def create_diststats_jobs(context, distances, streams, maxd):
# Compmake storage for results
store = StoreResults()
for id_distance in distances:
for delta in range(1, maxd):
for i, id_stream in enumerate(streams):
key = dict(id_distance=id_distance,
delta=delta,
stream=id_stream)
job_id = '%s-log%s-delta%s' % (id_distance, i, delta)
store[key] = context.comp_config(compute_dist_stats, id_distance,
id_stream, delta,
job_id=job_id)
for id_distance in distances:
subset = store.select(id_distance=id_distance)
stats = context.comp(compute_statistics, subset)
report = context.comp(report_statistics, id_distance, stats)
context.add_report(report, 'bydistance', id_distance=id_distance)
subsets = create_subsets(distances)
job_report(context, subsets, store)
def create_diststats_jobs(context, distances, streams, maxd):
# Compmake storage for results
store = StoreResults()
for id_distance in distances:
for delta in range(1, maxd):
for i, id_stream in enumerate(streams):
key = dict(id_distance=id_distance,
delta=delta,
stream=id_stream)
job_id = '%s-log%s-delta%s' % (id_distance, i, delta)
store[key] = context.comp_config(compute_dist_stats,
id_distance,
id_stream,
delta,
job_id=job_id)
for id_distance in distances:
subset = store.select(id_distance=id_distance)
stats = context.comp(compute_statistics, subset)
report = context.comp(report_statistics, id_distance, stats)
context.add_report(report, 'bydistance', id_distance=id_distance)
subsets = create_subsets(distances)
job_report(context, subsets, store)
def define_jobs_context(self, context):
sizes = np.linspace(16, 256, 32).astype("int")
# sizes = [16, 32, 64, 128, 256, 512]
nobs = 500
streams = ["test_gauss_drx1"]
estimators = [
"test_ddsest_unc_refine0",
"test_ddsest_unc_refine0ns", # don't stop
"test_ddsest_unc_fast_order",
]
max_displs = [0.1, 0.15, 0.2, 0.25, 0.3]
def should_do(estimator, shape):
if estimator in ["test_ddsest_unc_refine0", "test_ddsest_unc_refine0ns"]:
return True
if estimator == "test_ddsest_unc_fast_order":
return shape <= 128
assert False, estimator
results = StoreResults()
comp_stats = StoreResults()
combs = iterate_context_names_quartet(context, sizes, max_displs, streams, estimators)
for c, shape, max_displ, stream, estimator in combs:
if not should_do(estimator, shape):
continue
id_stream = stream + "_%s_%s" % (shape, nobs)
key = dict(
length=nobs, shape=shape, stream=stream, estimator=estimator, id_stream=id_stream, max_displ=max_displ
)
learned = c.subtask(DDSLLearn, stream=id_stream, estimator=estimator, max_displ=max_displ)
results[key] = learned
comp_stats[key] = compmake_execution_stats(learned)
source_descs = {}
# For each sample, show the cpu for each algorithm
jobs_tables_by_sample(
context,
id_table="cpu",
allstats=comp_stats,
one_table_for_each="id_stream",
cols_fields=["cpu_time", "wall_time"],
rows_field="estimator",
source_descs=source_descs,
)
estimators_subsets = get_estimators_subsets(estimators)
# one plot for each group
for id_group, estimators in estimators_subsets.items():
c = context.child(id_group)
group_runs = comp_stats.select(lambda k: k["estimator"] in estimators)
report = c.comp(report_cputime, group_runs)
c.add_report(report, "cputime", group=id_group)
def define_jobs_context(self, context):
sizes = np.linspace(16, 256, 32).astype('int')
# sizes = [16, 32, 64, 128, 256, 512]
nobs = 500
streams = ['test_gauss_drx1']
estimators = ['test_ddsest_unc_refine0',
'test_ddsest_unc_refine0ns', # don't stop
'test_ddsest_unc_fast_order']
max_displs = [0.1, 0.15, 0.2, 0.25, 0.3]
def should_do(estimator, shape):
if estimator in ['test_ddsest_unc_refine0', 'test_ddsest_unc_refine0ns']:
return True
if estimator == 'test_ddsest_unc_fast_order':
return shape <= 128
assert False, estimator
results = StoreResults()
comp_stats = StoreResults()
combs = iterate_context_names_quartet(context, sizes, max_displs, streams, estimators)
for c, shape, max_displ, stream, estimator in combs:
if not should_do(estimator, shape):
continue
id_stream = stream + '_%s_%s' % (shape, nobs)
key = dict(length=nobs, shape=shape, stream=stream, estimator=estimator,
id_stream=id_stream, max_displ=max_displ)
learned = c.subtask(DDSLLearn, stream=id_stream, estimator=estimator,
max_displ=max_displ)
results[key] = learned
comp_stats[key] = compmake_execution_stats(learned)
source_descs = {}
# For each sample, show the cpu for each algorithm
jobs_tables_by_sample(context, id_table='cpu',
allstats=comp_stats,
one_table_for_each='id_stream',
cols_fields=[
'cpu_time',
'wall_time',
],
rows_field='estimator',
source_descs=source_descs)
estimators_subsets = get_estimators_subsets(estimators)
# one plot for each group
for id_group, estimators in estimators_subsets.items():
c = context.child(id_group)
group_runs = comp_stats.select(lambda k: k['estimator'] in estimators)
report = c.comp(report_cputime, group_runs)
c.add_report(report, 'cputime', group=id_group)