- A+
本次将进行下期双色球号码的预测,想想有些小激动啊。
代码中使用了线性回归算法,这个场景使用这个算法,预测效果一般,各位可以考虑使用其他算法尝试结果。
发现之前有很多代码都是重复的工作,为了让代码看的更优雅,定义了函数,去调用,顿时高大上了
- #!/usr/bin/python
- # -*- coding:UTF-8 -*-
- #导入需要的包
- import pandas as pd
- import numpy as np
- import matplotlib.pyplot as plt
- import operator
- from sklearn import datasets,linear_model
- from sklearn.linear_model import LogisticRegression
- #读取文件
- df = pd.read_table('newdata.txt',header=None,sep=',')
- #读取日期
- tdate = sorted(df.loc[:,0])
- #将以列项为数据,将球号码取出,写入到csv文件中,并取50行数据
- # Function to red number to csv file
- def RedToCsv(h_num,num,csv_name):
- h_num = df.loc[:,num:num].values
- h_num = h_num[50::-1]
- renum2 = pd.DataFrame(h_num)
- renum2.to_csv(csv_name,header=None)
- fp = file(csv_name)
- s = fp.read()
- fp.close()
- a = s.split('\n')
- a.insert(0, 'numid,number')
- s = '\n'.join(a)
- fp = file(csv_name, 'w')
- fp.write(s)
- fp.close()
- #调用取号码函数
- # create file
- RedToCsv('red1',1,'rednum1data.csv')
- RedToCsv('red2',2,'rednum2data.csv')
- RedToCsv('red3',3,'rednum3data.csv')
- RedToCsv('red4',4,'rednum4data.csv')
- RedToCsv('red5',5,'rednum5data.csv')
- RedToCsv('red6',6,'rednum6data.csv')
- RedToCsv('blue1',7,'bluenumdata.csv')
- #获取数据,X_parameter为numid数据,Y_parameter为number数据
- # Function to get data
- def get_data(file_name):
- data = pd.read_csv(file_name)
- X_parameter = []
- Y_parameter = []
- for single_square_feet ,single_price_value in zip(data['numid'],data['number']):
- X_parameter.append([float(single_square_feet)])
- Y_parameter.append(float(single_price_value))
- return X_parameter,Y_parameter
- #训练线性模型
- # Function for Fitting our data to Linear model
- def linear_model_main(X_parameters,Y_parameters,predict_value):
- # Create linear regression object
- regr = linear_model.LinearRegression()
- #regr = LogisticRegression()
- regr.fit(X_parameters, Y_parameters)
- predict_outcome = regr.predict(predict_value)
- predictions = {}
- predictions['intercept'] = regr.intercept_
- predictions['coefficient'] = regr.coef_
- predictions['predicted_value'] = predict_outcome
- return predictions
- #获取预测结果函数
- def get_predicted_num(inputfile,num):
- X,Y = get_data(inputfile)
- predictvalue = 51
- result = linear_model_main(X,Y,predictvalue)
- print "num "+ str(num) +" Intercept value " , result['intercept']
- print "num "+ str(num) +" coefficient" , result['coefficient']
- print "num "+ str(num) +" Predicted value: ",result['predicted_value']
- #调用函数分别预测红球、蓝球
- get_predicted_num('rednum1data.csv',1)
- get_predicted_num('rednum2data.csv',2)
- get_predicted_num('rednum3data.csv',3)
- get_predicted_num('rednum4data.csv',4)
- get_predicted_num('rednum5data.csv',5)
- get_predicted_num('rednum6data.csv',6)
- get_predicted_num('bluenumdata.csv',1)
- # 获取X,Y数据预测结果
- # X,Y = get_data('rednum1data.csv')
- # predictvalue = 21
- # result = linear_model_main(X,Y,predictvalue)
- # print "red num 1 Intercept value " , result['intercept']
- # print "red num 1 coefficient" , result['coefficient']
- # print "red num 1 Predicted value: ",result['predicted_value']
- # Function to show the resutls of linear fit model
- def show_linear_line(X_parameters,Y_parameters):
- # Create linear regression object
- regr = linear_model.LinearRegression()
- #regr = LogisticRegression()
- regr.fit(X_parameters, Y_parameters)
- plt.figure(figsize=(12,6),dpi=80)
- plt.legend(loc='best')
- plt.scatter(X_parameters,Y_parameters,color='blue')
- plt.plot(X_parameters,regr.predict(X_parameters),color='red',linewidth=4)
- plt.xticks(())
- plt.yticks(())
- plt.show()
- #显示模型图像,如果需要画图,将“获取X,Y数据预测结果”这块注释去掉,“调用函数分别预测红球、蓝球”这块代码注释下
- # show_linear_line(X,Y)
画图结果:
预测2016-05-15开奖结果:
实际开奖结果:05 06 10 16 22 26 11
以下为预测值:
#取5个数,计算的结果
num 1 Intercept value 5.66666666667
num 1 coefficient [-0.6]
num 1 Predicted value: [ 2.06666667]
num 2 Intercept value 7.33333333333
num 2 coefficient [ 0.2]
num 2 Predicted value: [ 8.53333333]
num 3 Intercept value 14.619047619
num 3 coefficient [-0.51428571]
num 3 Predicted value: [ 11.53333333]
num 4 Intercept value 17.7619047619
num 4 coefficient [-0.37142857]
num 4 Predicted value: [ 15.53333333]
num 5 Intercept value 21.7142857143
num 5 coefficient [ 1.11428571]
num 5 Predicted value: [ 28.4]
num 6 Intercept value 28.5238095238
num 6 coefficient [ 0.65714286]
num 6 Predicted value: [ 32.46666667]
num 1 Intercept value 9.57142857143
num 1 coefficient [-0.82857143]
num 1 Predicted value: [ 4.6]
四舍五入结果:
2 9 12 16 28 33 5
#取12个数,计算的结果四舍五入:
3 7 12 15 24 30 7
#取15个数,计算的结果四舍五入:
4 7 13 15 25 31 7
#取18个数,计算的结果四舍五入:
4 8 13 16 23 31 8
#取20个数,计算的结果四舍五入:
4 7 12 22 24 27 10
#取25个数,计算的结果四舍五入:
7 8 13 17 24 30 6
#取50个数,计算的结果四舍五入:
4 10 14 18 23 29 8
#取100个数,计算的结果四舍五入:
5 11 15 19 24 29 8
#取500个数,计算的结果四舍五入:
5 10 15 20 24 29 9
#取1000个数,计算的结果四舍五入:
5 10 14 19 24 29 9
#取1939个数,计算的结果四舍五入:
5 10 14 19 24 29 9
看来预测中奖真是有些难度,随机性太高,双色球预测案例,只是为了让入门数据分析的朋友有些思路,要想中大奖还是有难度的,多做好事善事多积德行善吧。
2019年1月9日 下午4:52 沙发
你好 能告知一下 txt的数据格式么?