public void CanTrainSupervised()
{
using var fastText = new FastTextWrapper(loggerFactory: _loggerFactory);
string outPath = Path.Combine(_tempDir, "cooking");
var args = new SupervisedArgs();
var tuneArgs = new AutotuneArgs();
fastText.Supervised("cooking.train.txt", outPath, args, tuneArgs, true);
fastText.IsModelReady().Should().BeTrue();
fastText.GetModelDimension().Should().Be(100);
fastText.ModelPath.Should().Be(outPath + ".bin");
AssertLabels(fastText.GetLabels());
File.Exists(outPath + ".bin").Should().BeTrue();
File.Exists(outPath + ".vec").Should().BeTrue();
var debugArgs = DebugArgs.Load("_train.txt");
AssertSupervisedArgs(args, debugArgs.ExternalArgs);
AssertSupervisedArgs(args, debugArgs.ConvertedArgs);
AssertAutotuneArgs(tuneArgs, debugArgs.ExternalTune);
AssertAutotuneArgs(tuneArgs, debugArgs.ConvertedTune);
debugArgs.ExternalInput.Should().Be("cooking.train.txt");
debugArgs.ConvertedInput.Should().Be("cooking.train.txt");
debugArgs.ExternalOutput.Should().Be(outPath);
debugArgs.ConvertedOutput.Should().Be(outPath);
}
private void AssertAutotuneArgs(AutotuneArgs expected, AutotuneArgs actual)
{
(actual.ValidationFile ?? "").Should().Be(expected.ValidationFile ?? "");
(actual.Metric ?? "").Should().Be(expected.Metric ?? "");
actual.Predictions.Should().Be(expected.Predictions);
actual.Duration.Should().Be(expected.Duration);
(actual.ModelSize ?? "").Should().Be(expected.ModelSize ?? "");
}
public void CanAutotuneSupervisedModel()
{
using var fastText = new FastTextWrapper(loggerFactory: _loggerFactory);
string outPath = Path.Combine(_tempDir, "cooking");
var args = new SupervisedArgs
{
bucket = 2100000,
dim = 250,
epoch = 10,
loss = LossName.HierarchicalSoftmax,
lr = 0.5,
maxn = 5,
minn = 2,
neg = 6,
seed = 42,
t = 0.0002,
thread = 10,
verbose = 1,
ws = 6,
minCount = 2,
saveOutput = true,
wordNgrams = 2,
lrUpdateRate = 110,
minCountLabel = 1
};
var autotuneArgs = new AutotuneArgs
{
Duration = 30,
Metric = "precisionAtRecall:30",
Predictions = 2,
ValidationFile = "cooking.valid.txt"
};
fastText.Supervised("cooking.train.txt", outPath, args, autotuneArgs, true);
fastText.IsModelReady().Should().BeTrue();
fastText.GetModelDimension().Should().Be(250);
fastText.ModelPath.Should().Be(outPath + ".bin");
File.Exists(outPath + ".bin").Should().BeTrue();
File.Exists(outPath + ".vec").Should().BeTrue();
var debugArgs = DebugArgs.Load("_train.txt");
AssertSupervisedArgs(args, debugArgs.ExternalArgs);
AssertSupervisedArgs(args, debugArgs.ConvertedArgs);
AssertAutotuneArgs(autotuneArgs, debugArgs.ExternalTune);
AssertAutotuneArgs(autotuneArgs, debugArgs.ConvertedTune);
debugArgs.ExternalInput.Should().Be("cooking.train.txt");
debugArgs.ConvertedInput.Should().Be("cooking.train.txt");
debugArgs.ExternalOutput.Should().Be(outPath);
debugArgs.ConvertedOutput.Should().Be(outPath);
}
public void CanTrainSupervisedWithRelativeOutput()
{
using var fastText = new FastTextWrapper(loggerFactory: _loggerFactory);
var args = new SupervisedArgs();
var tuneArgs = new AutotuneArgs();
fastText.Supervised("cooking.train.txt", "cooking", args, tuneArgs, true);
fastText.IsModelReady().Should().BeTrue();
fastText.GetModelDimension().Should().Be(100);
fastText.ModelPath.Should().Be("cooking.bin");
AssertLabels(fastText.GetLabels());
File.Exists("cooking.bin").Should().BeTrue();
File.Exists("cooking.vec").Should().BeTrue();
File.Delete("cooking.bin");
File.Delete("cooking.vec");
}
/// <summary>
/// Trains a new supervised model. If <see cref="AutotuneArgs.ValidationFile"/> is specified, an automated
/// hyperparameter search will be performed.
/// </summary>
/// <param name="inputPath">Path to a training set.</param>
/// <param name="outputPath">Path to write the model to (excluding extension).</param>
/// <param name="args">
/// Training arguments. If <see cref="SupervisedArgs"/> is passed, a supervised model will be trained.
/// If <see cref="QuantizedSupervisedArgs"/> is passed, model will be quantized after training.
/// </param>
/// <param name="autotuneArgs">Autotune arguments.</param>
/// <param name="debug">Whether to write debug info.</param>
/// <remarks>Trained model will consist of two files: .bin (main model) and .vec (word vectors).</remarks>
internal void Supervised(string inputPath, string outputPath, SupervisedArgs args, AutotuneArgs autotuneArgs, bool debug)
{
ValidatePaths(inputPath, outputPath, args.PretrainedVectors);
if (args.model != ModelName.Supervised)
{
_logger?.LogWarning($"{args.model} model type specified in a Supervised() call. Model type will be changed to Supervised.");
}
var quantizedArgs = args as QuantizedSupervisedArgs;
if (!string.IsNullOrEmpty(autotuneArgs.ModelSize) && quantizedArgs == null)
{
throw new InvalidOperationException("You specified model size in autotuneArgs, but passed SupervisedArgs instance. Pass QuantizedSupervisedArgs instead.");
}
bool quantizeWithNoQuantTune = quantizedArgs != null && string.IsNullOrEmpty(autotuneArgs.ModelSize);
var argsStruct = _mapper.Map <FastTextArgsStruct>(args);
argsStruct.model = model_name.sup;
var autotuneStruct = _mapper.Map <AutotuneArgsStruct>(autotuneArgs);
CheckForErrors(Train(
_fastText,
inputPath,
quantizeWithNoQuantTune ? null : outputPath,
argsStruct,
autotuneStruct,
args.TrainProgressCallback,
autotuneArgs.AutotuneProgressCallback,
args.LabelPrefix,
args.PretrainedVectors,
debug));
if (quantizeWithNoQuantTune)
{
Quantize(quantizedArgs, outputPath);
}
else
{
_maxLabelLen = CheckForErrors(GetMaxLabelLength(_fastText));
ModelPath = AdjustPath(outputPath, !string.IsNullOrEmpty(autotuneArgs.ModelSize));
}
}
/// <summary>
/// Trains a new supervised model. If <see cref="AutotuneArgs.ValidationFile"/> is specified, an automated
/// hyperparameter search will be performed.
/// </summary>
/// <param name="inputPath">Path to a training set.</param>
/// <param name="outputPath">Path to write the model to (excluding extension).</param>
/// <param name="args">
/// Training arguments. If <see cref="SupervisedArgs"/> is passed, a supervised model will be trained.
/// If <see cref="QuantizedSupervisedArgs"/> is passed, model will be quantized after training.
/// </param>
/// <param name="autotuneArgs">Autotune arguments.</param>
/// <param name="progressCallback">Optional progress callback.</param>
/// <remarks>Trained model will consist of two files: .bin (main model) and .vec (word vectors).</remarks>
public void Supervised(string inputPath, string outputPath, SupervisedArgs args, AutotuneArgs autotuneArgs, TrainProgressCallback progressCallback = null)
{
Supervised(inputPath, outputPath, args, autotuneArgs, false);
}
