首先當然要配置r語言環(huán)境變量什么的

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;

?

本來用python也可以實現關聯規(guī)則，雖然沒包，但是可視化挺麻煩的

#!/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()'''??????????????????????????????????????????????????????'''# 映射為frozenset唯一性的，可使用其構造字典return list(map(frozenset, C1)) # 從候選K項集到頻繁K項集（支持度計算） 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 # 此處可設置返回全部的支持度數據（或者頻繁項集的支持度數據）return relist, supportData# 改進剪枝算法 def aprioriGen(Lk, k): # 創(chuàng)建候選K項集 ##LK為頻繁K項集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項相等，則可相乘，這樣可防止重復項出現# 進行剪枝（a1為k項集中的一個元素，b為它的所有k-1項子集）a = Lk[i] | Lk[j] # a為frozenset()集合a1 = list(a)b = []# 遍歷取出每一個元素，轉換為set，依次從a1中剔除該元素，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:# 當b（即所有k-1項子集）都是Lk（頻繁的）的子集，則保留，否則刪除。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()轉換為列表L1, supportData = calSupport(D, C1, minSupport)L = [L1] # 加列表框，使得1項集為一個單獨元素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最后一個值為空集k += 1del L[-1] # 刪除最后一個空集return L, supportData # L為頻繁項集，為一個列表，1，2，3項集分別為一個元素。# 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] # 計算置信度# 提升度lift計算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值為', 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值為：', round(lift, 2)) # =============================================================================# 生成規(guī)則 def gen_rule(L, supportData, minConf=0.7):bigRuleList = []for i in range(1, len(L)): # 從二項集開始計算for freqSet in L[i]: # freqSet為所有的k項集# 求該三項集的所有非空子集，1項集，2項集，直到k-1項集，用H1表示，為list類型,里面為frozenset類型，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("")''' 具體公式：P(B|A)/P(B)稱為A條件對于B事件的提升度,如果該值=1,說明兩個條件沒有任何關聯, 如果<1,說明A條件(或者說A事件的發(fā)生)與B事件是相斥的, 一般在數據挖掘中當提升度大于3時,我們才承認挖掘出的關聯規(guī)則是有價值的。 ''' View Code

之后還是用r吧，要下載rpy2，見https://www.cnblogs.com/caiyishuai/p/9520214.html?

還要下載兩個R的包

import rpy2.robjects as robjects b=('''install.packages("arules")install.packages("arulesViz") ''') robjects.r(b)

然后就是主代碼了

import rpy2.robjects as robjectsa=('''Encoding("UTF-8") setwd("F:/goverment/Aprior")all_data<-read.csv("F:/goverment/Aprior/NewData.csv",header = T,#將數據轉化為因子型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 #這五條就是去冗余（感興趣可以去網上搜），我雖然這里寫了，但我沒有去冗余，我的去了以后一個規(guī)則都沒了 which(redundant) rules.pruned<-rules.sorted[!redundant] #inspect(rules.pruned) #輸出去冗余后的規(guī)則 ''')c=('''library(arulesViz)#掉包jpeg(file="plot1.jpg") #inspect(rule.subset) plt<-plot(rule.subset,shading = "lift")#畫散點圖 dev.off()subrules<-head(sort(rule.subset,by="lift"),50) #jpeg(file="plot2.jpg") plot(subrules,method = "graph")#畫圖 #dev.off()rule.sorted <- sort(rule.subset, decreasing=TRUE, by="lift") #按提升度排序 rules.write<-as(rule.sorted,"data.frame") #將規(guī)則轉化為data類型 write.csv(rules.write,"F:/goverment/Aprior/NewRules.csv",fileEncoding="UTF-8") ''') robjects.r(c)#取出保存的規(guī)則，放到一個列表中 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)

?

轉載于:https://www.cnblogs.com/caiyishuai/p/9530871.html

總結

以上是生活随笔為你收集整理的python调用R语言，关联规则可视化的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。