#!/usr/bin/python #encoding:utf-8 import numpy import matplotlib.pyplot as plt print("本程序中使用机械学习的方法来预估未来值,预测准确性取决于数据和拟合度,未考虑特殊因素") y=[2719450, 3567320, 4863750, 6133990, 7181360, 7971500, 8519550, 9056440, 10028010, 11086310, 12171740, 13742200, 16184020, 18731890, 21943850, 27009230, 31924460, 34851770, 41211930, 48794020, 53858000, 59296320, 64356310, 68885820, 74639510, 83203590, 91928110, 99086510 ] x=list(range(len(y))) mymodel = numpy.poly1d(numpy.polyfit(x, y, 3)) myline = numpy.linspace(1, len(y)) plt.scatter(x, y) plt.plot(myline, mymodel(myline)) from sklearn.metrics import r2_score print("图像拟合度为:") print(r2_score(y, mymodel(x))) wen=int(input("你想预测哪一年的,请输入int类型的数字")) wen=int(wen-1991) speed = mymodel(wen) print("预测值") print(speed) plt.savefig('./Drawing of mechanical learning.jpg') plt.show() while True: wen=int(input("你想预测哪一年的,请输入int类型的数字")) wen=int(wen-1991) speed = mymodel(wen) print("预测值") print(speed)
机械学习预估未来GDP
最新推荐文章于 2022-06-25 21:14:24 发布