public async Task <PredictionModel <TInput, TOutput> > TrainAsync()
{
//1.通过反射获取Tinput的attributes
Type ti = typeof(TInput), to = typeof(TOutput);
//2.获取input属性
List <string> inputColoums = new List <string>();
Array.ForEach(ti.GetFields(), new Action <System.Reflection.FieldInfo>(p =>
{
inputColoums.Add(p.Name);
}));
//3.获取output属性
string outputColoum = to.GetFields().Length > 0 ? to.GetFields()[0].Name : null;
//4.聚合输入输出层参数名称
ColumnConcatenator coloums = new ColumnConcatenator(outputColoum, inputColoums.ToArray());
//4.构建学习机
//LearningPipeline pipeline = new LearningPipeline();
//pipeline.Add()\
//CollectionDataSource.Create(new List<Input>() { new Input { Number1 = 1, String1 = "1" } })
LearningPipeline pipeline = new LearningPipeline
{
coloums,
new LogisticRegressionBinaryClassifier()
};
PredictionModel <TInput, TOutput> model = pipeline.Train <TInput, TOutput>();
//model写入zip file
await model.WriteAsync(_workDirectory + System.DateTime.Now.ToLongDateString() + ".zip");
//返回model对象
return(model);
}
static void Main(string[] args)
{
//step2:创建一个管道并且加载你的数据
var pipeline = new LearningPipeline();
string dataPath = "SourceData/iris-data.txt";
var loaderData = new TextLoader <IrisData>(dataPath, separator: ",");
pipeline.Add(loaderData);
//step3:转换数据
//因为在模型训练的时候只能处理数字，所以在Label列中将数值分配给文本
var dictionarizer = new Dictionarizer("Label");
pipeline.Add(dictionarizer);
var concatenator = new ColumnConcatenator("Features", "SepalLength", "SepalWidth", "PetalLength", "PetalWidth");
pipeline.Add(concatenator);
//step4:添加学习者
//添加一个学习算法到管道中，这是一种分类方案（这是什么类型的Iris）
pipeline.Add(new StochasticDualCoordinateAscentClassifier());
//在步骤三转换为数字之后将Label转换回原始文本
pipeline.Add(new PredictedLabelColumnOriginalValueConverter()
{
PredictedLabelColumn = "PredictedLabel"
});
//step5:根据数据集来训练模型
var model = pipeline.Train <IrisData, IrisPrediction>();
var prediction = model.Predict(new IrisData()
{
SepalLength = 10.8f,
SepalWidth = 5.1f,
PetalLength = 2.55f,
PetalWidth = 0.3f
});
Console.WriteLine($"Predicted flower type is {prediction.PredictedLabels}");
Console.Read();
}
public static async Task <PredictionModel <TaxiTrip, TaxiTripFarePrediction> > TrainModel()
{
var pipeline = new LearningPipeline();
var loadData = new TextLoader(_dataPath).CreateFrom <TaxiTrip>(useHeader: true, separator: ',');
var copyLabels = new ColumnCopier(("FareAmount", "Label"));
var convertToNumeric = new CategoricalOneHotVectorizer("VendorId", "RateCode", "PaymentType");
var features = new ColumnConcatenator("Features",
"VendorId", "RateCode", "PassengerCount", "TripDistance", "PaymentType");
pipeline.Add(loadData);
pipeline.Add(copyLabels);
pipeline.Add(convertToNumeric);
pipeline.Add(features);
pipeline.Add(new FastTreeRegressor());
var model = pipeline.Train <TaxiTrip, TaxiTripFarePrediction>();
await model.WriteAsync(_modelPath);
return(model);
}
