partitions = get_partition_list(args.partition)
partition_str = '-'.join(partitions)
for m in models:
dir_path = p.outdir + '/' + m
if args.ablated_models:
data_path = dir_path + '/X_conv_' + partition_str + '.csv'
else:
data_path = p.outdir + '/' + m.split(
'!')[0] + '/X_conv_' + partition_str + '.csv'
stderr('Two-step analysis using data file %s\n' % data_path)
if os.path.exists(data_path):
p.set_model(m)
f = Formula(p['formula'])
model_form = f.to_lmer_formula_string(
z=args.zscore, correlated=not args.uncorrelated)
model_form = model_form.replace('-', '_')
is_lme = '|' in model_form
df = pd.read_csv(data_path, sep=' ', skipinitialspace=True)
for c in df.columns:
if df[c].dtype.name == 'object':
df[c] = df[c].astype(str)
new_cols = []
for c in df.columns:
new_cols.append(c.replace('-', '_'))
df.columns = new_cols
argparser.add_argument('-z', '--standardize_response', action='store_true', help='Standardize (Z-transform) response in plots. Ignored unless model was fitted using setting ``standardize_respose=True``.')
argparser.add_argument('-n', '--nsamples', type=int, default=None, help='Number of posterior samples to average (only used for CDRBayes)')
argparser.add_argument('-u', '--unscaled', action='store_true', help='Do not multiply outputs by CDR-fitted coefficients')
argparser.add_argument('-a', '--algorithm', type=str, default='MAP', help='Algorithm ("sampling" or "MAP") to use for extracting predictions.')
argparser.add_argument('-A', '--ablated_models', action='store_true', help='Perform convolution using ablated models. Otherwise only convolves using the full model in each ablation set.')
args, unknown = argparser.parse_known_args()
for path in args.config_paths:
p = Config(path)
if not p.use_gpu_if_available:
os.environ['CUDA_VISIBLE_DEVICES'] = '-1'
models = filter_models(p.model_list, args.models)
cdr_formula_list = [Formula(p.models[m]['formula']) for m in models if (m.startswith('CDR') or m.startswith('DTSR'))]
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:
models = filter_models(p.model_list, args.models)
run_baseline = False
run_cdr = False
for m in models:
if not run_baseline and m.startswith('LM') or m.startswith('GAM'):
run_baseline = True
elif not run_cdr and (m.startswith('CDR') or m.startswith('DTSR')):
run_cdr = True
if not (run_baseline or run_cdr):
stderr('No models to run. Exiting...\n')
exit()
cdr_formula_list = [
Formula(p.models[m]['formula']) for m in models
if (m.startswith('CDR') or m.startswith('DTSR'))
]
cdr_formula_name_list = [
m for m in p.model_list
if (m.startswith('CDR') or m.startswith('DTSR'))
]
all_rangf = [v for x in cdr_formula_list for v in x.rangf]
partitions = get_partition_list(args.partition)
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])))
args, unknown = argparser.parse_known_args()
p = Config(args.config_path)
models = filter_models(p.model_list, args.models)
run_baseline = False
run_cdr = False
for m in models:
if not run_baseline and m.startswith('LM') or m.startswith('GAM'):
run_baseline = True
elif not run_cdr and (m.startswith('CDR') or m.startswith('DTSR')):
run_cdr = True
cdr_formula_list = [
Formula(p.models[m]['formula']) for m in models
if (m.startswith('CDR') or m.startswith('DTSR'))
]
cdr_formula_name_list = [
m for m in p.model_list
if (m.startswith('CDR') or m.startswith('DTSR'))
]
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)
if 'impulse_to_transform' in config:
for key in config['impulse_to_transform']:
impulse_to_transform[key] = config['impulse_to_transform'][key]
newpred_rangf = ['subject']
if 'newpred_rangf' in config:
newpred_rangf = config['newpred_rangf']['rangf'].strip().split()
baseline_found = False
for name in config:
if (name.startswith('model_CDR')
or name.startswith('model_DTSR')) and name.endswith('_BASELINE'):
baseline_found = True
new_name = name[:-9]
model_template = config[name]
f = Formula(model_template['formula'])
for effect in main_effects:
if effect.startswith('~'):
ablate = True
effect = effect[1:]
else:
ablate = False
irf_str = impulse_to_irf.get(effect, default_irf_str)
effect_name = effect
transform = impulse_to_transform.get(effect, ['s'])
if transform == 'None':
transform = []
elif isinstance(transform, str):
transform = transform.strip().split()
argparser.add_argument('-e', '--extra_cols', action='store_true', help='For prediction from CDR models, dump prediction outputs and response metadata to a single csv.')
args, unknown = argparser.parse_known_args()
p = Config(args.config_path)
models = filter_models(p.model_list, args.models)
run_baseline = False
run_cdr = False
for m in models:
if not run_baseline and m.startswith('LM') or m.startswith('GAM'):
run_baseline = True
elif not run_cdr and (m.startswith('CDR') or m.startswith('DTSR')):
run_cdr = True
cdr_formula_list = [Formula(p.models[m]['formula']) for m in models if (m.startswith('CDR') or m.startswith('DTSR'))]
cdr_formula_name_list = [m for m in p.model_list if (m.startswith('CDR') or m.startswith('DTSR'))]
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,