Skip to content

Commit

Permalink
Changed all MLContext creation to include a fixed seed (#4736)
Browse files Browse the repository at this point in the history 
* Changed all MLContext creation to include a fixed seed

* Reverted fixed seed related changes from the code generator tests
  • Loading branch information
@harishsk
harishsk authored Jan 31, 2020
1 parent 69b55d2 commit 24c8274
Show file tree
Hide file tree
Showing 49 changed files with 149 additions and 149 deletions.
10 changes: 5 additions & 5 deletions test/Microsoft.ML.AutoML.Tests/AutoFitTests.cs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@ public class AutoFitTests
[Fact]
public void AutoFitBinaryTest()
{
var context = new MLContext();
var context = new MLContext(1);
var dataPath = DatasetUtil.DownloadUciAdultDataset();
var columnInference = context.Auto().InferColumns(dataPath, DatasetUtil.UciAdultLabel);
var textLoader = context.Data.CreateTextLoader(columnInference.TextLoaderOptions);
Expand All @@ -37,7 +37,7 @@ public void AutoFitBinaryTest()
[Fact]
public void AutoFitMultiTest()
{
var context = new MLContext();
var context = new MLContext(1);
var columnInference = context.Auto().InferColumns(DatasetUtil.TrivialMulticlassDatasetPath, DatasetUtil.TrivialMulticlassDatasetLabel);
var textLoader = context.Data.CreateTextLoader(columnInference.TextLoaderOptions);
var trainData = textLoader.Load(DatasetUtil.TrivialMulticlassDatasetPath);
Expand Down Expand Up @@ -79,7 +79,7 @@ public void AutoFitImageClassification()
// This test executes the code path that model builder code will take to get a model using image
// classification API.

var context = new MLContext();
var context = new MLContext(1);
context.Log += Context_Log;
var datasetPath = DatasetUtil.GetFlowersDataset();
var columnInference = context.Auto().InferColumns(datasetPath, "Label");
Expand All @@ -102,7 +102,7 @@ private void Context_Log(object sender, LoggingEventArgs e)
[Fact]
public void AutoFitRegressionTest()
{
var context = new MLContext();
var context = new MLContext(1);
var dataPath = DatasetUtil.DownloadMlNetGeneratedRegressionDataset();
var columnInference = context.Auto().InferColumns(dataPath, DatasetUtil.MlNetGeneratedRegressionLabel);
var textLoader = context.Data.CreateTextLoader(columnInference.TextLoaderOptions);
Expand All @@ -125,7 +125,7 @@ public void AutoFitRecommendationTest()
string userColumnName = "User";
string itemColumnName = "Item";
string scoreColumnName = "Score";
MLContext mlContext = new MLContext();
MLContext mlContext = new MLContext(1);

// STEP 1: Load data
var reader = new TextLoader(mlContext, GetLoaderArgs(labelColumnName, userColumnName, itemColumnName));
Expand Down
22 changes: 11 additions & 11 deletions test/Microsoft.ML.AutoML.Tests/ColumnInferenceTests.cs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,7 @@ public class ColumnInferenceTests
public void UnGroupReturnsMoreColumnsThanGroup()
{
var dataPath = DatasetUtil.DownloadUciAdultDataset();
var context = new MLContext();
var context = new MLContext(1);
var columnInferenceWithoutGrouping = context.Auto().InferColumns(dataPath, DatasetUtil.UciAdultLabel, groupColumns: false);
foreach (var col in columnInferenceWithoutGrouping.TextLoaderOptions.Columns)
{
Expand All @@ -28,20 +28,20 @@ public void UnGroupReturnsMoreColumnsThanGroup()
public void IncorrectLabelColumnThrows()
{
var dataPath = DatasetUtil.DownloadUciAdultDataset();
var context = new MLContext();
var context = new MLContext(1);
Assert.Throws<ArgumentException>(new System.Action(() => context.Auto().InferColumns(dataPath, "Junk", groupColumns: false)));
}

