davidson_te = DataSet(os.path.join("data", "davidson.te.csv"),
reader=csvreader,
formatter=df,
name="davidson_test")
davidson_te.read()
features = Features(get_feature_functions(mname))
primary_train_fs, aux_train_fs, dev_fs, test_fs_primary, test_fs_aux = features.load(
waseem_tr_composite, davidson_tr, waseem_de_composite,
waseem_te_composite, davidson_te)
print("Number of features in primary: {0}".format(
primary_train_fs[0].shape[1]))
print("Number of features aux (=): {0}".format(aux_train_fs[0].shape[1]))
model = MTMLP(primary_train_fs[0].shape[1], get_model_shape(), 3, 3)
if gpu():
model.cuda()
if model_exists(mname) and os.getenv("TRAIN").lower() not in [
"y", "1", "t", "yes"
]:
model.load_state_dict(torch.load("models/{0}.model".format(mname)))
else:
train_mt(model, (primary_train_fs, aux_train_fs),
50,
1e-3,
45,
dev=dev_fs,
lr_schedule=lambda a, b: exp_lr_scheduler(a, b, 0.5, 5))
waseem_te_composite = CompositeDataset(name="waseem_composite_test")
for dataset in datasets_te:
dataset.read()
waseem_te_composite.add(dataset)
davidson_te = DataSet(os.path.join("data","davidson.te.csv"),reader=csvreader,formatter=df,name="davidson_test")
davidson_te.read()
features = Features(get_feature_functions(mname))
train_fs, dev_fs, test_fs_primary, test_fs_aux = features.load(waseem_tr_composite, waseem_de_composite, waseem_te_composite, davidson_te)
print("Number of features in primary: {0}".format(train_fs[0].shape[1]))
model = MLP(train_fs[0].shape[1],get_model_shape(),3)
if gpu():
model.cuda()
if model_exists(mname) and os.getenv("TRAIN").lower() not in ["y","1","t","yes"]:
model.load_state_dict(torch.load("models/{0}.model".format(mname)))
else:
train(model, train_fs, 50, 1e-3, 45, dev=dev_fs,
lr_schedule=lambda a, b: exp_lr_scheduler(a, b, 0.5, 5))
torch.save(model.state_dict(), "models/{0}.model".format(mname))
create_log_dir(mname)
print_evaluation(model,test_fs_primary, WaseemLabelSchema(),log="logs/{0}/primary.jsonl".format(mname))
print_evaluation(model,test_fs_aux, WaseemLabelSchema(),log="logs/{0}/aux.jsonl".format(mname))