def __iter__(self):
pid_iterators = [ps.filtered_pid_iterator(set_hard_coded_key_dec(ps.filtered_pid_iterator,'surgpids')(ps.all_ucla_pid_iterator(), ps.bin_f(ps.ucla_treatment_f(),ps.equals_bin([ps.ucla_treatment_f.surgery]))), ps.is_good_pid())]
#pid_iterators = [ps.all_ucla_pid_iterator()]
#filter_fs = [hard_coded_filter_fs.old_filter_f]
filter_fs = [ps.always_true_f()]
#filtered_data_fs = [ps.generic_filtered_get_data_f(filter_f) for filter_f in filter_fs]
upscale_vals = [0]
diffcovs_iters = [1000]
diffcovs_numchains = [1]
diffcovs_seeds = [1]
perf_percentiles = [[0.25, 0.5, 0.75]]
perf_times = [[1,2,4,8,12,18,24,30,36,42,48]]
get_pops_fs = [ps.train_better_pops_f()]
summarize_fs = [ps.get_param_mean_f()]
cv_fs = [ps.cv_fold_f(3)]
upscale_vals = [0.0] #
ys_fs = [ps.modified_ys_f(ps.ys_f(ps.ys_f.sexual_function), ps.score_modifier_f(c)) for c in upscale_vals]
post_process_fs = [ps.normalized_data_f()]
actual_ys_f_shifts = [1]
loss_fs = [ps.scaled_logistic_loss_f(10.0)]
feature_sets_iterator = [hard_coded_feature_sets.default_simple_indicators]
hypers = [hard_coded_hypers.default_hyper]
x_abc_fs = ps.keyed_list([set_hard_coded_key_dec(ps.x_abc_fs, feature_set.get_key())(feature_set, feature_set, feature_set) for feature_set in feature_sets_iterator])
return itertools.product(pid_iterators, filter_fs, diffcovs_iters, diffcovs_numchains, diffcovs_seeds, perf_percentiles, perf_times, get_pops_fs, summarize_fs, cv_fs, ys_fs, hypers, x_abc_fs, loss_fs, actual_ys_f_shifts, post_process_fs)
def __iter__(self):
pid_iterators = [set_hard_coded_key_dec(ps.filtered_pid_iterator,'surgpids')(ps.all_ucla_pid_iterator(), ps.bin_f(ps.ucla_treatment_f(),ps.equals_bin([ps.ucla_treatment_f.surgery])))]
filtered_data_fs = [ps.old_filtered_get_data_f(), ps.medium_filtered_get_data_f(), ps.filtered_get_data_f()]
upscale_vals = [0]
diffcovs_iters = [5000]
diffcovs_numchains = [4]
diffcovs_seeds = [1]
perf_percentiles = [[0.25, 0.5, 0.75]]
get_pops_fs = [ps.train_better_pops_f()]
summarize_fs = [ps.get_param_mean_f()]
cv_fs = [ps.cv_fold_f(4)]
upscale_vals = [0.0] #
perf_times = [[1,2,4,8,12,18,24,30,36,42,48]]
ys_fs = [ps.modified_ys_f(ps.ys_f(ps.ys_f.sexual_function), ps.score_modifier_f(c)) for c in upscale_vals]
actual_ys_f_shifts = [0,1]
loss_fs = [ps.scaled_logistic_loss_f(10.0)]
feature_sets_iterator = [hard_coded_feature_sets.default_initial_categorical_f, hard_coded_feature_sets.medium_initial_categorical_f, hard_coded_feature_sets.highminus_initial_categorical_f, hard_coded_feature_sets.high_initial_categorical_f, hard_coded_feature_sets.higher_initial_categorical_f]
hypers = [hard_coded_hypers.default_hyper]
x_abc_fs = ps.keyed_list([set_hard_coded_key_dec(ps.x_abc_fs, feature_set.get_key())(feature_set, feature_set, feature_set) for feature_set in feature_sets_iterator])
return itertools.product(pid_iterators, filtered_data_fs, diffcovs_iters, diffcovs_numchains, diffcovs_seeds, perf_percentiles, perf_times, get_pops_fs, summarize_fs, cv_fs, ys_fs, hypers, x_abc_fs, loss_fs, actual_ys_f_shifts)