[Fact]
public void LabelIndexOutOfBoundsThrows()
{
Assert.Throws<ArgumentOutOfRangeException>(() => new MLContext().Auto().InferColumns(DatasetUtil.DownloadUciAdultDataset(), 100));
Assert.Throws<ArgumentOutOfRangeException>(() => new MLContext(1).Auto().InferColumns(DatasetUtil.DownloadUciAdultDataset(), 100));
}

[Fact]
public void IdentifyLabelColumnThroughIndexWithHeader()
{
var result = new MLContext().Auto().InferColumns(DatasetUtil.DownloadUciAdultDataset(), 14, hasHeader: true);
var result = new MLContext(1).Auto().InferColumns(DatasetUtil.DownloadUciAdultDataset(), 14, hasHeader: true);
Assert.True(result.TextLoaderOptions.HasHeader);
var labelCol = result.TextLoaderOptions.Columns.First(c => c.Source[0].Min == 14 && c.Source[0].Max == 14);
Assert.Equal("hours-per-week", labelCol.Name);
Expand All @@ -51,7 +51,7 @@ public void IdentifyLabelColumnThroughIndexWithHeader()
[Fact]
public void IdentifyLabelColumnThroughIndexWithoutHeader()
{
var result = new MLContext().Auto().InferColumns(DatasetUtil.DownloadIrisDataset(), DatasetUtil.IrisDatasetLabelColIndex);
var result = new MLContext(1).Auto().InferColumns(DatasetUtil.DownloadIrisDataset(), DatasetUtil.IrisDatasetLabelColIndex);
Assert.False(result.TextLoaderOptions.HasHeader);
var labelCol = result.TextLoaderOptions.Columns.First(c => c.Source[0].Min == DatasetUtil.IrisDatasetLabelColIndex &&
c.Source[0].Max == DatasetUtil.IrisDatasetLabelColIndex);
Expand All @@ -62,15 +62,15 @@ public void IdentifyLabelColumnThroughIndexWithoutHeader()
[Fact]
public void DatasetWithEmptyColumn()
{
var result = new MLContext().Auto().InferColumns(Path.Combine("TestData", "DatasetWithEmptyColumn.txt"), DefaultColumnNames.Label, groupColumns: false);
var result = new MLContext(1).Auto().InferColumns(Path.Combine("TestData", "DatasetWithEmptyColumn.txt"), DefaultColumnNames.Label, groupColumns: false);
var emptyColumn = result.TextLoaderOptions.Columns.First(c => c.Name == "Empty");
Assert.Equal(DataKind.Single, emptyColumn.DataKind);
}

[Fact]
public void DatasetWithBoolColumn()
{
var result = new MLContext().Auto().InferColumns(Path.Combine("TestData", "BinaryDatasetWithBoolColumn.txt"), DefaultColumnNames.Label);
var result = new MLContext(1).Auto().InferColumns(Path.Combine("TestData", "BinaryDatasetWithBoolColumn.txt"), DefaultColumnNames.Label);
Assert.Equal(2, result.TextLoaderOptions.Columns.Count());

var boolColumn = result.TextLoaderOptions.Columns.First(c => c.Name == "Bool");
Expand All @@ -88,7 +88,7 @@ public void DatasetWithBoolColumn()
[Fact]
public void WhereNameColumnIsOnlyFeature()
{
var result = new MLContext().Auto().InferColumns(Path.Combine("TestData", "NameColumnIsOnlyFeatureDataset.txt"), DefaultColumnNames.Label);
var result = new MLContext(1).Auto().InferColumns(Path.Combine("TestData", "NameColumnIsOnlyFeatureDataset.txt"), DefaultColumnNames.Label);
Assert.Equal(2, result.TextLoaderOptions.Columns.Count());

