sklearn中logical regression的底层代码

在sklearn中，logistic regression的底层代码主要是基于两种算法实现的：梯度下降和拟牛顿法。

1. 使用梯度下降算法实现的代码：

class LogisticRegressionGD(BaseEstimator, ClassifierMixin):
    def __init__(self, eta=0.1, n_iter=100):
        self.eta = eta
        self.n_iter = n_iter

    def fit(self, X, y):
        self.w_ = np.zeros(1 + X.shape[1])
        self.cost_ = []

        for i in range(self.n_iter):
            output = self.net_input(X)
            errors = (y - output)
            self.w_[1:] += self.eta * X.T.dot(errors)
            self.w_[0] += self.eta * errors.sum()
            cost = (-y.dot(np.log(output)) - ((1 - y).dot(np.log(1 - output))))
            self.cost_.append(cost)
        return self

    def net_input(self, X):
        return np.dot(X, self.w_[1:]) + self.w_[0]

    def predict(self, X):
        return np.where(self.net_input(X) >= 0.0, 1, 0)

2. 使用拟牛顿法实现的代码：

class LogisticRegressionNM(BaseEstimator, ClassifierMixin):
    def __init__(self, eta=1.0, n_iter=50, random_state=1):
        self.eta = eta
        self.n_iter = n_iter
        self.random_state = random_state

    def fit(self, X, y):
        rgen = np.random.RandomState(self.random_state)
        self.w_ = rgen.normal(loc=0.0, scale=0.01, size=1 + X.shape[1])
        self.cost_ = []

        X_augmented = np.insert(X, 0, 1, axis=1)
        for i in range(self.n_iter):
            output = self.sigmoid(X_augmented.dot(self.w_))
            errors = y - output
            grad = X_augmented.T.dot(errors) / len(X)
            hessian = X_augmented.T.dot(np.diag(output * (1 - output)).dot(X_augmented)) / len(X)
            self.w_ += self.eta * np.linalg.inv(hessian).dot(grad)
            cost = (-y.dot(np.log(output)) - ((1 - y).dot(np.log(1 - output))))
            self.cost_.append(cost)

        return self

    def sigmoid(self, z):
        return 1 / (1 + np.exp(-z))

    def net_input(self, X):
        return np.dot(X, self.w_[1:]) + self.w_[0]

    def predict(self, X):
        return np.where(self.net_input(X) >= 0.0, 1, 0)

以上就是sklearn中logistic regression的底层代码。其中，LogisticRegressionGD使用梯度下降算法实现，而LogisticRegressionNM使用拟牛顿法实现。