def main(argv):
num_threads = 1
num_runs = 30
try:
opts, args = getopt.getopt(argv,"f:z:a:b:c:s:m:r:t:")
except getopt.GetoptError:
print "Bad Arguments to python script"
sys.exit(2)
settings = Elastic_Net_Settings()
for opt, arg in opts:
if opt == '-f':
settings.num_features = int(arg)
elif opt == '-z':
settings.num_nonzero_features = int(arg)
elif opt == '-a':
settings.train_size = int(arg)
elif opt == '-b':
settings.validate_size = int(arg)
elif opt == '-c':
settings.test_size = int(arg)
elif opt == "-s":
settings.snr = float(arg)
elif opt == "-m":
assert(arg in METHODS)
settings.method = arg
elif opt == "-t":
num_threads = int(arg)
elif opt == "-r":
num_runs = int(arg)
settings.print_settings()
sys.stdout.flush()
data_gen = DataGenerator(settings)
run_data = []
for i in range(num_runs):
observed_data = data_gen.make_correlated(settings.num_features, settings.num_nonzero_features)
run_data.append(Iteration_Data(i, observed_data, settings))
if settings.method not in ["SP", "SP0"] and num_threads > 1:
print "Do multiprocessing"
pool = Pool(num_threads)
results = pool.map(fit_data_for_iter_safe, run_data)
else:
print "Avoiding multiprocessing"
results = map(fit_data_for_iter_safe, run_data)
method_results = MethodResults(settings.method, settings.method_result_keys)
num_crashes = 0
for r in results:
if r is not None:
method_results.append(r)
else:
num_crashes += 1
print "==========TOTAL RUNS %d============" % method_results.get_num_runs()
method_results.print_results()
print "num crashes %d" % num_crashes
def main(argv):
seed = 10
print "seed", seed
np.random.seed(seed)
num_threads = 1
num_runs = 1
try:
opts, args = getopt.getopt(argv, "m:t:r:")
except getopt.GetoptError:
print "Bad argument given to realdata_eval.py"
sys.exit(2)
settings = RealDataSettings()
for opt, arg in opts:
if opt == "-m":
assert (arg in ["HC", "GS"])
settings.method = arg
elif opt == "-t":
num_threads = int(arg)
elif opt == "-r":
num_runs = int(arg)
print "TOTAL NUM RUNS %d" % num_runs
sys.stdout.flush()
geneset_dict = read_geneset_file()
X_genesets, y, genesets = read_gene_expr_data(geneset_dict)
print "num features", sum(
[X_genesets[i].shape[1] for i in range(0, len(X_genesets))])
print "total genesets ever", len(X_genesets)
X_genesets = normalize_data(X_genesets)
run_data = []
for i in range(num_runs):
data = Shuffled_Gene_Data(X_genesets, y, genesets)
run_data.append(Iteration_Data(i, data, settings))
if num_threads > 1:
print "Do multiprocessing"
pool = Pool(num_threads)
results = pool.map(fit_data_for_iter_safe, run_data)
else:
print "Avoiding multiprocessing"
results = map(fit_data_for_iter_safe, run_data)
method_results = MethodResults(settings.method,
settings.method_result_keys)
num_crashes = 0
for r in results:
if r is not None:
method_results.append(r)
else:
num_crashes += 1
print "==========TOTAL RUNS %d============" % method_results.get_num_runs()
method_results.print_results()
print "num crashes %d" % num_crashes
def fit_penalized(self,
train_set,
penalty_params,
max_em_iters,
val_set_evaluator=None,
init_theta=None,
reference_pen_param=None,
pool=None):
"""
@param penalty_params: penalty parameter for fitting penalized model
@param val_set_evaluator: LikelihoodComparer with a given reference model
@param reference_pen_param: the penalty parameters for the reference model
@return the fitted model after the 2-step procedure
"""
if init_theta is None:
init_theta = initialize_theta(self.theta_shape,
self.possible_theta_mask,
self.zero_theta_mask)
penalized_theta, _, _, _ = self.em_algo.run(
train_set,
self.feat_generator,
theta=init_theta,
possible_theta_mask=self.possible_theta_mask,
zero_theta_mask=self.zero_theta_mask,
burn_in=self.burn_in,
penalty_params=penalty_params,
max_em_iters=max_em_iters,
max_e_samples=self.num_e_samples * 4,
pool=pool,
)
curr_model_results = MethodResults(penalty_params)
