static void Main(string[] args)
{
var mlContext = new MLContext();
// Creates a loader which will help format the data
var reader = mlContext.Data.CreateTextLoader(
columns: new TextLoader.Column[]
{
new TextLoader.Column(CocoaPercent, DataKind.Single, 1),
new TextLoader.Column("Label", DataKind.Single, 4) // Customer happiness is the label. The predicted features is called the Label.
},
hasHeader: true // First line of the data file is a header and not data row
);
IDataView trainingData = reader.Load(TrainDataPath);
PreviewUtil.Show(trainingData);
// Creates a pipeline - All operations like data operations, transformation, training are bundled as a pipeline
var pipeline =
mlContext.Transforms.Concatenate(outputColumnName: "Features", inputColumnNames: CocoaPercent)
.Append(mlContext.Regression.Trainers.LbfgsPoissonRegression());
// Train the model
var trainingModel = pipeline.Fit(trainingData);
// Using the training for one-time prediction
var predictionEngine = mlContext.Model.CreatePredictionEngine <ChocolateInput, ChocolateOutput>(trainingModel);
// Get the prediction
ChocolateOutput prediction = predictionEngine.Predict(new ChocolateInput()
{
CocoaPercent = 100
});
Console.WriteLine($"Predicted happiness: {prediction.CustomerHappiness}");
ChartGeneratorUtil.PlotRegressionChart(new PlotChartGeneratorModel()
{
Title = "Chocolate Consumer Happiness Prediction",
LabelX = "Cocoa Percent",
LabelY = "Customer Happiness",
ImageName = "CocoaPercentToHappiness.png",
PointsList = new List <PlotChartPointsList>
{
new PlotChartPointsList {
Points = ChartGeneratorUtil.GetChartPointsFromFile(TrainDataPath, 1, 4).ToList()
}
},
MaxLimitY = ChartGeneratorUtil.GetMaxColumnValueFromFile(TrainDataPath, 4) + 10
});
Console.ReadKey();
}
static void Main(string[] args)
{
// Create MLContext to be shared across the model creation workflow objects
MLContext mlContext = new MLContext();
// Define a reader: specify the data columns, types, and where to find them in the text file
var reader = mlContext.Data.CreateTextLoader(
columns: new TextLoader.Column[]
{
new TextLoader.Column("AverageGoalsPerMatch", DataKind.Single, 0),
new TextLoader.Column("Label", DataKind.Boolean, 1)
},
// First line of the file is a header, not a data row
hasHeader: true
);
// Read the training data
var trainingData = reader.Load(TrainDataPath);
var preview = trainingData.Preview();
Console.WriteLine($"******************************************");
Console.WriteLine($"Loaded training data: {preview}");
Console.WriteLine($"******************************************");
/* Build the basic graph */
ChartGeneratorUtil.PlotRegressionChart(new PlotChartGeneratorModel
{
Title = string.Empty,
LabelX = "Average number of goals scored per match",
LabelY = "Competition Win",
ImageName = "CompetitionWin.png",
PointsList = new List <PlotChartPointsList>
{
new PlotChartPointsList {
Points = ChartGeneratorUtil.GetChartPointsFromFile(TrainDataPath, 0, 1, 1, 1).ToList(), Color = CommonConstants.PPLplotColorRed
},
new PlotChartPointsList {
Points = ChartGeneratorUtil.GetChartPointsFromFile(TrainDataPath, 0, 1, 1, 0).ToList()
}
},
MaxLimitY = 1.25,
MinLimitY = -0.25,
MinLimitX = -0.25,
MaxLimitX = ChartGeneratorUtil.GetMaxColumnValueFromFile(TrainDataPath, 0) + 0.25,
DrawRegressionLine = false
});
// Apply standard ML.NET normalization to the raw data
var pipeline =
mlContext.Transforms.Concatenate("Features", "AverageGoalsPerMatch")
.Append(mlContext.BinaryClassification.Trainers.LogisticRegression(
new Microsoft.ML.Trainers.LogisticRegression.Options
{
ShowTrainingStats = true
}
));
// Train the model
var model = pipeline.Fit(trainingData);
// View training stats
var linearModel = model.LastTransformer.Model.SubModel as LinearBinaryModelParameters;
// This works out the loss
var coefficient = linearModel.Weights.FirstOrDefault();
var intercept = linearModel.Bias;
var step = 3 / (double)300;
var testX = Enumerable.Range((int)0, 300).Select(v => (v * step) + 0).ToList();
var loss = new List <double>();
foreach (var x in testX)