var nameColumn = result.TextLoaderOptions.Columns.First(c => c.Name == "Username");
Expand All @@ -104,7 +104,7 @@ public void WhereNameColumnIsOnlyFeature()
[Fact]
public void DefaultColumnNamesInferredCorrectly()
{
var result = new MLContext().Auto().InferColumns(Path.Combine("TestData", "DatasetWithDefaultColumnNames.txt"),
var result = new MLContext(1).Auto().InferColumns(Path.Combine("TestData", "DatasetWithDefaultColumnNames.txt"),
new ColumnInformation()
{
LabelColumnName = DefaultColumnNames.Label,
Expand All @@ -124,7 +124,7 @@ public void DefaultColumnNamesInferredCorrectly()
[Fact]
public void DefaultColumnNamesNoGrouping()
{
var result = new MLContext().Auto().InferColumns(Path.Combine("TestData", "DatasetWithDefaultColumnNames.txt"),
var result = new MLContext(1).Auto().InferColumns(Path.Combine("TestData", "DatasetWithDefaultColumnNames.txt"),
new ColumnInformation()
{
LabelColumnName = DefaultColumnNames.Label,
Expand All @@ -141,7 +141,7 @@ public void DefaultColumnNamesNoGrouping()
public void InferColumnsColumnInfoParam()
{
var columnInfo = new ColumnInformation() { LabelColumnName = DatasetUtil.MlNetGeneratedRegressionLabel };
var result = new MLContext().Auto().InferColumns(DatasetUtil.DownloadMlNetGeneratedRegressionDataset(),
var result = new MLContext(1).Auto().InferColumns(DatasetUtil.DownloadMlNetGeneratedRegressionDataset(),
columnInfo);
var labelCol = result.TextLoaderOptions.Columns.First(c => c.Name == DatasetUtil.MlNetGeneratedRegressionLabel);
Assert.Equal(DataKind.Single, labelCol.DataKind);
Expand Down
6 changes: 3 additions & 3 deletions test/Microsoft.ML.AutoML.Tests/DatasetDimensionsTests.cs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@ public class DatasetDimensionsTests
[Fact]
public void TextColumnDimensionsTest()
{
var context = new MLContext();
var context = new MLContext(1);
var dataBuilder = new ArrayDataViewBuilder(context);
dataBuilder.AddColumn("categorical", new string[] { "0", "1", "0", "1", "0", "1", "2", "2", "0", "1" });
dataBuilder.AddColumn("text", new string[] { "0", "1", "0", "1", "0", "1", "2", "2", "0", "1" });
Expand All @@ -35,7 +35,7 @@ public void TextColumnDimensionsTest()
[Fact]
public void FloatColumnDimensionsTest()
{
var context = new MLContext();
var context = new MLContext(1);
var dataBuilder = new ArrayDataViewBuilder(context);
dataBuilder.AddColumn("NoNan", NumberDataViewType.Single, new float[] { 0, 1, 0, 1, 0 });
dataBuilder.AddColumn("Nan", NumberDataViewType.Single, new float[] { 0, 1, 0, 1, float.NaN });
Expand All @@ -55,7 +55,7 @@ public void FloatColumnDimensionsTest()
[Fact]
public void FloatVectorColumnHasNanTest()
{
var context = new MLContext();
var context = new MLContext(1);
var dataBuilder = new ArrayDataViewBuilder(context);
var slotNames = new[] { "Col1", "Col2" };
var colValues = new float[][]
Expand Down
2 changes: 1 addition & 1 deletion test/Microsoft.ML.AutoML.Tests/DatasetUtil.cs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -28,7 +28,7 @@ public static IDataView GetUciAdultDataView()
{
if (_uciAdultDataView == null)
{
var context = new MLContext();
var context = new MLContext(1);
var uciAdultDataFile = DownloadUciAdultDataset();
var columnInferenceResult = context.Auto().InferColumns(uciAdultDataFile, UciAdultLabel);
var textLoader = context.Data.CreateTextLoader(columnInferenceResult.TextLoaderOptions);
Expand Down
4 changes: 2 additions & 2 deletions test/Microsoft.ML.AutoML.Tests/EstimatorExtensionTests.cs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@ public class EstimatorExtensionTests
[Fact]
public void EstimatorExtensionInstanceTests()
{
var context = new MLContext();
var context = new MLContext(1);
var pipelineNode = new PipelineNode()
{
InColumns = new string[] { "Input" },
Expand All @@ -35,7 +35,7 @@ public void EstimatorExtensionInstanceTests()
[Fact]
public void EstimatorExtensionStaticTests()
{
var context = new MLContext();
var context = new MLContext(1);
var inCol = "Input";
var outCol = "Output";
var inCols = new string[] { inCol };
Expand Down
4 changes: 2 additions & 2 deletions test/Microsoft.ML.AutoML.Tests/GetNextPipelineTests.cs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@ public class GetNextPipelineTests
[Fact]
public void GetNextPipeline()
{
var context = new MLContext();
var context = new MLContext(1);
var uciAdult = DatasetUtil.GetUciAdultDataView();
var columns = DatasetColumnInfoUtil.GetDatasetColumnInfo(context, uciAdult, new ColumnInformation() { LabelColumnName = DatasetUtil.UciAdultLabel });

