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):
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 main(argv):
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 = Simulation_Settings()
settings.results_folder = "results/realdata"
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 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
import gridsearch_interaction_effects
GENERATE_PLOT = False
NUM_RUNS = 15
# TRAIN_SIZE = 70
# NUM_EFFECTS = 40
# NUM_NONZERO_EFFECTS = 3
# NUM_NONZERO_INTERACTIONS = 300
TRAIN_SIZE = 40
NUM_EFFECTS = 20
NUM_NONZERO_EFFECTS = 3
NUM_NONZERO_INTERACTIONS = 40
hc_results = MethodResults("Hillclimb")
mu_results = MethodResults("MU")
gs_results = MethodResults("Gridsearch")
for i in range(0, NUM_RUNS):
beta_real, theta_real, X_train, W_train, y_train, X_validate, W_validate, y_validate, X_test, W_test, y_test = \
effects_and_interactions(TRAIN_SIZE, NUM_EFFECTS, NUM_NONZERO_EFFECTS, NUM_NONZERO_INTERACTIONS)
def _get_test_beta_theta_err(beta_guess, theta_guess):
test_err = testerror_interactions(X_test, W_test, y_test, beta_guess, theta_guess) / y_test.size * 2
beta_err = betaerror(beta_real, beta_guess)
theta_err = betaerror(theta_guess, theta_real)
return (test_err, beta_err, theta_err)
hc_beta_guess, hc_theta_guess, hc_costpath = hillclimb_interaction_effects.run(X_train, W_train, y_train, X_validate, W_validate, y_validate)
hc_results.append_test_beta_theta_err(_get_test_beta_theta_err(hc_beta_guess, hc_theta_guess))
def main(argv):
seed = 10
print "seed", seed
np.random.seed(seed)
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):
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():
SMOOTH_FCNS = [big_sin, identity_fcn, big_cos_sin, crazy_down_sin, pwr_small]
smooth_fcn_list = SMOOTH_FCNS[:NUM_FUNCS]
hc_results = MethodResults("Hillclimb")
hc_nesterov_results = MethodResults("Hillclimb_nesterov")
gs_results = MethodResults("Gridsearch")
for i in range(0, NUM_RUNS):
# Generate dataset
X_train, y_train, X_validate, y_validate, X_test, y_test = multi_smooth_features(
TRAIN_SIZE,
smooth_fcn_list,
desired_snr=SNR,
feat_range=[f * TRAIN_SIZE/60 for f in FEATURE_RANGE],
train_to_validate_ratio=VALIDATE_RATIO,
test_size=NUM_TEST
)
X_full, train_idx, validate_idx, test_idx = GenAddModelHillclimb.stack((X_train, X_validate, X_test))
def _create_method_result(best_thetas, runtime):
test_err = testerror_multi_smooth(y_test, test_idx, best_thetas)
validate_err = testerror_multi_smooth(y_validate, validate_idx, best_thetas)
print "create_method_result", test_err
return MethodResult(test_err=test_err, validation_err=validate_err, runtime=runtime)
def _run_hc(results, nesterov):
hillclimb_prob = GenAddModelHillclimb(X_train, y_train, X_validate, y_validate, X_test, nesterov=nesterov)
thetas, cost_path, runtime = _hillclimb_coarse_grid_search(hillclimb_prob, smooth_fcn_list)
results.append(_create_method_result(thetas, runtime))
if PLOT_RUNS:
_plot_res(
thetas[test_idx], smooth_fcn_list, X_test, y_test,
outfile="%s/test_%s_f%d.png" % (FIGURE_DIR, hillclimb_prob.method_label, NUM_FUNCS),
)
_plot_res(
thetas[validate_idx], smooth_fcn_list, X_validate, y_validate,
outfile="%s/validation_%s_f%d.png" % (FIGURE_DIR, hillclimb_prob.method_label, NUM_FUNCS),
