7.00.02 - UnsupervisedShapelet Arguments - Aster Analytics

Teradata Aster® Analytics Foundation User GuideUpdate 2

Product
Aster Analytics
Release Number
7.00.02
Release Date
September 2017
Content Type
Programming Reference
User Guide
Publication ID
B700-1022-700K
Language
English (United States)
InputTable
Specifies the name of the table that contains the input data.
OutputTable
[Optional] Specifies the name for the output table that the function creates. Default: 'output_table'.
OverwriteOutput
[Optional] Specifies whether to overwrite output_table, if it exists. Default: 'false'.
TimeColumn
Specifies the name of the input table column that contains the time series.
ValueColumn
Specifies the name of the input table column that contains the data point values.
SaxWindowSize
Specifies the SAX2 argument WindowSize, which specifies the size of the sliding window. The window_size must be an INTEGER in the range [1, 1000000].
SaxSymbolsPerWindow
[Optional] Specifies the SAX2 argument SymbolsPerWindow, which specifies the number of SAX code symbols to generate from a window. The symbols_per_window must an INTEGER in the range [1, 1000000]. If symbols_per_window is greater than window_size, the function changes symbols_per_window to window_size. Default: symbols_per_window is the same as window_size.
SaxOutputFrequency
[Optional] Specifies the SAX2 argument OutputFrequency, which specifies the number of data points to skip between successive sliding windows. The gap_between_windows must be an integer in the range [1, 1000]. Default: 1. A smaller value increases accuracy (the chance of distinguishing time series from each other) at the cost of higher execution time.
ID
Specifies the name of the input table column that contains the unique identity of a time series.
RandomProjections
[Optional] Specifies the number of iterations required for random masking of SAX words during u_shapelets selection. The projections must be an INTEGER in the range [1, 30]. Default: 10.

Specifying a greater projections for a longer input time series increases the probability of identifying better u_shapelets at the cost of higher execution time.

Threshold
[Optional] Specifies the value at which an iteration stops and the function stops. The iteration i ends when score iscore i-1 is less than threshold. The threshold must be a DOUBLE PRECISION value in the range (0, 1). Default: 0.5.
MaxNumIter
[Optional] Specifies the number of iterations at which the function stops. The max_iterations must be an INTEGER in the range [1, 50]. Default: 10.
ShapeletCutOff
[Optional] Specifies the percentage of u-shapelets to use. The cut_off must be a DOUBLE PRECISION value in the range (0, 1]. Default: 0.1 (10%).