def MFE(self, X_split, y_split, model):
if model == 'SVM':
X_split_scaled = standard_scale(X_split)
Model = SVM()
Model.fit(X_split_scaled[0], y_split[0])
y_hat = Model.predict(X_split_scaled[2])
elif model == 'RF':
Model = RF()
Model.fit(np.concatenate([X_split[0], X_split[1]]),
np.concatenate([y_split[0], y_split[1]]))
y_hat = Model.predict(X_split[2])
elif model == 'FNN':
X_split_scaled = standard_scale(X_split)
Model = FNN(model)
Model.fit(X_split_scaled[0],
y_split[0],
validation_data=[X_split_scaled[1], y_split[1]],
epochs=self.MAX_EPOCH,
batch_size=self.BATCH_SIZE,
callbacks=[self.es])
y_hat = Model.predict_classes(X_split_scaled[2])
else:
print('model undefined')
return self.evaluate(y_split[2], y_hat)
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)
# 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
evaluate_model(result, test_label)
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')
plt.show()
print(loss_history[::100])
# ********************* metrics ***********************
pred = np.argmax(model.predict(model.X, add_ones=False), axis=1)
pred_v = np.argmax(model.predict(Xv), axis=1)
pred_te = np.argmax(model.predict(Xte), axis=1)
# # ********************* metrics ***********************
print(metrics.accuracy(y, pred))
print(metrics.accuracy(Yv, pred_v))
print(metrics.accuracy(Yte, pred_te))
# print(np.mean(metrics.null_accuracy(Yte)))
# 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
evaluate_model(result, test_label)
# 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("./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("./samples/test_data")
# get feature from test data
#test_data, test_label = feature_data(tagger, exp, bag, test_review)
# predict model
result = model.predict(train_data)
# evaluate accuracy
evaluate_model(result, train_label)
with open("fault", "w") as ff:
for i, v in enumerate(train_data):
if result[i] != train_label[i]:
ff.write("real:{0!s:s}: {1!s:s}\n" .format(train_review[i][0], train_review[i][1]))
ff.write("[{0:f} {1:f} {2:f} {3:f} {4:f} {5:f} {6:f} {7:f}\n" .format(v[0], v[1], v[2], v[3], v[4], v[5], v[6], v[7]))