def test_sampler_diags(self):
stan = os.path.join(DATAFILES_PATH, 'bernoulli.stan')
jdata = os.path.join(DATAFILES_PATH, 'bernoulli.data.json')
bern_model = CmdStanModel(stan_file=stan)
bern_fit = bern_model.sample(data=jdata,
chains=2,
seed=12345,
iter_warmup=100,
iter_sampling=100)
diags = bern_fit.sampler_diagnostics()
self.assertEqual(SAMPLER_STATE, list(diags))
for key in diags:
self.assertEqual(diags[key].shape, (100, 2))
def test_sample_plus_quantities_dedup(self):
stan = os.path.join(DATAFILES_PATH, 'bernoulli_ppc.stan')
model = CmdStanModel(stan_file=stan)
jdata = os.path.join(DATAFILES_PATH, 'bernoulli.data.json')
bern_fit = model.sample(data=jdata,
chains=4,
cores=2,
seed=12345,
iter_sampling=100)
bern_gqs = model.generate_quantities(data=jdata, mcmc_sample=bern_fit)
self.assertEqual(bern_gqs.sample_plus_quantities.shape[1],
bern_gqs.mcmc_sample.shape[1])
def test_variational_eta_small(self):
stan = os.path.join(datafiles_path, 'variational',
'eta_should_be_small.stan')
model = CmdStanModel(stan_file=stan)
vi = model.variational(algorithm='meanfield', seed=12345)
self.assertEqual(vi.column_names,
('lp__', 'log_p__', 'log_g__', 'mu.1', 'mu.2'))
self.assertAlmostEqual(fabs(vi.variational_params_dict['mu.1']),
0.08,
places=1)
self.assertAlmostEqual(fabs(vi.variational_params_dict['mu.2']),
0.09,
places=1)
self.assertTrue(True)
def test_bernoulli_bad(self):
stan = os.path.join(DATAFILES_PATH, 'bernoulli.stan')
bern_model = CmdStanModel(stan_file=stan)
with self.assertRaisesRegex(RuntimeError, 'variable does not exist'):
bern_model.sample(chains=2, cores=2, seed=12345, iter_sampling=100)
with self.assertRaisesRegex(RuntimeError, 'variable does not exist'):
bern_model.sample(
data={'foo': 1},
chains=2,
cores=2,
seed=12345,
iter_sampling=100,
)
if platform.system() != 'Windows':
jdata = os.path.join(DATAFILES_PATH, 'bernoulli.data.json')
dirname1 = 'tmp1' + str(time())
os.mkdir(dirname1, mode=644)
dirname2 = 'tmp2' + str(time())
path = os.path.join(dirname1, dirname2)
with self.assertRaisesRegex(ValueError,
'invalid path for output files'):
bern_model.sample(data=jdata, chains=1, output_dir=path)
os.rmdir(dirname1)
def test_gen_quantities_csv_files_bad(self):
stan = os.path.join(DATAFILES_PATH, 'bernoulli_ppc.stan')
model = CmdStanModel(stan_file=stan)
jdata = os.path.join(DATAFILES_PATH, 'bernoulli.data.json')
# synthesize list of filenames
goodfiles_path = os.path.join(DATAFILES_PATH, 'runset-bad',
'bad-draws-bern')
csv_files = []
for i in range(4):
csv_files.append('{}-{}.csv'.format(goodfiles_path, i + 1))
with self.assertRaisesRegex(Exception, 'Invalid mcmc_sample'):
model.generate_quantities(data=jdata, mcmc_sample=csv_files)
def test_multi_proc(self):
logistic_stan = os.path.join(DATAFILES_PATH, 'logistic.stan')
logistic_model = CmdStanModel(stan_file=logistic_stan)
logistic_data = os.path.join(DATAFILES_PATH, 'logistic.data.R')
with LogCapture() as log:
logging.getLogger()
logistic_model.sample(data=logistic_data, chains=4, cores=1)
log.check_present(
('cmdstanpy', 'INFO', 'finish chain 1'),
('cmdstanpy', 'INFO', 'start chain 2'),
)
with LogCapture() as log:
logging.getLogger()
logistic_model.sample(data=logistic_data, chains=4, cores=2)
if cpu_count() >= 4:
