ó Α®i„9ãó*•SSKJr SSKJrJrJr SSKJr SSKJ r SSK J r SSK J r \(aSSKJr /r\SSSjj5r\SSS jj5r\SSS jj5rSS jr\SSS jj5r\SSSjj5r\SSSjj5rSSjrg )é)Ú annotations)Ú TYPE_CHECKINGÚLiteralÚoverload)Ú_C_ops)Úcheck_variable_and_dtype)Ú LayerHelper)Úin_dynamic_or_pir_mode)ÚTensorcó•g©N©©ÚrowÚcolptrÚ input_nodesÚ sample_sizeÚeidsÚ return_eidsÚ perm_bufferÚnames Úc/var/www/html/banglarbhumi/venv/lib/python3.13/site-packages/paddle/geometric/sampling/neighbors.pyÚsample_neighborsró€ð%(ócó•gr rrs rrr*ó€ð rcó•gr rrs rrr7ó€ð=@rNc óš•U(aUc [S5eUbSOSn[5(a/[R"UUUUUUUU5un n n U(aXšU 4$Xš4$[ USSS5 [ USSS5 [ US SS5 U(a[ US SS5 U(a[ US SS5 [ S0[ 5D6n U RURS 9n U RURS 9n U RURS 9n U RSUUUU(aUOSU(aUOSS .U U U S.UUUS.S9 U(aXšU 4$Xš4$)a¤ Graph Sample Neighbors API. This API is mainly used in Graph Learning domain, and the main purpose is to provide high performance of graph sampling method. For example, we get the CSC(Compressed Sparse Column) format of the input graph edges as `row` and `colptr`, so as to convert graph data into a suitable format for sampling. `input_nodes` means the nodes we need to sample neighbors, and `sample_sizes` means the number of neighbors and number of layers we want to sample. Besides, we support fisher-yates sampling in GPU version. Args: row (Tensor): One of the components of the CSC format of the input graph, and the shape should be [num_edges, 1] or [num_edges]. The available data type is int32, int64. colptr (Tensor): One of the components of the CSC format of the input graph, and the shape should be [num_nodes + 1, 1] or [num_nodes + 1]. The data type should be the same with `row`. input_nodes (Tensor): The input nodes we need to sample neighbors for, and the data type should be the same with `row`. sample_size (int, optional): The number of neighbors we need to sample. Default value is -1, which means returning all the neighbors of the input nodes. eids (Tensor, optional): The eid information of the input graph. If return_eids is True, then `eids` should not be None. The data type should be the same with `row`. Default is None. return_eids (bool, optional): Whether to return eid information of sample edges. Default is False. perm_buffer (Tensor, optional): Permutation buffer for fisher-yates sampling. If `use_perm_buffer` is True, then `perm_buffer` should not be None. The data type should be the same with `row`. If not None, we will use fiser-yates sampling to speed up. Only useful for gpu version. Default is None. name (str, optional): Name for the operation (optional, default is None). For more information, please refer to :ref:`api_guide_Name`. Returns: - out_neighbors (Tensor), the sample neighbors of the input nodes. - out_count (Tensor), the number of sampling neighbors of each input node, and the shape should be the same with `input_nodes`. - out_eids (Tensor), if `return_eids` is True, we will return the eid information of the