def train_atk_classifier(key, size=1900):
pca = None
X_train, Y_train = [], []
for i in [0, 1]:
f = open(PATH.format(key, i), 'r')
sents = [x[:-1] for x in f if x[:-1] != '']
embs = embedding(sents, EMB_PATH.format(key, i), ARCH)
if args.prefix != 'part':
embs = embs[np.random.choice(len(embs), size, replace=False), :]
X_train.append(embs)
Y_train.extend([i] * embs.shape[0])
X_train = np.concatenate(X_train, axis=0)
Y_train = np.array(Y_train)
train_embs = np.load(TRAIN_EMB_PATH)
# BottleNeck
# X_train = np.load(TRAIN_EMB_PATH)
# raw_train = list(open(TRAIN_PATH, 'r'))
# if IS_BALANCED:
# raw_train, X_train = balance(key, raw_train, X_train)
# Y_train = np.array([(key in x) for x in raw_train])
# load validation set
raw_valid, X_valid = list(open(TARGET_PATH, 'r')), np.load(TARGET_EMB_PATH)
if (key != 'potato' and IS_BALANCED):
raw_valid, X_valid = balance(key, raw_valid, X_valid)
print(len(raw_valid))
Y_valid = np.array([(key in x) for x in raw_valid])
acc = -1
# learn a transfer
# clf = linear_model.SGDClassifier(max_iter = 1000, verbose = 0)
# clf = SVC(kernel = 'rbf', gamma = 'scale', verbose = False)
# clf = KNeighborsClassifier(n_neighbors=1, p = 1)
if (NONLINEAR):
# clf = DANN(input_size = EMB_DIM, maxiter = 2000, verbose = False, name = key, batch_size = 128)
clf = DANN(input_size=EMB_DIM,
maxiter=4000,
verbose=True,
name=key,
batch_size=64,
lambda_adapt=1.0,
hidden_layer_size=25)
acc = clf.fit(X_train,
Y_train,
X_adapt=train_embs,
X_valid=X_valid,
Y_valid=Y_valid)
print("DANN Acc.: {:.4f}".format(acc))
# train_embs = train_embs[np.random.choice(len(train_embs), 2000), :]
# # apply pca first
# if(DO_PCA):
# train_embs = train_embs[np.random.choice(len(train_embs), size = 6 * int(len(X_train)), replace = False)]
# package = np.concatenate([X_train, train_embs], axis = 0)
# pca = PCA(n_components=INPUT_DIM)
# pca.fit(package)
# X_train, train_embs = pca.transform(X_train), pca.transform(train_embs)
# if NONLINEAR:
# clf = NonLinearClassifier(key, ARCH, cls_num = 2, pca = pca, use_pca = DO_PCA)
# clf.fit(X_train, Y_train)
if NONLINEAR:
clf.to(torch.device('cpu'))
# on current set
# correct = 0
if (VERBOSE):
print("TRAIN INFERENCE MODEL FROM EXTERNAL SOURCES (# = {})".format(
len(X_train)))
correct = np.sum((clf.predict(X_train) == Y_train))
print("Source Domain Acc.: {:.4f}".format(correct / len(Y_train)))
return clf, pca, acc
