Automatic Data Preparation

8.5 Automatic Data Preparation

Oracle Machine Learning for Python supports Automatic Data Preparation (ADP) and user-directed general data preparation.

The PREP_* settings enable you to request fully automated (ADP) or manual data preparation. By default, ADP is enabled (PREP_AUTO_ON) . When performed manually, data preparation requirements of each algorithm must be addressed

When you enable ADP, the model uses heuristics to transform the build data according to the requirements of the algorithm. Instead of ADP, you can request that the data be shifted and/or scaled with the PREP_SCALE_* and PREP_SHIFT_* settings. The transformation instructions are stored with the model and reused whenever the model is applied. The model settings can be viewed in USER_MINING_MODEL_SETTINGS.

PREP_* Settings

The values for the PREP_* settings are described in the following table.

Table 8-2 title

Setting Name	Setting Value	Description
`PREP_AUTO`	`PREP_AUTO_ON` `PREP_AUTO_OFF`	This setting enables fully automated data preparation. The default is `PREP_AUTO_ON`.
`PREP_SCALE_2DNUM`	`PREP_SCALE_STDDEV` `PREP_SCALE_RANGE`	This setting enables scaling data preparation for two-dimensional numeric columns. `PREP_AUTO` must be `OFF` for this setting to take effect. The following are the possible values. `PREP_SCALE_STDDEV`: A request to divide the column values by the standard deviation of the column and is often provided together with `PREP_SHIFT_MEAN` to yield z-score normalization. `PREP_SCALE_RANGE`: A request to divide the column values by the range of values and is often provided together with `PREP_SHIFT_MIN` to yield a range of [0,1].
`PREP_SCALE_NNUM`	`PREP_SCALE_MAXABS`	This setting enables scaling data preparation for nested numeric columns. `PREP_AUTO` must be `OFF` for this setting to take effect. If specified, then the valid value for this setting is `PREP_SCALE_MAXABS`, which yields data in the range of [-1,1].
`PREP_SHIFT_2DNUM`	`PREP_SHIFT_MEAN` `PREP_SHIFT_MIN`	This setting enables centering data preparation for two-dimensional numeric columns. `PREP_AUTO` must be `OFF` for this setting to take effect. The following are the possible values: `PREP_SHIFT_MEAN`: Results in subtracting the average of the column from each value. `PREP_SHIFT_MIN`: Results in subtracting the minimum of the column from each value.