def test_ecfp_3(data):
fps = ECFP(n_jobs=1, input_type='any')
try:
fps.transform(data['mols'] + data['smis'])
except BaseException as e:
print(e)
assert False, 'should not got error'
else:
assert True
def test_ecfp_4(data):
fps = ECFP(n_jobs=1, input_type='any')
with pytest.raises(ValueError):
fps.transform(data['err_smis'])
fps = ECFP(n_jobs=1, input_type='any', on_errors='nan')
ret = fps.transform(data['err_smis'])
assert pd.DataFrame(data=ret).shape == (4, 2048)
assert np.isnan(ret[1][10])
assert np.isnan(ret[2][20])
def test_iqspr_1(data):
np.random.seed(0)
ecfp = ECFP(n_jobs=1, input_type='smiles')
bre = BayesianRidgeEstimator(descriptor=ecfp)
ngram = NGram()
iqspr = IQSPR(estimator=bre, modifier=ngram)
X, y = data['pg']
bre.fit(X, y)
ngram.fit(data['pg'][0][0:20], train_order=10)
beta = np.linspace(0.05, 1, 10)
for s, ll, p, f in iqspr(data['pg'][0][:5], beta, yield_lpf=True, bandgap=(0.1, 0.2), density=(0.9, 1.2)):
assert np.abs(np.sum(p) - 1.0) < 1e-5
assert np.sum(f) == 5, print(f)
def data():
# ignore numpy warning
import warnings
print('ignore NumPy RuntimeWarning\n')
warnings.filterwarnings("ignore", message="numpy.dtype size changed")
warnings.filterwarnings("ignore", message="numpy.ndarray size changed")
pwd = Path(__file__).parent
pg_data = pd.read_csv(str(pwd / 'polymer_test_data.csv'))
X = pg_data['smiles']
y = pg_data.drop(['smiles', 'Unnamed: 0'], axis=1)
ecfp = ECFP(n_jobs=1, input_type='smiles', target_col=0)
rdkitfp = RDKitFP(n_jobs=1, input_type='smiles', target_col=0)
bre = GaussianLogLikelihood(descriptor=ecfp)
bre2 = GaussianLogLikelihood(descriptor=rdkitfp)
bre.fit(X, y[['bandgap', 'glass_transition_temperature']])
bre2.fit(X, y[['density', 'refractive_index']])
bre.update_targets(bandgap=(1, 2), glass_transition_temperature=(200, 300))
bre2.update_targets(refractive_index=(2, 3), density=(0.9, 1.2))
class MyLogLikelihood(BaseLogLikelihoodSet):
def __init__(self):
super().__init__()
self.loglike = bre
self.loglike = bre2
like_mdl = MyLogLikelihood()
ngram = NGram()
ngram.fit(X[0:20], train_order=5)
iqspr = IQSPR(estimator=bre, modifier=ngram)
# prepare test data
yield dict(ecfp=ecfp,
rdkitfp=rdkitfp,
bre=bre,
bre2=bre2,
like_mdl=like_mdl,
ngram=ngram,
iqspr=iqspr,
pg=(X, y))
print('test over')
def test_fps_4(data):
fps = Fingerprints(n_jobs=1, input_type='any')
try:
fps.transform(data['err_smis'])
except ValueError:
assert True
else:
assert False, 'should not got error'
fps = ECFP(n_jobs=1, input_type='any', on_errors='nan')
try:
ret = fps.transform(data['err_smis'])
assert pd.DataFrame(data=ret).shape == (4, 2048)
assert np.isnan(ret[1][10])
assert np.isnan(ret[2][20])
except:
assert False
else:
assert True
def data():
# ignore numpy warning
import warnings
print('ignore NumPy RuntimeWarning\n')
warnings.filterwarnings("ignore", message="numpy.dtype size changed")
warnings.filterwarnings("ignore", message="numpy.ndarray size changed")
pwd = Path(__file__).parent
pg_data = pd.read_csv(str(pwd / 'polymer_test_data.csv'))
X = pg_data['smiles']
y = pg_data.drop(['smiles', 'Unnamed: 0'], axis=1)
ecfp = ECFP(n_jobs=1, input_type='smiles')
bre = BayesianRidgeEstimator(descriptor=ecfp)
ngram = NGram()
iqspr = IQSPR(estimator=bre, modifier=ngram)
# prepare test data
yield dict(ecfp=ecfp, bre=bre, ngram=ngram, iqspr=iqspr, pg=(X, y))
print('test over')
def test_ecfp_2(data):
fps = ECFP(n_jobs=1, input_type='smiles')
try:
fps.transform(data['mols'])
except TypeError:
assert True
else:
assert False, 'should not got error'
try:
fps.transform(data['smis'])
except:
assert False, 'should not got error'
else:
assert True
def test_ecfp_1(data):
fps = ECFP(n_jobs=1)
try:
fps.transform(data['mols'])
except:
assert False, 'should not got error'
else:
assert True
try:
fps.transform(data['smis'])
except TypeError:
assert True
else:
assert False, 'should not got error'
def test_ecfp_3(data):
fps = ECFP(n_jobs=1, input_type='any')
fps.transform(data['mols'] + data['smis'])
def test_ecfp_2(data):
fps = ECFP(n_jobs=1, input_type='smiles')
with pytest.raises(TypeError):
fps.transform(data['mols'])
fps.transform(data['smis'])
def test_ecfp_1(data):
fps = ECFP(n_jobs=1)
fps.transform(data['mols'])
with pytest.raises(TypeError):
fps.transform(data['smis'])
def __init__(self, n_jobs=-1):
super().__init__()
self.n_jobs = n_jobs
self.rdkit_fp = ECFP(n_jobs, on_errors='nan', input_type='smiles')
self.rdkit_fp = MACCS(n_jobs, on_errors='nan', input_type='smiles')
