- ON clause
- Specifies the table name, view name or query as a ParameterTable and AttributeTable.
- OutputTable
- Specifies the name of the output table. If this argument is provided, the output is stored in the specified OutputTable name.
- TargetAttributes
- Specifies the target attributes names from AttributeNameColumn which need to be considered for Scaling.
- Default: All the attributes from AttributeNameColumn will be considered for Scaling.
Argument for sparse input, disallowed otherwise.
- PartitionColumns
- Specifies the name of the InputTable columns on which to partition the input.
- Column range is not supported for the PartitionColumns argument.
- If the partition column names specified in the PARTITION BY clause contains UNICODE characters, you must specify the PartitionColumns argument.
- Columns specified in the PartitionColumns argument must match exactly with the columns specified in the PARTITION BY clause(s) of ON clause(s) for InputTable, ParameterTable, and AttributeTable.
- MissValue
- Specifies how to process NULL values in input.
Default: KEEP
| Option |
Description |
|---|
| KEEP |
Keep NULL values. |
| ZERO |
Replace each NULL value with 0. |
| LOCATION |
Replace each NULL value with its location value. |
- GlobalScale
- Specifies whether all input columns are scaled to the same location and scale. If set to false, each input column is scaled separately.
- Default: false
- Multiplier
- Specifies one or more multiplying factors to apply to the input variables—multiplier in the following formula:
- X' = intercept + multiplier * ((X - location)/scale)
- If you specify only one argument value, it applies to all columns specified by the TargetColumns argument. If you specify multiple argument values, each argument value applies to the corresponding input column. For example, the first argument value applies to the first column specified by the TargetColumns argument, the second argument value applies to the second input column, and so on..
- Default: multiplier is 1
- Intercept
- Specifies one or more addition factors incrementing the scaled results intercept in the following formula:
- X' = intercept + multiplier * ((X - location)/scale)
- The syntax of intercept is: [-] {number | min | mean | max }
- Where min, mean, and max are the scaled global minimum, maximum, mean values of the corresponding columns.
- The formula for computing the scaled global minimum is:
- scaledmin = (minX - location)/scale
- The formulas for computing the scaled global mean and maximum are analogous to the preceding formula.
- For example, if intercept is '- min' and multiplier is 1, the formula for computing the scaled result X' from the original value X is:
- X' = -scaledmin + 1 * ((X – location)/scale)
- If you specify only one argument value, it applies to all columns specified by the TargetColumns argument. If you specify multiple argument values, each argument value applies to the corresponding input column. For example, the first argument value applies to the first column specified by the TargetColumns argument, the second argument value applies to the second input column, and so on.
- Default: intercept is 0
- IgnoreInvalidLocationScale
- Specifies whether to ignore invalid values of location and scale parameters.
- If it is set to false, the function will report an error for invalid values of location and scale parameters.
- If it is set to true, the function will ignore invalid values for location and scale parameters and replace them with with 0 and 1 respectively.
- Default: false
- UnusedAttributes
Specifies whether to emit out unused attributes of different partitions as unscaled values or NULLs. This argument is allowed only when AttributeTable is specified.
Default: UNSCALED
| Option |
Description |
|---|
| UNSCALED |
Emit out unscaled values for unused attributes. |
| NULLIFY |
Emit out NULL values for unused attributes. |
UnusedAttributes argument is applicable only for dense input.