python matplotlib绘图：探究各省人均GDP与出生率的关系

# readexcel.py
# 读取一个excel文档
 
def read(filename: str):
    import xlrd
    # 打开一个Excel文件
    data = xlrd.open_workbook(filename)
    # 打开第一个工作表
    table = data.sheets()[0]
    # 遍历各行
    the_excel = []
    for i in range(table.nrows):
        the_excel.append(table.row_values(i))
 
    return the_excel

————————————————
版权声明：本文为CSDN博主「Ng Wing Kei」的原创文章，遵循CC 4.0 BY-SA版权协议，转载请附上原文出处链接及本声明。
原文链接：https://blog.csdn.net/weixin_42237817/article/details/120856790

import readexcel
import numpy as np
import matplotlib.pyplot as plt
import random

data = readexcel.read('MyExcel.xlsx')

def linear_plot():
    SumXiYi = 0
    SumXi = 0
    SumYi = 0
    SumXi2 = 0

    data_1 = list()

    for item in range(len(data)):
        a_note = list()
        for i in range(3):
            a_note.append([data[item][i*2], data[item][i*2+1]])
        data_1.append(a_note)

    for i in range(3):
        PointX = []
        PointY = []
        SumXiYi = 0
        SumXi = 0
        SumYi = 0
        SumXi2 = 0
        for item in range(len(data_1)):
            PointX.append(data_1[item][i][0])
            PointY.append(data_1[item][i][1])
            XiYi = PointX[item] * PointY[item]
            SumXiYi += XiYi
            SumXi += PointX[item]
            SumYi += PointY[item]
            SumXi2 += PointX[item]**2

        w = (len(data) * SumXiYi - SumXi * SumYi) / (len(data_1) * SumXi2 - SumXi * SumXi)
        b = (SumXi2 * SumYi - SumXiYi * SumXi) / (len(data) * SumXi2 - SumXi * SumXi)

        X = np.arange(min(PointX) - 1, max(PointX) + 2)
        Y = w * X + b

        plt.plot(X, Y, color=['green','red','blue'][i])
        # plt.scatter(PointX, PointY, color=['green','red','blue'][i])  # 散点图
        plt.text(max(PointX), w * max(PointX) + b, f'{2015+2*i}',color=['green','red','blue'][i])

    for item in range(len(data_1)):
        PointX = []
        PointY = []
        col = (random.randint(0, 255) / 255, random.randint(0, 255) / 255, random.randint(0, 255) / 255)
        for i in range(3):
            PointX.append(data_1[item][i][0])
            PointY.append(data_1[item][i][1])
        X = [PointX[0], PointX[1]]
        Y = [PointY[0], PointY[1]]
        plt.plot(X, Y, color=col)
        X = [PointX[1], PointX[2]]
        Y = [PointY[1], PointY[2]]
        plt.plot(X, Y, color=col)
        plt.scatter(PointX[0], PointY[0], marker=10, color=col)  # 散点图
        plt.scatter(PointX[1:3], PointY[1:3], color=col)



    plt.title("birth rate-GDP per 10k capita")
    plt.xlabel("GDP per 10k capita\nThe triangle represents the 2015 data of China's provinces. The data along the line are 2017 and 2019.")
    plt.ylabel("birth rate(‰)")

    # plt.text(max(PointX)/2, w * max(PointX) + b, f'y={w:.2f}*X+{b:.2f}')
    plt.show()

    return w, b

linear_plot()

数据：

第0、1列是2015年的数据，2、3列是2017年的数据，4、5列是2019年的数据；

第0、2、4列是人均GDP（亿元/万人），第1、3、5为出生率（‰） ；

11.325

7.96

13.62032817

9.06