我在Internet上找到了Apriori算法的实现,但是其中有些我无法理解。我希望有人可以帮助我。
# region----- Apriori-gen
//Generates Candidate Itemsets
static ArrayList AprioriGen (ArrayList L)
{
ArrayList Lk = new ArrayList (); //List to store generated Candidate Itemsets
Regex r = new Regex (",");
for (int i = 0 ; i <L.Count ; i++)
{
string [] subL1 = r.Split (L [i]. ToString ());
for (int j = i+1 ; j <L.Count ; j++)
{
string [] subL2 = r.Split (L [j]. ToString ());
// Compare two items in L, and set them in temp
string temp = L [j]. ToString (); //store two key sets
for (int m = 0; m <subL1.Length; m++)
{
bool subL1mInsubL2 = false;
for (int n = 0; n <subL2.Length; n++)
{
if (subL1 [m] == subL2 [n]) subL1mInsubL2 = true;
}
if (subL1mInsubL2 == false) temp = temp + "," + subL1 [m];
}
// If temp contains the entry for L in the (itemset size +1)
//and the focus is not with the candidates seeking the same items set temp
string [] subTemp = r.Split (temp);
if (subTemp.Length == subL1.Length + 1)
{
bool isExists = false;
for (int m = 0; m <Lk.Count; m++)
{
bool isContained = true;
for (int n = 0; n <subTemp.Length; n++)
{
if (!Lk[m].ToString().Contains(subTemp [n]) ) isContained = false;
}
if (isContained == true) isExists = true;
}
if (isExists == false) Lk.Add(temp);
}
}
}
return Lk;
}
# endregion----- Apriori-gen
现在,我知道了Apriori Gen的过程,在该过程中,我们通过将项目集结合在一起将它们变成更大的项目集。但是我看不到在先前的代码中是如何实现的。为什么我们使用温度? isExists和isContained如何帮助我们?这两个代码部分到底发生了什么?
首先,有两个循环:
for(int i = 0; i
这些循环用于将给定大小的每对项目集一起比较。关于此Apriori实现,我注意到的第一件事是它[[效率不高,因为如果项目集按词汇顺序排列,则无需将每个项目集彼此进行比较。您可以早点停下来。但是此代码没有这种优化。
我在这段代码中看到的第二个大问题是候选人存储为字符串。将其存储为整数数组会更加有效。将项目集存储为包含“,”的String并将其拆分为单独的数字是一个非常糟糕的设计决策,这将浪费内存和执行时间。对于数据挖掘算法,实现应尽可能高效。我认为,这意味着您正在查看的代码是由新手编写的。关于您的问题,变量“ temp”用于存储新的候选项。提醒候选人是两个项目集的串联。要合并两个项目集,您需要检查它们是否共享除一个以外的所有项目。例如,如果您有两个项目集ABC和ABD,则这两个项目集将生成一个新的候选项ABCD。但是,如果两个项目集具有多个不同的项目,则不应将它们组合在一起。这就是您演示给我的代码试图通过的方式。
如果要查看一些有效的Apriori实现,可以查看我的website(http://www.philippe-fournier-viger.com/spmf/),我提供了一些有效的Java实现。如果您想要一些有效的c ++实现,请查看:http://fimi.ua.ac.be/src/。
描述:Apriori算法的简单Python实现用法:
$python apriori.py -f DATASET.csv -s minSupport -c minConfidence $python apriori.py -f DATASET.csv -s 0.15 -c 0.6
import sys
from itertools import chain, combinations
from collections import defaultdict
from optparse import OptionParser
def subsets(arr):
""" Returns non empty subsets of arr"""
return chain(*[combinations(arr, i + 1) for i, a in enumerate(arr)])
def returnItemsWithMinSupport(itemSet, transactionList, minSupport, freqSet):
"""calculates the support for items in the itemSet and returns a subset
of the itemSet each of whose elements satisfies the minimum support"""
_itemSet = set()
localSet = defaultdict(int)
for item in itemSet:
for transaction in transactionList:
if item.issubset(transaction):
freqSet[item] += 1
localSet[item] += 1
for item, count in localSet.items():
support = float(count)/len(transactionList)
if support >= minSupport:
_itemSet.add(item)
return _itemSet
def joinSet(itemSet, length):
"""Join a set with itself and returns the n-element itemsets"""
return set([i.union(j) for i in itemSet for j in itemSet if len(i.union(j)) == length])
def getItemSetTransactionList(data_iterator):
transactionList = list()
