TD_DecisionForestPredict uses the following input tables.
| Table | Description |
|---|---|
| InputTable | Contains test data, for which to predict outcomes. The input table can have no partition or PARTITION BY ANY clause. |
| ModelTable | Has the same schema as the output table of TD_DecisionForest function. Model table must be a DIMENSION table, and must be from TD_DecisionForest function. |
InputTable Schema
| Column | Data Type | Description |
|---|---|---|
| ID_Column | Varies | Unique test point identifier. Cannot be NULL. |
| target_columns | INTEGER, BIGINT, SMALLINT, BYTEINT, FLOAT, DECIMAL, NUMBER | Predictor variable. Column appears once for each specified target_column. Cannot be NULL. |
| accumulate_columns | Varies | Column to copy to output table. Column appears once for each specified accumulate_column. |
ModelTable Schema
| Name | Data Type | Description |
|---|---|---|
| task_index | SMALLINT | Identifier of AMP that produced decision tree. |
| tree_num | Integer | Decision tree identifier. |
| tree_order | Integer | Sequence of substring of tree. |
| classification_tree | VARCHAR(16000) | JSON representation of decision tree. For JSON types that can appear in the representation. |
| Name | Data Type | Description |
|---|---|---|
| task_index | SMALLINT | Identifier of AMP that produced decision tree. |
| tree_num | Integer | Decision tree identifier. |
| tree_order | Integer | Sequence of substring of tree. |
| regression_tree | VARCHAR(16000) | JSON representation of decision tree. For JSON types that can appear in the representation. |
| JSON Type | Description |
|---|---|
| id_ | Node identifier. |
| sum_ | Sum of values of response variable at node identified by id. Only appears for regression trees. |
| sumSq_ | Sum of squared values of response variable at node identified by id. Only appears for regression trees. |
| responseCounts_ | Number of observations in each class at node identified by id. Only appears for regression trees. |
| size_ | Total number of observations at node identified by id. |
| maxDepth_ | Maximum possible depth of tree, starting from node identified by id. For root node, the value is max_depth. For leaf nodes, the value is 0. For other nodes, maximum possible depth of tree, starting from that node. |
| split_ | Start of JSON item describing a split at node identified by id. |
| score_ | Gini score of node identified by id. |
| attr_ | Attribute (predictor) that the algorithm split at node identified by id. |
| type_ | Type of tree and split. Options are:
|
| leftNodeSize_ | Number of observations assigned to left node of split. |
| rightNodeSize_ | Number of observations assigned to right node of split. |
| leftChild_ | Start of JSON item describing left child of node identified by id. |
| rightChild_ | Start of JSON item describing right child of node identified by id. |
| nodeType_ | Type of node identified by id. Options are:
|