def predict_proba(self, X):
assert self.theta_ is not None, 'you should fit before predict'
if self.copy_X:
X = X.copy()
if self.normalize:
X = StandardScaler_().fit_transform(X)
X = np.hstack([np.ones((X.shape[0], 1)), X])
return self._sigmoid(self.theta_, X)
def fit(self, X, y):
if self.copy_X:
X = X.copy()
if self.normalize:
X = StandardScaler_().fit_transform(X)
X_b = np.c_[np.ones((len(X), 1)), X] # 拼接构造含有常数项b的新样本数据
if self.solver == 'gd':
self._fit_gd(X_b, y)
else:
pass
return self
def fit(self, X, y):
if self.copy_X:
X = X.copy()
if self.normalize:
X = StandardScaler_().fit_transform(X)
X = np.hstack([np.ones((X.shape[0], 1)), X])
theta = np.ones(X.shape[1])
for _ in range(self.n_iters):
theta -= self.alpha * self._dJ(theta, X, y)
self.theta_ = theta
self.coef_ = self.theta_[1:]
self.intercept_ = self.theta_[0]
return self
def predict(self, X_test):
if self.copy_X:
X_test = X_test.copy()
if self.normalize:
X_test = StandardScaler_().fit_transform(X_test)
return np.c_[np.ones((len(X_test), 1)), X_test].dot(self._theta)