itemSet = set()
for record in data_iterator:
transaction = frozenset(record)
transactionList.append(transaction)
for item in transaction:
itemSet.add(frozenset([item])) # Generate 1-itemSets
return itemSet, transactionList
def runApriori(data_iter, minSupport, minConfidence):
"""
run the apriori algorithm. data_iter is a record iterator
Return both:
- items (tuple, support)
- rules ((pretuple, posttuple), confidence)
"""
itemSet, transactionList = getItemSetTransactionList(data_iter)
freqSet = defaultdict(int)
largeSet = dict()
# Global dictionary which stores (key=n-itemSets,value=support)
# which satisfy minSupport
assocRules = dict()
# Dictionary which stores Association Rules
oneCSet = returnItemsWithMinSupport(itemSet,
transactionList,
minSupport,
freqSet)
currentLSet = oneCSet
k = 2
while(currentLSet != set([])):
largeSet[k-1] = currentLSet
currentLSet = joinSet(currentLSet, k)
currentCSet = returnItemsWithMinSupport(currentLSet,
transactionList,
minSupport,
freqSet)
currentLSet = currentCSet
k = k + 1
def getSupport(item):
"""local function which Returns the support of an item"""
return float(freqSet[item])/len(transactionList)
toRetItems = []
for key, value in largeSet.items():
toRetItems.extend([(tuple(item), getSupport(item))
for item in value])
toRetRules = []
for key, value in largeSet.items()[1:]:
for item in value:
_subsets = map(frozenset, [x for x in subsets(item)])
for element in _subsets:
remain = item.difference(element)
if len(remain) > 0:
confidence = getSupport(item)/getSupport(element)
if confidence >= minConfidence:
toRetRules.append(((tuple(element), tuple(remain)),
confidence))
return toRetItems, toRetRules
def printResults(items, rules):
"""prints the generated itemsets sorted by support and the confidence rules sorted by confidence"""
for item, support in sorted(items, key=lambda (item, support): support):
print "item: %s , %.3f" % (str(item), support)
print "\n------------------------ RULES:"
for rule, confidence in sorted(rules, key=lambda (rule, confidence): confidence):
pre, post = rule
print "Rule: %s ==> %s , %.3f" % (str(pre), str(post), confidence)
def dataFromFile(fname):
"""Function which reads from the file and yields a generator"""
file_iter = open(fname, 'rU')
for line in file_iter:
line = line.strip().rstrip(',') # Remove trailing comma
record = frozenset(line.split(','))
yield record
if __name__ == "__main__":
optparser = OptionParser()
optparser.add_option('-f', '--inputFile',
dest='input',
help='filename containing csv',
default=None)
optparser.add_option('-s', '--minSupport',
dest='minS',
help='minimum support value',
default=0.15,
type='float')
optparser.add_option('-c', '--minConfidence',
dest='minC',
help='minimum confidence value',
default=0.6,
type='float')
(options, args) = optparser.parse_args()
inFile = None
if options.input is None:
inFile = sys.stdin
elif options.input is not None:
inFile = dataFromFile(options.input)
else:
print 'No dataset filename specified, system with exit\n'
sys.exit('System will exit')
minSupport = options.minS
minConfidence = options.minC
items, rules = runApriori(inFile, minSupport, minConfidence)
printResults(items, rules)