def param_to_datasets_and_trainers(pid_iterator, filtered_data_f, diffcovs_iter, diffcovs_numchains, diffcovs_seed, perf_percentiles, perf_times, get_pops_f, summarize_f, cv_f, ys_f, hypers, x_abc_f, loss_f):
get_posterior_f = ps.get_diffcovs_posterior_f(get_pops_f, hypers, diffcovs_iter, diffcovs_numchains, diffcovs_seed)
diffcovs_trainer = ps.get_diffcovs_point_predictor_f(get_posterior_f, summarize_f)
prior_trainer = ps.get_prior_predictor_f(get_pops_f)
logreg_trainer = ps.get_logreg_predictor_f(perf_times)
init_f = ps.set_hard_coded_key_dec(ps.s_f, 'init')(ys_f)
data = ps.get_data_f(x_abc_f, init_f, ps.after_0_ys_f(ys_f))(pid_iterator)
filtered_data = filtered_data_f(data)
return ps.keyed_list([prior_trainer, logreg_trainer, diffcovs_trainer]), cv_f, loss_f, perf_percentiles, perf_times, filtered_data
def plot_model_performances(the_iterable):
for (
pid_iterator,
filter_f,
diffcovs_iter,
diffcovs_numchains,
diffcovs_seed,
perf_percentiles,
perf_times,
get_pops_f,
summarize_f,
cv_f,
ys_f,
hypers,
x_abc_f,
loss_f,
actual_ys_f_shift,
post_process_f,
) in the_iterable:
try:
get_posterior_f = ps.get_pystan_diffcovs_posterior_f(
get_pops_f, hypers, diffcovs_iter, diffcovs_numchains, diffcovs_seed
)
diffcovs_trainer = ps.get_diffcovs_point_predictor_f(get_posterior_f, summarize_f)
prior_trainer = ps.get_prior_predictor_f(get_pops_f)
shifted_perf_times = [t - actual_ys_f_shift for t in perf_times]
logreg_trainer = ps.get_logreg_predictor_f(shifted_perf_times)
trainers = ps.keyed_list([prior_trainer, logreg_trainer, diffcovs_trainer])
init_f = ps.set_hard_coded_key_dec(ps.s_f, "init")(ys_f)
actual_ys_f = ps.actual_ys_f(ys_f, actual_ys_f_shift)
data = ps.get_data_f(x_abc_f, init_f, actual_ys_f)(pid_iterator)
filtered_data = ps.generic_filtered_get_data_f(filter_f)(data)
filtered_data = post_process_f(filtered_data)
ps.model_comparer_f(trainers, cv_f, loss_f, perf_percentiles, shifted_perf_times)(filtered_data)
except Exception, e:
for frame in traceback.extract_tb(sys.exc_info()[2]):
fname, lineno, fn, text = frame
print "Error in %s on line %d" % (fname, lineno)
print e
pdb.set_trace()
pass
def plot_predicted_patient_curves(the_iterable):
for (
pid_iterator,
filtered_data_f,
diffcovs_iter,
diffcovs_numchains,
diffcovs_seed,
perf_percentiles,
perf_times,
get_pops_f,
summarize_f,
cv_f,
ys_f,
hypers,
x_abc_f,
loss_f,
actual_ys_f_shift,
post_process_f,
) in the_iterable:
try:
get_posterior_f = ps.get_pystan_diffcovs_posterior_f(
get_pops_f, hypers, diffcovs_iter, diffcovs_numchains, diffcovs_seed
)
diffcovs_trainer = ps.get_diffcovs_point_predictor_f(get_posterior_f, summarize_f)
prior_trainer = ps.get_prior_predictor_f(get_pops_f)
shifted_perf_times = [t - actual_ys_f_shift for t in perf_times]
logreg_trainer = ps.get_logreg_predictor_f(shifted_perf_times)
init_f = ps.set_hard_coded_key_dec(ps.s_f, "init")(ys_f)
actual_ys_f = ps.actual_ys_f(ys_f, actual_ys_f_shift)
data = ps.get_data_f(x_abc_f, init_f, actual_ys_f)(pid_iterator)
filtered_data = ps.generic_filtered_get_data_f(filter_f)(data)
filtered_data = post_process_f(filtered_data)
ps.plot_all_predictions_fig_f(
ps.keyed_list([prior_trainer, logreg_trainer, diffcovs_trainer]), cv_f, shifted_perf_times
)(filtered_data)
except:
pass
