def check_weights_diff(covs, meth, weights, model, kwargs):
res = clustered_model(covs, meth, model, **kwargs)
resw = clustered_model(covs, meth, model, weights=weights, **kwargs)
for k in 'p coef'.split():
for i in range(len(res[k])):
assert kwargs.get('bumping') or res[k][i] != resw[k][i], (k, i, res[k][i], resw[k][i])
for k in 'covariate model'.split():
for i in range(len(res[k])):
assert res[k][i] == resw[k][i]
def check_weights_diff(covs, meth, weights, model, kwargs):
res = clustered_model(covs, meth, model, **kwargs)
resw = clustered_model(covs, meth, model, weights=weights, **kwargs)
for k in 'p coef'.split():
for i in range(len(res[k])):
assert kwargs.get('bumping') or res[k][i] != resw[k][i], (
k, i, res[k][i], resw[k][i])
for k in 'covariate model'.split():
for i in range(len(res[k])):
assert res[k][i] == resw[k][i]
def check_weight_m(covs, meth, weights, model, kwargs):
res = clustered_model(covs, meth, model, **kwargs)
resw = clustered_model(covs, meth, model, weights=weights, **kwargs)
import sys
print sys.stderr, res
print sys.stderr, resw
for i in range(len(res)):
assert resw['p'][i] > res['p'][i], ('p', i, resw['p'][i], res['p'][i])
assert resw['coef'][i] <= res['coef'][i], ('coef', i, resw['coef'][i],
res['coef'][i])
def check_weight_m(covs, meth, weights, model, kwargs):
res = clustered_model(covs, meth, model, **kwargs)
resw = clustered_model(covs, meth, model, weights=weights, **kwargs)
import sys
print sys.stderr, res
print sys.stderr, resw
for i in range(len(res)):
assert resw['p'][i] > res['p'][i], (
'p', i, resw['p'][i], res['p'][i])
assert resw['coef'][i] <= res['coef'][i], (
'coef', i, resw['coef'][i], res['coef'][i])
def check_weights1(covs, meth, weights, model, kwargs):
res = clustered_model(covs, meth, model, **kwargs)
resw = clustered_model(covs, meth, model, weights=weights, **kwargs)
for k in 'p model covariate coef'.split():
assert k in res, res
assert k in resw, resw
if not 'bumping' in kwargs or k in ('model', 'covariate'):
for i in range(len(res[k])):
val, valw = res[k][i], resw[k][i]
eq = abs(val - valw) < 1e-4 if isinstance(val, float) \
else val == valw
assert eq or (np.isnan(res[k][i]) and np.isnan(resw[k][i])),\
(res[k][i], resw[k][i], k, i)
assert ("|" in model) == ("|" in res['model'][0]), (model, res['model'][0])
def check_weights1(covs, meth, weights, model, kwargs):
res = clustered_model(covs, meth, model, **kwargs)
resw = clustered_model(covs, meth, model, weights=weights, **kwargs)
for k in 'p model covariate coef'.split():
assert k in res, res
assert k in resw, resw
if not 'bumping' in kwargs or k in ('model', 'covariate'):
for i in range(len(res[k])):
val, valw = res[k][i], resw[k][i]
eq = abs(val - valw) < 1e-4 if isinstance(val, float) \
else val == valw
assert eq or (np.isnan(res[k][i]) and np.isnan(resw[k][i])),\
(res[k][i], resw[k][i], k, i)
assert ("|" in model) == ("|" in res['model'][0]), (model, res['model'][0])
def check_clustered_model(covs, meth, model, kwargs):
res = clustered_model(covs, meth, model, **kwargs)
#{'p': 0.153760092338262, 'model': 'methylation ~ disease', 'covariate':
# 'diseaseTRUE', 'liptak': True, 'coef': 0.125455808080808}
for k in 'p model covariate coef'.split():
assert k in res, res
assert ("|" in model) == ("|" in res['model'][0]), (model, res['model'][0])
def check_clustered_model(covs, meth, model, kwargs):
res = clustered_model(covs, meth, model, **kwargs)
#{'p': 0.153760092338262, 'model': 'methylation ~ disease', 'covariate':
# 'diseaseTRUE', 'liptak': True, 'coef': 0.125455808080808}
for k in 'p model covariate coef'.split():
assert k in res, res
assert ("|" in model) == ("|" in res['model'][0]), (model, res['model'][0])
def test_clustered_model():
# test for 20 samples and 5 CpGs
covs, meth = _make_data()
model = "methylation ~ disease + (1|id)"
r = clustered_model(covs, meth, model)
yield check_clustered, r, model
np.random.seed(42)
exp = meth.copy() * 1.15 + np.random.random(meth.shape)
for bad_name in ("", "-", " "):
with tempfile.NamedTemporaryFile(delete=True) as fh:
exp.index = ['gene' + bad_name + l for l in 'ABCDE']
exp.to_csv(fh.name, sep="\t", quote=False, index=True,
index_label="probe")
fh.flush()
r = clustered_model(covs, meth, model, X="'%s'" % fh.name)
yield check_clustered_df, r, model, exp
def test_clustered_model():
# test for 20 samples and 5 CpGs
covs, meth = _make_data()
model = "methylation ~ disease + (1|id)"
r = clustered_model(covs, meth, model)
yield check_clustered, r, model
np.random.seed(42)
exp = meth.copy() * 1.15 + np.random.random(meth.shape)
for bad_name in ("", "-", " "):
with tempfile.NamedTemporaryFile(delete=True) as fh:
exp.index = ['gene' + bad_name + l for l in 'ABCDE']
exp.to_csv(fh.name,
sep="\t",
quote=False,
index=True,
index_label="probe")
fh.flush()
r = clustered_model(covs, meth, model, X="'%s'" % fh.name)
yield check_clustered_df, r, model, exp