libcity.model.road_representation¶

class libcity.model.road_representation.ChebConv(config, data_feature)[source]¶

Bases: libcity.model.abstract_traffic_state_model.AbstractTrafficStateModel

calculate_loss(batch)[source]¶

Parameters: batch – dict, need key ‘node_features’, ‘node_labels’, ‘mask’

Returns:

forward(batch)[source]¶

自回归任务

Parameters: batch – dict, need key ‘node_features’ contains tensor shape=(N, feature_dim)
Returns: N, feature_dim
Return type: torch.tensor

predict(batch)[source]¶

Parameters: batch – dict, need key ‘node_features’
Returns: torch.tensor

training: bool¶

class libcity.model.road_representation.DeepWalk(config, data_feature)[source]¶

Bases: libcity.model.abstract_traffic_tradition_model.AbstractTraditionModel

run(data=None)[source]¶

Parameters: data – input of tradition model
Returns: output of tradition model

class libcity.model.road_representation.GAT(config, data_feature)[source]¶

Bases: libcity.model.abstract_traffic_state_model.AbstractTrafficStateModel

calculate_loss(batch)[source]¶

Parameters: batch – dict, need key ‘node_features’, ‘node_labels’, ‘mask’

Returns:

forward(batch)[source]¶

自回归任务 :param batch: dict, need key ‘node_features’ contains tensor shape=(N, feature_dim)

Returns: N, feature_dim
Return type: torch.tensor

predict(batch)[source]¶

Parameters: batch – dict, need key ‘node_features’
Returns: torch.tensor

training: bool¶

class libcity.model.road_representation.GeomGCN(config, data_feature)[source]¶

Bases: libcity.model.abstract_traffic_state_model.AbstractTrafficStateModel

calculate_loss(batch)[source]¶

Parameters: batch – dict, need key ‘node_features’, ‘node_labels’, ‘mask’

Returns:

forward(batch)[source]¶

自回归任务

Parameters: batch – dict, need key ‘node_features’ contains tensor shape=(N, feature_dim)
Returns: N, output_classes
Return type: torch.tensor

get_input(config, data_feature)[source]¶

predict(batch)[source]¶

Parameters: batch – dict, need key ‘node_features’
Returns: torch.tensor

training: bool¶

class libcity.model.road_representation.LINE(config, data_feature)[source]¶

Bases: libcity.model.abstract_traffic_state_model.AbstractTrafficStateModel

calculate_loss(batch)[source]¶

输入一个batch的数据，返回训练过程的loss，也就是需要定义一个loss函数

Parameters: batch (Batch) – a batch of input
Returns: return training loss
Return type: torch.tensor

forward(I, J)[source]¶

Parameters

I – origin indices of node i ; (B,)
J – origin indices of node j ; (B,)

Returns

[u_j^T * u_i for (i,j) in zip(I, J)]; (B,) elif order == ‘second’:

[u’_j^T * v_i for (i,j) in zip(I, J)]; (B,)

Return type

if order == ‘first’

training: bool¶

class libcity.model.road_representation.Node2Vec(config, data_feature)[source]¶

Bases: libcity.model.abstract_traffic_tradition_model.AbstractTraditionModel

run(data=None)[source]¶

Parameters: data – input of tradition model
Returns: output of tradition model