public static void PredictIssue()
{
// <SnippetLoadModel>
ITransformer loadedModel;
using (var stream = new FileStream(_modelPath, FileMode.Open, FileAccess.Read, FileShare.Read))
{
loadedModel = _mlContext.Model.Load(stream);
}
// </SnippetLoadModel>
// <SnippetAddTestIssue>
GitHubIssue singleIssue = new GitHubIssue()
{
Title = "Entity Framework crashes", Description = "When connecting to the database, EF is crashing"
};
// </SnippetAddTestIssue>
//Predict label for single hard-coded issue
// <SnippetCreatePredictionEngine>
_predEngine = loadedModel.CreatePredictionEngine <GitHubIssue, IssuePrediction>(_mlContext);
// </SnippetCreatePredictionEngine>
// <SnippetPredictIssue>
var prediction = _predEngine.Predict(singleIssue);
// </SnippetPredictIssue>
// <SnippetDisplayResults>
Console.WriteLine($"=============== Single Prediction - Result: {prediction.Area} ===============");
// </SnippetDisplayResults>
}
public static IEstimator <ITransformer> BuildAndTrainModel(IDataView trainingDataView, IEstimator <ITransformer> pipeline)
{
// STEP 3: Create the training algorithm/trainer
// Use the multi-class SDCA algorithm to predict the label using features.
//Set the trainer/algorithm and map label to value (original readable state)
var trainingPipeline = pipeline.Append(_mlContext.MulticlassClassification.Trainers.SdcaMaximumEntropy("Label", "Features"))
.Append(_mlContext.Transforms.Conversion.MapKeyToValue("PredictedLabel"));
Console.WriteLine($"=============== Training the model ===============");
_trainedModel = trainingPipeline.Fit(trainingDataView);
Console.WriteLine($"=============== Finished Training the model Ending time: {DateTime.Now:O} ===============");
// (OPTIONAL) Try/test a single prediction with the "just-trained model" (Before saving the model)
Console.WriteLine($"=============== Single Prediction just-trained-model ===============");
// Create prediction engine related to the loaded trained model
_predEngine = _mlContext.Model.CreatePredictionEngine <GitHubIssue, IssuePrediction>(_trainedModel);
var issue = new GitHubIssue
{
Title = "WebSockets communication is slow in my machine",
Description = "The WebSockets communication used under the covers by SignalR looks like is going slow in my development machine.."
};
var prediction = _predEngine.Predict(issue);
Console.WriteLine($"=============== Single Prediction just-trained-model - Result: {prediction.Area} ===============");
return(trainingPipeline);
}
//STEP 6 : Deploy and Predict with a model
private static void PredictIssue()
{
// <SnippetLoadModel>
ITransformer loadedModel = _mlContext.Model.Load(_modelPath, out var modelInputSchema);
// </SnippetLoadModel>
// <SnippetAddTestIssue>
GitHubIssue singleIssue = new GitHubIssue()
{
Title = "Entity Framework crashes", Description = "When connecting to the database, EF is crashing"
};
// </SnippetAddTestIssue>
//Predict label for single hard-coded issue
// <SnippetCreatePredictionEngine>
_predEngine = _mlContext.Model.CreatePredictionEngine <GitHubIssue, IssuePrediction>(loadedModel);
// </SnippetCreatePredictionEngine>
// <SnippetPredictIssue>
var prediction = _predEngine.Predict(singleIssue);
// </SnippetPredictIssue>
// <SnippetDisplayResults>
Console.WriteLine($"=============== Single Prediction - Result: {prediction.Area} ===============");
// </SnippetDisplayResults>
}
static void Main(String[] args)
{
Console.WriteLine("Hello World!");
var config = new TrainerConfig
{
TrainDataPath = Path.Combine(AppContext.BaseDirectory, "Data", "issues_train.tsv"),
TestDataPath = Path.Combine(AppContext.BaseDirectory, "Data", "issues_test.tsv"),
ModelPath = Path.Combine(AppContext.BaseDirectory, "Models", "github_issues.zip"),
Label = "Area",
}.WithFeature("Title").WithFeature("Description");
var trainer = new Trainer <GitHubIssue, IssuePrediction>(config);
Console.WriteLine("Training...");
var model = trainer.TrainOrLoad();
Console.WriteLine("Training...done!");
Console.WriteLine("Evaluating...");
trainer.Evaluate();
Console.WriteLine("Evaluating...done!");
trainer.Save();
var issue = new GitHubIssue()
{
Title = "WebSockets communication is slow in my machine",
Description = "The WebSockets communication used under the covers by SignalR looks like is going slow in my development machine.."
};
var prediction = trainer.Predict(issue);
Console.WriteLine($"The prediciton is...{prediction.Area}!");
Console.ReadLine();
}
public static EstimatorChain <KeyToValueMappingTransformer> BuildAndTrainModel(IDataView trainingDataView, EstimatorChain <ITransformer> pipeline)
{
// STEP 3: Create the training algorithm/trainer
// Use the multi-class SDCA model to predict the label using features.
