def get_activator_web(dev_split, test_split):
data_name = "Web"
ext_train = ExternalData(WebAllExternalDataParams())
ds = BilinearDataset(WebDatasetAllParams(), external_data=ext_train)
activator_params = WebBilinearActivatorParams()
activator_params.TEST_SPLIT = test_split
activator_params.DEV_SPLIT = dev_split
module_params = WebLayeredBilinearModuleParams(
ftr_len=ds.len_features, embed_vocab_dim=ext_train.len_embed())
return data_name, BilinearMultiClassActivator(
LayeredBilinearModuleGPU(module_params), activator_params, ds)
def get_activator_protein(dev_split, test_split, topological_ftrs=True):
data_name = "Protein"
ext_train = ExternalData(ProteinAllExternalDataParams())
ds_params = ProteinDatasetAllParams()
if not topological_ftrs:
ds_params.FEATURES = []
ds = BilinearDataset(ds_params, external_data=ext_train)
activator_params = ProteinBilinearActivatorParams()
activator_params.TEST_SPLIT = test_split
activator_params.DEV_SPLIT = dev_split
module_params = ProteinLayeredBilinearModuleParams(
ftr_len=ds.len_features, embed_vocab_dim=ext_train.len_embed())
return data_name, BilinearMultiClassActivator(
LayeredBilinearModule(module_params), activator_params, ds)
def get_params_by_dataset(data):
dict_classes = {
"AIDS": [
AidsDatasetAllParams, AidsLayeredBilinearModuleParams,
AidsBilinearActivatorParams,
ExternalData(AidsAllExternalDataParams()), False
],
"PROTEIN": [
ProteinDatasetAllParams, ProteinLayeredBilinearModuleParams,
ProteinBilinearActivatorParams,
ExternalData(ProteinAllExternalDataParams()), True
],
"MUTAGEN": [
MutagenDatasetAllParams, MutagenLayeredBilinearModuleParams,
MutagenBilinearActivatorParams,
ExternalData(MutagenAllExternalDataParams()), False
],
"GREC": [
GrecDatasetAllParams, GrecLayeredBilinearModuleParams,
GrecBilinearActivatorParams,
ExternalData(GrecAllExternalDataParams()), True
]
}
return dict_classes[data]
class AidsBilinearActivatorParams(BilinearActivatorParams):
def __init__(self):
super().__init__()
self.DEV_SPLIT = 0.1153
self.TEST_SPLIT = 0.538
self.LOSS = functional.binary_cross_entropy_with_logits # f.factor_loss #
self.BATCH_SIZE = 128
self.EPOCHS = 250
self.DATASET = "Aids"
if __name__ == '__main__':
ALL = True
if ALL == True:
ext_train = ExternalData(AidsAllExternalDataParams())
aids_train_ds = BilinearDataset(AidsDatasetAllParams(),
external_data=ext_train)
activator = BilinearActivator(
LayeredBilinearModule(
AidsLayeredBilinearModuleParams(
ftr_len=aids_train_ds.len_features,
embed_vocab_dim=ext_train.len_embed())),
AidsBilinearActivatorParams(), aids_train_ds)
activator.train()
if ALL == False:
ext_train = ExternalData(AidsTrainExternalDataParams())
ext_dev = ExternalData(AidsDevExternalDataParams(),
idx_to_symbol=ext_train.idx_to_symbol_dict)
self.BATCH_SIZE = 32
self.EPOCHS = 300
self.DATASET = "Protein - MultiClass"
if __name__ == '__main__':
from bilinear_model import LayeredBilinearModule
from dataset.dataset_model import BilinearDataset
from dataset.dataset_external_data import ExternalData
from multi_class_bilinear_activator import BilinearMultiClassActivator
t = time.time()
ALL = True
if ALL == True:
ext_train = ExternalData(ProteinAllExternalDataParams())
