Developer Guide for Intel® Data Analytics Acceleration Library 2016 Update 4
You can use the Naïve Bayes classifier algorithm in the online processing mode only at the training stage.
This computation mode assumes that the data arrives in blocks i = 1, 2, 3, …, nblocks.
Naïve Bayes classifier training in the online processing mode follows the general workflow described in Usage Model: Training and Prediction.
Naïve Bayes classifier in the online processing mode accepts the input described below. Pass the Input ID as a parameter to the methods that provide input for your algorithm. For more details, see Algorithms.
|
Input ID |
Input |
|
|---|---|---|
|
data |
Pointer to the ni x p numeric table that represents the current data block. This table can be an object of any class derived from NumericTable. |
|
|
labels |
Pointer to the ni x 1 numeric table with class labels associated with the current data block. This table can be an object of any class derived from NumericTable. |
|
Naïve Bayes classifier in the online processing mode has the following parameters:
|
Parameter |
Default Value |
Description |
|
|---|---|---|---|
|
algorithmFPType |
double |
The floating-point type that the algorithm uses for intermediate computations. Can be float or double. |
|
|
method |
defaultDense |
Available computation methods for the Naïve Bayes classifier:
|
|
|
nClasses |
Not applicable |
The number of classes, a required parameter. |
|
|
priorClassEstimates |
1/nClasses |
Vector of size nClasses that contains prior class estimates. The default value applies to each vector element. |
|
|
alpha |
1 |
Vector of size p that contains the imagined occurrences of features. The default value applies to each vector element. |
|
For a description of the output, refer to Usage Model: Training and Prediction.