)
_plot_res(
thetas[train_idx], smooth_fcn_list, X_train, y_train,
outfile="%s/train_%s_f%d.png" % (FIGURE_DIR, hillclimb_prob.method_label, NUM_FUNCS),
)
return thetas, cost_path
hc_thetas, hc_cost_path = _run_hc(hc_results, nesterov=False)
# hc_nesterov_thetas, hc_nesterov_cost_path = _run_hc(hc_nesterov_results, nesterov=True)
if PLOT_RUNS:
_plot_cost_paths(
cost_path_list=[hc_cost_path, hc_nesterov_cost_path],
labels=["HC", "HC_Nesterov"],
num_funcs=NUM_FUNCS,
)
print "=================================================="
start_time = time.time()
gs_thetas, best_lambdas = gs.run(
y_train,
y_validate,
X_full,
train_idx,
validate_idx,
num_lambdas=NUM_GS_LAMBDAS,
max_lambda=MAX_LAMBDA
)
gs_runtime = time.time() - start_time
gs_results.append(_create_method_result(gs_thetas, gs_runtime))
if PLOT_RUNS:
_plot_res(
gs_thetas[test_idx], smooth_fcn_list, X_test, y_test,
outfile="%s/test_gs_f%d.png" % (FIGURE_DIR, NUM_FUNCS),
)
_plot_gs_v_hc(
gs_thetas[train_idx], hc_thetas[train_idx], smooth_fcn_list, X_train, y_train,
outfile_prefix="%s/train_gs_v_hc_f%d" % (FIGURE_DIR, NUM_FUNCS),
)
print "===========RUN %d ============" % i
hc_results.print_results()
hc_nesterov_results.print_results()
gs_results.print_results()
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
def main():
seed = int(np.random.rand() * 1e15)
print "seed", seed
np.random.seed(seed)
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)
hc_results = MethodResults("HC")
gs_grouped_results = MethodResults("GS_Grouped")
gs_results = MethodResults("GS_Lasso")
for i in range(0, NUM_ITERS):
X_groups_train, y_train, X_groups_validate, y_validate, X_groups_test, y_test = shuffle_and_split_data(
X_genesets, y, TRAIN_SIZE, VALIDATE_SIZE)
X_validate = np.hstack(X_groups_validate)
X_test = np.hstack(X_groups_test)
start = time.time()
hc_betas, hc_cost_path = hc.run_for_lambdas(X_groups_train, y_train, X_groups_validate, y_validate, init_lambdas=INIT_LAMBDAS)
hc_runtime = time.time() - start
print "hc 1e-6", get_num_nonzero_betas(hc_betas, genesets, threshold=1e-6)
print "hc 1e-8", get_num_nonzero_betas(hc_betas, genesets, threshold=1e-8)
print "hc 1e-10", get_num_nonzero_betas(hc_betas, genesets, threshold=1e-10)
hc_validate_cost, hc_validate_rate = testerror_logistic_grouped(X_validate, y_validate, hc_betas)
print "hc_validate_cost", hc_validate_cost
start = time.time()
gs_grouped_betas, gs_grouped_cost = gs_grouped.run_classify(X_groups_train, y_train, X_groups_validate, y_validate)
gs_grouped_runtime = time.time() - start
print "gs_grouped 1e-6", get_num_nonzero_betas(gs_grouped_betas, genesets, threshold=1e-6)
print "gs_grouped 1e-8", get_num_nonzero_betas(gs_grouped_betas, genesets, threshold=1e-8)
print "gs_grouped 1e-10", get_num_nonzero_betas(gs_grouped_betas, genesets, threshold=1e-10)
gs_grouped_validate_cost, gs_grouped_validate_rate = testerror_logistic_grouped(X_validate, y_validate, gs_grouped_betas)
print "gs_grouped_validate_cost", gs_grouped_validate_cost
start = time.time()
gs_betas, gs_cost = gs.run_classify(X_groups_train, y_train, X_groups_validate, y_validate)
gs_runtime = time.time() - start
print "gs 1e-6", get_num_nonzero_betas(gs_betas, genesets, threshold=1e-6)
print "gs 1e-8", get_num_nonzero_betas(gs_betas, genesets, threshold=1e-8)