# finish chains 1, 2 before starting chains 3, 4
log.check_present(
('cmdstanpy', 'INFO', 'finish chain 1'),
('cmdstanpy', 'INFO', 'start chain 4'),
)
if cpu_count() >= 4:
with LogCapture() as log:
logging.getLogger()
logistic_model.sample(data=logistic_data, chains=4, cores=4)
log.check_present(
('cmdstanpy', 'INFO', 'start chain 4'),
('cmdstanpy', 'INFO', 'finish chain 1'),
)
def test_custom_metric(self):
stan = os.path.join(DATAFILES_PATH, 'bernoulli.stan')
jdata = os.path.join(DATAFILES_PATH, 'bernoulli.data.json')
bern_model = CmdStanModel(stan_file=stan)
jmetric = os.path.join(DATAFILES_PATH, 'bernoulli.metric.json')
# just test that it runs without error
bern_model.sample(
data=jdata,
chains=2,
cores=2,
seed=12345,
iter_sampling=200,
metric=jmetric,
)
def test_exe_only(self):
stan = os.path.join(DATAFILES_PATH, 'bernoulli.stan')
bern_model = CmdStanModel(stan_file=stan)
exe_only = os.path.join(DATAFILES_PATH, 'exe_only')
shutil.copyfile(bern_model.exe_file, exe_only)
os.chmod(exe_only, 0o755)
bern2_model = CmdStanModel(exe_file=exe_only)
jdata = os.path.join(DATAFILES_PATH, 'bernoulli.data.json')
mle = bern2_model.optimize(data=jdata)
self.assertEqual(mle.optimized_params_np[0],
mle.optimized_params_dict['lp__'])
self.assertEqual(mle.optimized_params_np[1],
mle.optimized_params_dict['theta'])
def test_dont_save_warmup(self):
stan = os.path.join(DATAFILES_PATH, 'bernoulli.stan')
jdata = os.path.join(DATAFILES_PATH, 'bernoulli.data.json')
bern_model = CmdStanModel(stan_file=stan)
bern_fit = bern_model.sample(
data=jdata,
chains=2,
seed=12345,
iter_warmup=200,
iter_sampling=100,
save_warmup=False,
)
self.assertEqual(bern_fit.column_names, tuple(BERNOULLI_COLS))
self.assertEqual(bern_fit.num_draws_sampling, 100)
self.assertEqual(bern_fit.draws().shape, (100, 2, len(BERNOULLI_COLS)))
with LogCapture() as log:
self.assertEqual(
bern_fit.draws(inc_warmup=True).shape,
(100, 2, len(BERNOULLI_COLS)),
)
log.check_present((
'cmdstanpy',
'WARNING',
'draws from warmup iterations not available,'
' must run sampler with "save_warmup=True".',
))
with LogCapture() as log:
self.assertEqual(
bern_fit.draws(inc_warmup=True, concat_chains=True).shape,
(200, len(BERNOULLI_COLS)),
)
log.check_present((
'cmdstanpy',
'WARNING',
'draws from warmup iterations not available,'
' must run sampler with "save_warmup=True".',
))
with LogCapture() as log:
self.assertEqual(
bern_fit.draws_pd(inc_warmup=True).shape,
(200, len(BERNOULLI_COLS)),
)
log.check_present((
'cmdstanpy',
'WARNING',
'draws from warmup iterations not available,'
' must run sampler with "save_warmup=True".',
))
def test_set_mle_attrs(self):
stan = os.path.join(datafiles_path, 'optimize', 'rosenbrock.stan')
model = CmdStanModel(stan_file=stan)
no_data = {}
args = OptimizeArgs(algorithm='Newton')
cmdstan_args = CmdStanArgs(
model_name=model.name,
model_exe=model.exe_file,
chain_ids=None,
data=no_data,
method_args=args,
)
runset = RunSet(args=cmdstan_args, chains=1)
mle = CmdStanMLE(runset)
self.assertIn('CmdStanMLE: model=rosenbrock', mle.__repr__())
self.assertIn('method=optimize', mle.__repr__())
self.assertEqual(mle._column_names, ())
self.assertEqual(mle._mle, {})
output = os.path.join(datafiles_path, 'optimize', 'rosenbrock_mle.csv')
mle._set_mle_attrs(output)
