public void TrainSentiment()
{
// Pipeline
var arguments = new TextLoader.Arguments()
{
Column = new TextLoader.Column[]
{
new TextLoader.Column()
{
Name = "Label",
Source = new[] { new TextLoader.Range()
{
Min = 0, Max = 0
} },
Type = DataKind.Num
},
new TextLoader.Column()
{
Name = "SentimentText",
Source = new[] { new TextLoader.Range()
{
Min = 1, Max = 1
} },
Type = DataKind.Text
}
},
HasHeader = true,
AllowQuoting = false,
AllowSparse = false
};
var loader = _env.Data.ReadFromTextFile(_sentimentDataPath, arguments);
var text = new TextFeaturizingEstimator(_env, "SentimentText", "WordEmbeddings", args =>
{
args.OutputTokens = true;
args.KeepPunctuations = false;
args.UseStopRemover = true;
args.VectorNormalizer = TextFeaturizingEstimator.TextNormKind.None;
args.UseCharExtractor = false;
args.UseWordExtractor = false;
}).Fit(loader).Transform(loader);
var trans = new WordEmbeddingsExtractingEstimator(_env, "WordEmbeddings_TransformedText", "Features",
WordEmbeddingsExtractingTransformer.PretrainedModelKind.Sswe).Fit(text).Transform(text);
// Train
var trainer = new SdcaMultiClassTrainer(_env, "Label", "Features", maxIterations: 20);
var predicted = trainer.Fit(trans);
_consumer.Consume(predicted);
}
public void TrainSentiment()
{
var env = new MLContext(seed: 1);
// Pipeline
var arguments = new TextLoader.Arguments()
{
Column = new TextLoader.Column[]
{
new TextLoader.Column()
{
Name = "Label",
Source = new[] { new TextLoader.Range()
{
Min = 0, Max = 0
} },
Type = DataKind.Num
},
new TextLoader.Column()
{
Name = "SentimentText",
Source = new[] { new TextLoader.Range()
{
Min = 1, Max = 1
} },
Type = DataKind.Text
}
},
HasHeader = true,
AllowQuoting = false,
AllowSparse = false
};
var loader = env.Data.ReadFromTextFile(_sentimentDataPath, arguments);
var text = TextFeaturizingEstimator.Create(env,
new TextFeaturizingEstimator.Arguments()
{
Column = new TextFeaturizingEstimator.Column
{
Name = "WordEmbeddings",
Source = new[] { "SentimentText" }
},
OutputTokens = true,
KeepPunctuations = false,
UsePredefinedStopWordRemover = true,
VectorNormalizer = TextFeaturizingEstimator.TextNormKind.None,
CharFeatureExtractor = null,
WordFeatureExtractor = null,
}, loader);
var trans = WordEmbeddingsExtractingTransformer.Create(env,
new WordEmbeddingsExtractingTransformer.Arguments()
{
Column = new WordEmbeddingsExtractingTransformer.Column[1]
{
new WordEmbeddingsExtractingTransformer.Column
{
Name = "Features",
Source = "WordEmbeddings_TransformedText"
}
},
ModelKind = WordEmbeddingsExtractingTransformer.PretrainedModelKind.Sswe,
}, text);
// Train
var trainer = new SdcaMultiClassTrainer(env, "Label", "Features", maxIterations: 20);
var predicted = trainer.Fit(trans);
_consumer.Consume(predicted);
}