Expand All @@ -40,7 +40,7 @@ public void GetNextPipeline()
[Fact]
public void GetNextPipelineMock()
{
var context = new MLContext();
var context = new MLContext(1);
var uciAdult = DatasetUtil.GetUciAdultDataView();
var columns = DatasetColumnInfoUtil.GetDatasetColumnInfo(context, uciAdult, new ColumnInformation() { LabelColumnName = DatasetUtil.UciAdultLabel });

Expand Down
2 changes: 1 addition & 1 deletion test/Microsoft.ML.AutoML.Tests/InferredPipelineTests.cs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,7 @@ public class InferredPipelineTests
[Fact]
public void InferredPipelinesHashTest()
{
var context = new MLContext();
var context = new MLContext(1);
var columnInfo = new ColumnInformation();

// test same learners with no hyperparams have the same hash code
Expand Down
2 changes: 1 addition & 1 deletion test/Microsoft.ML.AutoML.Tests/PurposeInferenceTests.cs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ public class PurposeInferenceTests
[Fact]
public void PurposeInferenceHiddenColumnsTest()
{
var context = new MLContext();
var context = new MLContext(1);

// build basic data view
var schemaBuilder = new DataViewSchema.Builder();
Expand Down
2 changes: 1 addition & 1 deletion test/Microsoft.ML.AutoML.Tests/SplitUtilTests.cs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@ public class SplitUtilTests
[Fact]
public void CrossValSplitThrowsWhenNotEnoughData()
{
var mlContext = new MLContext();
var mlContext = new MLContext(1);
var dataViewBuilder = new ArrayDataViewBuilder(mlContext);
dataViewBuilder.AddColumn("Number", NumberDataViewType.Single, 0f);
dataViewBuilder.AddColumn("Label", NumberDataViewType.Single, 0f);
Expand Down
2 changes: 1 addition & 1 deletion test/Microsoft.ML.AutoML.Tests/SuggestedPipelineBuilderTests.cs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@ namespace Microsoft.ML.AutoML.Test

public class SuggestedPipelineBuilderTests
{
private static MLContext _context = new MLContext();
private static MLContext _context = new MLContext(1);

[Fact]
public void TrainerWantsCaching()
Expand Down
6 changes: 3 additions & 3 deletions test/Microsoft.ML.AutoML.Tests/SweeperTests.cs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,7 @@ public void SmacQuickRunTest()
var longLogValueGenerator = new LongValueGenerator(new LongParamArguments() { Name = "longLog", Min = 1, Max = 1000, LogBase = true });
var discreteValueGeneator = new DiscreteValueGenerator(new DiscreteParamArguments() { Name = "discrete", Values = new[] { "200", "400", "600", "800" } });