sample edges. Examples: .. code-block:: python >>> import paddle >>> # edges: (3, 0), (7, 0), (0, 1), (9, 1), (1, 2), (4, 3), (2, 4), >>> # (9, 5), (3, 5), (9, 6), (1, 6), (9, 8), (7, 8) >>> row = [3, 7, 0, 9, 1, 4, 2, 9, 3, 9, 1, 9, 7] >>> colptr = [0, 2, 4, 5, 6, 7, 9, 11, 11, 13, 13] >>> nodes = [0, 8, 1, 2] >>> sample_size = 2 >>> row = paddle.to_tensor(row, dtype="int64") >>> colptr = paddle.to_tensor(colptr, dtype="int64") >>> nodes = paddle.to_tensor(nodes, dtype="int64") >>> out_neighbors, out_count = paddle.geometric.sample_neighbors(row, colptr, nodes, sample_size=sample_size, return_eids=False) Nú3`eids` should not be None if `return_eids` is True.TFÚRow©Úint32Úint64Úgraph_sample_neighborsÚCol_PtrÚXÚEidsÚ Perm_Buffer©Údtype)r"r'r(r)r*)ÚOutÚ Out_CountÚOut_Eids)rrÚflag_perm_buffer©ÚtypeÚinputsÚoutputsÚattrs)r) Ú ValueErrorr rr&rr ÚlocalsÚ"create_variable_for_type_inferencer,Ú append_op) rrrrrrrrÚuse_perm_bufferÚ out_neighborsÚ out_countÚout_eidsÚhelpers rrrDs²€öPØ ‰<ÜØEóð ð*Ñ5‘d¸5€Oä×Ñô × )Ò )Ø Ø Ø Ø Ø Ø Ø Ø ó ñ  Ø Ø Ø ö Ø ¨XÐ5Ð 5ØÐ'Ð'äØ ˆUÐ&Ð(@ôôØ Ð-Ð/GôôØSÐ,Ð.FôöÜ Ø &Ð,Ð.Fô öÜ Ø Ø Ø Ø $ô  ôÑ 8¬v«xÑ 8€FØ×=Ñ=ÀCÇIÁIÐ=ÐN€MØ×9Ñ9ÀÇ Á Ð9ÐJ€IØ×8Ñ8¸s¿y¹yÐ8ÐI€HØ ×ÑØ %àØØÞ'‘D¨TÞ*9™;¸tñ  ð!Ø"Ø ñ ð 'Ø&Ø /ñ ðñö(بÐ1Ð1Ø Ð #Ð#rcó•gr r©rrÚ edge_weightrrrrrs rÚweighted_sample_neighborsrBÙrrcó•gr rr@s rrBrBærrcó•gr rr@s rrBrBórrc óh•U(aUc [S5e[5(a.[R"UUUUUUU5unn n U(aX‰U 4$X‰4$[ USSS5 [ USSS5 [ USSS5 [ US SS5 U(a[ US SS5 [ S0[ 5D6n U RURS 9nU RURS 9n U RURS 9n U RSUUUUU(aUOSS .UU U S .UUS.S9 U(aX‰U 4$X‰4$)a Graph Weighted Sample Neighbors API. This API is mainly used in Graph Learning domain, and the main purpose is to provide high performance of graph weighted-sampling method. For example, we get the CSC(Compressed Sparse Column) format of the input graph edges as `row` and `colptr`, so as to convert graph data into a suitable format for sampling, and the input `edge_weight` should also match the CSC format. Besides, `input_nodes` means the nodes we need to sample neighbors, and `sample_sizes` means the number of neighbors and number of layers we want to sample. This API will finally return the weighted sampled neighbors, and the probability of being selected as a neighbor is related to its weight, with higher weight and higher probability. Args: row (Tensor): One of the components of the CSC format of the input graph, and the shape should be [num_edges, 1] or [num_edges]. The available data type is int32, int64. colptr (Tensor): One of the components of the CSC format of the input graph, and the shape should be [num_nodes + 1, 1] or [num_nodes + 1]. The data type should be the same with `row`. edge_weight (Tensor): The edge weight of the CSC format graph edges. And the shape should be [num_edges, 1] or [num_edges]. The available data type is float32. input_nodes (Tensor): The input nodes we need to sample neighbors for, and the data type