python调用R语言，关联规则可视化

首先当然要配置r语言环境变量什么的

D:\R-3.5.1\bin\x64;
D:\R-3.5.1\bin\x64\R.dll;
D:\R-3.5.1;
D:\ProgramData\Anaconda3\Lib\site-packages\rpy2;

本来用python也可以实现关联规则，虽然没包，但是可视化挺麻烦的

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
from pandas import read_csvdef loadDataSet():dataset = read_csv("F:/goverment/Aprior/No Number.csv")data = dataset.values[:,:]Data=[]for line in data:ls=[]for i in line:ls.append(i)Data.append(ls)#print(Data)return Data'''return [['a', 'c', 'e'], ['b', 'd'], ['b', 'c'], ['a', 'b', 'c', 'd'], ['a', 'b'], ['b', 'c'], ['a', 'b'],['a', 'b', 'c', 'e'], ['a', 'b', 'c'], ['a', 'c', 'e']]'''def createC1(dataSet):C1 = []for transaction in dataSet:for item in transaction:if not [item] in C1:C1.append([item])C1.sort()'''??????????????????????????????????????????????????????'''# 映射为frozenset唯一性的，可使用其构造字典return list(map(frozenset, C1))      # 从候选K项集到频繁K项集（支持度计算）
def scanD(D, Ck, minSupport):ssCnt = {}for tid in D:for can in Ck:if can.issubset(tid):if not can in ssCnt:ssCnt[can] = 1else:ssCnt[can] += 1numItems = float(len(D))retList = []supportData = {}for key in ssCnt:support = ssCnt[key] / numItemsif support >= minSupport:retList.insert(0, key)supportData[key] = support  return retList, supportDatadef calSupport(D, Ck, min_support):dict_sup = {}for i in D:for j in Ck:if j.issubset(i):if not j in dict_sup:dict_sup[j] = 1else:dict_sup[j] += 1sumCount = float(len(D))supportData = {}relist = []for i in dict_sup:temp_sup = dict_sup[i] / sumCountif temp_sup >= min_support:relist.append(i)supportData[i] = temp_sup  # 此处可设置返回全部的支持度数据（或者频繁项集的支持度数据）return relist, supportData# 改进剪枝算法
def aprioriGen(Lk, k):  # 创建候选K项集 ##LK为频繁K项集retList = []lenLk = len(Lk)for i in range(lenLk):for j in range(i + 1, lenLk):L1 = list(Lk[i])[:k - 2]L2 = list(Lk[j])[:k - 2]L1.sort()L2.sort()if L1 == L2:  # 前k-1项相等，则可相乘，这样可防止重复项出现#  进行剪枝（a1为k项集中的一个元素，b为它的所有k-1项子集）a = Lk[i] | Lk[j]  # a为frozenset()集合a1 = list(a)b = []# 遍历取出每一个元素，转换为set，依次从a1中剔除该元素，并加入到b中for q in range(len(a1)):t = [a1[q]]tt = frozenset(set(a1) - set(t))b.append(tt)t = 0for w in b:# 当b（即所有k-1项子集）都是Lk（频繁的）的子集，则保留，否则删除。if w in Lk:t += 1if t == len(b):retList.append(b[0] | b[1])return retListdef apriori(dataSet, minSupport=0.2):C1 = createC1(dataSet)D = list(map(set, dataSet))  # 使用list()转换为列表L1, supportData = calSupport(D, C1, minSupport)L = [L1]  # 加列表框，使得1项集为一个单独元素k = 2while (len(L[k - 2]) > 0):Ck = aprioriGen(L[k - 2], k)Lk, supK = scanD(D, Ck, minSupport)  # scan DB to get Lk
        supportData.update(supK)L.append(Lk)  # L最后一个值为空集k += 1del L[-1]  # 删除最后一个空集return L, supportData  # L为频繁项集，为一个列表，1，2，3项集分别为一个元素。# 生成集合的所有子集
def getSubset(fromList, toList):for i in range(len(fromList)):t = [fromList[i]]tt = frozenset(set(fromList) - set(t))if not tt in toList:toList.append(tt)tt = list(tt)if len(tt) > 1:getSubset(tt, toList)#def calcConf(freqSet, H, supportData, ruleList, minConf=0.7):
def calcConf(freqSet, H, supportData, Rule, minConf=0.7):for conseq in H:conf = supportData[freqSet] / supportData[freqSet - conseq]  # 计算置信度# 提升度lift计算lift = p(a & b) / p(a)*p(b)lift = supportData[freqSet] / (supportData[conseq] * supportData[freqSet - conseq])ls=[]if conf >= minConf and lift > 3:for i in freqSet - conseq:#print(i," ",end="")
                ls.append(i)ls.append(" ")#print('-->',end="")ls.append('-->')for i in conseq:#print(i," ",end="")
                ls.append(i)ls.append(" ")#print('支持度:', round(supportData[freqSet - conseq]*100, 1), "%",'  置信度:', round(conf*100,1),"%",'  lift值为', round(lift, 2))#ls.append(' 支持度:')#ls.append(round(supportData[freqSet - conseq]*100, 1))#ls.append("% ")#ls.append(' 置信度:')ls.append( round(conf*100,1))ls.append("% ")#ls.append( round(lift, 2))#ls.append(round(lift, 2))#ruleList.append((freqSet - conseq, conseq, conf))if ls!=[]: #print(len(ls))
            Rule.append(ls)
# =============================================================================
#     for line in Rule:
#         for i in line:
#             print(i,end="")
#         print("")
# =============================================================================return Rule
# =============================================================================
#             print(freqSet - conseq, '-->', conseq, '支持度', round(supportData[freqSet - conseq], 2), '置信度：', round(conf,3),
#                   'lift值为：', round(lift, 2))
# =============================================================================# 生成规则
def gen_rule(L, supportData, minConf=0.7):bigRuleList = []for i in range(1, len(L)):  # 从二项集开始计算for freqSet in L[i]:  # freqSet为所有的k项集# 求该三项集的所有非空子集，1项集，2项集，直到k-1项集，用H1表示，为list类型,里面为frozenset类型，H1 = list(freqSet)all_subset = []getSubset(H1, all_subset)  # 生成所有的子集
            calcConf(freqSet, all_subset, supportData, bigRuleList, minConf)return bigRuleListif __name__ == '__main__':dataSet = loadDataSet()#print(dataSet)L, supportData = apriori(dataSet, minSupport=0.05)rule = gen_rule(L, supportData, minConf=0.5)for i in rule:for j in i:if j==',':continueelse:print(j,end="")print("")'''
具体公式：P(B|A)/P(B)称为A条件对于B事件的提升度,如果该值=1,说明两个条件没有任何关联,
如果<1,说明A条件(或者说A事件的发生)与B事件是相斥的,
一般在数据挖掘中当提升度大于3时,我们才承认挖掘出的关联规则是有价值的。
'''