{
loss.Add(Sigmoid(x * coefficient + intercept));
}
// Get an array of the average data points
var lossPoints = GetAvgChartPointsFromData(testX, loss);
/* Build the Competition Win Likelihood graph */
ChartGeneratorUtil.PlotRegressionChart(new PlotChartGeneratorModel
{
Title = string.Empty,
LabelX = "Average number of goals per match",
LabelY = "Competition Win Likelihood",
ImageName = "CompetitionWinLikelihood.png",
PointsList = new List <PlotChartPointsList>
{
new PlotChartPointsList {
Points = ChartGeneratorUtil.GetChartPointsFromFile(TrainDataPath, 0, 1, 1, 1).ToList(), Color = CommonConstants.PPLplotColorRed
},
new PlotChartPointsList {
Points = ChartGeneratorUtil.GetChartPointsFromFile(TrainDataPath, 0, 1, 1, 0).ToList()
}
},
MaxLimitY = 1.25,
MinLimitY = -0.25,
MinLimitX = -0.25,
MaxLimitX = ChartGeneratorUtil.GetMaxColumnValueFromFile(TrainDataPath, 0) + 0.25,
DrawRegressionLine = true,
RegressionPointsList = new PlotChartPointsList {
Points = lossPoints.ToList(), Color = CommonConstants.PPLplotColorBlack
}
});
// Use the trained model for one-time prediction
var predictionEngine = model.CreatePredictionEngine <FootballInput, FootballOutput>(mlContext);
// Obtain the prediction
var goalsPerMatch = 2.422870462f;
var prediction = predictionEngine.Predict(new FootballInput
{
AverageGoalsPerMatch = goalsPerMatch
});
Console.WriteLine($"*************************************");
Console.WriteLine($"Probability of winning this year: { prediction.WonCompetition * 100 }%");
Console.WriteLine($"*************************************");
/* Build the Probability of winning this year graph */
ChartGeneratorUtil.PlotRegressionChart(new PlotChartGeneratorModel
{
Title = "Probability of winning this year",
LabelX = "Average number of goals per match",
LabelY = "Competition Win Likelihood",
ImageName = "ProbabilityOfWinningThisYear.png",
PointsList = new List <PlotChartPointsList>
{
new PlotChartPointsList {
Points = ChartGeneratorUtil.GetChartPointsFromFile(TrainDataPath, 0, 1, 1, 1).ToList(), Color = CommonConstants.PPLplotColorRed
},
new PlotChartPointsList {
Points = ChartGeneratorUtil.GetChartPointsFromFile(TrainDataPath, 0, 1, 1, 0).ToList()
}
},
MaxLimitY = 1.25,
MinLimitY = -0.25,
MinLimitX = -0.25,
MaxLimitX = ChartGeneratorUtil.GetMaxColumnValueFromFile(TrainDataPath, 0) + 0.25,
DrawRegressionLine = true,
DashedPoint = new PlotChartPoint {
X = goalsPerMatch, Y = prediction.WonCompetition
},
RegressionPointsList = new PlotChartPointsList {
Points = lossPoints.ToList(), Color = CommonConstants.PPLplotColorBlack
}
});
Console.ReadKey();
}
static void Main(string[] args)
{
// Create MLContext to be shared across the model creation workflow objects
MLContext mlContext = new MLContext();
// Read the training data
var trainingData = mlContext.Data.LoadFromTextFile <TreeInput>(TrainDataPath, separatorChar: '\t', hasHeader: true);
// Read the training data
var preview = trainingData.Preview();
Console.WriteLine($"******************************************");
Console.WriteLine($"Loaded training data: {preview}");
Console.WriteLine($"******************************************");
/* Build the classification plot for leaf features graph */
ChartGeneratorUtil.PlotRegressionChart(new PlotChartGeneratorModel
{
Title = "Classification plot for leaf features",
LabelX = "leaf width",
LabelY = "leaf length",
ImageName = "ClassificationPlotForLeafFeatures.png",
PointsList = new List <PlotChartPointsList>
{
new PlotChartPointsList {
Points = ChartGeneratorUtil.GetChartPointsFromFile(TrainDataPath, 0, 1, 4, 1).ToList(), Color = CommonConstants.PPLplotColorGreen
},
new PlotChartPointsList {
Points = ChartGeneratorUtil.GetChartPointsFromFile(TrainDataPath, 0, 1, 4, 0).ToList(), Color = CommonConstants.PPLplotColorBlue
}
},
MaxLimitX = ChartGeneratorUtil.GetMaxColumnValueFromFile(TrainDataPath, 0) + 0.25,
MaxLimitY = ChartGeneratorUtil.GetMaxColumnValueFromFile(TrainDataPath, 1) + 0.25,
DrawRegressionLine = false
});
/* Build the classification plot for trunk features graph */
