o Ne0@slddlZddlmZddlmZmZddlmZddlm Z ddlm Z m Z gZ d ddZ d d d ZdS) N) LayerHelper)_non_static_modeVariable)check_variable_and_dtype)core)_C_ops _legacy_C_opsc Cs |dur |dur dnd}tr"t|||||d|\}}} ||| fSt|dddt|dddt|d d d|rGt|d d dt|d d dtdit} | j|jd}| j|jd}| j|jd} | jd||||rn|nd|rs|ndd||| dd|id||| fS)a Reindex Graph API. This API is mainly used in Graph Learning domain, which should be used in conjunction with `paddle.geometric.sample_neighbors` API. And the main purpose is to reindex the ids information of the input nodes, and return the corresponding graph edges after reindex. Take input nodes x = [0, 1, 2] as an example. If we have neighbors = [8, 9, 0, 4, 7, 6, 7], and count = [2, 3, 2], then we know that the neighbors of 0 is [8, 9], the neighbors of 1 is [0, 4, 7], and the neighbors of 2 is [6, 7]. Then after graph_reindex, we will have 3 different outputs: reindex_src: [3, 4, 0, 5, 6, 7, 6], reindex_dst: [0, 0, 1, 1, 1, 2, 2] and out_nodes: [0, 1, 2, 8, 9, 4, 7, 6]. We can see that the numbers in `reindex_src` and `reindex_dst` is the corresponding index of nodes in `out_nodes`. Note: The number in x should be unique, otherwise it would cause potential errors. We will reindex all the nodes from 0. Args: x (Tensor): The input nodes which we sample neighbors for. The available data type is int32, int64. neighbors (Tensor): The neighbors of the input nodes `x`. The data type should be the same with `x`. count (Tensor): The neighbor count of the input nodes `x`. And the data type should be int32. value_buffer (Tensor|None): Value buffer for hashtable. The data type should be int32, and should be filled with -1. Only useful for gpu version. index_buffer (Tensor|None): Index buffer for hashtable. The data type should be int32, and should be filled with -1. Only useful for gpu version. `value_buffer` and `index_buffer` should be both not None if you want to speed up by using hashtable buffer. name (str, optional): Name for the operation (optional, default is None). For more information, please refer to :ref:`api_guide_Name`. Returns: - reindex_src (Tensor), the source node index of graph edges after reindex. - reindex_dst (Tensor), the destination node index of graph edges after reindex. - out_nodes (Tensor), the index of unique input nodes and neighbors before reindex, where we put the input nodes `x` in the front, and put neighbor nodes in the back. Examples: .. code-block:: python import paddle x = [0, 1, 2] neighbors = [8, 9, 0, 4, 7, 6, 7] count = [2, 3, 2] x = paddle.to_tensor(x, dtype="int64") neighbors = paddle.to_tensor(neighbors, dtype="int64") count = paddle.to_tensor(count, dtype="int32") reindex_src, reindex_dst, out_nodes = paddle.geometric.reindex_graph(x, neighbors, count) # reindex_src: [3, 4, 0, 5, 6, 7, 6] # reindex_dst: [0, 0, 1, 1, 1, 2, 2] # out_nodes: [0, 1, 2, 8, 9, 4, 7, 6] NTFflag_buffer_hashtableXint32Zint64 graph_reindex NeighborsCountr HashTable_ValueHashTable_Index reindex_graphdtyper rrrrZ Reindex_SrcZ Reindex_DstZ Out_NodestypeZinputsZoutputsattrs)r) rrr rrlocals"create_variable_for_type_inferencer append_op xZ neighborscountZ value_bufferZ index_buffernameZuse_buffer_hashtableZ reindex_srcZ reindex_dstZ out_nodeshelperr"HD:\Projects\ConvertPro\env\Lib\site-packages\paddle/geometric/reindex.pyrsX<    rc Cs|dur |dur dnd}tr0tj|dd}tj|dd}t|||||d|\}}} ||| fSt|tr8|g}t|tr@|g}tj|dd}tj|dd}t|ddd t|d dd t|d d d |rst|dd d