should be the same with `row`. sample_size (int, optional): The number of neighbors we need to sample. Default value is -1, which means returning all the neighbors of the input nodes. eids (Tensor, optional): The eid information of the input graph. If return_eids is True, then `eids` should not be None. The data type should be the same with `row`. Default is None. return_eids (bool, optional): Whether to return eid information of sample edges. Default is False. name (str, optional): Name for the operation (optional, default is None). For more information, please refer to :ref:`api_guide_Name`. Returns: - out_neighbors (Tensor), the sample neighbors of the input nodes. - out_count (Tensor), the number of sampling neighbors of each input node, and the shape should be the same with `input_nodes`. - out_eids (Tensor), if `return_eids` is True, we will return the eid information of the sample edges. Examples: .. code-block:: python >>> import paddle >>> # edges: (3, 0), (7, 0), (0, 1), (9, 1), (1, 2), (4, 3), (2, 4), >>> # (9, 5), (3, 5), (9, 6), (1, 6), (9, 8), (7, 8) >>> row = [3, 7, 0, 9, 1, 4, 2, 9, 3, 9, 1, 9, 7] >>> colptr = [0, 2, 4, 5, 6, 7, 9, 11, 11, 13, 13] >>> weight = [0.1, 0.5, 0.2, 0.5, 0.9, 1.9, 2.0, 2.1, 0.01, 0.9, 0,12, 0.59, 0.67] >>> nodes = [0, 8, 1, 2] >>> sample_size = 2 >>> row = paddle.to_tensor(row, dtype="int64") >>> colptr = paddle.to_tensor(colptr, dtype="int64") >>> weight = paddle.to_tensor(weight, dtype="float32") >>> nodes = paddle.to_tensor(nodes, dtype="int64") >>> out_neighbors, out_count = paddle.geometric.weighted_sample_neighbors( ... row, colptr, weight, nodes, sample_size=sample_size, return_eids=False ... ) Nr!rr#rBrrAÚfloat32rrr+)rrrArr)r;r<r=)rrr1)rB) r6r rrBrr r7r8r,r9) rrrArrrrrr;r<r=r>s rrBrBsš€öVØ ‰<ÜØEóð ô×Ñô × ,Ò ,Ø Ø Ø Ø Ø Ø Ø ó ñ  Ø Ø Ø ö Ø ¨XÐ5Ð 5ØÐ'Ð'äØ ˆUÐ&Ð(CôôØÐ,Ð.IôôØØØ Ø#ô ô ØØØØ#ô ö Ü Ø &Ð,Ð.Iô ôÑ A¼»Ñ A€FØ×=Ñ=ÀCÇIÁIÐ=ÐN€MØ×9Ñ9ÀÇ Á Ð9ÐJ€IØ×8Ñ8¸s¿y¹yÐ8ÐI€HØ ×ÑØ (àØØ&Ø&Þ'‘D¨Tñ  ð+Ø"Ø ñ ð 'Ø&ñ ðñö&بÐ1Ð1Ø Ð #Ð#r).....)rr rr rr rÚintrú Tensor | Nonerú Literal[True]rrHrú str | NoneÚreturnútuple[Tensor, Tensor, Tensor])rr rr rr rrGrrHrúLiteral[False]rrHrrJrKútuple[Tensor, Tensor])rr rr rr rrGrrHrÚboolrrHrrJrKú5tuple[Tensor, Tensor] | tuple[Tensor, Tensor, Tensor])éÿÿÿÿNFNN)....)rr rr rAr rr rrGrrHrrIrrJrKrL)rr rr rAr rr rrGrrHrrMrrJrKrN)rr rr rAr rr rrGrrHrrOrrJrKrP)rQNFN)Ú __future__rÚtypingrrrÚpaddlerÚpaddle.base.data_feederrÚpaddle.base.layer_helperr Úpaddle.frameworkr r Ú__all__rrBrrrÚrYsBðõ#ç3Ñ3åÝ<Ý0Ý3æÝØ €ð ð ØØ!$Ø!$Øð (Ø ð (à ð (ðð (ðð (ð ð (ð ð (ðð (ð ð (ð#ô (ó ð (ð ð ØØ"%Ø!$Øð  Ø ð  à ð  ðð  ðð  ð ð  ð  ð  ðð  ð ð  ðô  ó ð  ð ð ØØØ!$Øð @Ø ð @à ð @ðð @ðð @ð ð @ð ð @ðð @ð ð @ð;ô @ó ð @ð Ø ØØØ ôR$ðj ð ØØ!$Øð (Ø ð (à ð (ðð (ðð (ð ð (ð ð (ðð (ð ð (ð#ô (ó ð (ð ð ØØ"%Øð  Ø ð  à ð  ðð  ðð  ð ð  ð ð  ð ð  ð ð  ðô  ó ð  ð ð ØØØð @Ø ð @à ð @ðð @ðð @ð ð @ð ð @ðð @ð ð @ð;ô @ó ð @ð"Ø ØØ õS$r