self.assertEqual(mle.column_names, ('lp__', 'x', 'y'))
self.assertAlmostEqual(mle.optimized_params_dict['x'], 1, places=3)
self.assertAlmostEqual(mle.optimized_params_dict['y'], 1, places=3)
def test_model_includes_implicit(self):
stan = os.path.join(DATAFILES_PATH, 'bernoulli_include.stan')
exe = os.path.join(DATAFILES_PATH, 'bernoulli_include' + EXTENSION)
if os.path.exists(exe):
os.remove(exe)
model2 = CmdStanModel(stan_file=stan)
self.assertTrue(model2.exe_file.endswith(exe.replace('\\', '/')))
def test_model_includes_explicit(self):
if os.path.exists(BERN_EXE):
os.remove(BERN_EXE)
model = CmdStanModel(stan_file=BERN_STAN,
stanc_options={'include_paths': DATAFILES_PATH})
self.assertEqual(BERN_STAN, model.stan_file)
self.assertTrue(model.exe_file.endswith(BERN_EXE.replace('\\', '/')))
def test_set_variational_attrs(self):
stan = os.path.join(datafiles_path, 'variational',
'eta_should_be_big.stan')
model = CmdStanModel(stan_file=stan)
no_data = {}
args = VariationalArgs(algorithm='meanfield')
cmdstan_args = CmdStanArgs(model_name=model.name,
model_exe=model.exe_file,
chain_ids=None,
data=no_data,
method_args=args)
runset = RunSet(args=cmdstan_args, chains=1)
vi = CmdStanVB(runset)
self.assertIn('CmdStanVB: model=eta_should_be_big', vi.__repr__())
self.assertIn('method=variational', vi.__repr__())
# check CmdStanVB.__init__ state
self.assertEqual(vi._column_names, ())
self.assertEqual(vi._variational_mean, {})
self.assertEqual(vi._variational_sample, None)
# process csv file, check attrs
output = os.path.join(datafiles_path, 'variational',
'eta_big_output.csv')
vi._set_variational_attrs(output)
self.assertEqual(vi.column_names,
('lp__', 'log_p__', 'log_g__', 'mu.1', 'mu.2'))
self.assertAlmostEqual(vi.variational_params_dict['mu.1'],
31.0299,
places=2)
self.assertAlmostEqual(vi.variational_params_dict['mu.2'],
28.8141,
places=2)
self.assertEqual(vi.variational_sample.shape, (1000, 5))
def test_model_includes_implicit(self):
stan = os.path.join(DATAFILES_PATH, 'bernoulli_include.stan')
exe = os.path.join(DATAFILES_PATH, 'bernoulli_include' + EXTENSION)
if os.path.exists(exe):
os.remove(exe)
model2 = CmdStanModel(stan_file=stan)
self.assertPathsEqual(model2.exe_file, exe)
def test_instantiate(self):
stan = os.path.join(DATAFILES_PATH, 'variational',
'eta_should_be_big.stan')
model = CmdStanModel(stan_file=stan)
no_data = {}
args = VariationalArgs(algorithm='meanfield')
cmdstan_args = CmdStanArgs(
model_name=model.name,
model_exe=model.exe_file,
chain_ids=None,
data=no_data,
method_args=args,
)
runset = RunSet(args=cmdstan_args, chains=1)
runset._csv_files = [
os.path.join(DATAFILES_PATH, 'variational', 'eta_big_output.csv')
]
variational = CmdStanVB(runset)
self.assertIn('CmdStanVB: model=eta_should_be_big',
variational.__repr__())
self.assertIn('method=variational', variational.__repr__())
self.assertEqual(
variational.column_names,
('lp__', 'log_p__', 'log_g__', 'mu[1]', 'mu[2]'),
)
self.assertAlmostEqual(variational.variational_params_dict['mu[1]'],
31.0299,
places=2)
self.assertAlmostEqual(variational.variational_params_dict['mu[2]'],
28.8141,
places=2)
self.assertEqual(variational.variational_sample.shape, (1000, 5))
def test_check_sampler_csv_thin(self):
stan = os.path.join(DATAFILES_PATH, 'bernoulli.stan')