print "gs 1e-10", get_num_nonzero_betas(gs_betas, genesets, threshold=1e-10)
gs_validate_cost, gs_validate_rate = testerror_logistic_grouped(X_validate, y_validate, gs_betas)
print "gs_validate_cost", gs_validate_cost
print "================= hc ======================"
hc_test, hc_rate = testerror_logistic_grouped(X_test, y_test, hc_betas)
print "hc_test", hc_test, "hc_rate", hc_rate
hc_results.append(MethodResult(test_err=hc_test, validation_err=hc_validate_cost, sensitivity=hc_rate, runtime=hc_runtime))
print "================= gs grouped ======================"
gs_grouped_test, gs_grouped_rate = testerror_logistic_grouped(X_test, y_test, gs_grouped_betas)
print "gs_grouped_test", gs_grouped_test, "gs_grouped_rate", gs_grouped_rate
gs_grouped_results.append(MethodResult(test_err=gs_grouped_test, validation_err=gs_grouped_validate_cost, sensitivity=gs_grouped_rate, runtime=gs_grouped_runtime))
print "================= gs ======================"
gs_test, gs_rate = testerror_logistic_grouped(X_test, y_test, gs_betas)
print "gs_test", gs_test, "gs_rate", gs_rate
gs_results.append(MethodResult(test_err=gs_test, validation_err=gs_validate_cost, sensitivity=gs_rate, runtime=gs_runtime))
print "ITERATION", i
hc_results.print_results()
gs_grouped_results.print_results()
gs_results.print_results()
if i == 0:
pickle_data(PICKLE_DATA_FILENAME, X_groups_train, y_train, X_groups_validate, y_validate, X_groups_test, y_test, genesets)
pickle_betas(PICKLE_BETAS_FILENAME, hc_betas, gs_grouped_betas, gs_betas)
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:")
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)
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
for init_lambda1 in COARSE_LAMBDA_GRID:
kwargs["initial_lambda1"] = init_lambda1
kwargs["initial_lambda2"] = init_lambda1
beta_guess, cost_path = optimization_func(*args, **kwargs)
validation_cost = testerror(X_validate, y_validate, beta_guess)
if best_cost > validation_cost:
best_start_lambdas = [kwargs["initial_lambda1"], kwargs["initial_lambda2"]]
best_cost = validation_cost
best_beta = beta_guess
best_cost_path = cost_path
end_time = time.time()
print "HC: BEST best_cost", best_cost, "best_start_lambdas", best_start_lambdas
return beta_guess, cost_path, end_time - start_time
hc_results = MethodResults(HC_LAMBDA12_LABEL)
hc_results1 = MethodResults(HC_LAMBDA12_LABEL + "_SHRINK")
hc_dim_results = MethodResults(HC_LAMBDA12_DIM_LABEL)
hc_nesterov_results = MethodResults(HC_LAMBDA12_NESTEROV_LABEL)
hc_lambda_alpha_results = MethodResults(HC_LAMBDA_ALPHA_LABEL)
hc_lambda_alpha_results1 = MethodResults(HC_LAMBDA_ALPHA_LABEL + "_SHRINK")
hc_lambda_alpha_dim_results = MethodResults(HC_LAMBDA_ALPHA_DIM_LABEL)
hc_lambda_alpha_nesterov_results = MethodResults(HC_LAMBDA_ALPHA_NESTEROV_LABEL)
nm_results = MethodResults("NELDER-MEAD")
bs_results = MethodResults("BAYES_SPEARMINT")
gs_results = MethodResults(GS_LAMBDA12_LABEL)
for i in range(0, NUM_RUNS):
beta_real, X_train, y_train, X_validate, y_validate, X_test, y_test = data_generation.correlated(
TRAIN_SIZE, NUM_FEATURES, NUM_NONZERO_FEATURES, signal_noise_ratio=SIGNAL_NOISE_RATIO)
def _create_method_result(beta_guess, runtime):
def main(argv):
seed = 10
