private (Pipeline, ColumnInferenceResults) GetMockedOvaPipelineAndInference()
{
if (_mockedOvaPipeline == null)
{
MLContext context = new MLContext();
// same learners with different hyperparameters
var hyperparams1 = new Microsoft.ML.AutoML.ParameterSet(new List <Microsoft.ML.AutoML.IParameterValue>()
{
new LongParameterValue("NumLeaves", 2)
});
var trainer1 = new SuggestedTrainer(context, new FastForestOvaExtension(), new ColumnInformation(), hyperparams1);
var transforms1 = new List <SuggestedTransform>()
{
ColumnConcatenatingExtension.CreateSuggestedTransform(context, new[] { "In" }, "Out")
};
var inferredPipeline1 = new SuggestedPipeline(transforms1, new List <SuggestedTransform>(), trainer1, context, true);
this._mockedOvaPipeline = inferredPipeline1.ToPipeline();
var textLoaderArgs = new TextLoader.Options()
{
Columns = new[] {
new TextLoader.Column("Label", DataKind.Boolean, 0),
new TextLoader.Column("col1", DataKind.Single, 1),
new TextLoader.Column("col2", DataKind.Single, 0),
new TextLoader.Column("col3", DataKind.String, 0),
new TextLoader.Column("col4", DataKind.Int32, 0),
new TextLoader.Column("col5", DataKind.UInt32, 0),
},
AllowQuoting = true,
AllowSparse = true,
HasHeader = true,
Separators = new[] { ',' }
};
this._columnInference = new ColumnInferenceResults()
{
TextLoaderOptions = textLoaderArgs,
ColumnInformation = new ColumnInformation()
{
LabelColumnName = "Label"
}
};
}
return(_mockedOvaPipeline, _columnInference);
}
private (Pipeline, ColumnInferenceResults) GetMockedRecommendationPipelineAndInference()
{
if (mockedPipeline == null)
{
MLContext context = new MLContext();
var trainer1 = new SuggestedTrainer(context, new MatrixFactorizationExtension(), new ColumnInformation()
{
LabelColumnName = "Label",
UserIdColumnName = "userId",
ItemIdColumnName = "movieId",
}, hyperParamSet: null);
var transforms1 = new List <SuggestedTransform>()
{
ColumnConcatenatingExtension.CreateSuggestedTransform(context, new[] { "In" }, "Out")
};
var inferredPipeline1 = new SuggestedPipeline(transforms1, new List <SuggestedTransform>(), trainer1, context, false);
mockedPipeline = inferredPipeline1.ToPipeline();
var textLoaderArgs = new TextLoader.Options()
{
Columns = new[] {
new TextLoader.Column("Label", DataKind.String, 0),
new TextLoader.Column("userId", DataKind.String, 1),
new TextLoader.Column("movieId", DataKind.String, 2),
},
AllowQuoting = true,
AllowSparse = true,
HasHeader = true,
Separators = new[] { ',' }
};
this.columnInference = new ColumnInferenceResults()
{
TextLoaderOptions = textLoaderArgs,
ColumnInformation = new ColumnInformation()
{
LabelColumnName = "Label",
UserIdColumnName = "userId",
ItemIdColumnName = "movieId"
}
};
}
return(mockedPipeline, columnInference);
}
public void EstimatorExtensionStaticTests()
{
var context = new MLContext();
var inCol = "Input";
var outCol = "Output";
var inCols = new string[] { inCol };
var outCols = new string[] { outCol };
Assert.NotNull(ColumnConcatenatingExtension.CreateSuggestedTransform(context, inCols, outCol));
Assert.NotNull(ColumnCopyingExtension.CreateSuggestedTransform(context, inCol, outCol));
Assert.NotNull(MissingValueIndicatingExtension.CreateSuggestedTransform(context, inCols, outCols));
Assert.NotNull(MissingValueReplacingExtension.CreateSuggestedTransform(context, inCols, outCols));
Assert.NotNull(NormalizingExtension.CreateSuggestedTransform(context, inCol, outCol));
Assert.NotNull(OneHotEncodingExtension.CreateSuggestedTransform(context, inCols, outCols));
Assert.NotNull(OneHotHashEncodingExtension.CreateSuggestedTransform(context, inCols, outCols));
Assert.NotNull(TextFeaturizingExtension.CreateSuggestedTransform(context, inCol, outCol));
Assert.NotNull(TypeConvertingExtension.CreateSuggestedTransform(context, inCols, outCols));
Assert.NotNull(ValueToKeyMappingExtension.CreateSuggestedTransform(context, inCol, outCol));
