import numpy as np
class LinearRegression:
def __int__(self):
'''初始化lineargression 模型参数'''
# theta除第一个后的矩阵
self.coef_ = None
# 截距,第一个theta值
self.intercept_ = None
# theta矩阵
self._theta = None
# 使用正规方程解
def fit_normal(self, X_train, y_train):
'''根据训练集训练模型'''
assert X_train.shape[0] == y_train.shape[0], \
"the size of X_train must be equal to the size of y_train"
# 生成X_b为 n+1 维的矩阵,在第一列加上1
X_b = np.hstack([np.ones((len(X_train), 1)), X_train])
# 正规方程求解公式
self._theta = np.linalg.inv(X_b.T.dot(X_b)).dot(X_b.T).dot(y_train)
# 截距
self.intercept_ = self._theta[0]
self.coef_ = self._theta[1:]
return self
# 使用梯度下降法求theta
def fit_gd(self, X_train, y_trian, eta=0.1, n_iters=1e4):
'''使用梯度下降法训练Linear Regression模型'''
assert X_train.shape[0] == y_trian.shape[0], \
"the size of X_train must be equal to the size of y_train"
# 损失函数
def J(theta, X_b, y):
try:
return np.sum((y - X_b.dot(theta)) ** 2) / len(y)
except:
return float('inf')
# 梯度下降法求theta
def dJ(theta, X_b, y):
# res = np.empty(len(theta))
# res[0] = np.sum(X_b.dot(theta) - y)
#
# for i in range(1, len(theta)):
# res[i] = np.sum((X_b.dot(theta) - y).dot(X_b[:, i]))
# return res * 2 / len(X_b)
# 直接进行矩阵运算
return X_b.T.dot(X_b.dot(theta) - y) * 2 / len(y)
def gradient_descent(X_b, y, initial_theta, eta, n_iters=1e4, epsilon=1e-8):
# 现在的theta 是个矩阵
theta = initial_theta
n_iter = 0
while n_iter <= n_iters:
gradient = dJ(theta, X_b, y)
last_theta = theta
theta = theta - eta * gradient
if (abs(J(theta, X_b, y) - J(last_theta, X_b, y)) < epsilon):
break
n_iter += 1
return theta
# 将X_b 组成位N+1,第一列全为1的矩阵,
X_b = np.hstack([np.ones((len(X_train), 1)), X_train])
initial_theta = np.zeros(X_b.shape[1])
eta = 0.01
self._theta = gradient_descent(X_b, y_trian, initial_theta, eta)
self.intercept_ = self._theta[0]
self.coef_ = self._theta[1:]
def predcit(self, X_predict):
'''给定向量集预测数据,返回预测后的矩阵'''
assert self.intercept_ is not None and self.coef_ is not None, \
"must fit before predict"
assert X_predict.shape[1] == len(self.coef_), \
"the feature number of X_predict must be equal to X_train"
X_b = np.hstack([np.ones((len(X_predict), 1)), X_predict])
#
return X_b.dot(self._theta)
def score(self, X_test, y_test):
'''判断模型准确度'''
y_predict = self.predcit(X_test)
return 1 - (np.sum((y_predict - y_test) ** 2) / len(y_test)) / np.var(y_test)
def __repr__(self):
return 'LinearRegression'
# x = 2 * np.random.random(size=100)
# y = x * 3. + 4. + np.random.normal(size=100)
# X = x.reshape(-1, 1)
#
# lin_reg = LinearRegression()
# lin_reg.fit_gd(X, y)
# print(lin_reg.coef_)
# print(lin_reg.intercept_)
LinearRegression --- python实现
最新推荐文章于 2024-01-22 14:24:00 发布