def plot_runtime(ex, fname, func_xvalues, xlabel, func_title=None):
results = glo.ex_load_result(ex, fname)
value_accessor = lambda job_results: job_results['time_secs']
vf_pval = np.vectorize(value_accessor)
# results['job_results'] is a dictionary:
# {'test_result': (dict from running perform_test(te) '...':..., }
times = vf_pval(results['job_results'])
repeats, _, n_methods = results['job_results'].shape
time_avg = np.mean(times, axis=0)
time_std = np.std(times, axis=0)
xvalues = func_xvalues(results)
#ns = np.array(results[xkey])
#te_proportion = 1.0 - results['tr_proportion']
#test_sizes = ns*te_proportion
line_styles = func_plot_fmt_map()
method_labels = get_func2label_map()
func_names = [f.__name__ for f in results['method_funcs']]
for i in range(n_methods):
#te_proportion = 1.0 - results['tr_proportion']
fmt = line_styles[func_names[i]]
#plt.errorbar(ns*te_proportion, mean_rejs[:, i], std_pvals[:, i])
method_label = method_labels[func_names[i]]
plt.errorbar(xvalues,
time_avg[:, i],
yerr=time_std[:, i],
fmt=fmt,
label=method_label)
ylabel = 'Time (s)'
plt.ylabel(ylabel)
plt.xlabel(xlabel)
plt.xlim([np.min(xvalues), np.max(xvalues)])
plt.xticks(xvalues, xvalues)
plt.legend(loc='best')
plt.gca().set_yscale('log')
title = '%s. %d trials. ' % (
results['prob_label'],
repeats) if func_title is None else func_title(results)
plt.title(title)
#plt.grid()
return results
def run_problem(prob_label):
"""Run the experiment"""
# /////// submit jobs //////////
# create folder name string
#result_folder = glo.result_folder()
from kmod.config import expr_configs
tmp_dir = expr_configs['scratch_path']
foldername = os.path.join(tmp_dir, 'kmod_slurm', 'e%d' % ex)
logger.info("Setting engine folder to %s" % foldername)
# create parameter instance that is needed for any batch computation engine
logger.info("Creating batch parameter instance")
batch_parameters = BatchClusterParameters(foldername=foldername,
job_name_base="e%d_" % ex,
parameter_prefix="")
# Use the following line if Slurm queue is not used.
#engine = SerialComputationEngine()
partitions = expr_configs['slurm_partitions']
if partitions is None:
engine = SlurmComputationEngine(batch_parameters)
else:
engine = SlurmComputationEngine(batch_parameters, partition=partitions)
n_methods = len(method_funcs)
# problem setting
ns, P, Q, ds, = get_ns_pqrsource(prob_label)
# repetitions x len(ns) x #methods
aggregators = np.empty((reps, len(ns), n_methods), dtype=object)
for r in range(reps):
for ni, n in enumerate(ns):
for mi, f in enumerate(method_funcs):
# name used to save the result
func_name = f.__name__
fname = '%s-%s-n%d_r%d_a%.3f.p' \
%(prob_label, func_name, n, r, alpha,)
if not is_rerun and glo.ex_file_exists(ex, prob_label, fname):
logger.info('%s exists. Load and return.' % fname)
job_result = glo.ex_load_result(ex, prob_label, fname)
sra = SingleResultAggregator()
sra.submit_result(SingleResult(job_result))
aggregators[r, ni, mi] = sra
else:
# result not exists or rerun
job = Ex1Job(SingleResultAggregator(), P, Q, ds,
prob_label, r, f, n)
agg = engine.submit_job(job)
aggregators[r, ni, mi] = agg
# let the engine finish its business
logger.info("Wait for all call in engine")
engine.wait_for_all()
# ////// collect the results ///////////
logger.info("Collecting results")
job_results = np.empty((reps, len(ns), n_methods), dtype=object)
for r in range(reps):
for ni, n in enumerate(ns):
for mi, f in enumerate(method_funcs):
logger.info("Collecting result (%s, r=%d, n=%d)" %
(f.__name__, r, n))
# let the aggregator finalize things
aggregators[r, ni, mi].finalize()
# aggregators[i].get_final_result() returns a SingleResult instance,
# which we need to extract the actual result
job_result = aggregators[r, ni, mi].get_final_result().result
job_results[r, ni, mi] = job_result
#func_names = [f.__name__ for f in method_funcs]
#func2labels = exglobal.get_func2label_map()
#method_labels = [func2labels[f] for f in func_names if f in func2labels]
# save results
results = {
'job_results': job_results,
'P': P,
'Q': Q,
'data_source': ds,
'alpha': alpha,
'repeats': reps,
'ns': ns,
'method_funcs': method_funcs,
'prob_label': prob_label,
}
# class name
fname = 'ex%d-%s-me%d_rs%d_nmi%d_nma%d_a%.3f.p' \
%(ex, prob_label, n_methods, reps, min(ns), max(ns), alpha,)
glo.ex_save_result(ex, results, fname)
logger.info('Saved aggregated results to %s' % fname)
def plot_prob_reject(ex,
fname,
func_xvalues,
xlabel,
func_title=None,
return_plot_values=False):
"""
plot the empirical probability that the statistic is above the threshold.
