/// <summary>
/// Read a data view from a text file using <see cref="TextLoader"/>.
/// </summary>
/// <param name="catalog">The <see cref="DataOperations"/> catalog.</param>
/// <param name="path">Specifies a file from which to read.</param>
/// <param name="args">Defines the settings of the load operation.</param>
public static IDataView ReadFromTextFile(this DataOperations catalog, string path, TextLoader.Arguments args = null)
{
Contracts.CheckNonEmpty(path, nameof(path));
var env = catalog.GetEnvironment();
var source = new MultiFileSource(path);
return(new TextLoader(env, args, source).Read(source));
}
/// <summary>
/// Read a data view from a binary file using <see cref="BinaryLoader"/>.
/// </summary>
/// <param name="catalog">The catalog.</param>
/// <param name="path">The path to the file to read from.</param>
public static IDataView ReadFromBinary(this DataOperations catalog, string path)
{
Contracts.CheckNonEmpty(path, nameof(path));
var env = catalog.GetEnvironment();
var reader = new BinaryLoader(env, new BinaryLoader.Arguments(), path);
return(reader);
}
/// <summary>
/// Read a data view from a Stream on a binary file using <see cref="BinaryLoader"/>.
/// </summary>
/// <param name="catalog">The catalog.</param>
/// <param name="stream">The stream to read from.</param>
public static IDataView ReadFromBinary(this DataOperations catalog, Stream stream)
{
Contracts.CheckValue(stream, nameof(stream));
var env = catalog.GetEnvironment();
var reader = new BinaryLoader(env, new BinaryLoader.Arguments(), stream);
return(reader);
}
/// <summary>
/// Read a data view from an <see cref="IMultiStreamSource"/> on a binary file using <see cref="BinaryLoader"/>.
/// </summary>
/// <param name="catalog">The catalog.</param>
/// <param name="fileSource">The file source to read from. This can be a <see cref="MultiFileSource"/>, for example.</param>
public static IDataView ReadFromBinary(this DataOperations catalog, IMultiStreamSource fileSource)
{
Contracts.CheckValue(fileSource, nameof(fileSource));
var env = catalog.GetEnvironment();
var reader = new BinaryLoader(env, new BinaryLoader.Arguments(), fileSource);
return(reader);
}
/// <summary>
/// Read a data view from a text file using <see cref="TextLoader"/>.
/// </summary>
/// <param name="catalog">The catalog.</param>
/// <param name="columns">The columns of the schema.</param>
/// <param name="advancedSettings">The delegate to set additional settings</param>
/// <param name="path">The path to the file</param>
/// <returns>The data view.</returns>
public static IDataView ReadFromTextFile(this DataOperations catalog,
TextLoader.Column[] columns, string path, Action <TextLoader.Arguments> advancedSettings = null)
{
Contracts.CheckNonEmpty(path, nameof(path));
var env = catalog.GetEnvironment();
// REVIEW: it is almost always a mistake to have a 'trainable' text loader here.
// Therefore, we are going to disallow data sample.
var reader = new TextLoader(env, columns, advancedSettings, dataSample: null);
return(reader.Read(new MultiFileSource(path)));
}
/// <summary>
/// Save the data view into a binary stream.
/// </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);
}
/// <summary>
/// Read a data view from a text file using <see cref="TextLoader"/>.
/// </summary>
/// <param name="catalog">The catalog.</param>
/// <param name="columns">The columns of the schema.</param>
/// <param name="hasHeader">Whether the file has a header.</param>
/// <param name="separatorChar">The character used as separator between data points in a row. By default the tab character is used as separator.</param>
/// <param name="path">The path to the file.</param>
/// <returns>The data view.</returns>
public static IDataView ReadFromTextFile(this DataOperations catalog,
string path, Column[] columns, bool hasHeader = false, char separatorChar = '\t')
{
Contracts.CheckNonEmpty(path, nameof(path));
var env = catalog.GetEnvironment();
// REVIEW: it is almost always a mistake to have a 'trainable' text loader here.
// Therefore, we are going to disallow data sample.
var reader = new TextLoader(env, columns, hasHeader, separatorChar, dataSample: null);
return(reader.Read(new MultiFileSource(path)));
}
/// <summary>
/// Save the data view as text.
/// </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="separator">The column separator.</param>
/// <param name="headerRow">Whether to write the header row.</param>
/// <param name="schema">Whether to write the header comment with the schema.</param>
/// <param name="keepHidden">Whether to keep hidden columns in the dataset.</param>
public static void SaveAsText(this DataOperations catalog, IDataView data, Stream stream,
char separator = '\t', bool headerRow = true, bool schema = true, 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 TextSaver(env, new TextSaver.Arguments {
Separator = separator.ToString(), OutputHeader = headerRow, OutputSchema = schema
});
using (var ch = env.Start("Saving data"))
DataSaverUtils.SaveDataView(ch, saver, data, stream, keepHidden);
}