#### Calculate validation log likelihood (EM surrogate), use to determine if model is any good.
log_lik_ratio_lower_bound, log_lik_ratio = self._do_validation_set_checks(
penalized_theta,
val_set_evaluator,
)
curr_model_results.set_penalized_theta(
penalized_theta,
log_lik_ratio_lower_bound,
log_lik_ratio,
model_masks=ModelTruncation(penalized_theta, self.feat_generator),
reference_penalty_param=reference_pen_param,
)
log.info("==== Penalized theta, %s, nonzero %d ====" %
(penalty_params, curr_model_results.penalized_num_nonzero))
log.info(
get_nonzero_theta_print_lines(penalized_theta,
self.feat_generator))
return curr_model_results
def main(argv):
seed = 10
print "seed", seed
np.random.seed(seed)
num_threads = 1
num_runs = 1
try:
opts, args = getopt.getopt(argv, "g:f:a:b:c:s:m:t:r:i")
except getopt.GetoptError:
print "Bad argument given to sgl_eval.py"
sys.exit(2)
settings = SGL_Settings()
for opt, arg in opts:
if opt == '-g':
settings.expert_num_groups = int(arg)
elif opt == '-f':
settings.num_features = int(arg)
elif opt == '-a':
settings.train_size = int(arg)
elif opt == '-b':
settings.validate_size = int(arg)
elif opt == '-c':
settings.test_size = int(arg)
elif opt == "-s":
settings.snr = float(arg)
elif opt == "-m":
assert (arg in METHODS)
settings.method = arg
elif opt == "-t":
num_threads = int(arg)
elif opt == "-r":
num_runs = int(arg)
print "TOTAL NUM RUNS %d" % num_runs
settings.print_settings()
sys.stdout.flush()
data_gen = DataGenerator(settings)
run_data = []
for i in range(num_runs):
observed_data = data_gen.sparse_groups()
run_data.append(Iteration_Data(i, observed_data, settings))
if settings.method != "SP" and num_threads > 1:
print "Do multiprocessing"
pool = Pool(num_threads)
results = pool.map(fit_data_for_iter_safe, run_data)
else:
print "Avoiding multiprocessing"
results = map(fit_data_for_iter_safe, run_data)
method_results = MethodResults(settings.method,
settings.method_result_keys)
num_crashes = 0
for r in results:
if r is not None:
method_results.append(r)
else:
num_crashes += 1
print "==========TOTAL RUNS %d============" % method_results.get_num_runs()
method_results.print_results()
print "num crashes %d" % num_crashes
def main(argv):
seed = 10
print "seed", seed
np.random.seed(seed)
num_threads = 1
num_runs = 1
try:
opts, args = getopt.getopt(argv, "d:z:f:a:v:s:m:t:r:i")
except getopt.GetoptError:
print "Bad argument given to Matrix_Completion_eval.py"
sys.exit(2)
settings = Matrix_Completion_Settings()
for opt, arg in opts:
if opt == '-d':
arg_split = arg.split(",")
settings.num_rows = int(arg_split[0])
settings.num_cols = int(arg_split[1])
elif opt == '-z':
arg_split = arg.split(",")
settings.num_nonzero_row_features = int(arg_split[0])
settings.num_nonzero_col_features = int(arg_split[1])
elif opt == '-f':
arg_split = arg.split(",")
settings.num_row_features = int(arg_split[0])
settings.num_col_features = int(arg_split[1])
elif opt == '-a':
arg_split = arg.split(",")
settings.train_perc = float(arg_split[0])
settings.validate_perc = float(arg_split[1])
settings.test_perc = float(arg_split[2])
assert (settings.train_perc + settings.validate_perc +
settings.test_perc < 1)
elif opt == "-v":
settings.num_nonzero_s = int(arg)
elif opt == "-s":
settings.snr = float(arg)
elif opt == "-m":
assert (arg in METHODS)
settings.method = arg
elif opt == "-t":
num_threads = int(arg)
elif opt == "-r":
num_runs = int(arg)
elif opt == "-i":
settings.big_init_set = True
assert (settings.num_nonzero_s <= settings.num_rows
and settings.num_nonzero_s <= settings.num_cols)
# SP does not care about initialization
assert (not (settings.big_init_set == True
and settings.method in ["SP", "SP0"]))
settings.matrix_size = settings.num_rows * settings.num_cols
settings.train_size = int(settings.train_perc * settings.matrix_size)
settings.validate_size = int(settings.validate_perc * settings.matrix_size)
settings.test_size = int(settings.test_perc * settings.matrix_size)
print "TOTAL NUM RUNS %d" % num_runs
settings.print_settings()
sys.stdout.flush()
data_gen = DataGenerator(settings)
run_data = []
for i in range(num_runs):
observed_data = data_gen.matrix_completion()
run_data.append(Iteration_Data(i, observed_data, settings))
if settings.method != "SP" and num_threads > 1:
print "Do multiprocessing"
pool = Pool(num_threads)
results = pool.map(fit_data_for_iter_safe, run_data)
else:
