Python学习：利用线性回归预测双色球开奖号码（纯娱乐升级版）

在网上看了一下有相关的例子，不过没有完整源码，运行还会报错，稍微做修改和优化，修复部分已知错误。

特别提醒：仅供娱乐，请勿当真，双色球属于随机数，线性回归无法预测随机数的哦~~

编译运行环境：Python 3.7x

原版源码如下：（URL暂时无法正常使用了，改用升级版）

#!/usr/bin/python
# -*- coding:UTF-8 -*-# 导入需要的包
import os
import pandas as pd
import re
from urllib import request
from bs4 import BeautifulSoup
from sklearn import datasets, linear_modeldef get_http_content(href):"""读取网页内容"""request_headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:81.0) Gecko/20100101 Firefox/81.0'}req = request.Request(href, headers = request_headers)try:res = request.urlopen(req)return res.read()except request.HTTPError as e:raise edef get_page_num(url):"""获取总页数"""num = 0content = get_http_content(url)soup = BeautifulSoup(content, features='lxml')strong = soup.find('td', colspan='7')# print(strong)if strong:result = strong.get_text().split(' ')list_num = re.findall("[0-9]{1}", result[1])for i in range(len(list_num)):num = num * 10 + int(list_num[i])return numelse:return 0def get_history_lotto(page):"""按页爬取号码数据"""url = 'http://kaijiang.zhcw.com/zhcw/html/ssq/list_%d.html'href = url % pageprint('load......', page, href)content = get_http_content(href)soup = BeautifulSoup(content, features='lxml')em_list = soup.find_all('em')div_list = soup.find_all('td', {'align': 'center'})n = 0m = 0results = []group = []text = ''for div in em_list:if n == 0:# 日期group.append(str(div_list[m+0].get_text()))# 期数group.append(str(div_list[m+1].get_text()))# 号码lotto = str(div.get_text())group.append(lotto)# print(lotto)n = n + 1# 每7个号码组成一组if n == 7:group.append(text + lotto)# 将每组结果汇总到结果列表results.append(group)group = []text = ''n = 0  # 重置计数m += + 5  # 跳过5列else:text += lotto + ','return resultsdef get_history_result(out_file):"""爬取历史数据"""url = 'http://kaijiang.zhcw.com/zhcw/html/ssq/list_%d.html'# 获取页数num = get_page_num(url % 1)results = []# 按页数循环抓取数据for i in range(1, num):try:# 合并分页查询结果results += get_history_lotto(i)except Exception as e:# 爬取失败时，提示失败原因print('error......', i, e)# 表头columns = {'date': str,'id': str,  # 期数'r1': int,  # 红1'r2': int,  # 红2'r3': int,  # 红3'r4': int,  # 红4'r5': int,  # 红5'r6': int,  # 红6'b1': int,  # 蓝1'note': str}# 生成 DataFramedf = pd.DataFrame(columns=columns, data=results)print('保存结果')df.to_csv(out_file, index=False, encoding='utf-8-sig')print(df)return dfdef get_lotto_data(file, lotto, lotto_id):"""取读历史数据，指定标识"""data = pd.read_csv(file)data['lotto_id'] = lotto_idX = []Y = []# single_square_feet, single_price_valuefor s, p in zip(data['lotto_id'], data[lotto]):X.append([float(s)])Y.append(float(p))return X,  Y# 训练线性回归模型
def linear_model_test(X, Y, predict_value):regr = linear_model.LinearRegression()regr.fit(X, Y)predict_outcome = regr.predict(predict_value)predictions = {}predictions['intercept'] = regr.intercept_predictions['coefficient'] = regr.coef_predictions['predicted_value'] = predict_outcomereturn predictionsdef get_predicted_num(file, lotto, lotto_id, num):"""使用线性回归推测中奖号码"""X, Y = get_lotto_data(file, lotto, lotto_id)# print(X)# print(Y)predict_value = [[51]]result = linear_model_test(X, Y, predict_value)print("num", num,'Intercept value', result['intercept'],'Coefficient', result['coefficient'],'Predicted value', result['predicted_value'])if __name__ == '__main__':force_refresh = False  # 强制刷新数据file_name = './union_lotto_history_result.csv'if not os.path.exists(file_name) or force_refresh:# 获取历史数据get_history_result(file_name)# 使用线性回归模型进行预测 (o_o 预测结果纯属娱乐，请勿深信)get_predicted_num(file_name, 'r1', 1, 1)  # 预测红1get_predicted_num(file_name, 'r2', 2, 2)  # 预测红2get_predicted_num(file_name, 'r3', 3, 3)  # 预测红3get_predicted_num(file_name, 'r4', 4, 4)  # 预测红4get_predicted_num(file_name, 'r5', 5, 5)  # 预测红5get_predicted_num(file_name, 'r6', 6, 28)  # 预测红6get_predicted_num(file_name, 'b1', 7, 9)  # 预测蓝7

