def evaluate_reg(self):
reg_vals = []
for group in self.param_groups:
group_reg_val = 0.0
# define regularizer for this group
reg = group['reg']
# evaluate the reguarizer for each parametr in group
for p in group['params']:
group_reg_val += reg(p)
# append the group reg val
reg_vals.append(group_reg_val)
return reg_vals
def linear_grad(X, y, theta, reg=None, lambda_=0):
"""
compute the gradient of cost function
:param
X: matrix of dataset [x(0).T,x(1).T,...,x(m).T]
y: real value for each example (=row) in X
theta: vector of parameters for the feature
reg: <function>: function for regularization the gradient
lambda: limit the search area of theta
:return: cost'(X)
:efficiency: O(m*n + m*n^2 + n)
"""
grad = (X.T @ (X @ theta - y))
if reg:
grad[1:] += lambda_ * reg(theta[1:])
return (1 / X.shape[0]) * (X.T @ (X @ theta - y))
def linear_cost(X, y, theta, reg=None, lambda_=0):
"""
compute the cost of the range between X*theta and y
:param
X: matrix of dataset [x(0).T,x(1).T,...,x(m).T]
y: real value for each example (=row) in X
theta: vector of parameters for the feature
reg: <function>: function for regularization the cost
lambda: limit the search area of theta
:return: <float>: J cost of data x for the current theta
:efficiency: O(m*n^2)
"""
J = np.sum((X @ theta - y)**2)
if reg:
J += lambda_ * reg(theta[1:])
return (1 / (2 * X.shape[0])) * J
def class_cost(X, y, theta, reg=None, lambda_=0):
"""
compute the cost of the range between sigmoid(X*theta) and y
:param
X: matrix of dataset [x(0).T,x(1).T,...,x(m).T]
y: real value for each example (=row) in X
theta: vector of parameters for the feature
reg: <function>: function for regularization the cost
lambda: limit the search area of theta
:return: <float>: J cost of data x for the current theta
:efficiency: O(m*n^2)
"""
m = X.shape[0]
Z = sigmoid(X, theta)
J = (-1 / m) * (np.sum(np.log(Z[y == 1])) + np.sum(np.log(1 - Z[y == 0])))
if reg:
J += (lambda_ / (2 * m)) * reg(theta[1:]) # regularization
return J
def class_grad(X, y, theta, reg=None, lambda_=0):
"""
compute the gradient of cost function
:param
X: matrix of dataset [x(0).T,x(1).T,...,x(m).T]
y: real value for each example (=row) in X
theta: vector of parameters for the feature
reg: <function>: function for regularization the gradient
lambda: limit the search area of theta
:return: cost'(X)
:efficiency: O(m*n + m*n^2 + n)
"""
m = X.shape[0]
grad = (1 / m)
Z = sigmoid(X, theta)
grad *= (X.T @ (Z - y))
if reg:
grad[1:] += (lambda_ / m) * reg(theta[1:]) # regularization gradient
return grad
number = []
# Load text
f = textReader("uploaded/" + filename).readText()
for row in f:
temp = tokenize.sent_tokenize(row)
for text in temp:
sentenceContainer.append(text.lower())
# Select algorithm
if (algoritma == "bm"):
alg = bm()
elif (algoritma == "kmp"):
alg = kmp()
else:
alg = reg()
queryNumber = r"^([0-9]+([\.,:]?[0-9]*)*)$"
queryDate = r".?(([1-9]|1[0-9]|2[0-9]|3[0-1])(/|-)(0?[1-9]|1[0-2])(/|-|)([0-9]{0,4})).?"
queryMonth = r"\b(januari|februari|maret|april|mei|juni|juli|agustus|september|oktober|november|desember|jan|feb|mar|apr|jun|jul|ags|sep|okt|nov|des)\b"
queryDay = r"\b(senin|selasa|rabu|kamis|jumat|sabtu|minggu)\b"
queryTime = r"^(wib|wita|wit|pm|am)"
# Sub sentence
for row in sentenceContainer:
subsSentence = []
row = row.split(' ')
for sub in row:
subsSentence.append(sub)
newContainer.append(subsSentence)