bern_model = CmdStanModel(stan_file=stan)
bern_model.compile()
jdata = os.path.join(DATAFILES_PATH, 'bernoulli.data.json')
bern_fit = bern_model.sample(
data=jdata,
chains=1,
parallel_chains=1,
seed=12345,
iter_sampling=490,
iter_warmup=490,
thin=7,
max_treedepth=11,
adapt_delta=0.98,
)
csv_file = bern_fit.runset.csv_files[0]
dict = check_sampler_csv(
path=csv_file,
is_fixed_param=False,
iter_sampling=490,
iter_warmup=490,
thin=7,
)
self.assertEqual(dict['num_samples'], 490)
self.assertEqual(dict['thin'], 7)
self.assertEqual(dict['draws_sampling'], 70)
self.assertEqual(dict['seed'], 12345)
self.assertEqual(dict['max_depth'], 11)
self.assertEqual(dict['delta'], 0.98)
with self.assertRaisesRegex(ValueError, 'config error'):
check_sampler_csv(
path=csv_file,
is_fixed_param=False,
iter_sampling=490,
iter_warmup=490,
thin=9,
)
with self.assertRaisesRegex(ValueError,
'expected 490 draws, found 70'):
check_sampler_csv(
path=csv_file,
is_fixed_param=False,
iter_sampling=490,
iter_warmup=490,
)
def test_save_csv(self):
stan = os.path.join(DATAFILES_PATH, 'bernoulli.stan')
jdata = os.path.join(DATAFILES_PATH, 'bernoulli.data.json')
bern_model = CmdStanModel(stan_file=stan)
bern_fit = bern_model.sample(data=jdata,
chains=4,
cores=2,
seed=12345,
sampling_iters=200)
for i in range(bern_fit.runset.chains):
csv_file = bern_fit.runset.csv_files[i]
txt_file = ''.join([os.path.splitext(csv_file)[0], '.txt'])
self.assertTrue(os.path.exists(csv_file))
self.assertTrue(os.path.exists(txt_file))
# save files to good dir
bern_fit.save_csvfiles(dir=DATAFILES_PATH)
for i in range(bern_fit.runset.chains):
csv_file = bern_fit.runset.csv_files[i]
self.assertTrue(os.path.exists(csv_file))
with self.assertRaisesRegex(Exception, 'file exists'):
bern_fit.save_csvfiles(dir=DATAFILES_PATH)
tmp2_dir = os.path.join(HERE, 'tmp2')
os.mkdir(tmp2_dir)
bern_fit.save_csvfiles(dir=tmp2_dir)
for i in range(bern_fit.runset.chains):
csv_file = bern_fit.runset.csv_files[i]
self.assertTrue(os.path.exists(csv_file))
for i in range(bern_fit.runset.chains): # cleanup datafile_path dir
os.remove(bern_fit.runset.csv_files[i])
os.remove(bern_fit.runset.console_files[i])
shutil.rmtree(tmp2_dir, ignore_errors=True)
# regenerate to tmpdir, save to good dir
bern_fit = bern_model.sample(data=jdata,
chains=4,
cores=2,
seed=12345,
sampling_iters=200)
bern_fit.save_csvfiles() # default dir
for i in range(bern_fit.runset.chains):
csv_file = bern_fit.runset.csv_files[i]
self.assertTrue(os.path.exists(csv_file))
for i in range(bern_fit.runset.chains): # cleanup default dir
os.remove(bern_fit.runset.csv_files[i])
os.remove(bern_fit.runset.console_files[i])
def test_model_includes_explicit(self):
if os.path.exists(BERN_EXE):
os.remove(BERN_EXE)
model = CmdStanModel(
stan_file=BERN_STAN, stanc_options={'include_paths': DATAFILES_PATH}
)
self.assertEqual(BERN_STAN, model.stan_file)
self.assertPathsEqual(model.exe_file, BERN_EXE)
def test_ctor_compile_arg(self):
# instantiate, don't compile
if os.path.exists(BERN_EXE):
os.remove(BERN_EXE)
model = CmdStanModel(stan_file=BERN_STAN, compile=False)
self.assertEqual(BERN_STAN, model.stan_file)
self.assertEqual(None, model.exe_file)
model = CmdStanModel(stan_file=BERN_STAN, compile=True)
