yobx.xoptim.patterns_ml.tree_ensemble#

class yobx.xoptim.patterns_ml.tree_ensemble.TreeEnsembleRegressorConcatPattern(verbose: int = 0, priority: int = 1, min_opset: int = 1)[source]#

Replaces multiple TreeEnsembleRegressor + Concat(., axis=1) with one TreeEnsembleRegressor. All trees must have only one target (it can be extended to multiple) and is assigned a distinct dimension. The aggregation must be SUM.

Model with nodes to be fused:

        graph TD

    classDef ioNode fill:#dfd,stroke:#333,color:#333
    classDef initNode fill:#cccc00,stroke:#333,color:#333
    classDef constNode fill:#f9f,stroke:#333,stroke-width:2px,color:#333
    classDef opNode fill:#bbf,stroke:#333,stroke-width:2px,color:#333

    I_X(["X FLOAT(batch, 3)"])

    Concat_0[["Concat(., ., axis=1)"]]
    Sigmoid_1[["Sigmoid(.)"]]
    Sigmoid_2[["Sigmoid(.)"]]
    TreeEnsembleRegressor_3[["ai.onnx.ml.TreeEnsembleRegressor(.)"]]
    TreeEnsembleRegressor_4[["ai.onnx.ml.TreeEnsembleRegressor(.)"]]

    Sigmoid_1 --> Concat_0
    Sigmoid_2 --> Concat_0
    TreeEnsembleRegressor_3 -->|"FLOAT(batch, 1)"| Sigmoid_1
    TreeEnsembleRegressor_4 -->|"FLOAT(batch, 1)"| Sigmoid_2
    I_X -->|"FLOAT(batch, 3)"| TreeEnsembleRegressor_3
    I_X -->|"FLOAT(batch, 3)"| TreeEnsembleRegressor_4

    O_Y(["Y FLOAT(batch, 2)"])
    Concat_0 --> O_Y

    class I_X,O_Y ioNode
    class Concat_0,Sigmoid_1,Sigmoid_2,TreeEnsembleRegressor_3 opNode
    class TreeEnsembleRegressor_4 opNode

Outcome of the fusion:

        graph TD

    classDef ioNode fill:#dfd,stroke:#333,color:#333
    classDef initNode fill:#cccc00,stroke:#333,color:#333
    classDef constNode fill:#f9f,stroke:#333,stroke-width:2px,color:#333
    classDef opNode fill:#bbf,stroke:#333,stroke-width:2px,color:#333

    I_X(["X FLOAT(batch, 3)"])

    TreeEnsembleRegressor_0[["ai.onnx.ml.TreeEnsembleRegressor(.)"]]
    Sigmoid_1[["Sigmoid(.)"]]

    I_X -->|"FLOAT(batch, 3)"| TreeEnsembleRegressor_0
    TreeEnsembleRegressor_0 -->|"FLOAT(batch, 2)"| Sigmoid_1

    O_Y(["Y FLOAT(batch, 2)"])
    Sigmoid_1 --> O_Y

    class I_X,O_Y ioNode
    class TreeEnsembleRegressor_0,Sigmoid_1 opNode

apply(g: GraphBuilder, concat_node: NodeProto, *trees_or_sigmoid: NodeProto) → List[NodeProto][source]#

The method does the rewriting. It assumes it can happen. It takes a list of nodes impacted by the rewriting assumes no other pattern optimizer will be modify them. It receives the list of nodes returned by method apply. Since it is a list of argument, method match can include None values. The method returns the new nodes. The optimizer considers that any node given to this function is removed from the graph, and any node returned by it are added. If a received node must be kept, it must be added to the list of returned node.

Parameters:: nodes – nodes returned by method match, there are then removed
Returns:: nodes to add to graph.

match(g: GraphBuilderPatternOptimization, node: NodeProto, matched: List[MatchResult]) → MatchResult | None[source]#

Determines nodes around node which can be rewritten.

Parameters:

g – is a GraphBuilderPatternOptimization, it holds all the existing nodes, is able to return any information about type, shape, the node before, the node after another one.
node – the matching must determine if some nodes around this one are part of set of nodes this pattern optimizer can rewrite. From there, the function explores wherever it needs, checking any condition it needs.
matched – usually unused, it returns of nodes already matching a pattern

The method must not modify the graph. The method returns None if no match is found or an instance of class MatchResult. It must contain:

a list of nodes involved in the rewriting. It does not mean all of them will be removed but all of them are needed to do the rewriting and must not be impacted by other pattern optimizer.
A function doing the rewriting (usually method apply of the pattern class).
An existing node where the rewritten nodes can be inserted. Knowing it makes it faster to rewriter. If not specified, the optimizer will automatically determine the position of the new nodes.

class yobx.xoptim.patterns_ml.tree_ensemble.TreeEnsembleRegressorMulPattern(verbose: int = 0, priority: int = 1, min_opset: int = 1)[source]#

Replaces TreeEnsembleRegressor + Mul(., scalar) with TreeEnsembleRegressor.