def test_model_good_no_source(self):
exe = os.path.join(datafiles_path, 'bernoulli' + EXTENSION)
model = Model(exe_file=exe)
self.assertEqual(exe, model.exe_file)
self.assertEqual('bernoulli', model.name)
with self.assertRaises(RuntimeError):
model.code()
with self.assertRaises(RuntimeError):
model.compile()
def test_bernoulli_bad(self):
stan = os.path.join(datafiles_path, 'bernoulli.stan')
exe = os.path.join(datafiles_path, 'bernoulli' + EXTENSION)
bern_model = Model(stan_file=stan, exe_file=exe)
bern_model.compile()
with self.assertRaisesRegex(Exception, 'Error during sampling'):
bern_fit = bern_model.sample(
chains=4, cores=2, seed=12345, sampling_iters=100
)
def test_gen_quantities_good(self):
stan = os.path.join(datafiles_path, 'bernoulli_ppc.stan')
model = Model(stan_file=stan)
model.compile()
jdata = os.path.join(datafiles_path, 'bernoulli.data.json')
# synthesize stanfit object -
# see test_stanfit.py, method 'test_validate_good_run'
goodfiles_path = os.path.join(datafiles_path, 'runset-good')
output = os.path.join(goodfiles_path, 'bern')
sampler_args = SamplerArgs(
sampling_iters=100, max_treedepth=11, adapt_delta=0.95
)
cmdstan_args = CmdStanArgs(
model_name=model.name,
model_exe=model.exe_file,
chain_ids=[1, 2, 3, 4],
seed=12345,
data=jdata,
output_basename=output,
method_args=sampler_args,
)
sampler_fit = StanFit(args=cmdstan_args, chains=4)
for i in range(4):
sampler_fit._set_retcode(i, 0)
bern_fit = model.run_generated_quantities(
csv_files=sampler_fit.csv_files,
data=jdata)
# check results - ouput files, quantities of interest, draws
self.assertEqual(bern_fit.chains, 4)
for i in range(4):
self.assertEqual(bern_fit._retcodes[i], 0)
csv_file = bern_fit.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_fit.column_names, tuple(column_names))
self.assertEqual(bern_fit.draws, 100)
def test_save_csv(self):
stan = os.path.join(datafiles_path, 'bernoulli.stan')
exe = os.path.join(datafiles_path, 'bernoulli' + EXTENSION)
jdata = os.path.join(datafiles_path, 'bernoulli.data.json')
bern_model = Model(stan_file=stan, exe_file=exe)
bern_model.compile()
bern_fit = bern_model.sample(data=jdata,
chains=4,
cores=2,
seed=12345,
sampling_iters=200)
for i in range(bern_fit.chains):
csv_file = bern_fit.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.chains):
csv_file = bern_fit.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.chains): # cleanup datafile_path dir
os.remove(bern_fit.csv_files[i])
os.remove(bern_fit.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.chains):
csv_file = bern_fit.csv_files[i]
self.assertTrue(os.path.exists(csv_file))
for i in range(bern_fit.chains): # cleanup default dir
os.remove(bern_fit.csv_files[i])
os.remove(bern_fit.console_files[i])
def test_model_compile(self):
stan = os.path.join(datafiles_path, 'bernoulli.stan')
exe = os.path.join(datafiles_path, 'bernoulli' + EXTENSION)
model = Model(stan_file=stan)
self.assertEqual(None, model.exe_file)
model.compile()
self.assertTrue(model.exe_file.endswith(exe.replace('\\', '/')))
model = Model(stan_file=stan)
if os.path.exists(exe):
os.remove(exe)
model.compile()
self.assertTrue(model.exe_file.endswith(exe.replace('\\', '/')))
stan = os.path.join(datafiles_path, 'bernoulli_include.stan')
exe = os.path.join(datafiles_path, 'bernoulli_include' + EXTENSION)
here = os.path.dirname(os.path.abspath(__file__))
datafiles_abspath = os.path.join(here, 'data')
include_paths = [datafiles_abspath]
if os.path.exists(exe):
os.remove(exe)
model = Model(stan_file=stan)
model.compile(include_paths=include_paths)
self.assertEqual(stan, model.stan_file)
self.assertTrue(model.exe_file.endswith(exe.replace('\\', '/')))
def test_bernoulli_good(self):
stan = os.path.join(datafiles_path, 'bernoulli.stan')
exe = os.path.join(datafiles_path, 'bernoulli' + EXTENSION)
bern_model = Model(stan_file=stan, exe_file=exe)
bern_model.compile()
jdata = os.path.join(datafiles_path, 'bernoulli.data.json')
bern_fit = bern_model.sample(
data=jdata, chains=4, cores=2, seed=12345, sampling_iters=100
)
for i in range(bern_fit.chains):
csv_file = bern_fit.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(bern_fit.chains, 4)
self.assertEqual(bern_fit.draws, 100)
column_names = [
'lp__',
'accept_stat__',
'stepsize__',
'treedepth__',
'n_leapfrog__',
'divergent__',
'energy__',
'theta',
]
self.assertEqual(bern_fit.column_names, tuple(column_names))
bern_sample = bern_fit.sample
self.assertEqual(bern_sample.shape, (100, 4, len(column_names)))
self.assertEqual(bern_fit.metric_type, 'diag_e')
self.assertEqual(bern_fit.stepsize.shape, (4,))
self.assertEqual(bern_fit.metric.shape, (4, 1))
output = os.path.join(datafiles_path, 'test1-bernoulli-output')
bern_fit = bern_model.sample(
data=jdata,
chains=4,
cores=2,
seed=12345,
sampling_iters=100,
csv_basename=output,
)
for i in range(bern_fit.chains):
csv_file = bern_fit.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))
bern_sample = bern_fit.sample
self.assertEqual(bern_sample.shape, (100, 4, len(column_names)))
for i in range(bern_fit.chains): # cleanup datafile_path dir
os.remove(bern_fit.csv_files[i])
os.remove(bern_fit.console_files[i])
rdata = os.path.join(datafiles_path, 'bernoulli.data.R')
bern_fit = bern_model.sample(
data=rdata, chains=4, cores=2, seed=12345, sampling_iters=100
)
bern_sample = bern_fit.sample
self.assertEqual(bern_sample.shape, (100, 4, len(column_names)))
data_dict = {'N': 10, 'y': [0, 1, 0, 0, 0, 0, 0, 0, 0, 1]}
bern_fit = bern_model.sample(
data=data_dict, chains=4, cores=2, seed=12345, sampling_iters=100
)
bern_sample = bern_fit.sample
self.assertEqual(bern_sample.shape, (100, 4, len(column_names)))
# check if optimized_params_np returns first draw
# (actually first row from csv)
np.testing.assert_equal(
bern_fit.get_drawset().iloc[0].values, bern_fit.optimized_params_np
)