t|dd d tdit } | j |j d}| j |j d}| j |j d} tj|dd}tj|dd}| j d ||||r|nd|r|ndd||| dd|id||| fS)a Reindex HeterGraph API. This API is mainly used in Graph Learning domain, which should be used in conjunction with `paddle.geometric.sample_neighbors` API. And the main purpose is to reindex the ids information of the input nodes, and return the corresponding graph edges after reindex. Take input nodes x = [0, 1, 2] as an example. For graph A, suppose we have neighbors = [8, 9, 0, 4, 7, 6, 7], and count = [2, 3, 2], then we know that the neighbors of 0 is [8, 9], the neighbors of 1 is [0, 4, 7], and the neighbors of 2 is [6, 7]. For graph B, suppose we have neighbors = [0, 2, 3, 5, 1], and count = [1, 3, 1], then we know that the neighbors of 0 is [0], the neighbors of 1 is [2, 3, 5], and the neighbors of 3 is [1]. We will get following outputs: reindex_src: [3, 4, 0, 5, 6, 7, 6, 0, 2, 8, 9, 1], reindex_dst: [0, 0, 1, 1, 1, 2, 2, 0, 1, 1, 1, 2] and out_nodes: [0, 1, 2, 8, 9, 4, 7, 6, 3, 5]. Note: The number in x should be unique, otherwise it would cause potential errors. We support multi-edge-types neighbors reindexing in reindex_heter_graph api. We will reindex all the nodes from 0. Args: x (Tensor): The input nodes which we sample neighbors for. The available data type is int32, int64. neighbors (list|tuple): The neighbors of the input nodes `x` from different graphs. The data type should be the same with `x`. count (list|tuple): The neighbor counts of the input nodes `x` from different graphs. And the data type should be int32. value_buffer (Tensor|None): Value buffer for hashtable. The data type should be int32, and should be filled with -1. Only useful for gpu version. index_buffer (Tensor|None): Index buffer for hashtable. The data type should be int32, and should be filled with -1. Only useful for gpu version. `value_buffer` and `index_buffer` should be both not None if you want to speed up by using hashtable buffer. name (str, optional): Name for the operation (optional, default is None). For more information, please refer to :ref:`api_guide_Name`. Returns: - reindex_src (Tensor), the source node index of graph edges after reindex. - reindex_dst (Tensor), the destination node index of graph edges after reindex. - out_nodes (Tensor), the index of unique input nodes and neighbors before reindex, where we put the input nodes `x` in the front, and put neighbor nodes in the back. Examples: .. code-block:: python import paddle x = [0, 1, 2] neighbors_a = [8, 9, 0, 4, 7, 6, 7] count_a = [2, 3, 2] x = paddle.to_tensor(x, dtype="int64") neighbors_a = paddle.to_tensor(neighbors_a, dtype="int64") count_a = paddle.to_tensor(count_a, dtype="int32") neighbors_b = [0, 2, 3, 5, 1] count_b = [1, 3, 1] neighbors_b = paddle.to_tensor(neighbors_b, dtype="int64") count_b = paddle.to_tensor(count_b, dtype="int32") neighbors = [neighbors_a, neighbors_b] count = [count_a, count_b] reindex_src, reindex_dst, out_nodes = paddle.geometric.reindex_heter_graph(x, neighbors, count) # reindex_src: [3, 4, 0, 5, 6, 7, 6, 0, 2, 8, 9, 1] # reindex_dst: [0, 0, 1, 1, 1, 2, 2, 0, 1, 1, 1, 2] # out_nodes: [0, 1, 2, 8, 9, 4, 7, 6, 3, 5] NTFr)Zaxisr r r Zheter_graph_reindexrr rr rrreindex_heter_graphrrrr)r$) rpaddleconcatrr isinstancerrrrrrrrr"r"r#r$slD     r$)NNN)r%Zpaddle.fluid.layer_helperrZpaddle.fluid.frameworkrrZpaddle.fluid.data_feederrZ paddle.fluidrrr__all__rr$r"r"r"r#s    q