public override string ToString()
{
var sb = new StringBuilder();
sb.Append(Estimator.GetType().FullName);
sb.Append("{");
if (RoutingStructure.ColumnsProduced.Count() > 1)
{
for (var i = 0; i < RoutingStructure.ColumnsProduced.Count(); i++)
{
sb.Append($" col={RoutingStructure.ColumnsProduced[i].Name}:{RoutingStructure.ColumnsConsumed[i].Name}");
}
}
else
{
sb.Append($" col={RoutingStructure.ColumnsProduced.First().Name}:{string.Join(",", RoutingStructure.ColumnsConsumed.Select(c => c.Name))}");
}
if (Properties != null)
{
foreach (var property in Properties)
{
sb.Append($" {property.Key}={property.Value}");
}
}
sb.Append("}");
return(sb.ToString());
}
public Model(MLContext mlContext, IEstimator <ITransformer> algorythm, string trainingDataLocation)
{
_mlContext = mlContext;
_algorythim = algorythm;
_trainingDataView = _mlContext.Data.LoadFromTextFile <BikeSharingDemandSample>(
path: trainingDataLocation,
hasHeader: true,
separatorChar: ',');
Name = algorythm.GetType().ToString().Split('.').Last();
}
public ITransformer Fit(IEstimator <ITransformer> estimator, DateTime to)
{
Console.WriteLine($"Running {estimator.GetType().Name}");
MLContext mlContext = new MLContext();
DateTime from = _featurables.Min(c => c.Begin);
//to = _featurables.Max(c => c.End);
Period period = Period.S;
int periodCount = 5;
List <Dictionary <string, float> > features = new List <Dictionary <string, float> >();
for (DateTime date = from; date < to; date = date.AddPeriod(period, periodCount))
{
if (_featurables.All(c => c.HasFeatures(date)) && _pipExpectation._futurPip.ContainsKey(date))
{
Dictionary <string, float> feature = new Dictionary <string, float>();
var featuresDictionnary = GetFeatures(date);
if (featuresDictionnary == null)
{
continue;
}
foreach (var item in featuresDictionnary)
{
feature.Add(item.Key, item.Value);
}
feature["Label"] = decimal.ToSingle(_pipExpectation._futurPip[date].Long);
features.Add(feature);
}
}
IDataView data = new FloatsDataView(features);
using (FileStream stream = new FileStream("data.tsv", FileMode.Create))
mlContext.Data.SaveAsText(data, stream);
string[] featureNames = features.First().Keys.Where(c => c != "Label").ToArray();
var pipeline = mlContext.Transforms.Concatenate("Features", featureNames)
.Append(mlContext.Transforms.NormalizeMeanVariance("Features"))
.Append(mlContext.Transforms.NormalizeMinMax("Features"))
.AppendCacheCheckpoint(mlContext);
//.Append(mlContext.Regression.Trainers.OnlineGradientDescent(numberOfIterations:10));
// Create data prep transformer
ITransformer transformData = pipeline.Fit(data);
IDataView transformedData = transformData.Transform(data);
//IEstimator<ITransformer> estimator = mlContext.Regression.Trainers.OnlineGradientDescent(numberOfIterations:10);
var cvResults = mlContext.Regression.CrossValidate(transformedData, estimator, numberOfFolds: 5);
// Apply transforms to training data
var models = cvResults.OrderByDescending(fold => fold.Metrics.RSquared).ToArray();
// Get Top Model
var topModel = models[0];
Console.WriteLine($"\tR2: { topModel.Metrics.RSquared}");
Console.WriteLine($"\tLossfunction: { topModel.Metrics.LossFunction}");
Console.WriteLine($"\tMeanAbsoluteError: { topModel.Metrics.MeanAbsoluteError}");
//RegressionMetrics trainedModelMetrics = mlContext.Regression.Evaluate(testDataPredictions);
//double rSquared = trainedModelMetrics.RSquared;
return(transformData.Append(topModel.Model));
}
