Skip to content

switch housing dataset to wine #170

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 14 commits into from
May 23, 2018
Merged

switch housing dataset to wine #170

Show file tree
Hide file tree
Changes from 10 commits
Commits
Show all changes
14 commits
Select commit Hold shift + click to select a range
e6fde16
replace housing uci dataset to wine quality
May 4, 2018
dd969aa
proper order
May 4, 2018
8777327
unix slash
May 4, 2018
ccfad34
download only if they not present
May 16, 2018
40f1574
Merge branch 'master' into ivanidze/switch_housing_dataset_to_wine
May 16, 2018
a49ed52
remove parenthesis
May 16, 2018
dc2be36
fix build
May 16, 2018
ee307bf
Replace Result to DestinationFile
May 16, 2018
0353bb7
move Url to subelement
May 18, 2018
7d76cd3
formatting
May 18, 2018
08a2a00
switch to sub-elements
May 22, 2018
45478c2
merge from master
May 22, 2018
f9bcb74
Update CrossValidationMacro
May 22, 2018
72abef1
create dataset
May 22, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -328,3 +328,5 @@ ASALocalRun/

# MSBuild Binary and Structured Log
*.binlog
# Ignore external test datasets.
/test/data/external/
19 changes: 17 additions & 2 deletions build.proj
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@
<Import Project="$([MSBuild]::GetDirectoryNameOfFileAbove($(MSBuildThisFileDirectory), Directory.Build.props))\Directory.Build.props" />

<Import Project="$(ToolsDir)VersionTools.targets" Condition="Exists('$(ToolsDir)VersionTools.targets')" />

<UsingTask TaskName="DownloadFilesFromUrl" AssemblyFile="$(ToolsDir)Microsoft.DotNet.Build.Tasks.dll"/>
<PropertyGroup>
<!-- To disable the restoration of packages, set RestoreDuringBuild=false or pass /p:RestoreDuringBuild=false.-->
<RestoreDuringBuild Condition="'$(RestoreDuringBuild)'==''">true</RestoreDuringBuild>
Expand All @@ -33,6 +33,7 @@
RestoreProjects;
BuildNative;
$(TraversalBuildDependsOn);
DownloadExternalTestFiles;
RunTests;
</TraversalBuildDependsOn>
</PropertyGroup>
Expand All @@ -56,13 +57,27 @@
<ItemGroup>
<PkgProject Include="pkg\**\*.nupkgproj" />
</ItemGroup>

<MSBuild Projects="@(PkgProject)"
Targets="Restore" />
<MSBuild Projects="@(PkgProject)"
Targets="Pack" />
</Target>

<ItemGroup>
<TestFile Include="$(MSBuildThisFileDirectory)/test/data/external/winequality-white.csv">
<Url>https://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality-white.csv</Url>
<DestinationFile>$(MSBuildThisFileDirectory)test/data/external/winequality-white.csv</DestinationFile>
</TestFile>
</ItemGroup>

<Target Name="DownloadExternalTestFiles" Inputs="@(TestFile)" Outputs="%(TestFile.DestinationFile)">
<Message Importance="High" Text="Downloading external test files... %(TestFile.DestinationFile)" />
<DownloadFilesFromUrl Items="@(TestFile)"
DestinationDir="test/data/external"
TreatErrorsAsWarnings="true"/>
</Target>

<Target Name="RunTests" Condition="'$(RunTests)'=='true'">
<MSBuild Projects="test\run-tests.proj"
Targets="RunTests" />
Expand Down
8 changes: 4 additions & 4 deletions test/Microsoft.ML.Core.Tests/UnitTests/TestCSharpApi.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -269,10 +269,10 @@ public void TestCrossValidationBinaryMacro()
}
}

[Fact(Skip = "Missing data set. See https://github.com/dotnet/machinelearning/issues/3")]
[Fact()]
public void TestCrossValidationMacro()
{
var dataPath = GetDataPath(@"housing.txt");
var dataPath = GetDataPath(@"external/winequality-white.csv");
using (var env = new TlcEnvironment())
{
var subGraph = env.CreateExperiment();
Expand All @@ -295,7 +295,7 @@ public void TestCrossValidationMacro()
var modelCombineOutput = subGraph.Add(modelCombine);

var experiment = env.CreateExperiment();
var importInput = new ML.Data.TextLoader();
var importInput = new ML.Data.TextLoader() { CustomSchema = "col=Label:R4:11 col=Features:R4:0-10 sep=; header+" };
var importOutput = experiment.Add(importInput);

var crossValidate = new ML.Models.CrossValidator
Expand Down Expand Up @@ -324,7 +324,7 @@ public void TestCrossValidationMacro()
Assert.True(b);
double val = 0;
getter(ref val);
Assert.Equal(3.32, val, 1);
Assert.Equal(0.58, val, 1);
b = cursor.MoveNext();
Assert.False(b);
}
Expand Down
23 changes: 13 additions & 10 deletions test/Microsoft.ML.Core.Tests/UnitTests/TestEntryPoints.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -729,7 +729,7 @@ public void EntryPointTextToKeyToText()
}

