TD_OneClassSVMPredict accepts two inputs for Linear kernel:
- InputTable containing test input data set.
- ModelTable containing an SVM model trained by TD_OneClassSVM.
TD_OneClassSVMPredict accepts three inputs for RBF kernel:
- InputTable containing test input data set.
- ModelTable containing an SVM model trained by TD_OneClassSVM.
- FitTable containing weights and bias which is used to transform the training dataset.
TD_OneClassSVMPredict accepts two inputs:
- InputTable containing test input data set.
- ModelTable containing an SVM model trained by TD_OneClassSVM.
Input Table Schema
| Column Name | Data Type | Description |
|---|---|---|
| id_column | ANY | Unique row identifier of input observations. |
| target_column | INTEGER, BIGINT, SMALLINT, BYTEINT, DOUBLE PRECISION | Column used as predictors (features) for model training. |
| accumulate_column | ANY | Columns to copy to output table. |
Model Table Schema
| Column Name | Data Type | Description |
|---|---|---|
| attribute | SMALLINT | Contains a numeric index of predictor and model metrics. Intercept is specified using index 0 and rest of the predictors take positive values. Model metrics take negative indices. |
| predictor | VARCHAR | Contains the name of the predictor or Model metric. |
| estimate | FLOAT | Contains the predictor weights and metric numeric values. |
| value | VARCHAR | Contains the string values of the metric. |
RBFFitTable Schema
| Column | Data Type | Description |
|---|---|---|
| Feature 1 | FLOAT | Containsweights for the feature. |
| ... | ... | ... |
| FeatureN | FLOAT | Containsweights for the feature. |
| Bias | FLOAT | Contains bias. |