ChartGeneratorUtil.PlotRegressionChart(new PlotChartGeneratorModel
{
Title = "Classification plot for trunk features",
LabelX = "trunk girth",
LabelY = "trunk height",
ImageName = "ClassificationPlotForTrunkFeatures.png",
PointsList = new List <PlotChartPointsList>
{
new PlotChartPointsList {
Points = ChartGeneratorUtil.GetChartPointsFromFile(TrainDataPath, 2, 3, 4, 1).ToList(), Color = CommonConstants.PPLplotColorGreen
},
new PlotChartPointsList {
Points = ChartGeneratorUtil.GetChartPointsFromFile(TrainDataPath, 2, 3, 4, 0).ToList(), Color = CommonConstants.PPLplotColorBlue
}
},
MaxLimitX = ChartGeneratorUtil.GetMaxColumnValueFromFile(TrainDataPath, 0) + 0.25,
MaxLimitY = ChartGeneratorUtil.GetMaxColumnValueFromFile(TrainDataPath, 1) + 0.25
});
// Apply standard ML.NET normalization to the raw data
var pipeline =
// Specify the support vector machine trainer
mlContext.Transforms.Concatenate("Features", "LeafWidth", "LeafLength", "TrunkGirth", "TrunkHeight")
.Append(mlContext.BinaryClassification.Trainers.LinearSupportVectorMachines());
// Train the model
var model = pipeline.Fit(trainingData);
// Use the trained model for one-time prediction
var predictionEngine = model.CreatePredictionEngine <TreeInput, TreeOutput>(mlContext);
// Obtain the prediction
var prediction = predictionEngine.Predict(new TreeInput
{
LeafWidth = 5.13E+00f,
LeafLength = 6.18E+00f,
TrunkGirth = 8.26E+00f,
TrunkHeight = 8.74E+00f
});
Console.WriteLine($"*************************************");
Console.WriteLine("Tree type {0}", prediction.TreeType ? "0" : "1");
Console.WriteLine($"Score: {prediction.Score}");
Console.WriteLine($"Probability: {prediction.Probability}");
Console.WriteLine($"*************************************");
// Build the SVM plot for leaf features graph
ChartGeneratorUtil.PlotRegressionChart(new PlotChartGeneratorModel
{
Title = "SVM plot for leaf features",
LabelX = "leaf width",
LabelY = "leaf length",
ImageName = "SVMPlotForLeafFeatures.png",
PointsList = new List <PlotChartPointsList>
{
new PlotChartPointsList {
Points = ChartGeneratorUtil.GetChartPointsFromFile(TrainDataPath, 0, 1, 4, 1).ToList(), Color = CommonConstants.PPLplotColorGreen
},
new PlotChartPointsList {
Points = ChartGeneratorUtil.GetChartPointsFromFile(TrainDataPath, 0, 1, 4, 0).ToList(), Color = CommonConstants.PPLplotColorBlue
}
},
MaxLimitX = ChartGeneratorUtil.GetMaxColumnValueFromFile(TrainDataPath, 0) + 0.25,
MaxLimitY = ChartGeneratorUtil.GetMaxColumnValueFromFile(TrainDataPath, 1) + 0.25,
DrawRegressionLine = false,
DrawVectorMachinesAreas = true,
});
// Build the SVM plot for trunk features graph
ChartGeneratorUtil.PlotRegressionChart(new PlotChartGeneratorModel
{
Title = "SVM plot for trunk features",
LabelX = "trunk girth",
LabelY = "trunk height",
ImageName = "SVMPlotForTrunkFeatures.png",
PointsList = new List <PlotChartPointsList>
{
new PlotChartPointsList {
Points = ChartGeneratorUtil.GetChartPointsFromFile(TrainDataPath, 2, 3, 4, 1).ToList(), Color = CommonConstants.PPLplotColorGreen
},
new PlotChartPointsList {
Points = ChartGeneratorUtil.GetChartPointsFromFile(TrainDataPath, 2, 3, 4, 0).ToList(), Color = CommonConstants.PPLplotColorBlue
}
},
MaxLimitX = ChartGeneratorUtil.GetMaxColumnValueFromFile(TrainDataPath, 0) + 0.25,
MaxLimitY = ChartGeneratorUtil.GetMaxColumnValueFromFile(TrainDataPath, 1) + 0.25,
DrawRegressionLine = false,
DrawVectorMachinesAreas = true,
});
Console.ReadKey();
}
static void Main(string[] args)
{
MLContext mlContext = new MLContext();
// Define a reader: specify the data columns, types, and where to find them in the text file
var reader = mlContext.Data.CreateTextLoader(
columns: new TextLoader.Column[]
{
new TextLoader.Column("CocoaPercent", DataKind.Single, 1),
new TextLoader.Column("Label", DataKind.Single, 4)
},
// First line of the file is a header, not a data row
hasHeader: true
);
// Create a preview and print out like a CSV
var trainingData = reader.Load(TrainDataPath);
var preview = trainingData.Preview(10);
