Skip to content

Add hasHeader flag in ColumnInference function #4922

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.

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
Show file tree
Hide file tree
Changes from all commits
Commits
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
6 changes: 3 additions & 3 deletions src/Microsoft.ML.AutoML/ColumnInference/ColumnInferenceApi.cs
Original file line number Diff line number Diff line change
Expand Up @@ -36,12 +36,12 @@ public static ColumnInferenceResults InferColumns(MLContext context, string path
}

public static ColumnInferenceResults InferColumns(MLContext context, string path, ColumnInformation columnInfo,
char? separatorChar, bool? allowQuotedStrings, bool? supportSparse, bool trimWhitespace, bool groupColumns)
char? separatorChar, bool? allowQuotedStrings, bool? supportSparse, bool trimWhitespace, bool groupColumns, bool hasHeader = true)
{
var sample = TextFileSample.CreateFromFullFile(path);
var splitInference = InferSplit(context, sample, separatorChar, allowQuotedStrings, supportSparse);
var typeInference = InferColumnTypes(context, sample, splitInference, true, null, columnInfo.LabelColumnName);
return InferColumns(context, path, columnInfo, true, splitInference, typeInference, trimWhitespace, groupColumns);
var typeInference = InferColumnTypes(context, sample, splitInference, hasHeader, null, columnInfo.LabelColumnName);
return InferColumns(context, path, columnInfo, hasHeader, splitInference, typeInference, trimWhitespace, groupColumns);
}

public static ColumnInferenceResults InferColumns(MLContext context, string path, ColumnInformation columnInfo, bool hasHeader,
Expand Down
30 changes: 30 additions & 0 deletions test/Microsoft.ML.AutoML.Tests/ColumnInferenceTests.cs
Original file line number Diff line number Diff line change
@@ -1,4 +1,5 @@
using System;
using System.Collections.Generic;
using System.IO;
using System.Linq;
using Microsoft.ML.Data;
Expand Down Expand Up @@ -91,6 +92,35 @@ public void DatasetWithBoolColumn()
Assert.Equal(DefaultColumnNames.Label, result.ColumnInformation.LabelColumnName);
}

[Fact]
public void InferDatasetWithoutHeader()
{
var context = new MLContext(1);
var filePath = Path.Combine("TestData", "DatasetWithoutHeader.txt");
var columnInfo = new ColumnInformation()
{
LabelColumnName = "col0",
UserIdColumnName = "col1",
ItemIdColumnName = "col2",
};
columnInfo.IgnoredColumnNames.Add("col4");
var result = ColumnInferenceApi.InferColumns(context, filePath, columnInfo, ',', null, null, false, false, false);
Assert.Equal(6, result.TextLoaderOptions.Columns.Count());

var labelColumn = result.TextLoaderOptions.Columns.First(c => c.Name == "col0");
var userColumn = result.TextLoaderOptions.Columns.First(c => c.Name == "col1");
var itemColumn = result.TextLoaderOptions.Columns.First(c => c.Name == "col2");
var ignoreColumn = result.TextLoaderOptions.Columns.First(c => c.Name == "col4");

Assert.Equal(DataKind.String, labelColumn.DataKind);
Assert.Equal(DataKind.Single, userColumn.DataKind);
Assert.Equal(DataKind.Single, itemColumn.DataKind);
Assert.Equal(DataKind.Single, ignoreColumn.DataKind);

Assert.Single(result.ColumnInformation.CategoricalColumnNames);
Assert.Empty(result.ColumnInformation.TextColumnNames);
}

[Fact]
public void WhereNameColumnIsOnlyFeature()
{
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -14,6 +14,9 @@
<None Update="TestData\DatasetWithDefaultColumnNames.txt">
<CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
</None>
<None Update="TestData\DatasetWithoutHeader.txt">
<CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
</None>
<None Update="TestData\NameColumnIsOnlyFeatureDataset.txt">
<CopyToOutputDirectory>PreserveNewest</CopyToOutputDirectory>
</None>
Expand Down
20 changes: 20 additions & 0 deletions test/Microsoft.ML.AutoML.Tests/TestData/DatasetWithoutHeader.txt
Original file line number Diff line number Diff line change
@@ -0,0 +1,20 @@
CMT,1271,3.8,CRD,17.5,T
CMT,474,1.5,CRD,8,T
CMT,637,1.4,CRD,8.5,T
CMT,181,0.6,CSH,4.5,T
CMT,661,1.1,CRD,8.5,T
CMT,935,9.6,CSH,27.5,T
CMT,869,2.3,CRD,11.5,T
CMT,454,1.4,CRD,7.5,T
CMT,366,1.5,CSH,7.5,T
VTS,1140,5.61,CSH,18.5,F
VTS,120,0.67,CSH,4,F
VTS,240,1.7,CRD,6.5,F
VTS,660,2.52,CRD,10.5,F
VTS,420,0.82,CSH,6,F
VTS,420,1.04,CRD,6.5,F
VTS,2280,18,CRD,52,F
VTS,360,1.2,CRD,6.5,F
VTS,660,2.22,CSH,10,F
VTS,840,3.29,CSH,12.5,F
VTS,540,1.85,CRD,8.5,F