// <SnippetSdcaMultiClassTrainer>
var trainer = new SdcaMultiClassTrainer(_mlContext, DefaultColumnNames.Label, DefaultColumnNames.Features);
// </SnippetSdcaMultiClassTrainer>
//Set the trainer/algorithm and map label to value (original readable state)
// <SnippetAddTrainer>
var trainingPipeline = pipeline.Append(trainer)
.Append(_mlContext.Transforms.Conversion.MapKeyToValue("PredictedLabel"));
// </SnippetAddTrainer>
// STEP 4: Train the model fitting to the DataSet
Console.WriteLine($"=============== Training the model ===============");
// <SnippetTrainModel>
_trainedModel = trainingPipeline.Fit(trainingDataView);
// </SnippetTrainModel>
Console.WriteLine($"=============== Finished Training the model Ending time: {DateTime.Now.ToString()} ===============");
// (OPTIONAL) Try/test a single prediction with the "just-trained model" (Before saving the model)
Console.WriteLine($"=============== Single Prediction just-trained-model ===============");
// Create prediction engine related to the loaded trained model
// <SnippetCreatePredictionEngine>
_predEngine = _trainedModel.CreatePredictionEngine <GitHubIssue, IssuePrediction>(_mlContext);
// </SnippetCreatePredictionEngine>
// <SnippetCreateTestIssue1>
GitHubIssue issue = new GitHubIssue()
{
Title = "WebSockets communication is slow in my machine",
Description = "The WebSockets communication used under the covers by SignalR looks like is going slow in my development machine.."
};
// </SnippetCreateTestIssue1>
// <SnippetPredict>
var prediction = _predEngine.Predict(issue);
// </SnippetPredict>
// <SnippetOutputPrediction>
Console.WriteLine($"=============== Single Prediction just-trained-model - Result: {prediction.Area} ===============");
// </SnippetOutputPrediction>
// Save the new model to .ZIP file
// <SnippetCallSaveModel>
SaveModelAsFile(_mlContext, _trainedModel);
// </SnippetCallSaveModel>
// <SnippetReturnModel>
return(trainingPipeline);
// </SnippetReturnModel>
}
private static void PredictIssue()
{
var loadedModel = _mlContext.Model.Load(_modelPath, out var modelInputSchema);
var singleIssue = new GitHubIssue()
{
Title = "Entity Framework crashes", Description = "When connecting to the databese, EF is crashing"
};
_predEngine = _mlContext.Model.CreatePredictionEngine <GitHubIssue, IssuePrediction>(loadedModel);
var prediction = _predEngine.Predict(singleIssue);
Console.WriteLine($"=============== Single Prediction - Result: {prediction.Area} ===============");
}
private static void PredictIssue()
{
ITransformer loadedModel;
using (var stream = new FileStream(_modelPath, FileMode.Open, FileAccess.Read, FileShare.Read))
{
loadedModel = _mlContext.Model.Load(stream);
}
GitHubIssue singleIssue = new GitHubIssue()
{
Title = "Entity Framework crashes", Description = "When connecting to the database, EF is crashing"
};
_predEngine = loadedModel.CreatePredictionEngine <GitHubIssue, IssuePrediction>(_mlContext);
var prediction = _predEngine.Predict(singleIssue);
Console.WriteLine($"=============== Single Prediction - Result: {prediction.Area} ===============");
}
public static IEstimator <ITransformer> BuildAndTrainModel(IDataView trainingDataView, IEstimator <ITransformer> pipeline)
{
var trainingPipeline = pipeline.Append(_mlContext.MulticlassClassification.Trainers.SdcaMaximumEntropy("Label", "Features"))
.Append(_mlContext.Transforms.Conversion.MapKeyToValue("PredictedLabel"));
_trainedModel = trainingPipeline.Fit(trainingDataView);
_predEngine = _mlContext.Model.CreatePredictionEngine <GitHubIssue, IssuePrediction>(_trainedModel);
GitHubIssue issue = new GitHubIssue()
{
Title = "WebSockets communication is slow in my machine",
Description = "The WebSckets ommunication used under the covers by SignalR looks like is going slow in my development machine.."