Console.WriteLine($"******************************************");
Console.WriteLine($"Loaded training data: {preview.ToString()}");
Console.WriteLine($"******************************************");
foreach (var columnInfo in preview.ColumnView)
{
Console.Write($"{columnInfo.Column.Name},");
}
Console.WriteLine();
foreach (var rowInfo in preview.RowView)
{
foreach (var row in rowInfo.Values)
{
Console.Write($"{row.Value},");
}
Console.WriteLine();
}
/* Create pipeline */
// Apply standard ML.NET normalization to the raw data
var pipeline =
// Specify the PoissonRegression regression trainer
mlContext.Transforms.Concatenate("Features", "CocoaPercent")
.Append(mlContext.Regression.Trainers.PoissonRegression());
/* Train the model */
var model = pipeline.Fit(trainingData);
/* Get the prediction */
// Use the trained model for one-time prediction
var predictionEngine = model.CreatePredictionEngine <ChocolateInput, ChocolateOutput>(mlContext);
// Obtain the prediction
var prediction = predictionEngine.Predict(new ChocolateInput
{
CocoaPercent = 65, // trained value 65
});
Console.WriteLine($"*************************************");
Console.WriteLine($"Predicted customer happiness: {prediction.CustomerHappiness:0.##}");
Console.WriteLine($"*************************************");
// Generate graph with training data
ChartGeneratorUtil.PlotRegressionChart(new PlotChartGeneratorModel
{
Title = "Chocolate Consumer Happiness Prediction",
LabelX = "Cocoa Percent",
LabelY = "Customer Happiness",
ImageName = "CocoaPercentToHappiness.png",
PointsList = new List <PlotChartPointsList>
{
new PlotChartPointsList {
Points = ChartGeneratorUtil.GetChartPointsFromFile(TrainDataPath, 1, 4).ToList()
}
},
MaxLimitY = ChartGeneratorUtil.GetMaxColumnValueFromFile(TrainDataPath, 4) + 10,
});
Console.ReadKey();
}
static void Main(string[] args)
{
var mlContext = new MLContext();
var reader = mlContext.Data.CreateTextLoader(
columns: new TextLoader.Column[]
{
new TextLoader.Column("Weight", DataKind.Single, 0),
new TextLoader.Column("CocoaPercent", DataKind.Single, 1),
new TextLoader.Column("Cost", DataKind.Single, 2),
new TextLoader.Column("Label", DataKind.Single, 3)
},
// First line of the file is a header, not a data row
hasHeader: true
);
var trainingData = reader.Load(TrainDataPath);
var preview = trainingData.Preview();
Console.WriteLine($"******************************************");
Console.WriteLine($"Loaded training data: {preview.ToString()}");
Console.WriteLine($"******************************************");
var pipeline =
// Features to include in the prediction
mlContext.Transforms.Concatenate("Features", "Weight", "CocoaPercent", "Cost")
// Specify the regression trainer
.Append(mlContext.Regression.Trainers.PoissonRegression());
// Train the model
var model = pipeline.Fit(trainingData);
// The model's feature weight coefficients
var regressionModel = model.LastTransformer.Model;
var weights = regressionModel.Weights;
var intercept = regressionModel.Bias;
Console.WriteLine($"Coefficients: Weight={weights[0]:0.##}, CocoaPercent={weights[1]:0.##}, Cost={weights[2]:0.##}");
/* Build the graph */
var featureColumn = reader.GetOutputSchema().GetColumnOrNull("CocoaPercent").Value;
ChartGeneratorUtil.PlotRegressionChart(new PlotChartGeneratorModel
{
Title = "Chocolate Consumer Happiness Prediction",
LabelX = featureColumn.Name,
LabelY = "Customer Happiness",
ImageName = "FeatureToHappiness.png",
PointsList = new List <PlotChartPointsList>
{
new PlotChartPointsList {
Points = ChartGeneratorUtil.GetChartPointsFromFile(TrainDataPath, featureColumn.Index, 3).ToList()
}
},
MinLimitX = ChartGeneratorUtil.GetMinColumnValueFromFile(TrainDataPath, featureColumn.Index),
MaxLimitX = ChartGeneratorUtil.GetMaxColumnValueFromFile(TrainDataPath, featureColumn.Index) + 0.25,
MaxLimitY = ChartGeneratorUtil.GetMaxColumnValueFromFile(TrainDataPath, 3) + 5
});
// Compute the quality metrics of our prediction model
var predictions = model.Transform(trainingData);
PrintMetrics(mlContext, predictions);
Console.ReadKey();
}