verbosity = "high"
base_tox_data_dir = "/home/apappu/deepchem-models/toxcast_models/toxcast/toxcast_data"
tox_tasks, tox_dataset, tox_transformers = load_tox(base_tox_data_dir,
reload=reload)
#removes directory if present -- warning
base_tox_dir = "/home/apappu/deepchem-models/toxcast_models/toxcast/toxcast_analysis"
tox_train_dir = os.path.join(base_tox_dir, "train_dataset")
tox_valid_dir = os.path.join(base_tox_dir, "valid_dataset")
tox_test_dir = os.path.join(base_tox_dir, "test_dataset")
tox_model_dir = os.path.join(base_tox_dir, "model")
tox_splitter = StratifiedSplitter()
#default split is 80-10-10 train-valid-test split
tox_train_dataset, tox_valid_dataset, tox_test_dataset = tox_splitter.train_valid_test_split(
tox_dataset, tox_train_dir, tox_valid_dir, tox_test_dir)
# Fit Logistic Regression models
tox_task_types = {task: "classification" for task in tox_tasks}
classification_metric = Metric(metrics.roc_auc_score,
np.mean,
verbosity=verbosity,
mode="classification")
params_dict = {
"batch_size": None,
"data_shape": tox_train_dataset.get_data_shape(),
verbosity = "high"
base_tox_data_dir = "/home/apappu/deepchem-models/toxcast_models/toxcast/toxcast_data"
tox_tasks, tox_dataset, tox_transformers = load_tox(
base_tox_data_dir, reload=reload)
#removes directory if present -- warning
base_tox_dir = "/home/apappu/deepchem-models/toxcast_models/toxcast/toxcast_analysis"
tox_train_dir = os.path.join(base_tox_dir, "train_dataset")
tox_valid_dir = os.path.join(base_tox_dir, "valid_dataset")
tox_test_dir = os.path.join(base_tox_dir, "test_dataset")
tox_model_dir = os.path.join(base_tox_dir, "model")
tox_splitter = StratifiedSplitter()
#default split is 80-10-10 train-valid-test split
tox_train_dataset, tox_valid_dataset, tox_test_dataset = tox_splitter.train_valid_test_split(
tox_dataset, tox_train_dir, tox_valid_dir, tox_test_dir)
# Fit Logistic Regression models
tox_task_types = {task: "classification" for task in tox_tasks}
classification_metric = Metric(metrics.roc_auc_score, np.mean,
verbosity=verbosity,
mode="classification")
params_dict = {
"batch_size": None,
"data_shape": tox_train_dataset.get_data_shape(),
def test_stratified_multitask_split(self):
"""
Test multitask StratifiedSplitter class
"""
# ensure sparse dataset is actually sparse
sparse_dataset = self.load_sparse_multitask_dataset()
X, y, w, ids = sparse_dataset.to_numpy()
"""
sparsity is determined by number of w weights that are 0 for a given task
structure of w np array is such that each row corresponds to a sample -- e.g., analyze third column for third
sparse task
"""
frac_train = 0.5
cutoff = int(frac_train * w.shape[0])
w = w[:cutoff, :]
sparse_flag = False
col_index = 0
for col in w.T:
if not np.any(col): #check to see if any columns are all zero
sparse_flag = True
break
col_index+=1
if not sparse_flag:
print("Test dataset isn't sparse -- test failed")
else:
print("Column %d is sparse -- expected" % col_index)
assert sparse_flag
stratified_splitter = StratifiedSplitter()
train_data, valid_data, test_data = \
stratified_splitter.train_valid_test_split(
sparse_dataset,
self.train_dir, self.valid_dir, self.test_dir,
frac_train=0.8, frac_valid=0.1, frac_test=0.1
)
datasets = [train_data, valid_data, test_data]
dataset_index = 0
for dataset in datasets:
X, y, w, ids = dataset.to_numpy()
# verify that each task in the train dataset has some hits
for col in w.T:
if not np.any(col):
print("Fail -- one column doesn't have results")
if dataset_index == 0:
print("train_data failed")
elif dataset_index == 1:
print("valid_data failed")
elif dataset_index == 2:
print("test_data failed")
assert np.any(col)
if dataset_index == 0:
print("train_data passed")
elif dataset_index == 1:
print("valid_data passed")
elif dataset_index == 2:
print("test_data passed")
dataset_index+=1
print("end of stratified test")
assert 1 == 1
def test_stratified_multitask_split(self):
"""
Test multitask StratifiedSplitter class
"""
# ensure sparse dataset is actually sparse
sparse_dataset = self.load_sparse_multitask_dataset()
X, y, w, ids = sparse_dataset.to_numpy()
"""
sparsity is determined by number of w weights that are 0 for a given task
structure of w np array is such that each row corresponds to a sample -- e.g., analyze third column for third
sparse task
"""
frac_train = 0.5
cutoff = int(frac_train * w.shape[0])
w = w[:cutoff, :]
sparse_flag = False
col_index = 0
for col in w.T:
if not np.any(col): #check to see if any columns are all zero
sparse_flag = True
break
col_index += 1
if not sparse_flag:
print("Test dataset isn't sparse -- test failed")
else:
print("Column %d is sparse -- expected" % col_index)
assert sparse_flag
stratified_splitter = StratifiedSplitter()
train_data, valid_data, test_data = \
stratified_splitter.train_valid_test_split(
sparse_dataset,
self.train_dir, self.valid_dir, self.test_dir,
frac_train=0.8, frac_valid=0.1, frac_test=0.1
)
datasets = [train_data, valid_data, test_data]
dataset_index = 0
for dataset in datasets:
X, y, w, ids = dataset.to_numpy()
# verify that each task in the train dataset has some hits
for col in w.T:
if not np.any(col):
print("Fail -- one column doesn't have results")
if dataset_index == 0:
print("train_data failed")
elif dataset_index == 1:
print("valid_data failed")
elif dataset_index == 2:
print("test_data failed")
assert np.any(col)
if dataset_index == 0:
print("train_data passed")
elif dataset_index == 1:
print("valid_data passed")
elif dataset_index == 2:
print("test_data passed")
dataset_index += 1
print("end of stratified test")
assert 1 == 1
