[世界杯]根据赔率计算各种组合概率与赔率
目录
一、背景
二、数据输入
2.1 赔率示意图
2.2 字典保存数据
三、数据处理
3.1 计算各种组合可能性
3.2 修正概率
四、输出结果
五、代码
一、背景
本文以世界杯体彩“混合过关”4场串胜平负为的赔率进行编码
其他类型如比分 、总进球数可以参考代码进行相应修改
需要的库：numpy与pandas
二、数据输入
2.1 赔率示意图
2.2 字典保存数据
采用字典保存各比赛对应的胜平负的赔率
import pandas as pd
import numpy as np
vs1 = {"胜":2.38,"平":2.93,"负":2.65} #厄瓜多尔-塞内加尔
vs2 = {"胜":13.0,"平":6.20,"负":1.11} #卡塔尔-荷兰
vs3 = {"胜":3.58,"平":3.16,"负":1.84} #伊朗-美国
vs4 = {"胜":7.35,"平":4.16,"负":1.31} #威尔士-英格兰
三、数据处理
3.1 计算各种组合可能性
计算采用的公式主要为：（图中10%为抽水率,仅为假设）
其中0.9913为初步计算得到的体彩抽水率，实际不准确，该数值仅供初步计算，之后需要根据计算所得的概率进行相应修正。
count = 1
probList = []
probListIndex = []
probVs = []
timesList = []
vsCode1 = []
vsCode2 = []
vsCode3 = []
vsCode4 = []
for key1,each1 in vs1.items():
for key2,each2 in vs2.items():
for key3,each3 in vs3.items():
for key4,each4 in vs4.items():
# print(count,key1,key2,key3,each1*each2*each3)
prob = 99.13 / (each1*each2*each3*each4)
#print(count,key1,key2,key3,key4,prob)
probList.append(prob)
probListIndex.append(count)
probVs.append(key1+key2+key3+key4)
timesList.append(each1*each2*each3*each4)
vsCode1.append(key1)
vsCode2.append(key2)
vsCode3.append(key3)
vsCode4.append(key4)
count += 1
data = pd.DataFrame(probList,index = probListIndex,columns=["prob"])
data_temp = pd.DataFrame(probVs,index = probListIndex,columns=["vs"])
data_times = pd.DataFrame(timesList,index = probListIndex,columns=["times"])
data_vs1 = pd.DataFrame(vsCode1,index = probListIndex,columns=["vs1"])
data_vs2 = pd.DataFrame(vsCode2,index = probListIndex,columns=["vs2"])
data_vs3 = pd.DataFrame(vsCode3,index = probListIndex,columns=["vs3"])
data_vs4 = pd.DataFrame(vsCode4,index = probListIndex,columns=["vs4"])
# data = data.add(data_temp,fill_value=False)
data["vs"] = data_temp["vs"]
data["vs1"] = data_vs1["vs1"]
data["vs2"] = data_vs2["vs2"]
data["vs3"] = data_vs3["vs3"]
data["vs4"] = data_vs4["vs4"]
data["times"] = data_times["times"]
data = data.sort_values(by="prob",ascending=False)
data["total_prob"] = 0
sum_prob = 0
for each in data.index:
# print(each)
sum_prob += data["prob"].loc[each]
data["total_prob"].loc[each] = sum_prob
3.2 修正概率
该段代码无实际含义，仅为修正由于采用估计抽水率计算所得的概率偏差
主要思路是采用数据标准化后并将数据映射到合理的区间，并对部分概率进行转换
total_prob_min = data["total_prob"].min()
data["total_prob"] = (data["total_prob"]-data["total_prob"].min())/(data["total_prob"].max()-data["total_prob"].min())*(100-total_prob_min)+total_prob_min
data["total_prob"].iloc[0] = (data["total_prob"].iloc[1]*data["total_prob"].iloc[0])/(data["prob"].iloc[1]+data["total_prob"].iloc[0])
temp = data["total_prob"] - data["total_prob"].shift(1)
temp[0] = data["total_prob"].iloc[0]
data["prob"] = temp
data["prob"].iloc[0] = data["total_prob"].iloc[0]
data.to_csv(r"C:\Users\kkkk\Desktop\世界杯1129.csv")
四、输出结果
prob该组合可能性，total_prob为累计可能性，times为赔率，VS1~4为该组合对应的胜平负
以11.29日赛程为参考，卡塔尔与威尔士大概率负，因此采用Excel筛选出相关组合，在所列组合中选取赔率较高的组合。
五、代码
import pandas as pd
import numpy as np
vs1 = {"胜":2.38,"平":2.93,"负":2.65}
vs2 = {"胜":13.0,"平":6.20,"负":1.11}
vs3 = {"胜":3.58,"平":3.16,"负":1.84}
vs4 = {"胜":7.35,"平":4.16,"负":1.31}
count = 1
probList = []
probListIndex = []
probVs = []
timesList = []
vsCode1 = []
vsCode2 = []
vsCode3 = []
vsCode4 = []
for key1,each1 in vs1.items():
for key2,each2 in vs2.items():
for key3,each3 in vs3.items():
for key4,each4 in vs4.items():
# print(count,key1,key2,key3,each1*each2*each3)
prob = 99.13 / (each1*each2*each3*each4)
print(count,key1,key2,key3,key4,prob)
probList.append(prob)
probListIndex.append(count)
probVs.append(key1+key2+key3+key4)
timesList.append(each1*each2*each3*each4)
vsCode1.append(key1)
vsCode2.append(key2)
vsCode3.append(key3)
vsCode4.append(key4)
count += 1
data = pd.DataFrame(probList,index = probListIndex,columns=["prob"])
data_temp = pd.DataFrame(probVs,index = probListIndex,columns=["vs"])
data_times = pd.DataFrame(timesList,index = probListIndex,columns=["times"])
data_vs1 = pd.DataFrame(vsCode1,index = probListIndex,columns=["vs1"])
data_vs2 = pd.DataFrame(vsCode2,index = probListIndex,columns=["vs2"])
data_vs3 = pd.DataFrame(vsCode3,index = probListIndex,columns=["vs3"])
data_vs4 = pd.DataFrame(vsCode4,index = probListIndex,columns=["vs4"])
# data = data.add(data_temp,fill_value=False)
data["vs"] = data_temp["vs"]
data["vs1"] = data_vs1["vs1"]
data["vs2"] = data_vs2["vs2"]
data["vs3"] = data_vs3["vs3"]
data["vs4"] = data_vs4["vs4"]
data["times"] = data_times["times"]
data = data.sort_values(by="prob",ascending=False)
data["total_prob"] = 0
sum_prob = 0
for each in data.index:
# print(each)
sum_prob += data["prob"].loc[each]
data["total_prob"].loc[each] = sum_prob
total_prob_min = data["total_prob"].min()
data["total_prob"] = (data["total_prob"]-data["total_prob"].min())/(data["total_prob"].max()-data["total_prob"].min())*(100-total_prob_min)+total_prob_min
data["total_prob"].iloc[0] = (data["total_prob"].iloc[1]*data["total_prob"].iloc[0])/(data["prob"].iloc[1]+data["total_prob"].iloc[0])
temp = data["total_prob"] - data["total_prob"].shift(1)
temp[0] = data["total_prob"].iloc[0]
data["prob"] = temp
data["prob"].iloc[0] = data["total_prob"].iloc[0]
data.to_csv(r"C:\Users\kkkk\Desktop\世界杯1129.csv")