之后还是用r吧，要下载rpy2，见https://www.cnblogs.com/caiyishuai/p/9520214.html 

还要下载两个R的包

import rpy2.robjects as robjects

b=('''install.packages("arules")install.packages("arulesViz")
''')
robjects.r(b)

然后就是主代码了

import rpy2.robjects as robjectsa=('''Encoding("UTF-8")
setwd("F:/goverment/Aprior")all_data<-read.csv("F:/goverment/Aprior/NewData.csv",header = T,#将数据转化为因子型colClasses=c("factor","factor","factor","factor","factor","factor","factor","factor","factor","factor","factor","factor"))
library(arules)
rule=apriori(data=all_data[,c(1,4,5,6,7,8,9,10,12)], parameter = list(support=0.05,confidence=0.7,minlen=2,maxlen=10))       ''')
robjects.r(a)robjects.r('''                        
rule.subset<-subset(rule,lift>1)
#inspect(rule.subset)
rules.sorted<-sort(rule.subset,by="lift")
subset.matrix<-is.subset(rules.sorted,rules.sorted)
lower.tri(subset.matrix,diag=T)
subset.matrix[lower.tri(subset.matrix,diag = T)]<-NA
redundant<-colSums(subset.matrix,na.rm = T)>=1          #这五条就是去冗余（感兴趣可以去网上搜），我虽然这里写了，但我没有去冗余，我的去了以后一个规则都没了
which(redundant)
rules.pruned<-rules.sorted[!redundant]
#inspect(rules.pruned) #输出去冗余后的规则
''')c=('''library(arulesViz)#掉包jpeg(file="plot1.jpg")
#inspect(rule.subset)
plt<-plot(rule.subset,shading = "lift")#画散点图
dev.off()subrules<-head(sort(rule.subset,by="lift"),50)
#jpeg(file="plot2.jpg")
plot(subrules,method = "graph")#画图
#dev.off()rule.sorted <- sort(rule.subset, decreasing=TRUE,  by="lift") #按提升度排序
rules.write<-as(rule.sorted,"data.frame") #将规则转化为data类型
write.csv(rules.write,"F:/goverment/Aprior/NewRules.csv",fileEncoding="UTF-8")
''')
robjects.r(c)#取出保存的规则，放到一个列表中
from pandas import read_csv
data_set = read_csv("F:/goverment/Aprior/NewRules.csv")
data = data_set.values[:, :]
rul = []
for line in data:ls = []for j in line:try :j=float(j)if j>0 and j<=1:j=str(round(j*100,2))+"%"ls.append(j)else:ls.append(round(j,2))except:ls.append(j)rul.append(ls)for line in rul:print(line)

转载于:https://www.cnblogs.com/caiyishuai/p/9530871.html

本文来自互联网用户投稿，文章观点仅代表作者本人，不代表本站立场，不承担相关法律责任。如若转载，请注明出处。 如若内容造成侵权/违法违规/事实不符，请点击【内容举报】进行投诉反馈！