Skip to content

Adding binary saving and loading to MLContext.Data #1678

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
merged 3 commits into from
Nov 21, 2018
Merged
Changes from 1 commit
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
Original file line number Diff line number Diff line change
@@ -0,0 +1,52 @@
// Licensed to the .NET Foundation under one or more agreements.
// The .NET Foundation licenses this file to you under the MIT license.
// See the LICENSE file in the project root for more information.

using System.IO;
using Microsoft.ML.Runtime;
using Microsoft.ML.Runtime.Data;
using Microsoft.ML.Runtime.Data.IO;

namespace Microsoft.ML
{
public static class BinaryLoaderSaverCatalog
{
/// <summary>
/// Read a data view from a binary file using <see cref="BinaryLoader"/>.
/// </summary>
/// <param name="catalog">The catalog.</param>
/// <param name="args">The arguments to binary reader.</param>
/// <param name="path"></param>
public static IDataView ReadFromBinaryFile(this DataOperations catalog,
BinaryLoader.Arguments args, string path)
{
Contracts.CheckNonEmpty(path, nameof(path));

var env = catalog.GetEnvironment();

var reader = new BinaryLoader(env, args, path);
return reader;
}

/// <summary>
/// Save the data view as binary.
/// </summary>
/// <param name="catalog">The catalog.</param>
/// <param name="data">The data view to save.</param>
/// <param name="stream">The stream to write to.</param>
/// <param name="keepHidden">Whether to keep hidden columns in the dataset.</param>
public static void SaveAsBinary(this DataOperations catalog, IDataView data, Stream stream,
bool keepHidden = false)
{
Contracts.CheckValue(catalog, nameof(catalog));
Contracts.CheckValue(data, nameof(data));
Contracts.CheckValue(stream, nameof(stream));

var env = catalog.GetEnvironment();
var saver = new BinarySaver(env, new BinarySaver.Arguments());

using (var ch = env.Start("Saving data"))
DataSaverUtils.SaveDataView(ch, saver, data, stream, keepHidden);
}
}
}