private void RunTrainScoreEvaluate(string learner, string evaluator, string dataPath, string warningsPath, string overallMetricsPath,
string instanceMetricsPath, string confusionMatrixPath = null)
string instanceMetricsPath, string confusionMatrixPath = null, string loader = null)
{
string inputGraph = string.Format(@"
{{
Expand All @@ -738,6 +738,7 @@ private void RunTrainScoreEvaluate(string learner, string evaluator, string data
'Name': 'Data.TextLoader',
'Inputs': {{
'InputFile': '$file'
{8}
}},
'Outputs': {{
'Data': '$AllData'
Expand Down Expand Up @@ -797,7 +798,8 @@ private void RunTrainScoreEvaluate(string learner, string evaluator, string data
}}
}}", learner, evaluator, EscapePath(dataPath), EscapePath(warningsPath), EscapePath(overallMetricsPath), EscapePath(instanceMetricsPath),
confusionMatrixPath != null ? ", 'ConfusionMatrix': '$ConfusionMatrix'" : "",
confusionMatrixPath != null ? string.Format(", 'ConfusionMatrix' : '{0}'", EscapePath(confusionMatrixPath)) : "");
confusionMatrixPath != null ? string.Format(", 'ConfusionMatrix' : '{0}'", EscapePath(confusionMatrixPath)) : "",
string.IsNullOrWhiteSpace(loader) ? "" : string.Format(",'CustomSchema': '{0}'", loader));

var jsonPath = DeleteOutputPath("graph.json");
File.WriteAllLines(jsonPath, new[] { inputGraph });
Expand Down Expand Up @@ -855,15 +857,16 @@ public void EntryPointEvaluateMultiClass()
Assert.Equal(3, CountRows(loader));
}

[Fact(Skip = "Missing data set. See https://github.com/dotnet/machinelearning/issues/3")]
[Fact]
public void EntryPointEvaluateRegression()
{
var dataPath = GetDataPath("housing.txt");
var dataPath = GetDataPath(@"external/winequality-white.csv");
Copy link
Contributor

@glebuk glebuk May 22, 2018 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@"external/winequality-white.csv [](start = 39, length = 32)

Extract dataset info into static dataset classes so that no need to repeat paths and schemas. Ideally you can even just return a new loader for each dataset. #Closed

var warningsPath = DeleteOutputPath("warnings.idv");
var overallMetricsPath = DeleteOutputPath("overall.idv");
var instanceMetricsPath = DeleteOutputPath("instance.idv");

RunTrainScoreEvaluate("Trainers.StochasticDualCoordinateAscentRegressor", "Models.RegressionEvaluator", dataPath, warningsPath, overallMetricsPath, instanceMetricsPath);
RunTrainScoreEvaluate("Trainers.StochasticDualCoordinateAscentRegressor", "Models.RegressionEvaluator",
dataPath, warningsPath, overallMetricsPath, instanceMetricsPath, loader: "col=Label:R4:11 col=Features:R4:0-10 sep=; header+");

using (var loader = new BinaryLoader(Env, new BinaryLoader.Arguments(), warningsPath))
Assert.Equal(0, CountRows(loader));
Expand All @@ -872,7 +875,7 @@ public void EntryPointEvaluateRegression()
Assert.Equal(1, CountRows(loader));

using (var loader = new BinaryLoader(Env, new BinaryLoader.Arguments(), instanceMetricsPath))
Assert.Equal(104, CountRows(loader));
Assert.Equal(975, CountRows(loader));
}

[Fact]
Expand All @@ -887,10 +890,10 @@ public void EntryPointSDCAMultiClass()
TestEntryPointRoutine("iris.txt", "Trainers.StochasticDualCoordinateAscentClassifier");
}

[Fact(Skip = "Missing data set. See https://github.com/dotnet/machinelearning/issues/3")]
[Fact()]
public void EntryPointSDCARegression()
{
TestEntryPointRoutine("housing.txt", "Trainers.StochasticDualCoordinateAscentRegressor");
TestEntryPointRoutine(@"external/winequality-white.csv", "Trainers.StochasticDualCoordinateAscentRegressor", loader: "col=Label:R4:11 col=Features:R4:0-10 sep=; header+");
}

[Fact]
Expand Down Expand Up @@ -961,10 +964,10 @@ public void EntryPointHogwildSGD()
TestEntryPointRoutine("breast-cancer.txt", "Trainers.StochasticGradientDescentBinaryClassifier");
}

[Fact(Skip = "Missing data set. See https://github.com/dotnet/machinelearning/issues/3")]
[Fact()]
public void EntryPointPoissonRegression()
{
TestEntryPointRoutine("housing.txt", "Trainers.PoissonRegressor");
TestEntryPointRoutine(@"external/winequality-white.csv", "Trainers.PoissonRegressor", loader: "col=Label:R4:11 col=Features:R4:0-10 sep=; header+");
}

[Fact]
Expand Down
2 changes: 1 addition & 1 deletion test/Microsoft.ML.Tests/Microsoft.ML.Tests.csproj
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,6 @@

<ItemGroup>
<NativeAssemblyReference Include="CpuMathNative" />
<NativeAssemblyReference Include="FastTreeNative" />
<NativeAssemblyReference Include="FastTreeNative" />
</ItemGroup>
</Project>