def __calc_dm(graph: gc.Graph, removed_nodes: [int],
save_info: sl.MemoryAccess, i: int) -> (int, pd.DataFrame):
if save_info.has_distance_matrix(removed_nodes=removed_nodes, iteration=i):
# print("Distance matrix for removed nodes", removed_nodes, "and iteration", i, "is already trained")
return i, save_info.load_distance_matrix(removed_nodes=removed_nodes,
iteration=i)
else:
# print(f'Calculate distance matrix for removed nodes {removed_nodes} iteration {i}')
# model = embedding_function(graph=graph, save_info=save_info, removed_nodes=removed_nodes, iteration=i)
# thows error if embedding does not exist
model = save_info.load_embedding(removed_nodes=removed_nodes,
iteration=i)
dm = cd.calc_distances(model=model,
graph=graph,
save_info=save_info,
removed_nodes=removed_nodes,
iteration=i,
save=False)
save_info.save_distance_matrix(removed_nodes=removed_nodes,
iteration=i,
dm=dm)
return i, dm
def calc_distances(model,
save_info: sl.MemoryAccess,
removed_nodes: [int],
iteration: int,
graph: gc.Graph = None,
save: bool = True,
check_for_existing: bool = True):
if check_for_existing and save_info.has_distance_matrix(
removed_nodes, iteration):
return save_info.load_distance_matrix(removed_nodes, iteration)
dm = calc_distances_based_on_gensim_fast(model=model)
"""
if type(model) == pd.DataFrame:
dm = __calc_distances_based_on_df(embedding=model)
else:
dm = calc_distances_based_on_gensim_fast(model=model)
# dm = __calc_distances_based_on_gensim(model=model, node_names=node_names)
"""
if save:
save_info.save_distance_matrix(removed_nodes, iteration, dm)
return dm