def main(out_path, bundle, workers=0, local=False):
"""Evaluate the pure multinomial model over a range of smoothing values."""
def yield_jobs():
run_data = borg.storage.RunData.from_bundle(bundle)
validation = sklearn.cross_validation.KFold(len(run_data),
10,
indices=False)
for (train_mask, test_mask) in validation:
split = uuid.uuid4()
alphas = numpy.r_[1e-8:1e-1:64j]
for alpha in alphas:
yield (evaluate_split,
[run_data, alpha, split, train_mask, test_mask])
with open(out_path, "w") as out_file:
writer = csv.writer(out_file)
writer.writerow(
["alpha", "instances", "split", "mean_log_probability"])
for (_, row) in condor.do(yield_jobs(), workers, local):
writer.writerow(row)
out_file.flush()
if __name__ == "__main__":
borg.script(main)
seed = numpy.random.randint(sys.maxint)
yield (run_solver_on, [suite_path, solver_name, path, budget, store_answers, seed])
distributor = borg.distributors.make(distributor_name, workers=workers)
for row in distributor.do(yield_runs()):
# unpack run outcome
(cnf_path, solver_name, budget, cost, succeeded, answer) = row
if answer is None:
answer_text = None
else:
answer_text = base64.b64encode(zlib.compress(pickle.dumps(answer)))
# write it to disk
csv_path = cnf_path + suffix
existed = os.path.exists(csv_path)
with open(csv_path, "a") as csv_file:
writer = csv.writer(csv_file)
if not existed:
writer.writerow(["solver", "budget", "cost", "succeeded", "answer"])
writer.writerow([solver_name, budget, cost, succeeded, answer_text])
if __name__ == "__main__":
borg.script(main)