}
public void InferredPipelinesHashTest()
{
var context = new MLContext();
var columnInfo = new ColumnInformation();
// test same learners with no hyperparams have the same hash code
var trainer1 = new SuggestedTrainer(context, new LightGbmBinaryExtension(), columnInfo);
var trainer2 = new SuggestedTrainer(context, new LightGbmBinaryExtension(), columnInfo);
var transforms1 = new List <SuggestedTransform>();
var transforms2 = new List <SuggestedTransform>();
var inferredPipeline1 = new SuggestedPipeline(transforms1, new List <SuggestedTransform>(), trainer1, context, false);
var inferredPipeline2 = new SuggestedPipeline(transforms2, new List <SuggestedTransform>(), trainer2, context, false);
Assert.Equal(inferredPipeline1.GetHashCode(), inferredPipeline2.GetHashCode());
// test same learners with hyperparams set vs empty hyperparams have different hash codes
var hyperparams1 = new ParameterSet(new List <IParameterValue>()
{
new LongParameterValue("NumberOfLeaves", 2)
});
trainer1 = new SuggestedTrainer(context, new LightGbmBinaryExtension(), columnInfo, hyperparams1);
trainer2 = new SuggestedTrainer(context, new LightGbmBinaryExtension(), columnInfo);
inferredPipeline1 = new SuggestedPipeline(transforms1, new List <SuggestedTransform>(), trainer1, context, false);
inferredPipeline2 = new SuggestedPipeline(transforms2, new List <SuggestedTransform>(), trainer2, context, false);
Assert.NotEqual(inferredPipeline1.GetHashCode(), inferredPipeline2.GetHashCode());
// same learners with different hyperparams
hyperparams1 = new ParameterSet(new List <IParameterValue>()
{
new LongParameterValue("NumberOfLeaves", 2)
});
var hyperparams2 = new ParameterSet(new List <IParameterValue>()
{
new LongParameterValue("NumberOfLeaves", 6)
});
trainer1 = new SuggestedTrainer(context, new LightGbmBinaryExtension(), columnInfo, hyperparams1);
trainer2 = new SuggestedTrainer(context, new LightGbmBinaryExtension(), columnInfo, hyperparams2);
inferredPipeline1 = new SuggestedPipeline(transforms1, new List <SuggestedTransform>(), trainer1, context, false);
inferredPipeline2 = new SuggestedPipeline(transforms2, new List <SuggestedTransform>(), trainer2, context, false);
Assert.NotEqual(inferredPipeline1.GetHashCode(), inferredPipeline2.GetHashCode());
// same learners with same transforms
trainer1 = new SuggestedTrainer(context, new LightGbmBinaryExtension(), columnInfo);
trainer2 = new SuggestedTrainer(context, new LightGbmBinaryExtension(), columnInfo);
transforms1 = new List <SuggestedTransform>()
{
ColumnConcatenatingExtension.CreateSuggestedTransform(context, new[] { "In" }, "Out")
};
transforms2 = new List <SuggestedTransform>()
{
ColumnConcatenatingExtension.CreateSuggestedTransform(context, new[] { "In" }, "Out")
};
inferredPipeline1 = new SuggestedPipeline(transforms1, new List <SuggestedTransform>(), trainer1, context, false);
inferredPipeline2 = new SuggestedPipeline(transforms2, new List <SuggestedTransform>(), trainer2, context, false);
Assert.Equal(inferredPipeline1.GetHashCode(), inferredPipeline2.GetHashCode());
// same transforms with different learners
trainer1 = new SuggestedTrainer(context, new SdcaLogisticRegressionBinaryExtension(), columnInfo);
trainer2 = new SuggestedTrainer(context, new LightGbmBinaryExtension(), columnInfo);
transforms1 = new List <SuggestedTransform>()
{
ColumnConcatenatingExtension.CreateSuggestedTransform(context, new[] { "In" }, "Out")
};
transforms2 = new List <SuggestedTransform>()
{
ColumnConcatenatingExtension.CreateSuggestedTransform(context, new[] { "In" }, "Out")
};
inferredPipeline1 = new SuggestedPipeline(transforms1, new List <SuggestedTransform>(), trainer1, context, false);
inferredPipeline2 = new SuggestedPipeline(transforms2, new List <SuggestedTransform>(), trainer2, context, false);
Assert.NotEqual(inferredPipeline1.GetHashCode(), inferredPipeline2.GetHashCode());
}