This can be interpreted as type-1 error (when H0 is true) or test power
(when H1 is true). The plot is against the specified x-axis.
- ex: experiment number
- fname: file name of the aggregated result
- func_xvalues: function taking aggregated results dictionary and return the values
to be used for the x-axis values.
- xlabel: label of the x-axis.
- func_title: a function: results dictionary -> title of the plot
- return_plot_values: if true, also return a PlotValues as the second
output value.
Return loaded results
"""
#from IPython.core.debugger import Tracer
#Tracer()()
results = glo.ex_load_result(ex, fname)
def rej_accessor(jr):
rej = jr['test_result']['h0_rejected']
# When used with vectorize(), making the value float will make the resulting
# numpy array to be of float. nan values can be stored.
return float(rej)
#value_accessor = lambda job_results: job_results['test_result']['h0_rejected']
vf_pval = np.vectorize(rej_accessor)
# results['job_results'] is a dictionary:
# {'test_result': (dict from running perform_test(te) '...':..., }
rejs = vf_pval(results['job_results'])
repeats, _, n_methods = results['job_results'].shape
# yvalues (corresponding to xvalues) x #methods
mean_rejs = np.mean(rejs, axis=0)
#print mean_rejs
#std_pvals = np.std(rejs, axis=0)
#std_pvals = np.sqrt(mean_rejs*(1.0-mean_rejs))
xvalues = func_xvalues(results)
#ns = np.array(results[xkey])
#te_proportion = 1.0 - results['tr_proportion']
#test_sizes = ns*te_proportion
line_styles = func_plot_fmt_map()
method_labels = get_func2label_map()
func_names = [f.__name__ for f in results['method_funcs']]
plotted_methods = []
for i in range(n_methods):
#te_proportion = 1.0 - results['tr_proportion']
fmt = line_styles[func_names[i]]
#plt.errorbar(ns*te_proportion, mean_rejs[:, i], std_pvals[:, i])
method_label = method_labels[func_names[i]]
plotted_methods.append(method_label)
plt.plot(xvalues, mean_rejs[:, i], fmt, label=method_label)
'''
else:
# h0 is true
z = stats.norm.isf( (1-confidence)/2.0)
for i in range(n_methods):
phat = mean_rejs[:, i]
conf_iv = z*(phat*(1-phat)/repeats)**0.5
#plt.errorbar(test_sizes, phat, conf_iv, fmt=line_styles[i], label=method_labels[i])
plt.plot(test_sizes, mean_rejs[:, i], line_styles[i], label=method_labels[i])
'''
ylabel = 'Rejection rate'
plt.ylabel(ylabel)
plt.xlabel(xlabel)
plt.xticks(np.hstack((xvalues)))
alpha = results['alpha']
plt.legend(loc='best')
title = '%s. %d trials. $\\alpha$ = %.2g.' % (
results['prob_label'], repeats,
alpha) if func_title is None else func_title(results)
plt.title(title)
plt.grid()
if return_plot_values:
return results, PlotValues(xvalues=xvalues,
methods=plotted_methods,
plot_matrix=mean_rejs.T)
else:
return results