self.assertPathsEqual(model.exe_file, BERN_EXE)
exe_time = os.path.getmtime(model.exe_file)
model = CmdStanModel(stan_file=BERN_STAN)
self.assertTrue(exe_time == os.path.getmtime(model.exe_file))
model = CmdStanModel(stan_file=BERN_STAN, compile='force')
self.assertTrue(exe_time < os.path.getmtime(model.exe_file))
def test_show_console(self):
stan = os.path.join(DATAFILES_PATH, 'bernoulli.stan')
bern_model = CmdStanModel(stan_file=stan)
jdata = os.path.join(DATAFILES_PATH, 'bernoulli.data.json')
bern_fit = bern_model.sample(
data=jdata,
chains=4,
parallel_chains=2,
seed=12345,
iter_sampling=100,
)
stan = os.path.join(DATAFILES_PATH, 'bernoulli_ppc.stan')
model = CmdStanModel(stan_file=stan)
sys_stdout = io.StringIO()
with contextlib.redirect_stdout(sys_stdout):
model.generate_quantities(
data=jdata,
mcmc_sample=bern_fit,
show_console=True,
)
console = sys_stdout.getvalue()
self.assertTrue('Chain [1] method = generate' in console)
self.assertTrue('Chain [2] method = generate' in console)
self.assertTrue('Chain [3] method = generate' in console)
self.assertTrue('Chain [4] method = generate' in console)
def test_dont_save_warmup(self):
stan = os.path.join(DATAFILES_PATH, 'bernoulli.stan')
jdata = os.path.join(DATAFILES_PATH, 'bernoulli.data.json')
bern_model = CmdStanModel(stan_file=stan)
bern_fit = bern_model.sample(
data=jdata,
chains=2,
seed=12345,
iter_warmup=200,
iter_sampling=100,
save_warmup=False,
)
self.assertEqual(bern_fit.column_names, tuple(BERNOULLI_COLS))
self.assertEqual(bern_fit.num_draws_warmup, 0)
self.assertEqual(bern_fit.warmup, None)
self.assertEqual(bern_fit.num_draws, 100)
self.assertEqual(bern_fit.sample.shape, (100, 2, len(BERNOULLI_COLS)))
def test_variable_bern(self):
stan = os.path.join(DATAFILES_PATH, 'bernoulli.stan')
jdata = os.path.join(DATAFILES_PATH, 'bernoulli.data.json')
bern_model = CmdStanModel(stan_file=stan)
bern_fit = bern_model.sample(data=jdata,
chains=2,
seed=12345,
iter_warmup=100,
iter_sampling=100)
self.assertEqual(1, len(bern_fit._stan_variable_dims))
self.assertTrue('theta' in bern_fit._stan_variable_dims)
self.assertEqual(bern_fit._stan_variable_dims['theta'], 1)
theta = bern_fit.stan_variable(name='theta')
self.assertEqual(theta.shape, (200, ))
with self.assertRaises(ValueError):
bern_fit.stan_variable(name='eta')
with self.assertRaises(ValueError):
bern_fit.stan_variable(name='lp__')
def test_model_syntax_error(self):
stan = os.path.join(DATAFILES_PATH, 'bad_syntax.stan')
with LogCapture(level=logging.WARNING) as log:
logging.getLogger()
with self.assertRaises(ValueError):
CmdStanModel(stan_file=stan)
log.check_present(
('cmdstanpy', 'WARNING', StringComparison(r'(?s).*Syntax error.*'))
)
def test_variational_eta_small(self):
stan = os.path.join(DATAFILES_PATH, 'variational',
'eta_should_be_small.stan')
model = CmdStanModel(stan_file=stan)
variational = model.variational(algorithm='meanfield', seed=12345)
self.assertEqual(
variational.column_names,
('lp__', 'log_p__', 'log_g__', 'mu[1]', 'mu[2]'),
)
self.assertAlmostEqual(fabs(
variational.variational_params_dict['mu[1]']),
0.08,
places=1)
self.assertAlmostEqual(fabs(
variational.variational_params_dict['mu[2]']),
0.09,
places=1)
self.assertTrue(True)
def test_gen_quantities_csv_files(self):
