def train_model(*args):
model, y_train = args[0], args[-1]
#print (y_train)
loss_fn = nn.CrossEntropyLoss(
) if sourceType == SourceType.age else nn.BCELoss()
loss_fn = nn.BCELoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
model.train()
for t in range(epochs):
for i in range(0, len(y_train), batch_size):
if processType == ProcessType.mlp:
models, embedding_train, y_train = args
y_pred = model(embedding_train[i:i + batch_size])
#auc = eval_model(model, embedding_train, y_train)
#print ("epoch "+str(t)+" "+str(auc))
elif processType == ProcessType.name_c_tbn:
model, embedding_train, train_names_idx, train_names_len, y_train = args
y_pred = model(embedding_train[i:i + batch_size],
train_names_idx[i:i + batch_size],
train_names_len[i:i + batch_size])
elif processType == ProcessType.tbn_att or processType == ProcessType.tbnn_att:
model, numerical_train, embedding_train, y_train = args
y_pred = model(numerical_train[i:i + batch_size],
embedding_train[i:i + batch_size])
#auc = eval_model(model, embedding_train, y_train)
#print (y_pred.numpy().tolist())
#print (y_train.numpy().tolist())
#print ("epoch "+str(t)+str(auc))
#break
elif processType == ProcessType.name:
model, train_names_idx, train_names_len, y_train = args
y_pred = model(None, train_names_idx[i:i + batch_size],
train_names_len[i:i + batch_size])
elif processType == ProcessType.tbn_c_name_att:
model, numerical_train, train_names_idx, embedding_train, train_names_len, y_train = args
y_pred = model(numerical_train[i:i + batch_size],
embedding_train[i:i + batch_size],
[(train_names_idx[i:i + batch_size],
train_names_len[i:i + batch_size])])
elif processType == ProcessType.tbnn_e_att:
model, numerical_train, train_emoji_idx, embedding_train, y_train = args
batch_emoji_idx = get_batch_emojis(batch_size, train_emoji_idx,
i)
y_pred = model(numerical_train[i:i + batch_size],
embedding_train[i:i + batch_size],
[(batch_emoji_idx, None)])
else: #if processType == ProcessType.tbn_real_att:
model, numerical_train, embedding_train, y_train = args
y_pred = model(numerical_train[i:i + batch_size],
embedding_train[i:i + batch_size])
#print (1/0)
y_train = y_train.reshape(-1, 1)
#print (y_pred)
#print ( y_train[i:i+batch_size])
loss = loss_fn(y_pred, y_train[i:i + batch_size])
loss.backward()
optimizer.step()
optimizer.zero_grad()
if t % 100 == 99:
print(t, loss.item())
def train_model(*args):
model, y_train = args[0], args[-1]
loss_fn = nn.CrossEntropyLoss() if sourceType == SourceType.age else nn.BCELoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
model.train()
for t in range(epochs):
for i in range(0, len(y_train), batch_size):
if processType == ProcessType.mlp:
model, embedding_train, y_train = args
y_pred = model(embedding_train[i:i+batch_size])
elif processType == ProcessType.name_c_tbn:
model, embedding_train, train_names_idx, train_names_len, y_train = args
y_pred = model(embedding_train[i:i+batch_size], train_names_idx[i:i+batch_size], train_names_len[i:i+batch_size])
elif processType == ProcessType.tbn_att or processType == ProcessType.tbnn_att:
model, numerical_train, embedding_train, y_train = args
y_pred = model(None, embedding_train[i:i+batch_size])
elif processType == ProcessType.name:
model, train_names_idx, train_names_len, y_train = args
y_pred = model(None, train_names_idx[i:i+batch_size], train_names_len[i:i+batch_size])
elif processType == ProcessType.tbn_c_name_att:
model, numerical_train, train_names_idx, embedding_train, train_names_len, y_train = args
y_pred = model(None, embedding_train[i:i+batch_size], [(train_names_idx[i:i+batch_size], train_names_len[i:i+batch_size]) ])
else:
model, numerical_train, train_emoji_idx, embedding_train, y_train = args
batch_emoji_idx = get_batch_emojis(batch_size, train_emoji_idx, i)
y_pred = model(numerical_train[i:i+batch_size], embedding_train[i:i+batch_size], [(batch_emoji_idx, None) ])
loss = loss_fn(y_pred, y_train[i:i+batch_size])
loss.backward()
optimizer.step()
optimizer.zero_grad()
if t % 100 == 99:
print(t, loss.item())
torch.save(model, "saved_model/model_text_name")
def eval_model(*args):
model = args[0]
model.eval()
if processType == ProcessType.mlp:
models, embedding_test, y_test = args
y_hat_test = model(embedding_test)
elif processType == ProcessType.name_c_tbn:
model, embedding_test, test_names_idx, test_names_len, y_test = args
y_hat_test = model(embedding_test, test_names_idx, test_names_len)
elif processType == ProcessType.tbn_att or processType == ProcessType.tbnn_att:
model, numerical_test, embedding_test, y_test = args
y_hat_test = model(numerical_test, embedding_test)
elif processType == ProcessType.name:
model, test_names_idx, test_names_len, y_test = args
y_hat_test = model(test_names_idx, test_names_len)
elif processType == ProcessType.tbn_c_name_att:
model, numerical_test, test_names_idx, embedding_test, test_names_len, y_test = args
y_hat_test = model(numerical_test, embedding_test,
[(test_names_idx, test_names_len)])
elif processType == ProcessType.tbnn_e_att:
model, numerical_test, test_emoji_idx, embedding_test, y_test = args
y_hat_test = []
for i in range(0, len(y_test), batch_size):
batch_emoji_idx = get_batch_emojis(batch_size, test_emoji_idx, i)
with torch.no_grad():
y_hat_test_batch = model(numerical_test[i:i + batch_size],
embedding_test[i:i + batch_size],
[(batch_emoji_idx, None)])
y_hat_test.append(y_hat_test_batch)
y_hat_test = torch.cat(y_hat_test)
elif processType == ProcessType.tbn_real_att:
model, numerical_test, embedding_test, y_test = args
y_hat_test = model(numerical_test, embedding_test)
y_hat_test_class = np.where(
y_hat_test.cpu().detach().numpy() < 0.5, 0, 1
) #np.argmax(y_hat_test.cpu().detach().numpy(), axis=1) if sourceType == SourceType.age else np.where(y_hat_test.cpu().detach().numpy()<0.5, 0, 1)
y_test = torch.squeeze(y_test).cpu().detach().numpy()
#auc = roc_auc_score(y_test, y_hat_test_class, multi_class="ovr" )
print(classification_report(y_test, y_hat_test_class))
print("-----------------")
f1 = f1_score(y_test, y_hat_test_class, average='macro')
return f1