if args.pool:
args.ablation = True
ablations = None
basenames_to_pool = None
exps_outdirs = []
for path in args.config_paths:
p = Config(path)
models = filter_models(p.model_list, args.models)
cdr_models = [
x for x in models if (x.startswith('CDR') or x.startswith('DTSR'))
]
partitions = get_partition_list(args.partition)
partition_str = '-'.join(partitions)
if args.metric == 'loss':
file_name = 'losses_mse_%s.txt' % partition_str
else:
file_name = 'loglik_%s.txt' % partition_str
if args.twostep:
file_name = 'LM_2STEP_' + file_name
if args.ablation:
comparison_sets = {}
for model_name in cdr_models:
model_basename = model_name.split('!')[0]
if model_basename not in comparison_sets:
comparison_sets[model_basename] = []
cdr_models = [m for m in models if (m.startswith('CDR') or m.startswith('DTSR'))]
if not args.ablated_models:
cdr_models_new = []
for model_name in cdr_models:
if len(model_name.split('!')) == 1: #No ablated variables, which are flagged with "!"
cdr_models_new.append(model_name)
cdr_models = cdr_models_new
evaluation_sets = []
evaluation_set_partitions = []
evaluation_set_names = []
evaluation_set_paths = []
for p_name in args.partition:
partitions = get_partition_list(p_name)
partition_str = '-'.join(partitions)
X_paths, y_paths = paths_from_partition_cliarg(partitions, p)
X, y = read_data(X_paths, y_paths, p.series_ids, categorical_columns=list(
set(p.split_ids + p.series_ids + [v for x in cdr_formula_list for v in x.rangf])))
X, y, select, X_response_aligned_predictor_names, X_response_aligned_predictors, X_2d_predictor_names, X_2d_predictors = preprocess_data(
X,
y,
cdr_formula_list,
p.series_ids,
filters=p.filters,
compute_history=True,
history_length=p.history_length
)
evaluation_sets.append((X, y, select, X_response_aligned_predictor_names, X_response_aligned_predictors,
X_2d_predictor_names, X_2d_predictors))