stan = os.path.join(DATAFILES_PATH, 'bernoulli_ppc.stan')
model = CmdStanModel(stan_file=stan)
jdata = os.path.join(DATAFILES_PATH, 'bernoulli.data.json')
# synthesize list of filenames
goodfiles_path = os.path.join(DATAFILES_PATH, 'runset-good', 'bern')
csv_files = []
for i in range(4):
csv_files.append('{}-{}.csv'.format(goodfiles_path, i + 1))
bern_gqs = model.generate_quantities(data=jdata, mcmc_sample=csv_files)
self.assertEqual(
bern_gqs.runset._args.method, Method.GENERATE_QUANTITIES
)
self.assertIn('CmdStanGQ: model=bernoulli_ppc', bern_gqs.__repr__())
self.assertIn('method=generate_quantities', bern_gqs.__repr__())
# check results - ouput files, quantities of interest, draws
self.assertEqual(bern_gqs.runset.chains, 4)
for i in range(bern_gqs.runset.chains):
self.assertEqual(bern_gqs.runset._retcode(i), 0)
csv_file = bern_gqs.runset.csv_files[i]
self.assertTrue(os.path.exists(csv_file))
column_names = [
'y_rep[1]',
'y_rep[2]',
'y_rep[3]',
'y_rep[4]',
'y_rep[5]',
'y_rep[6]',
'y_rep[7]',
'y_rep[8]',
'y_rep[9]',
'y_rep[10]',
]
self.assertEqual(bern_gqs.column_names, tuple(column_names))
self.assertEqual(
bern_gqs.sample_plus_quantities.shape[1],
bern_gqs.mcmc_sample.shape[1]
+ bern_gqs.generated_quantities_pd.shape[1],
)
def test_optimize_good_dict(self):
exe = os.path.join(DATAFILES_PATH, 'bernoulli' + EXTENSION)
stan = os.path.join(DATAFILES_PATH, 'bernoulli.stan')
model = CmdStanModel(stan_file=stan, exe_file=exe)
with open(os.path.join(DATAFILES_PATH, 'bernoulli.data.json')) as fd:
data = json.load(fd)
with open(os.path.join(DATAFILES_PATH, 'bernoulli.init.json')) as fd:
init = json.load(fd)
mle = model.optimize(
data=data,
seed=1239812093,
inits=init,
algorithm='BFGS',
init_alpha=0.001,
iter=100,
)
# test numpy output
self.assertAlmostEqual(mle.optimized_params_np[0], -5, places=2)
self.assertAlmostEqual(mle.optimized_params_np[1], 0.2, places=3)
def test_model_good(self):
stan = os.path.join(datafiles_path, 'bernoulli.stan')
exe = os.path.join(datafiles_path, 'bernoulli' + EXTENSION)
# compile on instantiation
model = CmdStanModel(stan_file=stan)
self.assertEqual(stan, model.stan_file)
self.assertTrue(model.exe_file.endswith(exe.replace('\\', '/')))
# instantiate with existing exe
model = CmdStanModel(stan_file=stan, exe_file=exe)
self.assertEqual(stan, model.stan_file)
self.assertTrue(model.exe_file.endswith(exe))
# instantiate, don't compile
os.remove(exe)
model = CmdStanModel(stan_file=stan, compile=False)
self.assertEqual(stan, model.stan_file)
self.assertEqual(None, model.exe_file)
def test_fixed_param_good(self):
stan = os.path.join(DATAFILES_PATH, 'datagen_poisson_glm.stan')
datagen_model = CmdStanModel(stan_file=stan)
no_data = {}
datagen_fit = datagen_model.sample(data=no_data,
seed=12345,
sampling_iters=100,
fixed_param=True)
self.assertEqual(datagen_fit.runset._args.method, Method.SAMPLE)
for i in range(datagen_fit.runset.chains):
csv_file = datagen_fit.runset.csv_files[i]
txt_file = ''.join([os.path.splitext(csv_file)[0], '.txt'])
self.assertTrue(os.path.exists(csv_file))
self.assertTrue(os.path.exists(txt_file))
self.assertEqual(datagen_fit.runset.chains, 1)
column_names = [
'lp__', 'accept_stat__', 'N', 'y_sim.1', 'y_sim.2', 'y_sim.3',
