def run_experiment(k, N, dataset=DEFAULT_DATASET, theta=DEFAULT_THETA,
dfnc_window=DEFAULT_WINDOW, m=DEFAULT_M, n=DEFAULT_N,
metrics=METRIC_NAMES,
methods=METHOD_NAMES, **kwargs):
"""
Run an experiment with a particular choice of
1. Data set
2. Data Parameters k, n, theta, dfnc_window, m, n
3. metric
4. method
5. Method parameters passed in kwargs
"""
X = get_dataset(N, dataset=dataset, theta=theta,
dfnc_window=dfnc_window, m=m, n=n)
res = {method: run_method(X, k, method=method, **kwargs)
for method in methods}
measures = {res[r]['name']: {metric: evaluate_metric(res[r]['X'],
res[r]['cluster_labels'], metric)
for metric in metrics} for r in res}
return measures, res
local.gradient_step(remote_optimizer, remote_centroids)
# Check the stopping condition "locally" at the aggregator
# - returns false if converged
remote_check, delta = local.check_stopping(remote_centroids, previous,
epsilon)
if verbose:
print("Multi-Shot %s ; iter : %d delta : %f" %
(optimization, num_iter, delta))
not_converged = remote_check
tracked_delta.append(delta)
num_iter += 1
# Compute the final clustering "locally" at the aggregator
cluster_labels = [
clusters for node in nodes
for clusters in local.compute_clustering(node, remote_centroids)
]
return {
'centroids': remote_centroids,
'cluster_labels': cluster_labels,
'X': X,
'delta': tracked_delta,
'num_iter': i,
'name': 'multishot_%s' % optimization
}
if __name__ == '__main__':
w = main(get_dataset(100, theta=[[-1, 0.1], [1, 0.1]], m=1, n=2), 2)