Add(learnerInput);
var modelCombine = new ML.Transforms.ManyHeterogeneousModelCombiner
{
TransformModels = new ArrayVar <ITransformModel>(nopOutput.Model),
PredictorModel = learnerOutput.PredictorModel
};
var modelCombineOutput = subGraph.Add(modelCombine);
var experiment = env.CreateExperiment();
var importInput = new ML.Data.TextLoader(dataPath);
importInput.Arguments.Column = new ML.Data.TextLoaderColumn[]
{
new ML.Data.TextLoaderColumn {
Name = "Label", Source = new[] { new ML.Data.TextLoaderRange(0) }
},
new ML.Data.TextLoaderColumn {
Name = "Strat", Source = new[] { new ML.Data.TextLoaderRange(1) }
},
new ML.Data.TextLoaderColumn {
Name = "Features", Source = new[] { new ML.Data.TextLoaderRange(2, 9) }
}
};
var importOutput = experiment.Add(importInput);
var crossValidate = new ML.Models.CrossValidator
{
Data = importOutput.Data,
Nodes = subGraph,
TransformModel = null,
StratificationColumn = "Strat"
};
crossValidate.Inputs.Data = nop.Data;
crossValidate.Outputs.Model = 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[0]);
var schema = data.Schema;
var b = schema.TryGetColumnIndex("AUC", out int metricCol);
Assert.True(b);
using (var cursor = data.GetRowCursor(col => col == metricCol))
{
var getter = cursor.GetGetter <double>(metricCol);
b = cursor.MoveNext();
Assert.True(b);
double val = 0;
getter(ref val);
Assert.Equal(0.99, val, 2);
b = cursor.MoveNext();
Assert.False(b);
}
}
}
static void Predict(PredictionModel <WineData, WinePrediction> model)
{
using (var environment = new TlcEnvironment())
{
var textLoader = new Microsoft.ML.Data.TextLoader(TestDataPath).CreateFrom <WineData>(useHeader: true, separator: ',', trimWhitespace: false);
var experiment = environment.CreateExperiment();
var output = textLoader.ApplyStep(null, experiment) as ILearningPipelineDataStep;
experiment.Compile();
textLoader.SetInput(environment, experiment);
experiment.Run();
var data = experiment.GetOutput(output.Data);
var wineDatas = new List <WineData>();
using (var cursor = data.GetRowCursor((a => true)))
{
var getters = new ValueGetter <float>[] {
cursor.GetGetter <float>(0),
cursor.GetGetter <float>(1),
cursor.GetGetter <float>(2),
cursor.GetGetter <float>(3),
cursor.GetGetter <float>(4),
cursor.GetGetter <float>(5),
cursor.GetGetter <float>(6),
cursor.GetGetter <float>(7),
cursor.GetGetter <float>(8),
cursor.GetGetter <float>(9),
cursor.GetGetter <float>(10),
cursor.GetGetter <float>(11),
cursor.GetGetter <float>(12)
};
while (cursor.MoveNext())
{
float value0 = 0;
float value1 = 0;
float value2 = 0;
float value3 = 0;
float value4 = 0;
float value5 = 0;
float value6 = 0;
float value7 = 0;
float value8 = 0;
float value9 = 0;
float value10 = 0;
float value11 = 0;
float value12 = 0;
getters[0](ref value0);
getters[1](ref value1);
getters[2](ref value2);
getters[3](ref value3);
getters[4](ref value4);
getters[5](ref value5);
getters[6](ref value6);
getters[7](ref value7);
getters[8](ref value8);
getters[9](ref value9);
getters[10](ref value10);
getters[11](ref value11);
getters[12](ref value12);
var wdata = new WineData()
{
FixedAcidity = value0,
VolatileAcidity = value1,
CitricACID = value2,
ResidualSugar = value3,
Chlorides = value4,
FreeSulfurDioxide = value5,
TotalSulfurDioxide = value6,
Density = value7,
PH = value8,
Sulphates = value9,
Alcohol = value10,
Quality = value11,
Id = value12,
};
wineDatas.Add(wdata);
}
}
var predictions = model.Predict(wineDatas);
var wineDataAndPredictions = wineDatas.Zip(predictions, (wineData, prediction) => (wineData, prediction));
Console.WriteLine($"Wine Id: {wineDataAndPredictions.Last().wineData.Id}, Quality: {wineDataAndPredictions.Last().wineData.Quality} | Prediction: { wineDataAndPredictions.Last().prediction.PredictionQuality}");
Console.WriteLine();
}
}
static IEnumerable <PokerHandData> LoadData(string path)
{
using (var environment = new TlcEnvironment())
{
var pokerHandData = new List <PokerHandData>();
var textLoader = new Microsoft.ML.Data.TextLoader(path).CreateFrom <PokerHandData>(useHeader: false, separator: ',', trimWhitespace: false);
var experiment = environment.CreateExperiment();
var output = textLoader.ApplyStep(null, experiment) as ILearningPipelineDataStep;
experiment.Compile();
textLoader.SetInput(environment, experiment);
experiment.Run();
var data = experiment.GetOutput(output.Data);
using (var cursor = data.GetRowCursor((a => true)))
{
var getters = new ValueGetter <float>[] {
cursor.GetGetter <float>(0),
cursor.GetGetter <float>(1),
cursor.GetGetter <float>(2),
cursor.GetGetter <float>(3),
cursor.GetGetter <float>(4),
cursor.GetGetter <float>(5),
cursor.GetGetter <float>(6),
cursor.GetGetter <float>(7),
cursor.GetGetter <float>(8),
cursor.GetGetter <float>(9),
cursor.GetGetter <float>(10)
};
while (cursor.MoveNext())
{
float value0 = 0;
float value1 = 0;
float value2 = 0;
float value3 = 0;
float value4 = 0;
float value5 = 0;
float value6 = 0;
float value7 = 0;
float value8 = 0;
float value9 = 0;
float value10 = 0;
getters[0](ref value0);
getters[1](ref value1);
getters[2](ref value2);
getters[3](ref value3);
getters[4](ref value4);
getters[5](ref value5);
getters[6](ref value6);
getters[7](ref value7);
getters[8](ref value8);
getters[9](ref value9);
getters[10](ref value10);
var hands = new PokerHandData()
{
S1 = value0,
C1 = value1,
S2 = value2,
C2 = value3,
S3 = value4,
C3 = value5,
S4 = value6,
C4 = value7,
S5 = value8,
C5 = value9,
Power = value10
};
hands.Init();
pokerHandData.Add(hands);
}
}
return(pokerHandData);
}
}
