// Normal constructor.
internal TimeSeriesImputerTransformer(IHostEnvironment host, TimeSeriesImputerEstimator.Options options, IDataView input)
{
_host = host.Register(nameof(TimeSeriesImputerTransformer));
_timeSeriesColumn = options.TimeSeriesColumn;
_grainColumns = options.GrainColumns;
_imputeMode = options.ImputeMode;
_suppressTypeErrors = options.SupressTypeErrors;
IEnumerable <string> tempDataColumns;
if (options.FilterMode == TimeSeriesImputerEstimator.FilterMode.Exclude)
{
tempDataColumns = input.Schema.Where(x => !options.FilterColumns.Contains(x.Name)).Select(x => x.Name);
}
else if (options.FilterMode == TimeSeriesImputerEstimator.FilterMode.Include)
{
tempDataColumns = input.Schema.Where(x => options.FilterColumns.Contains(x.Name)).Select(x => x.Name);
}
else
{
tempDataColumns = input.Schema.Select(x => x.Name);
}
// Time series and Grain columns should never be included in the data columns
_dataColumns = tempDataColumns.Where(x => x != _timeSeriesColumn && !_grainColumns.Contains(x)).ToArray();
// 1 is for the time series column. Make one array in the correct order of all the columns.
// Order is Timeseries column, All grain columns, All data columns.
_allColumnNames = new string[1 + _grainColumns.Length + _dataColumns.Length];
_allColumnNames[0] = _timeSeriesColumn;
Array.Copy(_grainColumns, 0, _allColumnNames, 1, _grainColumns.Length);
Array.Copy(_dataColumns, 0, _allColumnNames, 1 + _grainColumns.Length, _dataColumns.Length);
TransformerHandle = CreateTransformerFromEstimator(input);
}
// Factory method for SignatureLoadModel.
internal TimeSeriesImputerTransformer(IHostEnvironment host, ModelLoadContext ctx)
{
_host = host.Register(nameof(TimeSeriesImputerTransformer));
_host.Check(!CommonExtensions.OsIsCentOS7(), "CentOS7 is not supported");
// *** Binary format ***
// name of time series column
// length of grain column array
// all column names in grain column array
// length of filter column array
// all column names in filter column array
// byte value of filter mode
// byte value of impute mode
// length of C++ state array
// C++ byte state array
_timeSeriesColumn = ctx.Reader.ReadString();
_grainColumns = new string[ctx.Reader.ReadInt32()];
for (int i = 0; i < _grainColumns.Length; i++)
{
_grainColumns[i] = ctx.Reader.ReadString();
}
_dataColumns = new string[ctx.Reader.ReadInt32()];
for (int i = 0; i < _dataColumns.Length; i++)
{
_dataColumns[i] = ctx.Reader.ReadString();
}
_imputeMode = (TimeSeriesImputerEstimator.ImputationStrategy)ctx.Reader.ReadByte();
_allColumnNames = new string[1 + _grainColumns.Length + _dataColumns.Length];
_allColumnNames[0] = _timeSeriesColumn;
Array.Copy(_grainColumns, 0, _allColumnNames, 1, _grainColumns.Length);
Array.Copy(_dataColumns, 0, _allColumnNames, 1 + _grainColumns.Length, _dataColumns.Length);
var nativeState = ctx.Reader.ReadByteArray();
TransformerHandle = CreateTransformerFromSavedData(nativeState);
}
/// <summary>
/// Create a <see cref="TimeSeriesImputerEstimator"/>, Imputes missing rows and column data per grain. Applies the imputation strategy on
/// a filtered list of columns in the IDataView. Columns that are excluded will have the default value for that data type used when a row
/// is imputed. Currently only float/double/string columns are supported for imputation strategies, and an empty string is considered "missing" for the
/// purpose of this estimator.
/// </summary>
/// <param name="catalog">The transform catalog.</param>
/// <param name="timeSeriesColumn">Column representing the time series. Should be of type <see cref="long"/> or <see cref="System.DateTime"/></param>
/// <param name="grainColumns">List of columns to use as grains</param>
/// <param name="filterColumns">List of columns to filter. If <paramref name="filterMode"/> is <see cref="TimeSeriesImputerEstimator.FilterMode.Exclude"/> than columns in the list will be ignored.
/// If <paramref name="filterMode"/> is <see cref="TimeSeriesImputerEstimator.FilterMode.Include"/> than values in the list are the only columns imputed.</param>
/// <param name="filterMode">Whether the list <paramref name="filterColumns"/> should include or exclude those columns.</param>
/// <param name="imputeMode">Mode of imputation for missing values in column. If not passed defaults to forward fill</param>
/// <param name="suppressTypeErrors">Suppress the errors that would occur if a column and impute mode are incompatible. If true, will skip the column and use the default value. If false, will stop and throw an error.</param>
public static TimeSeriesImputerEstimator ReplaceMissingTimeSeriesValues(this TransformsCatalog catalog, string timeSeriesColumn,
string[] grainColumns, string[] filterColumns, TimeSeriesImputerEstimator.FilterMode filterMode = TimeSeriesImputerEstimator.FilterMode.Exclude,
TimeSeriesImputerEstimator.ImputationStrategy imputeMode = TimeSeriesImputerEstimator.ImputationStrategy.ForwardFill,
bool suppressTypeErrors = false)
=> new TimeSeriesImputerEstimator(CatalogUtils.GetEnvironment(catalog), timeSeriesColumn, grainColumns, filterColumns, filterMode, imputeMode, suppressTypeErrors);
/// <summary>
/// Create a <see cref="TimeSeriesImputerEstimator"/>, Imputes missing rows and column data per grain. Operates on all columns in the IDataView.
/// Currently only float/double/string columns are supported for imputation strategies, and an empty string is considered "missing" for the
/// purpose of this estimator. Other column types will have the default value placed if a row is imputed.
/// </summary>
/// <param name="catalog">The transform catalog.</param>
/// <param name="timeSeriesColumn">Column representing the time series. Should be of type <see cref="long"/> or <see cref="System.DateTime"/></param>
/// <param name="grainColumns">List of columns to use as grains</param>
/// <param name="imputeMode">Mode of imputation for missing values in column. If not passed defaults to forward fill</param>
public static TimeSeriesImputerEstimator ReplaceMissingTimeSeriesValues(this TransformsCatalog catalog, string timeSeriesColumn, string[] grainColumns,
TimeSeriesImputerEstimator.ImputationStrategy imputeMode = TimeSeriesImputerEstimator.ImputationStrategy.ForwardFill)
=> new TimeSeriesImputerEstimator(CatalogUtils.GetEnvironment(catalog), timeSeriesColumn, grainColumns, null, TimeSeriesImputerEstimator.FilterMode.NoFilter, imputeMode, true);