var sweeper = new SmacSweeper(new MLContext(), new SmacSweeper.Arguments()
var sweeper = new SmacSweeper(new MLContext(1), new SmacSweeper.Arguments()
{
SweptParameters = new IValueGenerator[] {
floatValueGenerator,
Expand Down Expand Up @@ -80,7 +80,7 @@ public void SmacQuickRunTest()
[Fact(Skip = "This test is too slow to run as part of automation.")]
public void Smac4ParamsConvergenceTest()
{
var sweeper = new SmacSweeper(new MLContext(), new SmacSweeper.Arguments()
var sweeper = new SmacSweeper(new MLContext(1), new SmacSweeper.Arguments()
{
SweptParameters = new INumericValueGenerator[] {
new FloatValueGenerator(new FloatParamArguments() { Name = "x1", Min = 1, Max = 1000}),
Expand Down Expand Up @@ -133,7 +133,7 @@ public void Smac4ParamsConvergenceTest()
[Fact(Skip = "This test is too slow to run as part of automation.")]
public void Smac2ParamsConvergenceTest()
{
var sweeper = new SmacSweeper(new MLContext(), new SmacSweeper.Arguments()
var sweeper = new SmacSweeper(new MLContext(1), new SmacSweeper.Arguments()
{
SweptParameters = new INumericValueGenerator[] {
new FloatValueGenerator(new FloatParamArguments() { Name = "foo", Min = 1, Max = 5}),
Expand Down
8 changes: 4 additions & 4 deletions test/Microsoft.ML.AutoML.Tests/TrainerExtensionsTests.cs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@ public class TrainerExtensionsTests
[Fact]
public void TrainerExtensionInstanceTests()
{
var context = new MLContext();
var context = new MLContext(1);
var columnInfo = new ColumnInformation();
var trainerNames = Enum.GetValues(typeof(TrainerName)).Cast<TrainerName>()
.Except(new[] { TrainerName.Ova });
Expand Down Expand Up @@ -45,7 +45,7 @@ public void TrainerExtensionInstanceTests()
[TensorFlowFact]
public void TrainerExtensionTensorFlowInstanceTests()
{
var context = new MLContext();
var context = new MLContext(1);
var columnInfo = new ColumnInformation();
var extension = TrainerExtensionCatalog.GetTrainerExtension(TrainerName.ImageClassification);
var instance = extension.CreateInstance(context, null, columnInfo);
Expand Down Expand Up @@ -359,15 +359,15 @@ public void PublicToPrivateTrainerNamesNullTest()
[Fact]
public void AllowedTrainersWhitelistNullTest()
{
var trainers = RecipeInference.AllowedTrainers(new MLContext(), TaskKind.BinaryClassification, new ColumnInformation(), null);
var trainers = RecipeInference.AllowedTrainers(new MLContext(1), TaskKind.BinaryClassification, new ColumnInformation(), null);
Assert.True(trainers.Any());
}

[Fact]
public void AllowedTrainersWhitelistTest()
{
var whitelist = new[] { TrainerName.AveragedPerceptronBinary, TrainerName.FastForestBinary };
var trainers = RecipeInference.AllowedTrainers(new MLContext(), TaskKind.BinaryClassification, new ColumnInformation(), whitelist);
var trainers = RecipeInference.AllowedTrainers(new MLContext(1), TaskKind.BinaryClassification, new ColumnInformation(), whitelist);
Assert.Equal(whitelist.Count(), trainers.Count());
}
}
Expand Down
2 changes: 1 addition & 1 deletion test/Microsoft.ML.AutoML.Tests/TransformInferenceTests.cs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -756,7 +756,7 @@ private static void TransformInferenceTestCore(
string expectedJson,
TaskKind task = TaskKind.BinaryClassification)
{
var transforms = TransformInferenceApi.InferTransforms(new MLContext(), task, columns);
var transforms = TransformInferenceApi.InferTransforms(new MLContext(1), task, columns);
TestApplyTransformsToRealDataView(transforms, columns);
var pipelineNodes = transforms.Select(t => t.PipelineNode);
Util.AssertObjectMatchesJson(expectedJson, pipelineNodes);
Expand Down
2 changes: 1 addition & 1 deletion test/Microsoft.ML.AutoML.Tests/TransformPostTrainerInferenceTests.cs
View file
Original file line number Diff line number Diff line change
Expand Up @@ -62,7 +62,7 @@ private static void TransformPostTrainerInferenceTestCore(
DatasetColumnInfo[] columns,
string expectedJson)
{
var transforms = TransformInferenceApi.InferTransformsPostTrainer(new MLContext(), task, columns);
var transforms = TransformInferenceApi.InferTransformsPostTrainer(new MLContext(1), task, columns);
var pipelineNodes = transforms.Select(t => t.PipelineNode);
Util.AssertObjectMatchesJson(expectedJson, pipelineNodes);
}
Expand Down
Loading

0 comments on commit 24c8274

Please sign in to comment.