libcity.model.road_representation.DeepWalk¶

class libcity.model.road_representation.DeepWalk.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.DeepWalk.Graph[source]¶

Bases: collections.defaultdict

adjacency_iter()[source]¶

check_self_loops()[source]¶

degree(nodes=None)[source]¶

has_edge(v1, v2)[source]¶

make_consistent()[source]¶

make_undirected()[source]¶

nodes()[source]¶

number_of_edges()[source]¶: Returns the number of nodes in the graph

number_of_nodes()[source]¶: Returns the number of nodes in the graph

order()[source]¶: Returns the number of nodes in the graph

random_walk(path_length, alpha=0, rand=<random.Random object>, start=None)[source]¶: Returns a truncated random walk. path_length: Length of the random walk. alpha: probability of restarts. start: the start node of the random walk.

remove_self_loops()[source]¶

subgraph(nodes={})[source]¶

libcity.model.road_representation.DeepWalk.build_deepwalk_corpus(G, num_paths, path_length, alpha=0, rand=<random.Random object>)[source]¶

libcity.model.road_representation.DeepWalk.from_numpy(x, directed=False)[source]¶

libcity.model.road_representation.DeepWalk.learn_embeddings(walks, dimensions, window_size, workers, iters, min_count=0, sg=1, hs=0)[source]¶