/// <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.Count));
}
}
/// <summary>
/// Given a repository, returns the save context for saving the data loader model.
/// </summary>
public static ModelSaveContext GetDataModelSavingContext(RepositoryWriter rep)
{
Contracts.CheckValue(rep, nameof(rep));
return(new ModelSaveContext(rep, DirDataLoaderModel, ModelLoadContext.ModelStreamName));
}
