def train():
train_loader = DataLoader(dataset=dataset,
batch_size=config.batch,
shuffle=True,
collate_fn=collate_fn,
num_workers=0)
model = SVM(config.embedding, config.strmaxlen, dataset.get_vocab_size(), config.output_size)
optimizer = optim.SGD(model.parameters(), lr=config.lr)
model.train()
for epoch in range(config.epoch):
sum_loss = 0
for i, (data, labels) in enumerate(train_loader):
optimizer.zero_grad()
output = model(data).squeeze()
weight = model.weight.squeeze()
weight = weight.reshape((weight.shape[0],1))
loss = model.loss(output, labels)
tmp = weight.t() @ weight
loss += config.c * tmp[0][0] / 2.0
loss.backward()
optimizer.step()
sum_loss += float(loss)
print("Epoch: {:4d}\tloss: {}".format(epoch, sum_loss /len(dataset)))
def svm():
# ********************* load the dataset and divide to X&y ***********************
from sklearn.datasets import make_blobs
X, Y = make_blobs(cluster_std=0.9,
random_state=20,
n_samples=1000,
centers=10,
n_features=10)
from Algorithms.ML_.helper.data_helper import split_train_val_test
X, Xv, y, Yv, Xt, Yt = split_train_val_test(X, Y)
print(X.shape, y.shape, Xv.shape, Yv.shape, Xt.shape, Yt.shape)
# ********************* build model ***********************
from model import SVM
from activation import Activation, Softmax, Hinge
from regularization import Regularization, L1, L2, L12
from optimizer import Vanilla
model = SVM()
learning_rate, reg_rate = 1e-3, 5e-1
model.compile(alpha=learning_rate,
lambda_=reg_rate,
activation=Softmax(),
reg=L2(),
opt=Vanilla())
model.describe()
# ********************* train ***********************
loss_train, loss_val = model.train(X,
y,
val=(Xv, Yv),
iter_=1000,
return_loss=True,
verbose=True,
eps=1e-3)
import matplotlib.pyplot as plt
plt.plot(range(len(loss_train)), loss_train)
plt.plot(range(len(loss_val)), loss_val)
plt.legend(['train', 'val'])
plt.xlabel('Iteration')
plt.ylabel('Training loss')
plt.title('Training Loss history')
plt.show()
# ********************* predict ***********************
pred_train = model.predict(X)
pred_val = model.predict(Xv)
pred_test = model.predict(Xt)
import metrics
print('train accuracy=', metrics.accuracy(y, pred_train))
print('val accuracy=', metrics.accuracy(Yv, pred_val))
print('test accuracy=', metrics.accuracy(Yt, pred_test))
print('null accuracy=', metrics.null_accuracy(y))
import metrics
metrics.print_metrics(Yt, pred_test)
def test_svm(train_data,
test_data,
kernel_func=linear_kernel,
lambda_param=.1):
"""
Create an SVM classifier with a specificied kernel_func, train it with
train_data and print the accuracy of model on test_data
:param train_data: a namedtuple including training inputs and training labels
:param test_data: a namedtuple including test inputs and test labels
:param kernel_func: kernel function to use in the SVM
:return: None
"""
svm_model = SVM(kernel_func=kernel_func, lambda_param=lambda_param)
svm_model.train(train_data.inputs, train_data.labels)
train_accuracy = svm_model.accuracy(train_data.inputs, train_data.labels)
test_accuracy = svm_model.accuracy(test_data.inputs, test_data.labels)
if not (train_accuracy is None):
print('Train accuracy: ', round(train_accuracy * 100, 2), '%')
if not (test_accuracy is None):
print('Test accuracy:', round(test_accuracy * 100, 2), '%')
# load sentiment dictionary
bag = utils.load_dictionary()
# load model if exist
try:
with open("../Resources/models/model", "rb") as model_file:
model = pickle.load(model_file)
except IOError as err:
# load training reviews from file
train_review = utils.load_reviews("../Resources/samples/train_data")
# get feature from train data
train_data, train_label = feature_data(tagger, exp, bag, train_review)
# initalize classifer class
model = SVM()
# train model
model.train(train_data, train_label)
#save model
with open("../Resources/models/model", "wb") as model_file:
pickle.dump(model, model_file)
else:
print("use saved model..")
# load test reviews from file
test_review = utils.load_reviews("../Resources/samples/test_data")
# get feature from test data
test_data, test_label = feature_data(tagger, exp, bag, test_review)
# predict model
result = model.predict(test_data)
# evaluate accuracy
# ********************* train ***********************
# model = SVM()
# model.compile(lambda_=2.5e4, alpha=1e-7) # 1e-7, reg=2.5e4,
# loss_history = model.train(X, y, eps=0.001, batch=200, iter_=1500)
#
# plt.plot(range(len(loss_history)), loss_history)
# plt.xlabel('Iteration number')
# plt.ylabel('Loss value')
# plt.show()
# print(loss_history[::100])
# lr, rg = SVM.ff(X, y, Xv, Yv, [1e-7, 1e-6],[2e4, 2.5e4, 3e4, 3.5e4, 4e4, 4.5e4, 5e4, 6e4])
# print(lr, rg)
model = SVM()
model.compile(alpha=1e-7, lambda_=2, activation=Softmax, reg=L2)
# model.compile(alpha=0, lambda_=0, activation=Hinge, Reg=L2, dReg=dL2)
history = model.train(Xd, Yd, iter_=0, eps=0.0001)
print(model.loss(model.X, model.y, add_ones=False),
np.sum(model.grad(model.X, model.y, False)))
L, dW = model.grad(model.X, model.y, True)
print(L, np.sum(dW))
# print(np.sum(model.W))
# print(np.sum(model.grad(model.X, model.y, loss_=False)))
# print(np.sum(model.grad1(model.X, model.y)))
# L, dW = model.activation.loss_grad_loop(model.X, model.W, model.y)
# print(L, np.sum(dW))
loss_history = model.train(X, y, eps=0.0001, batch=200, iter_=1500)
plt.plot(range(len(loss_history)), loss_history)
plt.xlabel('Iteration number')
plt.ylabel('Loss value')
# load sentiment dictionary
bag = utils.load_dictionary()
# load model if exist
try:
with open("../Resources/models/model", "rb") as model_file:
model = pickle.load(model_file)
except IOError as err:
# load training reviews from file
train_review = utils.load_reviews("../Resources/samples/train_data")
# get feature from train data
train_data, train_label = feature_data(tagger, exp, bag, train_review)
# initalize classifer class
model = SVM()
# train model
model.train(train_data, train_label)
#save model
with open("../Resources/models/model", "wb") as model_file:
pickle.dump(model, model_file)
else:
print("use saved model..")
# load test reviews from file
test_review = utils.load_reviews("../Resources/samples/test_data")
# get feature from test data
test_data, test_label = feature_data(tagger, exp, bag, test_review)
# predict model
result = model.predict(test_data)
# evaluate accuracy