def getGraphs(K, verbose=1):
""" Returns a dictionary of graphs with relevant topologies """
graphs = {}
for topo in ['ring']:
try:
graphs[topo] = define_graph_topology(K, topo, verbose=verbose)
except:
graphs[topo] = None
return graphs
def main(dataset, dataset_path, dataset_size, use_split_dataset, split_by,
random_state, algoritmname, max_global_steps, local_iters, solvername,
output_dir, exit_time, lambda_, l1_ratio, theta, graph_topology, c,
logmode, ckpt_freq, n_connectivity):
# Fix gamma = 1.0 according to:
# Adding vs. Averaging in Distributed Primal-Dual Optimization
gamma = 1.0
# Initialize process group
comm.init_process_group('mpi')
# Get rank of current process
rank = comm.get_rank()
world_size = comm.get_world_size()
# Create graph with specified topology
graph = define_graph_topology(world_size,
graph_topology,
n_connectivity=n_connectivity)
if use_split_dataset:
X, y = load_dataset_by_rank(dataset,
rank,
world_size,
dataset_size,
split_by,
dataset_path=dataset_path,
random_state=random_state)
else:
X, y = load_dataset(dataset,
rank,
world_size,
dataset_size,
split_by,
dataset_path=dataset_path,
random_state=random_state)
# Define subproblem
solver = configure_solver(name=solvername,
split_by=split_by,
l1_ratio=l1_ratio,
lambda_=lambda_,
C=c,
random_state=random_state)
# Add hooks to log and save metrics.
monitor = Monitor(solver, output_dir, ckpt_freq, exit_time, split_by,
logmode)
# Always use this value throughout this project
Akxk, xk = run_algorithm(algoritmname, X, y, solver, gamma, theta,
max_global_steps, local_iters, world_size, graph,
monitor)
monitor.save(Akxk, xk, weightname='weight.npy', logname='result.csv')
def main(dataset, dataset_path, dataset_size, datapoints, use_split_dataset,
split_by, random_state, algoritmname, max_global_steps, local_iters,
solvername, output_dir, exit_time, lambda_, l1_ratio, theta,
graph_topology, c, logmode, ckpt_freq, n_connectivity, fit_intercept,
normalize, verbose):
# Fix gamma = 1.0 according to:
# Adding vs. Averaging in Distributed Primal-Dual Optimization
gamma = 1.0
# Initialize process group
comm.init_process_group('mpi')
# Get rank of current process
rank = comm.get_rank()
world_size = comm.get_world_size()
# Create graph with specified topology
graph = define_graph_topology(world_size,
graph_topology,
n_connectivity=n_connectivity,
verbose=verbose)
if use_split_dataset:
if not dataset_path:
dataset_path = os.path.join('data', dataset, split_by,
f'{world_size}')
X, y, X_test, y_test = load_dataset_by_rank(dataset,
rank,
world_size,
dataset_size,
datapoints,
split_by,
dataset_path=dataset_path,
random_state=random_state,
verbose=verbose)
else:
X, y = load_dataset(dataset,
rank,
world_size,
dataset_size,
datapoints,
split_by,
dataset_path=dataset_path,
random_state=random_state,
verbose=verbose)
# Define subproblem
solver = configure_solver(name=solvername,
split_by=split_by,
l1_ratio=l1_ratio,
lambda_=lambda_,
C=c,
random_state=random_state)
# Add hooks to log and save metrics.
if algoritmname != 'cola':
output_dir = os.path.join(output_dir, algoritmname)
if dataset:
output_dir = os.path.join(output_dir, dataset, f'{world_size:0>2}',
graph_topology)
monitor = Monitor(output_dir,
ckpt_freq=ckpt_freq,
exit_time=exit_time,
split_by=split_by,
mode=logmode,
verbose=verbose,
Ak=X,
Ak_test=X_test,
y_test=y_test)
# Run CoLA
comm.barrier()
if algoritmname == 'cola':
model = Cola(gamma, solver, theta, fit_intercept, normalize)
monitor.init(model, graph)
model = model.fit(X, y, graph, monitor, max_global_steps, local_iters)
else:
raise NotImplementedError()
# Show test stats
if X_test is not None:
monitor.show_test_statistics()
# Save final model
monitor.save(modelname='model.pickle', logname=f'result.csv')