private static void UseModelWithUserInput(string userInput)
{
PredictionEngine <FeedbackData, FeedbackPrediction> predictionFunction = _mlContext.Model.CreatePredictionEngine <FeedbackData, FeedbackPrediction>(_trainedModel);
FeedbackData sampleStatement = new FeedbackData
{
FeedbackText = userInput
};
var resultPrediction = predictionFunction.Predict(sampleStatement);
Console.WriteLine();
Console.WriteLine("=============== Prediction Test of model with a single sample and test dataset ===============");
Console.WriteLine();
Console.WriteLine($"Prediction: {resultPrediction.PredictedStars}");
Console.WriteLine("=============== End of Predictions ===============");
Console.WriteLine();
Console.WriteLine("Was this prediction correct? (Y/N): ");
var correctStars = 0;
var predictionCorrect = Console.ReadLine();
if (string.Equals(predictionCorrect.ToUpper(), "N"))
{
Console.WriteLine("How many stars should it be? ");
correctStars = int.Parse(Console.ReadLine());
}
else
{
correctStars = resultPrediction.PredictedStars;
}
File.AppendAllText(_dataPath, userInput + "\t" + correctStars + Environment.NewLine);
}
public static void BuildAndTrainModel(IDataView trainingDataView, IEstimator <ITransformer> pipeline)
{
var trainingPipeline = pipeline.Append(_mlContext.MulticlassClassification.Trainers.SdcaMaximumEntropy("Label", "Features"))
.Append(_mlContext.Transforms.Conversion.MapKeyToValue("PredictedLabel"));
_trainedModel = trainingPipeline.Fit(trainingDataView);
_predEngine = _mlContext.Model.CreatePredictionEngine <FeedbackData, FeedbackPrediction>(_trainedModel);
FeedbackData feedback = new FeedbackData()
{
FeedbackText = "I love this feedback",
Stars = 5
};
var prediction = _predEngine.Predict(feedback);
Console.WriteLine($"=============== Single Prediction just-trained-model - Result: {prediction.PredictedStars} ===============");
}
