Question

我正在尝试学习如何按类对函数进行分组。作为一个例子，我试图编码一个广义最小二乘法来找到一组（x，y）坐标之间的最佳拟合线的方程。对于我的特定情况，我选择了一个简单的行y = x + 5，因此斜率应接近1，y截距应接近5。在下面的编码解决方案中运行我的尝试会产生错误TypeError: set_x() takes 1 positional argument but 2 were given，尽管我试图传递一个x点数组。我该如何规避这个错误？

import numpy as np
from scipy.optimize import minimize


class GeneralizedLeastSquares:

    def __init__(self, residuals=None, parameters=None, x=None, y_true=None, y_fit=None, weights=None, method=None):
        self.residuals = residuals
        self.parameters = parameters
        self.x = x
        self.y_true = y_true
        self.y_fit = y_fit
        self.weights = weights
        self.method = method

    def set_residuals(self, residuals):
        self.residuals = residuals

    def set_parameters(self, parameters):
        self.parameters = parameters

    def set_x(self, x):
        self.x = x

    def set_y_true(self, y_true):
        self.y_true = y_true

    def set_y_fit(self, y_fit):
        self.y_fit = y_fit

    def set_weights(self, weights):
        self.weights = weights

    def set_method(self, method):
        self.method = method

    def get_residuals(self):
        return [(self.y_true[idx] - self.y_fit[idx])**2 for idx in range(len(self.y_true)) if len(self.y_true) == len(self.y_fit) ]

    def get_parameters(self):
        return self.parameters

    def get_x(self):
        return self.x

    def get_y_true(self):
        return self.y_true

    def get_y_fit(self):
        return [self.parameters[0] * self.x[idx] + self.parameters[1] for idx in range(len(self.x))]

    def get_weights(self):
        return self.weights

    def update_weights(self):
        inverse_residuals = [1/self.residuals[idx] for idx in range(len(residuals))]
        inverse_residuals_abs = [abs(inverse_residual) for inverse_residual in inverse_residuals]
        residual_abs_total = sum(inverse_residuals_abs)
        return [inverse_residuals_abs[idx]/residual_abs_total for idx in range(len(inverse_residuals_abs))]

    def get_method(self):
        return self.method

    def get_error_by_residuals(self):
        return sum([self.weights[idx] * self.residuals[idx] for idx in range(len(self.residuals))])

    def get_error_by_std_mean(self):
        return np.std(self.y_true)/np.sqrt(len(self.y_true))

    def get_linear_fit(self):
        """

        """
        if self.parameters == 'estimate':
            slope_init = (self.y_true[-1] - self.y_true[0]) / (self.x[-1] - self.x[0])
            b_init = np.mean([self.y_true[-1] - slope_init * self.x[-1], self.y_true[0] - slope_init * self.x[0]])
            self.parameters = [slope_init, b_init]
        elif not isinstance(self.parameters, (list, np.ndarray)):
            raise ValueError("parameters = 'estimate' or [slope, y-intercept]")
        meths = ['residuals', 'std of mean']
        funcs = [get_error_by_residuals, get_error_by_std_mean]
        func = dict(zip(meths, funcs))[self.method]
        res = minimize(func, x0=self.parameters, args=(self,), method='Nelder-Mead')
        self.parameters = [res.x[0], res.x[1]]
        self.y_fit = get_y_fit(self)
        self.residuals = get_residuals(self)
        self.weights = update_weights(self)
        return self.parameters, self.y_fit, self.residuals, self.weights

x = np.linspace(0, 4, 5)
y_true = np.linspace(5, 9, 5) ## using slope=1, y-intercept=5
y_actual = np.array([4.8, 6.2, 7, 8.1, 8.9]) ## test data
GLS = GeneralizedLeastSquares()
GLS.set_x(x)
GLS.set_y_true(y_actual)
GLS.set_weights(np.ones(len(x)))
GLS.set_parameters('estimate')
# GLS.set_parameters([1.2, 4.9])
GLS.set_method('residuals')
results = GLS.get_linear_fit()
print(results)

Answer 1

你的方法没有争论。它应该是：

def set_x(self, x):
    self.x = x

在get / set方法中包装属性是一种非常Java /过时的处理方式。访问类外的底层属性要容易得多。即而不是：GLS.set_x(12)，考虑更多Pythonic：GLS.x = 12。这样您就不必为每个属性编写get和set方法。

此外，对象的繁重提升方法get_linear_fit放入__call__方法可能更有意义。这样，您只需输入GLS()而不是GLS.get_linear_fit()

即可运行回归

如何将不同类型的参数（例如：数组）传递给功能类？

1 个答案: