Python 生成二维数据（带偏移量）（用于求拟合直线）

import random

import numpy as np


class faker_xy_data:

    def __init__(self):
        self.N = None
        self.a = None
        self.b = None
        self.x_plus = None
        # 设置 直线 y= ax +b
        self.data = []

    def build(self):
        self.a = random.uniform(1, 2)
        #   系数 a
        self.b = random.uniform(10, 20)
        # 系数 B
        self.x_plus = 0
        # x 的起始点
        self.N = 100
        #  生成数据点个数

        for i in range(self.N):
            self.next_x()
            self.data.append(self.offset())

        return self.data

    def next_x(self):
        '''
        生成下一个 x的坐标
        基本加数 为 1
        偏移量 符合正太分布

        '''
        self.x_plus += np.random.normal(loc=1)
        return self.x_plus

    def real_xy(self):
        x = self.x_plus
        y = self.x_plus * self.a + self.b

        return x, y

    def offset(self):
        """
        对真实的数据点 进行偏移
        偏移量符合正态分布

        """
        x, y = self.real_xy()

        x_x = round(x + np.random.normal(0), 2)
        y_y = round(y + np.random.normal(0), 2)
        # round 保留两位小数
        return x_x, y_y


x1 = faker_xy_data()
data = x1.build()

print(f"A={x1.a} B={x1.b}")
for i in data:
    print(i)

生成的一组数据

A=1.7552930636605855 B=15.899836050171853
(1.68, 19.41)
(0.6, 18.83)
(2.89, 21.98)
(3.42, 22.49)
(4.87, 24.07)
(4.24, 25.84)
(6.31, 28.13)
(5.09, 28.73)
(5.6, 27.59)
(6.92, 27.59)
(9.55, 32.1)
(8.18, 32.37)
(12.13, 34.53)
(11.96, 37.34)
(11.02, 40.05)
(15.64, 39.3)
(13.13, 42.11)
(12.4, 40.63)
(16.3, 45.86)
(18.02, 48.05)
(20.92, 47.55)
(18.28, 49.61)
(19.22, 50.23)
(18.89, 51.33)
(18.6, 49.89)
(23.12, 55.21)
(22.74, 56.94)
(23.77, 56.32)
(25.91, 56.26)
(23.32, 59.6)
(26.61, 64.1)
(27.69, 65.48)
(29.15, 65.07)
(28.18, 64.37)
(32.31, 71.24)
(31.76, 73.35)
(32.27, 73.61)
(31.78, 71.86)
(33.23, 70.76)
(30.13, 71.55)
(37.37, 79.89)
(37.58, 81.51)
(38.65, 83.05)
(40.29, 83.85)
(38.07, 83.49)
(42.54, 88.97)
(43.55, 92.71)
(45.46, 93.95)
(46.1, 94.23)
(46.96, 97.61)
(47.35, 99.99)
(46.11, 97.57)
(47.06, 98.88)
(49.24, 102.27)
(51.11, 104.28)
(52.38, 108.75)
(52.82, 110.42)
(55.15, 114.03)
(58.04, 114.65)
(58.04, 119.35)
(58.76, 119.67)
(59.91, 119.15)
(60.59, 122.56)
(60.65, 122.45)
(62.99, 127.08)
(62.91, 126.81)
(64.65, 128.88)
(63.69, 131.39)
(66.52, 134.73)
(70.09, 137.28)
(72.03, 143.61)
(73.53, 145.03)
(72.33, 144.18)
(75.2, 148.04)
(77.52, 150.7)
(77.71, 151.8)
(76.98, 152.45)
(80.9, 155.71)
(81.21, 158.6)
(83.51, 161.62)
(85.97, 166.23)
(88.42, 169.79)
(88.94, 172.16)
(90.12, 176.91)
(93.3, 178.24)
(93.0, 181.51)
(93.31, 179.74)
(94.07, 182.65)
(96.2, 187.75)
(97.03, 187.6)
(98.66, 188.96)
(98.26, 190.44)
(99.9, 192.58)
(101.17, 195.9)
(103.86, 196.18)
(104.58, 200.77)
(106.58, 202.77)
(109.03, 208.29)
(109.71, 211.88)
(108.8, 206.42)