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);
}
public void CanTrainCbowWithProgressCallback()
{
using var fastText = new FastTextWrapper(loggerFactory: _loggerFactory);
string outPath = Path.Combine(_tempDir, "cooking");
int callNum = 0;
var args = new UnsupervisedArgs
{
TrainProgressCallback = (progress, loss, wst, lr, eta) =>
{
callNum++;
}
};
fastText.Unsupervised(UnsupervisedModel.CBow, "cooking.train.nolabels.txt", outPath, args);
callNum.Should().BeGreaterThan(0);
fastText.IsModelReady().Should().BeTrue();
fastText.GetModelDimension().Should().Be(100);
fastText.ModelPath.Should().Be(outPath + ".bin");
File.Exists(outPath + ".bin").Should().BeTrue();
File.Exists(outPath + ".vec").Should().BeTrue();
}
public void CanTrainSupervisedWithProgressCallback()
{
using var fastText = new FastTextWrapper();
string outPath = Path.Combine(_tempDir, "cooking");
int callNum = 0;
var args = new SupervisedArgs
{
TrainProgressCallback = (progress, loss, wst, lr, eta) =>
{
callNum++;
}
};
fastText.Supervised("cooking.train.txt", outPath, args);
callNum.Should().BeGreaterThan(0);
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();
}
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 CanLoadSupervisedModel()
{
using var fastText = new FastTextWrapper(loggerFactory: _loggerFactory);
fastText.LoadModel(_fixture.FastText.ModelPath);
fastText.IsModelReady().Should().BeTrue();
fastText.GetModelDimension().Should().Be(100);
AssertLabels(fastText.GetLabels());
}
public void CanQuantizeLoadedSupervisedModel()
{
using var fastText = new FastTextWrapper(loggerFactory: _loggerFactory);
fastText.LoadModel(_fixture.FastText.ModelPath);
fastText.IsModelReady().Should().BeTrue();
fastText.GetModelDimension().Should().Be(100);
AssertLabels(fastText.GetLabels());
string newPath = Path.Combine(Path.GetDirectoryName(_fixture.FastText.ModelPath), Path.GetFileNameWithoutExtension(_fixture.FastText.ModelPath));
fastText.Quantize();
fastText.IsModelReady().Should().BeTrue();
fastText.GetModelDimension().Should().Be(100);
fastText.ModelPath.Should().Be(newPath + ".ftz");
File.Exists(newPath + ".ftz").Should().BeTrue();
File.Exists(newPath + ".vec").Should().BeTrue();
}
public void CanTrainCbowModel()
{
using var fastText = new FastTextWrapper(loggerFactory: _loggerFactory);
string outPath = Path.Combine(_tempDir, "cooking");
fastText.Unsupervised(UnsupervisedModel.CBow, "cooking.train.nolabels.txt", outPath);
fastText.IsModelReady().Should().BeTrue();
fastText.GetModelDimension().Should().Be(100);
fastText.ModelPath.Should().Be(outPath + ".bin");
File.Exists(outPath + ".bin").Should().BeTrue();
File.Exists(outPath + ".vec").Should().BeTrue();
}
public void CanTrainSupervised()
{
var fastText = new FastTextWrapper(loggerFactory: _loggerFactory);
string outPath = Path.Combine(_tempDir, "cooking");
fastText.Supervised("cooking.train.txt", outPath, FastTextArgs.SupervisedDefaults());
fastText.IsModelReady().Should().BeTrue();
fastText.GetModelDimension().Should().Be(100);
CheckLabels(fastText.GetLabels());
File.Exists(outPath + ".bin").Should().BeTrue();
File.Exists(outPath + ".vec").Should().BeTrue();
}
public void CanTrainSupervisedWithNoLoggingAndNoArgs()
{
using var fastText = new FastTextWrapper();
string outPath = Path.Combine(_tempDir, "cooking");
fastText.Supervised("cooking.train.txt", outPath);
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();
}
public void CanUsePretrainedVectorsForSupervisedModel()
{
var fastText = new FastTextWrapper(loggerFactory: _loggerFactory);
string outPath = Path.Combine(_tempDir, "cooking");
var args = FastTextArgs.SupervisedDefaults();
args.PretrainedVectors = "cooking.unsup.300.vec";
args.dim = 300;
fastText.Supervised("cooking.train.txt", outPath, args);
fastText.IsModelReady().Should().BeTrue();
fastText.GetModelDimension().Should().Be(300);
CheckLabels(fastText.GetLabels());
File.Exists(outPath + ".bin").Should().BeTrue();
File.Exists(outPath + ".vec").Should().BeTrue();
}
public void CanTrainSupervisedWithPretrainedVectors()
{
using var fastText = new FastTextWrapper(loggerFactory: _loggerFactory);
string outPath = Path.Combine(_tempDir, "cooking");
var args = new SupervisedArgs();
args.PretrainedVectors = "cooking.unsup.300.vec";
args.dim = 300;
fastText.Supervised("cooking.train.txt", outPath, args, new AutotuneArgs(), true);
fastText.IsModelReady().Should().BeTrue();
fastText.GetModelDimension().Should().Be(300);
fastText.ModelPath.Should().Be(outPath + ".bin");
AssertLabels(fastText.GetLabels());
File.Exists(outPath + ".bin").Should().BeTrue();
File.Exists(outPath + ".vec").Should().BeTrue();
}
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");
}