public void LambdaTransformCreate()
{
var env = new MLContext(seed: 42);
var data = ReadBreastCancerExamples();
var idv = env.CreateDataView(data);
var filter = LambdaTransform.CreateFilter <BreastCancerExample, object>(env, idv,
(input, state) => input.Label == 0, null);
Assert.Null(filter.GetRowCount());
// test re-apply
var applied = env.CreateDataView(data);
applied = ApplyTransformUtils.ApplyAllTransformsToData(env, filter, applied);
var saver = new TextSaver(env, new TextSaver.Arguments());
Assert.True(applied.Schema.TryGetColumnIndex("Label", out int label));
using (var fs = File.Create(GetOutputPath(OutputRelativePath, "lambda-output.tsv")))
saver.SaveData(fs, applied, label);
}
/// <summary>
/// Save schema associations of role/column-name in <paramref name="rep"/>.
/// </summary>
internal static void SaveRoleMappings(IHostEnvironment env, IChannel ch, RoleMappedSchema schema, RepositoryWriter rep)
{
// REVIEW: Should we also save this stuff, for instance, in some portion of the
// score command or transform?
Contracts.AssertValue(env);
env.AssertValue(ch);
ch.AssertValue(schema);
ArrayDataViewBuilder builder = new ArrayDataViewBuilder(env);
List <string> rolesList = new List <string>();
List <string> columnNamesList = new List <string>();
// OrderBy is stable, so there is no danger in it "reordering" columns
// when a role is filled by multiple columns.
foreach (var role in schema.GetColumnRoleNames().OrderBy(r => r.Key.Value))
{
rolesList.Add(role.Key.Value);
columnNamesList.Add(role.Value);
}
builder.AddColumn("Role", rolesList.ToArray());
builder.AddColumn("Column", columnNamesList.ToArray());
using (var entry = rep.CreateEntry(DirTrainingInfo, RoleMappingFile))
{
// REVIEW: It seems very important that we have the role mappings
// be easily human interpretable and even manipulable, but relying on the
// text saver/loader means that special characters like '\n' won't be reinterpretable.
// On the other hand, no one is such a big lunatic that they will actually
// ever go ahead and do something so stupid as that.
var saver = new TextSaver(env, new TextSaver.Arguments()
{
Dense = true, Silent = true
});
var view = builder.GetDataView();
saver.SaveData(entry.Stream, view, Utils.GetIdentityPermutation(view.Schema.ColumnCount));
}
}
/// <summary>
/// Saves the dataframe in a stream as text format.
/// </summary>
/// <param name="filename">filename</param>
/// <param name="sep">column separator</param>
/// <param name="header">add header</param>
/// <param name="silent">Suppress any info output (not warnings or errors)</param>
public static void ViewToCsv(IDataView view, Stream st, string sep = ",", bool header = true,
bool silent = false, IHost host = null)
{
IHostEnvironment env = host;
if (env == null)
{
env = new ConsoleEnvironment();
}
var saver = new TextSaver(env, new TextSaver.Arguments()
{
Separator = sep,
OutputSchema = false,
OutputHeader = header,
Silent = silent
});
var columns = new int[view.Schema.Count];
for (int i = 0; i < columns.Length; ++i)
{
columns[i] = i;
}
saver.SaveData(st, view, columns);
}