print "seed", seed
np.random.seed(seed)
num_threads = 1
num_runs = 1
try:
opts, args = getopt.getopt(argv,"f:z:a:b:c:s:m:t:r:i")
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)
elif opt == "-i":
settings.big_init_set = True
# SP does not care about initialization
assert(not (settings.big_init_set == True and settings.method in ["SP", "SP0"]))
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
def main(argv):
try:
opts, args = getopt.getopt(argv,"d:p")
except getopt.GetoptError:
print "BAD REQUEST"
print "accepts a folder name. reads the XML files inside"
sys.exit(2)
RUN_HC_POOLED = False
for opt, arg in opts:
if opt == '-d':
data_type = int(arg)
if data_type == 0:
TRAIN_SIZE = 10
TOTAL_FEATURES = 30
NUM_GROUPS = 3
elif data_type == 1:
TRAIN_SIZE = 60
TOTAL_FEATURES = 300
NUM_GROUPS = 30
elif data_type == 2:
TRAIN_SIZE = 90
TOTAL_FEATURES = 900
NUM_GROUPS = 60
elif data_type == 3:
TRAIN_SIZE = 90
TOTAL_FEATURES = 1200
NUM_GROUPS = 100
elif opt == '-p':
RUN_HC_POOLED = True
TRUE_GROUP_FEATURE_SIZES = [TOTAL_FEATURES / TRUE_NUM_GROUPS] * TRUE_NUM_GROUPS
EXPERT_KNOWLEDGE_GROUP_FEATURE_SIZES = [TOTAL_FEATURES / NUM_GROUPS] * NUM_GROUPS
COARSE_LAMBDA1S = [1, 1e-1]
if RUN_HC_POOLED:
print "RUN POOLED FOR GS and HC"
else:
print "UNPOOLED VS. POOLED"
seed = np.random.randint(0, 1e5)
seed = 10
np.random.seed(seed)
print "RANDOM SEED", seed
print "TRAIN_SIZE", TRAIN_SIZE
print "TOTAL_FEATURES", TOTAL_FEATURES
print "NUM_GROUPS", NUM_GROUPS
print "COARSE_LAMBDA1S", COARSE_LAMBDA1S
def _hillclimb_coarse_grid_search(optimization_func, *args, **kwargs):
start_time = time.time()
best_cost = 1e10
best_beta = []
best_cost_path = []
best_lambda = 0
for init_lambda in COARSE_LAMBDA1S:
kwargs["initial_lambda1"] = init_lambda
beta_guess, cost_path = optimization_func(*args, **kwargs)
if best_cost > cost_path[-1]:
best_cost = cost_path[-1]
best_cost_path = cost_path
best_beta = beta_guess
best_lambda = init_lambda
print "init_lambda better!", init_lambda
print "HC: best_cost", best_cost
sys.stdout.flush()
print "HC_FINAL: best_cost", best_cost, "best_lambda", best_lambda
end_time = time.time()
print "runtime", end_time - start_time
return best_beta, best_cost_path, end_time - start_time
hc_results = MethodResults(HC_GROUPED_LASSO_LABEL)
hc_nesterov_results = MethodResults("NESTEROV")
hc_pooled_results = MethodResults(HC_GROUPED_LASSO_LABEL + "_POOLED")
hc_pooled_nesterov_results = MethodResults("NESTEROV_POOLED")
nm_results = MethodResults("NELDER_MEAD")
gs_results = MethodResults(GS_GROUPED_LASSO_LABEL)
for i in range(0, NUM_RUNS):
beta_reals, X_train, y_train, X_validate, y_validate, X_test, y_test = sparse_groups(TRAIN_SIZE, TRUE_GROUP_FEATURE_SIZES)
def _create_method_result(beta_guesses, runtime):
test_err = testerror_grouped(X_test, y_test, beta_guesses)
validation_err = testerror_grouped(X_validate, y_validate, beta_guesses)
beta_guesses_all = np.concatenate(beta_guesses)
beta_reals_all = np.concatenate(beta_reals)
beta_err = betaerror(beta_reals_all, beta_guesses_all)
guessed_nonzero_elems = np.where(get_nonzero_indices(beta_guesses_all, threshold=ZERO_THRESHOLD))
true_nonzero_elems = np.where(get_nonzero_indices(beta_reals_all, threshold=ZERO_THRESHOLD))