aids_train_ds = BilinearDataset(ProteinDatasetAllParams(),
external_data=ext_train)
activator = BilinearMultiClassActivator(
LayeredBilinearModule(
ProteinLayeredBilinearModuleParams(
ftr_len=aids_train_ds.len_features,
embed_vocab_dim=ext_train.len_embed())),
ProteinBilinearActivatorParams(), aids_train_ds)
activator.train()
if ALL == False:
ext_train = ExternalData(ProteinTrainExternalDataParams())
ext_dev = ExternalData(ProteinDevExternalDataParams(),
idx_to_symbol=ext_train.idx_to_symbol_dict)
dropout=self.DROPOUT)
]
self.BILINEAR_PARAMS = CoilRagBilinearLayerParams(
self.LINEAR_PARAMS_LIST[self.NUM_LAYERS - 1].COL_DIM,
self.LINEAR_PARAMS_LIST[0].ROW_DIM)
class CoilRagBilinearActivatorParams(BilinearActivatorParams):
def __init__(self):
super().__init__()
self.DEV_SPLIT = 0.15
self.TEST_SPLIT = 0.15
self.LOSS = cross_entropy # f.factor_loss #
self.BATCH_SIZE = 16
self.EPOCHS = 500
self.DATASET = "COIL_RAG - MultiClass"
if __name__ == '__main__':
ext_train = ExternalData(CoilRagAllExternalDataParams())
aids_train_ds = BilinearDataset(CoilRagDatasetAllParams(),
external_data=ext_train)
activator = BilinearMultiClassActivator(
LayeredBilinearModule(
CoilRagLayeredBilinearModuleParams(
ftr_len=aids_train_ds.len_features,
embed_vocab_dim=ext_train.len_embed())),
CoilRagBilinearActivatorParams(), aids_train_ds)
activator.train()
x0 = torch.cat([x0] + list_embed, dim=2)
x1 = x0
self._sync()
for i in range(self._num_layers):
x1 = self._linear_layers[i](A, x1)
x2 = self._bilinear_layer(A, x0, x1)
return x2
if __name__ == "__main__":
from dataset.datset_sampler import ImbalancedDatasetSampler
from params.aids_params import AidsAllExternalDataParams, AidsDatasetAllParams
from dataset.dataset_external_data import ExternalData
from dataset.dataset_model import BilinearDataset
ext_train = ExternalData(AidsAllExternalDataParams())
ds = BilinearDataset(AidsDatasetAllParams(), external_data=ext_train)
dl = DataLoader(dataset=ds,
collate_fn=ds.collate_fn,
batch_size=64,
sampler=ImbalancedDatasetSampler(ds))
m_params = LayeredBilinearModuleParams(
ftr_len=ds.len_features, embed_vocab_dim=ext_train.len_embed())
m_params.EMBED_DIMS = [20, 20]
module = LayeredBilinearModule(m_params)
# module = BilinearModule(BilinearModuleParams())
for i, (_A, _D, _x0, _l) in enumerate(dl):
_x2 = module(_A, _D, _x0)
e = 0
labels_batch.append(l)
return Tensor(adjacency_batch), Tensor(x_batch), Tensor(
embeddings_batch).long(), Tensor(labels_batch).long()
def __getitem__(self, index):
gnx_id = self._idx_to_name[index]
A, x, embed, label = self._data[gnx_id]
embed = 0 if embed is None else Tensor(embed).long()
return Tensor(A), Tensor(x), embed, label
def __len__(self):
return len(self._idx_to_name)
if __name__ == "__main__":
from dataset.datset_sampler import ImbalancedDatasetSampler
from params.aids_params import AidsAllExternalDataParams, AidsDatasetAllParams
ext_train = ExternalData(AidsAllExternalDataParams())
ds = BilinearDataset(AidsDatasetAllParams(), external_data=ext_train)
# ds = BilinearDataset(AidsDatasetTestParams())
dl = DataLoader(dataset=ds,
collate_fn=ds.collate_fn,
batch_size=64,
sampler=ImbalancedDatasetSampler(ds))
p = []