升级版源码如下：

import requests
import jsonimport pandas as pd
from sklearn import datasets, linear_modeldef get_history_lotto():"""爬取号码数据"""url = 'http://www.cwl.gov.cn/cwl_admin/kjxx/findDrawNotice?name=ssq&issueCount=100'headers = {'Host': 'www.cwl.gov.cn','Referer': 'http://www.cwl.gov.cn/kjxx/ssq/kjgg/','User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:81.0) Gecko/20100101 Firefox/81.0'}columns = {'date': str,'id': str,  # 期数'r1': int,  # 红1'r2': int,  # 红2'r3': int,  # 红3'r4': int,  # 红4'r5': int,  # 红5'r6': int,  # 红6'b1': int,  # 蓝1'note': str}response = requests.get(url=url, headers=headers)# print(response.text)response_data = json.loads(response.text)result = response_data['result']results = []for i in result:dit = {}cnt = 1dit['id'] = i['code']dit['date'] = i['date']for j in str(i['red']).split(','):dit['r' + str(cnt)] = jcnt += 1dit['b1'] = i['blue']dit['note'] = i['red'] + ',' + i['blue']# print(dit)results.append(dit)return pd.DataFrame(columns=columns, data=results)def get_lotto_data(data, lotto, lotto_id):"""取读历史数据，指定标识"""data['lotto_id'] = lotto_idX = []Y = []# single_square_feet, single_price_valuefor s, p in zip(data['lotto_id'], data[lotto]):X.append([float(s)])Y.append(float(p))return X, Y# 训练线性回归模型
def linear_model_test(X, Y, predict_value):regr = linear_model.LinearRegression()regr.fit(X, Y)predict_outcome = regr.predict(predict_value)predictions = {}predictions['intercept'] = regr.intercept_predictions['coefficient'] = regr.coef_predictions['predicted_value'] = predict_outcomereturn predictionsdef get_predicted_num(file, lotto, lotto_id, num):"""使用线性回归推测中奖号码"""X, Y = get_lotto_data(file, lotto, lotto_id)# print(X)# print(Y)predict_value = [[33]]result = linear_model_test(X, Y, predict_value)print("num", num,'Intercept value', result['intercept'],'Coefficient', result['coefficient'],'Predicted value', result['predicted_value'])if __name__ == '__main__':force_refresh = False  # 强制刷新数据file_name = './data/union_lotto_history_result.csv'df = get_history_lotto()df.to_csv(file_name, encoding='utf-8-sig', index=False)df = df.sample(100)# 使用线性回归模型进行预测 (o_o 预测结果纯属娱乐，请勿深信)get_predicted_num(df, 'r1', 1, 5)  # 预测红1get_predicted_num(df, 'r2', 2, 10)  # 预测红2get_predicted_num(df, 'r3', 3, 15)  # 预测红3get_predicted_num(df, 'r4', 4, 20)  # 预测红4get_predicted_num(df, 'r5', 5, 24)  # 预测红5get_predicted_num(df, 'r6', 6, 29)  # 预测红6get_predicted_num(df, 'b1', 7, 9)  # 预测蓝7