'y_sim.4', 'y_sim.5', 'y_sim.6', 'y_sim.7', 'y_sim.8', 'y_sim.9',
'y_sim.10', 'y_sim.11', 'y_sim.12', 'y_sim.13', 'y_sim.14',
'y_sim.15', 'y_sim.16', 'y_sim.17', 'y_sim.18', 'y_sim.19',
'y_sim.20', 'x_sim.1', 'x_sim.2', 'x_sim.3', 'x_sim.4', 'x_sim.5',
'x_sim.6', 'x_sim.7', 'x_sim.8', 'x_sim.9', 'x_sim.10', 'x_sim.11',
'x_sim.12', 'x_sim.13', 'x_sim.14', 'x_sim.15', 'x_sim.16',
'x_sim.17', 'x_sim.18', 'x_sim.19', 'x_sim.20', 'pop_sim.1',
'pop_sim.2', 'pop_sim.3', 'pop_sim.4', 'pop_sim.5', 'pop_sim.6',
'pop_sim.7', 'pop_sim.8', 'pop_sim.9', 'pop_sim.10', 'pop_sim.11',
'pop_sim.12', 'pop_sim.13', 'pop_sim.14', 'pop_sim.15',
'pop_sim.16', 'pop_sim.17', 'pop_sim.18', 'pop_sim.19',
'pop_sim.20', 'alpha_sim', 'beta_sim', 'eta.1', 'eta.2', 'eta.3',
'eta.4', 'eta.5', 'eta.6', 'eta.7', 'eta.8', 'eta.9', 'eta.10',
'eta.11', 'eta.12', 'eta.13', 'eta.14', 'eta.15', 'eta.16',
'eta.17', 'eta.18', 'eta.19', 'eta.20'
]
self.assertEqual(datagen_fit.column_names, tuple(column_names))
self.assertEqual(datagen_fit.draws, 100)
self.assertEqual(datagen_fit.sample.shape, (100, 1, len(column_names)))
self.assertEqual(datagen_fit.metric, None)
self.assertEqual(datagen_fit.metric_type, None)
self.assertEqual(datagen_fit.stepsize, None)
def test_save_warmup_thin(self):
stan = os.path.join(DATAFILES_PATH, 'bernoulli.stan')
jdata = os.path.join(DATAFILES_PATH, 'bernoulli.data.json')
bern_model = CmdStanModel(stan_file=stan)
bern_fit = bern_model.sample(
data=jdata,
chains=2,
seed=12345,
iter_warmup=200,
iter_sampling=100,
thin=5,
save_warmup=True,
)
self.assertEqual(bern_fit.column_names, tuple(BERNOULLI_COLS))
self.assertEqual(bern_fit.num_draws, 60)
self.assertEqual(bern_fit.draws().shape, (20, 2, len(BERNOULLI_COLS)))
self.assertEqual(
bern_fit.draws(inc_warmup=True).shape,
(60, 2, len(BERNOULLI_COLS)))
def test_save_csv(self):
stan = os.path.join(datafiles_path, 'bernoulli.stan')
jdata = os.path.join(datafiles_path, 'bernoulli.data.json')
bern_model = CmdStanModel(stan_file=stan)
bern_fit = bern_model.sample(data=jdata,
chains=4,
cores=2,
seed=12345,
sampling_iters=200)
for i in range(bern_fit.runset.chains):
csv_file = bern_fit.runset.csv_files[i]
txt_file = ''.join([os.path.splitext(csv_file)[0], '.txt'])
self.assertTrue(os.path.exists(csv_file))
self.assertTrue(os.path.exists(txt_file))
# save files to good dir
basename = 'bern_save_csvfiles_test'
bern_fit.save_csvfiles(dir=datafiles_path, basename=basename)
for i in range(bern_fit.runset.chains):
csv_file = bern_fit.runset.csv_files[i]
self.assertTrue(os.path.exists(csv_file))
with self.assertRaisesRegex(Exception, 'file exists'):
bern_fit.save_csvfiles(dir=datafiles_path, basename=basename)
for i in range(bern_fit.runset.chains): # cleanup datafile_path dir
os.remove(bern_fit.runset.csv_files[i])
os.remove(bern_fit.runset.console_files[i])
# regenerate to tmpdir, save to good dir
bern_fit = bern_model.sample(data=jdata,
chains=4,
cores=2,
seed=12345,
sampling_iters=200)
bern_fit.save_csvfiles(basename=basename) # default dir
for i in range(bern_fit.runset.chains):
csv_file = bern_fit.runset.csv_files[i]
self.assertTrue(os.path.exists(csv_file))
for i in range(bern_fit.runset.chains): # cleanup default dir
os.remove(bern_fit.runset.csv_files[i])
os.remove(bern_fit.runset.console_files[i])