print "Avoiding multiprocessing"
results = map(fit_data_for_iter_safe, run_data)
method_results = MethodResults(settings.method,
settings.method_result_keys)
num_crashes = 0
for r in results:
if r is not None:
method_results.append(r)
else:
num_crashes += 1
print "==========TOTAL RUNS %d============" % method_results.get_num_runs()
method_results.print_results()
print "num crashes %d" % num_crashes
def main(argv):
num_threads = 1
num_runs = 1
try:
opts, args = getopt.getopt(argv, "d:z:f:g:a:v:s:m:t:r:i:")
except getopt.GetoptError:
print "Bad argument given"
sys.exit(2)
settings = Matrix_Completion_Group_Settings()
for opt, arg in opts:
if opt == '-d':
arg_split = arg.split(",")
settings.num_rows = int(arg_split[0])
settings.num_cols = int(arg_split[1])
elif opt == '-z':
arg_split = arg.split(",")
settings.num_nonzero_row_groups = int(arg_split[0])
settings.num_nonzero_col_groups = int(arg_split[1])
elif opt == '-f':
arg_split = arg.split(",")
settings.num_row_features = int(arg_split[0])
settings.num_col_features = int(arg_split[1])
elif opt == '-g':
arg_split = arg.split(",")
settings.num_row_groups = int(arg_split[0])
settings.num_col_groups = int(arg_split[1])
elif opt == '-a':
arg_split = arg.split(",")
settings.train_perc = float(arg_split[0])
settings.validate_perc = float(arg_split[1])
assert (settings.train_perc + settings.validate_perc <= 1.0)
elif opt == "-v":
settings.num_nonzero_s = int(arg)
elif opt == "-s":
settings.snr = float(arg)
elif opt == "-m":
assert (arg in METHODS)
settings.method = arg
elif opt == "-t":
num_threads = int(arg)
elif opt == "-r":
num_runs = int(arg)
elif opt == "-i":
settings.gamma_to_row_col_m = float(arg)
assert (settings.num_nonzero_s <= settings.num_rows
and settings.num_nonzero_s <= settings.num_cols)
settings.matrix_size = settings.num_rows * settings.num_cols
print "TOTAL NUM RUNS %d" % num_runs
settings.print_settings()
sys.stdout.flush()
data_gen = DataGenerator(settings)
run_data = []
for i in range(num_runs):
observed_data = data_gen.matrix_completion_groups(
gamma_to_row_col_m=settings.gamma_to_row_col_m,
feat_factor=settings.feat_factor)
run_data.append(Iteration_Data(i, observed_data, settings))
if settings.method != "SP" and num_threads > 1:
print "Do multiprocessing"
pool = Pool(num_threads)
results = pool.map(fit_data_for_iter_safe, run_data)
else:
print "Avoiding multiprocessing"
results = map(fit_data_for_iter_safe, run_data)
method_results = MethodResults(settings.method,
settings.method_result_keys)
num_crashes = 0
for r in results:
if r is not None:
method_results.append(r)
else:
num_crashes += 1
print "==========TOTAL RUNS %d============" % method_results.get_num_runs()
method_results.print_results()
print "num crashes %d" % num_crashes
def main(argv):
num_threads = 1
num_runs = 1
try:
opts, args = getopt.getopt(argv, "f:z:a:b:c:s:m:t:r:")
except getopt.GetoptError:
sys.exit(2)
settings = Sparse_Add_Models_Settings()
for opt, arg in opts:
if opt == '-f':
settings.num_funcs = int(arg)
elif opt == '-z':
settings.num_zero_funcs = int(arg)
elif opt == '-a':
settings.train_size = int(arg)
elif opt == '-b':
settings.validate_size = int(arg)
elif opt == '-c':
settings.test_size = int(arg)
elif opt == "-s":
settings.snr = float(arg)
elif opt == "-m":
assert (arg in METHODS)
settings.method = arg
elif opt == "-t":
num_threads = int(arg)
elif opt == "-r":
num_runs = int(arg)
print "TOTAL NUM RUNS %d" % num_runs
settings.print_settings()
sys.stdout.flush()
assert (settings.num_funcs <= len(settings.smooth_fcns))
smooth_fcn_list = settings.smooth_fcns[:settings.num_funcs] + [
const_zero
] * settings.num_zero_funcs
data_gen = DataGenerator(settings)
run_data = []
for i in range(num_runs):
observed_data = data_gen.make_additive_smooth_data(smooth_fcn_list)
run_data.append(Iteration_Data(i, observed_data, settings))
if settings.method != "SP" and num_threads > 1:
print "Do multiprocessing"
pool = Pool(num_threads)
results = pool.map(fit_data_for_iter_safe, run_data)
else:
print "Avoiding multiprocessing"
results = map(fit_data_for_iter_safe, run_data)
method_results = MethodResults(settings.method,
settings.method_result_keys)
num_crashes = 0
for r in results:
if r is not None:
method_results.append(r)
else:
num_crashes += 1
print "==========TOTAL RUNS %d============" % method_results.get_num_runs()
method_results.print_results()
print "num crashes %d" % num_crashes
