基于3D彩票Knn算法的遗漏模式挖掘

作者：白于空

关于3D彩票的介绍：略

摘要:根据遗漏模型；建立<期望遗漏，当前遗漏，平均遗漏，最大遗漏，遗漏方差>进行knn分类；挖掘模式；

直接在代码中传递表达信息；结论预测精度比期望值约高20%；

import numpy as np
import pandas as pd
data = pd.read_csv('F:/2014.csv')
data = np.array(data.value)
data = data[np.arange(0,300)]
for i in np.arange(0,len(data)):
data[i] = data[i].split(',')
data[i] = np.array(data[i],dtype = 'int32')
#到这里，301个数字已经完全提取完毕；开始计算遗漏值
ylz = {}
for k in np.arange(10):
ws = ylz[k] = [] #这里是起始空列表
for j in np.arange(0,len(data)) :
if k in data[j]:
ws.append(1)
else:
ws.append(0)
'''
#对于0-1序列，返回其中首个1到最终添加1的间隔数；
例[0,1,0,0,1,1,0,0]目标返回[2,4,1,2];总长为len+1
[0,0,0,1,1]返回[4,1,1]
'''
ylxl = {}
for s in np.arange(10):
ylxl[s] = []
ylz[s].append(1)
ycc = ylz[s]
for so in np.arange(0,len(ycc)):
if ycc[so]==1:
ylxl[s].append(so)
else:
pass
zc = {}
for oi in np.arange(10):
tu = np.array(ylxl[oi])
zc[oi] = [tu[1:len(tu)] - tu[0:(len(tu)-1)]]
zc[oi].insert(0,tu[0])
zc #记录各个值在3D彩票2014年中的历史遗漏序列
#开始记录每个值得历史遗漏，最大遗漏，平均遗漏，数学期望遗漏

上面的文件命名为zcp3d.py；另外excel历史数据表修改------将excel中对应值得一列命名为value;

开始进行主函数的计算：

import numpy as np
import zcp3d2
'''
每一次的zcc和yxdl都得重新计算生成新的序列集;;50-240

'''
def sd(c):
c = np.array(c)
for i in np.arange(len(c)-1):
sd = np.sum((c[i]-np.mean(c))**2)/len(c)
return sd
# classify using kNN
def Classify(newInput, dataSet, labels, k):
numSamples = dataSet.shape[0] # shape[0] stands for the num of row
diff = np.tile(newInput, (numSamples, 1)) - dataSet
squaredDiff = diff ** 2
squaredDist = np.sum(squaredDiff, axis = 1)
distance = squaredDist ** 0.5
sortedDistIndices = np.argsort(distance)
classCount = {} # define a dictionary (can be append element)
for i in np.arange(k):
voteLabel = labels[sortedDistIndices[i]]
classCount[voteLabel] = classCount.get(voteLabel, 0) + 1
maxCount = 0
for key, value in classCount.items():
if value > maxCount:
maxCount = value
maxIndex = key
return maxIndex

def qhj(knz):
ylzc = ylz[knz]
def train_set(p):
ylzp = ylzc[0:p]#检测项就是ylzc[p+1]了；这里不能直接替换。
#开始对ylzc
x_xsj = []
for l in np.arange(p):
if ylzp[l]==1:
x_xsj.append(l)
else:
pass
tu = np.array(x_xsj)
jh_xl = [tu[1:(len(tu)-1)] - tu[0:(len(tu)-2)]]
#实现在数组中首单元插入新元素
zcc = [tu[0]]
zcc.extend(jh_xl)
zcc = np.array(zcc[1])
train_x = [np.mean(zcc),np.max(zcc),sd(zcc),np.min(zcc),zcc[(len(zcc)-1)]]
return train_x
train = []
lable = []
x = data.shape[0]
def cesl(x):
for ik in np.arange(50,x):
train.append(train_set(ik))
lable.append(ylzc[ik+1])
#train试验集合
#lable目标集合
t = 1 #t取与数据集相差t内的单位,t小于70
dataSet, labels = np.array(train), lable
testX = train_set(x+t)
k = 9
outputLabel = Classify(testX, dataSet, labels, k)
return outputLabel
return cesl(x)
jgyc = []
for u in np.arange(10):
jgyc.append(qhj[u])

jgyc