for i, (A, x, e, l) in enumerate(dl):
print(i, A, x, e, l)
e = 0
config + ftrs
res_list.append(config_line)
with open(os.path.join("grid_results", file_name.strip(".txt") + "_analyzed.csv"), "wt") as f:
writer = csv.writer(f)
writer.writerows(res_list)
if __name__ == "__main__":
# n = int(sys.argv[1])
n = 0
if n == 0:
GridSearch(AidsDatasetAllParams, AidsLayeredBilinearModuleParams, AidsBilinearActivatorParams,
ExternalData(AidsAllExternalDataParams()), multi_class=False).go("_Aids")
#
# elif n == 1:
# GridSearch(WebDatasetAllParams, WebLayeredBilinearModuleParams, WebBilinearActivatorParams,
# ExternalData(WebAllExternalDataParams()), multi_class=True,
# layers=[[[None, 50], [50, 25]], [[None, 200], [200, 100], [100, 50]]]).go("_Web")
#
# elif n == 2:
# GridSearch(MutagenDatasetAllParams, MutagenLayeredBilinearModuleParams, MutagenBilinearActivatorParams,
# ExternalData(MutagenAllExternalDataParams()), multi_class=False).go("_Mutagen")
#
# elif n == 3:
# GridSearch(ProteinDatasetAllParams, ProteinLayeredBilinearModuleParams, ProteinBilinearActivatorParams,
# ExternalData(ProteinAllExternalDataParams()), multi_class=True,
# layers=[[[None, 25], [50, 25]], [[None, 100], [100, 50], [50, 25]]]).go("_Protein")
#
with open(
os.path.join("grid_results",
file_name.strip(".txt") + "_analyzed.csv"),
"wt") as f:
writer = csv.writer(f)
writer.writerows(res_list)
if __name__ == "__main__":
n = 8 # int(sys.argv[1])
if n == 0:
GridSearch(AidsDatasetAllParams,
AidsLayeredBilinearModuleParams,
AidsBilinearActivatorParams,
ExternalData(AidsAllExternalDataParams()),
multi_class=False).go("_Aids")
elif n == 1:
GridSearch(WebDatasetAllParams,
WebLayeredBilinearModuleParams,
WebBilinearActivatorParams,
ExternalData(WebAllExternalDataParams()),
multi_class=True).go("_Web")
elif n == 2:
GridSearch(MutagenDatasetAllParams,
MutagenLayeredBilinearModuleParams,
MutagenBilinearActivatorParams,
ExternalData(MutagenAllExternalDataParams()),
multi_class=False).go("_Mutagen")
class AidsBilinearActivatorParams(BilinearActivatorParams):
def __init__(self):
super().__init__()
self.DEV_SPLIT = 0.1153
self.TEST_SPLIT = 0.538
self.LOSS = functional.binary_cross_entropy_with_logits # f.factor_loss #
self.BATCH_SIZE = 128
self.EPOCHS = 25
self.DATASET = "Aids"
if __name__ == '__main__':
ALL = True
if ALL == True:
ext_train = ExternalData(AidsAllExternalDataParams())
aids_train_ds = BilinearDataset(AidsDatasetAllParams(), external_data=ext_train)
activator = BilinearActivator(LayeredBilinearModule(AidsLayeredBilinearModuleParams(
ftr_len=aids_train_ds.len_features, embed_vocab_dim=ext_train.len_embed())),
AidsBilinearActivatorParams(), aids_train_ds)
activator.train()
if ALL == False:
ext_train = ExternalData(AidsTrainExternalDataParams())
ext_dev = ExternalData(AidsDevExternalDataParams(), idx_to_symbol=ext_train.idx_to_symbol_dict)
ext_test = ExternalData(AidsTestExternalDataParams(), idx_to_symbol=ext_train.idx_to_symbol_dict)
aids_train_ds = BilinearDataset(AidsDatasetTrainParams(), external_data=ext_train)
aids_dev_ds = BilinearDataset(AidsDatasetDevParams(), external_data=ext_dev)
aids_test_ds = BilinearDataset(AidsDatasetTestParams(), external_data=ext_test)
