def main(options):
# create sub folder
subm_folder = "%s/ensemble_selection"%config.SUBM_DIR
os_utils._create_dirs( [subm_folder] )
subm_prefix = "%s/test.pred.[%s]" % (subm_folder, options.outfile)
# get model list
log_folder = "%s/level%d_models"%(config.LOG_DIR, options.level-1)
model_list = get_model_list(log_folder, options.size)
# get instance splitter
if options.level not in [2, 3]:
inst_splitter = None
elif options.level == 2:
inst_splitter = splitter_level2
elif options.level == 3:
inst_splitter = splitter_level3
ees = ExtremeEnsembleSelection(
model_folder=config.OUTPUT_DIR,
model_list=model_list,
subm_prefix=subm_prefix,
weight_opt_max_evals=options.weight_opt_max_evals,
w_min=-1.,
w_max=1.,
inst_subsample=options.inst_subsample,
inst_subsample_replacement=options.inst_subsample_replacement,
inst_splitter=inst_splitter,
model_subsample=options.model_subsample,
model_subsample_replacement=options.model_subsample_replacement,
bagging_size=options.bagging_size,
init_top_k=options.init_top_k,
epsilon=options.epsilon,
multiprocessing=False,
multiprocessing_num_cores=config.NUM_CORES,
enable_extreme=options.enable_extreme,
random_seed=config.RANDOM_SEED
)
ees.go()
def main(options):
# create sub folder
subm_folder = "%s/ensemble_selection" % config.SUBM_DIR
os_utils._create_dirs([subm_folder])
subm_prefix = "%s/test.pred.[%s]" % (subm_folder, options.outfile)
# get model list
log_folder = "%s/level%d_models" % (config.LOG_DIR, options.level - 1)
model_list = get_model_list(log_folder, options.size)
# get instance splitter
if options.level not in [2, 3]:
inst_splitter = None
elif options.level == 2:
inst_splitter = splitter_level2
elif options.level == 3:
inst_splitter = splitter_level3
ees = ExtremeEnsembleSelection(
model_folder=config.OUTPUT_DIR,
model_list=model_list,
subm_prefix=subm_prefix,
weight_opt_max_evals=options.weight_opt_max_evals,
w_min=-1.,
w_max=1.,
inst_subsample=options.inst_subsample,
inst_subsample_replacement=options.inst_subsample_replacement,
inst_splitter=inst_splitter,
model_subsample=options.model_subsample,
model_subsample_replacement=options.model_subsample_replacement,
bagging_size=options.bagging_size,
init_top_k=options.init_top_k,
epsilon=options.epsilon,
multiprocessing=False,
multiprocessing_num_cores=config.NUM_CORES,
enable_extreme=options.enable_extreme,
random_seed=config.RANDOM_SEED)
ees.go()
RANDOM_SEED = 2016 PLATFORM = platform.system() NUM_CORES = 4 if PLATFORM == "Windows" else 14 DATA_PROCESSOR_N_JOBS = 4 if PLATFORM == "Windows" else 6 AUTO_SPELLING_CHECKER_N_JOBS = 4 if PLATFORM == "Windows" else 8 # multi processing is not faster AUTO_SPELLING_CHECKER_N_JOBS = 1 ## rgf RGF_CALL_EXE = "%s/rgf1.2/test/call_exe.pl"%THIRDPARTY_DIR RGF_EXTENSION = ".exe" if PLATFORM == "Windows" else "" RGF_EXE = "%s/rgf1.2/bin/rgf%s"%(THIRDPARTY_DIR, RGF_EXTENSION) # ---------------------- CREATE PATH -------------------- DIRS = [] DIRS += [CLEAN_DATA_DIR] DIRS += [SPLIT_DIR] DIRS += [FEAT_DIR, FEAT_CONF_DIR] DIRS += ["%s/All"%FEAT_DIR] DIRS += ["%s/Run%d"%(FEAT_DIR,i+1) for i in range(N_RUNS)] DIRS += ["%s/Combine"%FEAT_DIR] DIRS += [OUTPUT_DIR, SUBM_DIR] DIRS += ["%s/All"%OUTPUT_DIR] DIRS += ["%s/Run%d"%(OUTPUT_DIR,i+1) for i in range(N_RUNS)] DIRS += [LOG_DIR, FIG_DIR, TMP_DIR] DIRS += [WORD2VEC_MODEL_DIR, DOC2VEC_MODEL_DIR, GLOVE_WORD2VEC_MODEL_DIR] os_utils._create_dirs(DIRS)
MISSING_VALUE_STRING = "MISSINGVALUE"
MISSING_VALUE_NUMERIC = -1
# Other
TERM_VEC_MAX_NUM_TERMS = 50
RANDOM_SEED = 42
NUM_CORES = 4
DBN_CONFIG = {
'MAX_ITERATIONS': 40,
'DEBUG': False,
'PRETTY_LOG': True,
'MIN_DOCS_PER_QUERY': 10,
'MAX_DOCS_PER_QUERY': 10,
'SERP_SIZE': 10,
'QUERY_INDEPENDENT_PAGER': False,
'DEFAULT_REL': 0.5
}
DIRS = [
DATA_DIR,
CLEAN_DATA_DIR,
FEAT_DIR,
FEAT_DIR + '/Combine',
FEAT_CONF_DIR,
LOG_DIR,
TMP_DIR,
]
os_utils._create_dirs(DIRS)