};
var prediction = _predEngine.Predict(issue);
Console.WriteLine($"=============== Single Prediction just-trained-model - Result: {prediction.Area} ===============");
return(trainingPipeline);
}
/// <summary>
/// 使用神经网络模型预测问题分类
/// </summary>
/// <param name="mlContext"></param>
/// <param name="model"></param>
private static void Predict(MLContext mlContext, ITransformer model)
{
// 创建预测引擎
Helper.PrintLine("创建预测引擎...");
var engine = mlContext.Model.CreatePredictionEngine <GitHubIssue, IssuePrediction>(model);
(string Title, string Description, bool Exit)inputs;
while (!(inputs = GetInputs()).Exit)
{
var issue = new GitHubIssue()
{
Title = inputs.Title, Description = inputs.Description
};
var prediction = engine.Predict(issue);
Helper.PrintLine($"=> {prediction.Area}");
}
Console.ResetColor();
Helper.PrintLine("结束预测");
(string Title, string Description, bool Exit) GetInputs()
{
Console.ResetColor();
Helper.PrintLine("输入问题标题以预测问题分类 (输入 exit 跳出预测)：");
Console.Write(">>>\t请输入：");
Console.ForegroundColor = ConsoleColor.Yellow;
var title = Console.ReadLine();
if (title.ToLower() == "exit")
{
return(title, string.Empty, true);
}
Console.ResetColor();
Helper.PrintLine("输入问题描述以预测问题分类：");
Console.Write(">>>\t请输入：");
Console.ForegroundColor = ConsoleColor.Yellow;
var description = Console.ReadLine();
Console.ForegroundColor = ConsoleColor.Magenta;
return(title, description, false);
}
}
static void Main(string[] args)
{
_mlContext = new MLContext(seed: 0);
// Prepare Data
_trainingDataView = _mlContext.Data.LoadFromTextFile <GitHubIssue>(_trainDataPath, hasHeader: true);
// Prepare Pipeline
var pipeline = _mlContext.Transforms.Conversion.MapValueToKey(inputColumnName: "Area", outputColumnName: "Label")
.Append(_mlContext.Transforms.Text.FeaturizeText(inputColumnName: "Title", outputColumnName: "TitleFeaturized"))
.Append(_mlContext.Transforms.Text.FeaturizeText(inputColumnName: "Description", outputColumnName: "DescriptionFeaturized"))
.Append(_mlContext.Transforms.Concatenate("Features", "TitleFeaturized", "DescriptionFeaturized"))
.AppendCacheCheckpoint(_mlContext)
.Append(_mlContext.MulticlassClassification.Trainers.SdcaMaximumEntropy("Label", "Features", maximumNumberOfIterations: 1000))
.Append(_mlContext.Transforms.Conversion.MapKeyToValue("PredictedLabel"));
// Training Model
_trainedModel = pipeline.Fit(_trainingDataView);
// Single Prediction
_predEngine = _mlContext.Model.CreatePredictionEngine <GitHubIssue, IssuePrediction>(_trainedModel);
GitHubIssue issue = new GitHubIssue()
{
Title = "WebSockets communication is slow in my machine",
Description = "The WebSockets communication used under the covers by SignalR looks like is going slow in my development machine.."
};
var prediction = _predEngine.Predict(issue);
Console.WriteLine($"=============== Single Prediction just-trained-model - Result: {prediction.Area}===============");
// Evaluate
var testDataView = _mlContext.Data.LoadFromTextFile <GitHubIssue>(_testDataPath, hasHeader: true);
var testMetrics = _mlContext.MulticlassClassification.Evaluate(_trainedModel.Transform(testDataView));
Console.WriteLine($"*************************************************************************************************************");
Console.WriteLine($"* Metrics for Multi-class Classification model - Test Data ");
Console.WriteLine($"*----------------------------------------------------------------------------------------------------------- - ");
Console.WriteLine($"* MicroAccuracy: {testMetrics.MicroAccuracy:0.###}");
Console.WriteLine($"* MacroAccuracy: {testMetrics.MacroAccuracy:0.###}");
Console.WriteLine($"* LogLoss: {testMetrics.LogLoss:#.###}");
Console.WriteLine($"* LogLossReduction: {testMetrics.LogLossReduction:#.###}");
Console.WriteLine($"*************************************************************************************************************");
// Save Model
_mlContext.Model.Save(_trainedModel, _trainingDataView.Schema, _modelPath);
// Predict Issue
ITransformer loadedModel = _mlContext.Model.Load(_modelPath, out var modelInputSchema);
GitHubIssue singleIssue = new GitHubIssue()
{
//Title = "socket 중계 서버..",
//Description = "오랜만에 질문 올립니다. tcp socket 중계 서버를 만들어야 하는데요.. 간단하게 얘기하면 n개의 장비가 있고 n개의 컨트롤 시스템이 존재 각 장비는 지정 컨트롤 시스템과 정보 송/수신. 말하자면 1:1의 양방향 통신이 n개가 관리 가능해야 한다는 얘긴데 . socket.poll, threadPool.. 등등... 뭘 어찌 구현할지 좀 감이 안오네요. 비슷한 구현 해보신 분 힌트좀 주세요..."
Title = "오랜만에 송년회 어떠세요?",
Description = "참석하고 싶은 마음이 불처럼 타오르는 분들 계신가요!!!!"
};
_predEngine = _mlContext.Model.CreatePredictionEngine <GitHubIssue, IssuePrediction>(loadedModel);
var prediction2 = _predEngine.Predict(singleIssue);
Console.WriteLine($"=============== Single Prediction - Result: {prediction2.Area} ===============");
}