intersection = np.intersect1d(np.array(guessed_nonzero_elems), np.array(true_nonzero_elems))
sensitivity = intersection.size / float(guessed_nonzero_elems[0].size) * 100
print "test_err", test_err, "beta_err", beta_err, "sensitivity", sensitivity
sys.stdout.flush()
return MethodResult(test_err=test_err, validation_err=validation_err, beta_err=beta_err, sensitivity=sensitivity, runtime=runtime)
if RUN_HC_POOLED:
hc_pooled_beta_guesses, hc_pooled_costpath, runtime = _hillclimb_coarse_grid_search(hc_pooled.run, X_train, y_train, X_validate, y_validate, EXPERT_KNOWLEDGE_GROUP_FEATURE_SIZES)
hc_pooled_results.append(_create_method_result(hc_pooled_beta_guesses, runtime))
# hc_pooled_nesterov_beta_guesses, hc_pooled_nesterov_costpath, runtime = _hillclimb_coarse_grid_search(hc_pooled.run_nesterov, X_train, y_train, X_validate, y_validate, EXPERT_KNOWLEDGE_GROUP_FEATURE_SIZES)
# hc_pooled_nesterov_results.append(_create_method_result(hc_pooled_nesterov_beta_guesses, runtime))
else:
hc_beta_guesses, hc_costpath, runtime = _hillclimb_coarse_grid_search(hc.run, X_train, y_train, X_validate, y_validate, EXPERT_KNOWLEDGE_GROUP_FEATURE_SIZES)
hc_results.append(_create_method_result(hc_beta_guesses, runtime))
# hc_nesterov_beta_guesses, hc_nesterov_costpath, runtime = _hillclimb_coarse_grid_search(hc.run_nesterov, X_train, y_train, X_validate, y_validate, EXPERT_KNOWLEDGE_GROUP_FEATURE_SIZES)
# hc_nesterov_results.append(_create_method_result(hc_nesterov_beta_guesses, runtime))
nm_beta_guesses, runtime = nm.run(X_train, y_train, X_validate, y_validate, EXPERT_KNOWLEDGE_GROUP_FEATURE_SIZES)
nm_results.append(_create_method_result(nm_beta_guesses, runtime))
start = time.time()
gs_beta_guesses, gs_lowest_cost = gridsearch_grouped_lasso.run(X_train, y_train, X_validate, y_validate, EXPERT_KNOWLEDGE_GROUP_FEATURE_SIZES)
runtime = time.time() - start
gs_results.append(_create_method_result(gs_beta_guesses, runtime))
print "NUM RUN", i
print "FEATURE GROUPS", TRUE_GROUP_FEATURE_SIZES
print "NUM_GROUPS", NUM_GROUPS
print "TRAIN SIZE", TRAIN_SIZE
if RUN_HC_POOLED:
hc_pooled_results.print_results()
nm_results.print_results()
hc_pooled_nesterov_results.print_results()
else:
hc_results.print_results()
nm_results.print_results()
hc_nesterov_results.print_results()
gs_results.print_results()
if GENERATE_PLOT and i == 0:
plt.clf()
if RUN_HC_POOLED:
plt.plot(hc_pooled_costpath, label="Gradient Descent", color="red")
plt.plot(hc_pooled_nesterov_costpath, label="Nesterov's Gradient Descent", color="blue")
# Integer ticks only
plt.xticks(np.arange(0, max(len(hc_pooled_costpath), len(hc_pooled_nesterov_costpath)), 1.0))
else:
plt.plot(hc_costpath, label=HC_GROUPED_LASSO_LABEL, color=HC_GROUPED_LASSO_COLOR)
plt.plot(hc_nesterov_costpath, label="Nesterov", color="purple")
# Integer ticks only
plt.xticks(np.arange(0, max(len(hc_costpath), len(hc_nesterov_costpath)), 1.0))
plt.axhline(gs_lowest_cost, label="Grid Search", color=GS_COLOR)
plt.legend(fontsize="x-small")
# plt.title("Train=%d p=%d, g=%d, m=%d" % (TRAIN_SIZE, TOTAL_FEATURES, TRUE_NUM_GROUPS, NUM_GROUPS))
plt.xlabel("Number of iterations")
plt.ylabel("Validation test error")
plt.savefig("figures/grouped_lasso_%d_%d_%d_%d.png" % (TRAIN_SIZE, TOTAL_FEATURES, TRUE_NUM_GROUPS, NUM_GROUPS))
sys.stdout.flush()