测试结果：

num 1 Intercept value 4.73266129032258 Coefficient [0.] Predicted value [4.73266129]
num 2 Intercept value 9.621774193548386 Coefficient [0.] Predicted value [9.62177419]
num 3 Intercept value 14.393145161290322 Coefficient [0.] Predicted value [14.39314516]
num 4 Intercept value 19.2625 Coefficient [0.] Predicted value [19.2625]
num 5 Intercept value 24.161290322580644 Coefficient [0.] Predicted value [24.16129032]
num 28 Intercept value 28.938709677419354 Coefficient [0.] Predicted value [28.93870968]
num 9 Intercept value 8.578225806451613 Coefficient [0.] Predicted value [8.57822581]

Python学习：利用线性回归预测双色球开奖号码（纯娱乐升级版）相关推荐

【Python爬虫】利用爬虫抓取双色球开奖号码，获取完整数据，简洁45行代码实现，更新时间2023-06-28
链接:https://pan.baidu.com/s/18oE308_NVNPaCOACw_H5Hw?pwd=abc1 利用爬虫抓取双色球开奖号码,获取完整数据,简洁45行代码实现,更新时间2023- ...
Pandas学习（二）——双色球开奖数据分析
学习笔记汇总 Pandas学习(一)–数据的导入 pandas学习(二)–双色球数据分析 pandas学习(三)–NAB球员薪资分析 pandas学习(四)–数据的归一化 pandas学习(五)–pa ...
scrapy 抓取体彩-超级大乐透，历年开奖号码【娱乐篇】
最近正好在看scrapy,手贱有了如下代码,核心代码如下:(不要给我讲pipline,我完全是图方便才这么写的) 彩票中出现频率最高的号码整理,如下: [05,19,29,33,35][11,12] ...
【Python】爬虫初体验，40行代码爬取双色球2003年至今的开奖号码
爬虫爬取的双色球开奖号码按我目前的理解,爬虫的工作原理大致是: 获取目标网页,在网页(html文件)中筛选目标数据,最后把数据导出利用爬虫爬取数据看似很"高深莫测",只需几分钟 ...
Java小程序：模拟双色球开奖
双色球规则: // 双色球 :红色球号码 + 蓝色球号码// 六个红色球和一个蓝色球号码// 红色球号码从1~33中选择// 蓝色球号码从1~16中选择// 一等奖:七个号码相符(六个红色号码和一个蓝 ...
结合读取 https://kj.sscejia.com/ssq/kaijiang/61.html 开奖号码分析下一次数字组合
根据所提供的网页,我们可以看到上一次的双色球开奖号码为 02.04.05.11.16.26,红色球号码为 01.由于双色球号码范围是从 01 到 33,因此下一次的数字组合可能是任意 6 个从 01 ...
利用Python获取历史双色球开奖结果
import requests import pymssql from lxml import etree #配置连接数据库信息 server = "-------------" ...
Python爬虫系列之双色球开奖信息爬取
Python基于Beautiful Soup库对双色球开奖信息进行爬取代码仅供学习交流,请勿用于非法用途小程序爬虫接单.app爬虫接单.网页爬虫接单.接口定制.网站开发.小程序开发 > 点击 ...
python+requests+ 爬取官网双色球开奖数据
python+requests+mysql 爬取官网双色球开奖数据分析网页数据获取方式第一种查询方式第二种查询方式完整代码分析网页数据获取方式第一种查询方式在官网上可以找到多种数据查询 ...

Python学习：利用线性回归预测双色球开奖号码（纯娱乐升级版）

Python学习：利用线性回归预测双色球开奖号码（纯娱乐升级版）相关推荐

最新文章

热门文章