public static void PredictDocument()
{
// <SnippetLoadModel>
ITransformer loadedModel = _mlContext.Model.Load(_modelPath, out var modelInputSchema);
// </SnippetLoadModel>
// <SnippetAddTestIssue>
// Correct Type: 5
CustomerMessage sample = new CustomerMessage()
{
Contents = "Favor realizar cambio de plan a los abonados: 989990999 / 999999090 Plan actual ZVB, favor cambiar plan y dejar activo plan ZVC de 8GB. Agradecido. Saludos. SA"
};
// </SnippetAddTestIssue>
//Predict label for single hard-coded issue
// <SnippetCreatePredictionEngine>
_predEngine = _mlContext.Model.CreatePredictionEngine <CustomerMessage, MessageTypePrediction>(loadedModel);
// </SnippetCreatePredictionEngine>
// <SnippetPredictIssue>
var prediction = _predEngine.Predict(sample);
// </SnippetPredictIssue>
// <SnippetDisplayResults>
Console.WriteLine($"=============== Single Prediction - Result: {prediction.TypeCode} ===============");
// </SnippetDisplayResults>
}
public static IEstimator <ITransformer> BuildAndTrainModel(IDataView trainingDataView, IEstimator <ITransformer> pipeline)
{
// STEP 3: Create the training algorithm/trainer
// Use the multi-class SDCA algorithm to predict the label using features.
// Set the trainer/algorithm and map label to value (original readable state)
// <SnippetAddTrainer>
var trainingPipeline =
pipeline.Append(_mlContext.MulticlassClassification.Trainers.SdcaMaximumEntropy("Label", "ContentsFeaturized"))
.Append(_mlContext.Transforms.Conversion.MapKeyToValue("PredictedLabel"));
// </SnippetAddTrainer>
// STEP 4: Train the model fitting to the DataSet
Console.WriteLine($"=============== Training the model ===============");
// <SnippetTrainModel>
_trainedModel = trainingPipeline.Fit(trainingDataView);
// </SnippetTrainModel>
Console.WriteLine($"=============== Finished Training the model Ending time: {DateTime.Now.ToString()} ===============");
// (OPTIONAL) Try/test a single prediction with the "just-trained model" (Before saving the model)
// Create prediction engine related to the loaded trained model
// <SnippetCreatePredictionEngine1>
_predEngine = _mlContext.Model.CreatePredictionEngine <CustomerMessage, MessageTypePrediction>(_trainedModel);
// </SnippetCreatePredictionEngine1>
// Original type: 2 ALTA
CustomerMessage sample = new CustomerMessage();
sample.Contents = "Necesito que por favor habiliten el numero +99 9 8999 9009 para realizar llamadas internacionales, principalmente Brasil";
var prediction = _predEngine.Predict(sample);
Console.WriteLine($"Prediction just-trained-model - {sample.Contents}\nResult: {prediction.TypeCode} ===============");
// Original type: 3 BAJA
sample.Contents = "Estimados Favor solicito bajar servicio , Roaming ,Larga distancia internacional y SMS ( Solo emisión ) a los celulares";
prediction = _predEngine.Predict(sample);
Console.WriteLine($"Prediction just-trained-model - {sample.Contents}\nResult: {prediction.TypeCode} ===============");
// Original type: 9 Reclamo
sample.Contents = "esta mañana realicé req 999999, el cual ustedes lo finalizaron, adjuntando un pdf, el requerimiento fue otro, el cual indica que la plataforma no funciona, ¿cuando estará disponible?";
prediction = _predEngine.Predict(sample);
Console.WriteLine($"Prediction just-trained-model - {sample.Contents}\nResult: {prediction.TypeCode} ===============");
// Original type: 9 RECLAMO
sample.Contents = "Buen día tengo problemas de comunicación no se puede realizar ni recibir llamados es urgente las lineas son";
prediction = _predEngine.Predict(sample);
Console.WriteLine($"Prediction just-trained-model - {sample.Contents}\nResult: {prediction.TypeCode} ===============");
// <SnippetReturnModel>
return(trainingPipeline);
// </SnippetReturnModel>
}
