def mineTweets(tweetArray, minSup=5):
parsedList = []
for i in range(14):
for j in range(100):
parsedList.append(textParse(tweetArray[i][j].text))
initDict = FPGrowth.createInitSet(parsedList)
twitterFPTree, twitterHeaderTab = FPGrowth.createTree(initDict, minSup)
twitterFreqList = []
FPGrowth.mineTree(twitterFPTree, twitterHeaderTab, set([]),
twitterFreqList)
return twitterFreqList
def main():
# Connect to database
ppsd_data = connect_db('train')
fuzzified_data = Fuzzification.fuzzify(ppsd_data)
# print(fuzzified_data)
# Insert Fuzzified Data
insert_db(fuzzified_data, ppsd_data)
# Apriori Algorithm
fuzzy_csv = pd.read_csv('fuzzified.csv')
# FP Grwoth
start_time = time.time()
rules, confi = FPGrowth.mine('fuzzified.csv')
print("FP: --- %s seconds ---" % (time.time() - start_time))
insert_fprules(rules, confi)
# insert_fprulesCSV(rules,confi)
start_time = time.time()
ant, con, conf, lift = Apriori.mine('fuzzified.csv')
print("Apriori: --- %s seconds ---" % (time.time() - start_time))
insert_arules(ant, con, conf, lift)
import FPGrowth
'''
rootNode = FPGrowth.treeNode('pyramid', 9, None)
rootNode.children['eye'] = FPGrowth.treeNode('eye', 13, None)
rootNode.children['phoenix'] = FPGrowth.treeNode('phoenix', 3, None)
rootNode.disp()
'''
'''
simpDat = FPGrowth.loadSimpDat()
initSet = FPGrowth.createInitSet(simpDat)
myFPtree, myHeaderTab = FPGrowth.createTree(initSet, 3)
# myFPtree.disp()
# print FPGrowth.findPrefixPath('t', myHeaderTab['t'][1])
freqItems = []
FPGrowth.mineTree(myFPtree, myHeaderTab, 3, set([]), freqItems)
print freqItems
'''
FPGrowth.kosarakTest("E:/TestDatas/MachineLearningInAction/Ch12/kosarak.dat")
freq_sets, HTs, item_list = getPickledData(filename, min_sup,
confidence)
except (OSError, IOError) as e:
use_pickled = False
if not use_pickled:
if algo is 'ap':
freq_sets, item_list = Apriori.aprioriAlgo(data_folder + filename,
min_sup)
else:
freq_sets, item_list = FPGrowth.fPGrowthAlgo(
data_folder + filename, min_sup)
HTs = HashTree.generateHTs(data_folder + filename, freq_sets, min_sup)
max_freq_sets = FrequentSetOps.getMaxFreqSets(freq_sets)
closed_freq_sets = FrequentSetOps.getClosedFreqSets(freq_sets, HTs)
print(len(max_freq_sets))
print(len(closed_freq_sets))
rules = FrequentSetOps.findRules(freq_sets, HTs, confidence)
HashTree.documentFreqSets(HTs, item_list, min_sup, filename)
HashTree.documentRules(HTs, item_list, rules, min_sup, confidence,
str = str + data[i+n]
if n != k-1:
str = str + " "
final_list.append(str)
data_list = final_list
result_list.append(data_list)
return result_list
result = readFile(k=4)
# Apriori Method
# L, supportData = Apriori.apriori(result, minSupport=0.05)
# rules = Apriori.generateRules(L, supportData)
# print(L)
# print(supportData)
# print(rules)
# print("count Apriori: " + str(len(rules)))
# FPGrowth
initSet = FPGrowth.createInitSet(result)
myFPtree, myHeaderTab = FPGrowth.createFPtree(initSet, 8) #用数据集构造FP树，最小支持度10
freqItems = [] # 挖掘FP树
FPGrowth.mineFPtree(myFPtree, myHeaderTab, 8 , set([]), freqItems)
counta = 0
for x in freqItems:
if len(x) != 1:
print(x)
counta = counta + 1
print("count: " + str(counta))
# -*- coding: utf-8 -*-
"""
FPGrowth：从新闻网站点击流中挖掘
@author: Jerry
"""
import FPGrowth
if __name__ == '__main__':
fr = open('kosarak.dat','r')
parsedData = [line.split() for line in fr.readlines()]
initDict = FPGrowth.createInitSet(parsedData)
newsFPTree, newsHeaderTab = FPGrowth.createTree(initDict,100000)
newsFPTree.disp()
newsFreqItems = []
FPGrowth.mineTree(newsFPTree, newsHeaderTab, 100000, set([]), newsFreqItems)
print('newsFreqItems=',newsFreqItems)
"""
import FPGrowth
# 创建数据集
def loadSimpDat():
simpDat = [['r', 'z', 'h', 'j', 'p'],
['z', 'y', 'x', 'w', 'v', 'u', 't', 's'], ['z'],
['r', 'x', 'n', 'o', 's'], ['y', 'r', 'x', 'z', 'q', 't', 'p'],
['y', 'z', 'x', 'e', 'q', 's', 't', 'm']]
return simpDat
if __name__ == '__main__':
simpleData = loadSimpDat()
initDict = FPGrowth.createInitSet(simpleData)
myFPTree, myHeaderTab = FPGrowth.createTree(initDict, 3)
myFPTree.disp()
print(
'-----------------------------------------------------------------------'
)
print(FPGrowth.findPrefixPath('x', myHeaderTab['x'][1]))
print(FPGrowth.findPrefixPath('z', myHeaderTab['z'][1]))
print(FPGrowth.findPrefixPath('r', myHeaderTab['r'][1]))
print(
'-----------------------------------------------------------------------'
)
#! encoding utf-8
import part2
import Apriori
import FPGrowth
if __name__ == '__main__':
#get buckets
dataset = part2.LSH()
# Apriori Method
L, supportData = Apriori.apriori(dataset, minSupport=0.05)
rules = Apriori.generateRules(L, supportData)
print(L)
print(supportData)
print(rules)
print("count Apriori: " + str(len(rules)))
# FPGrowth
initSet = FPGrowth.createInitSet(dataset)
myFPtree, myHeaderTab = FPGrowth.createFPtree(initSet,
2) #用数据集构造FP树，最小支持度10
freqItems = [] # 挖掘FP树
FPGrowth.mineFPtree(myFPtree, myHeaderTab, 2, set([]), freqItems)
count = 0
for x in freqItems:
if len(x) != 1:
print(x)
count = count + 1
print("count: " + str(count))
import GSP
import time
if __name__ == '__main__':
# dic = ReadData.readcsv_notime("../data/new4gtrain.csv")
# dic_t = ReadData.readcsv_withtime("../data/new4gtrain.csv")
dic = TestData.gettest()
dic_t = TestData.getTimeTest()
start = time.time()
Afrequent, sup = Apriori.apriori(dataSet=dic, minSupport=2)
end = time.time()
ATime = end - start
start = time.time()
Ffrequent = FPGrowth.FPgrowth(dataSet=dic, minsupport=2)
end = time.time()
FTime = end - start
start = time.time()
Gfrequent = GSP.gsp(dataSet=dic_t, minsupport=2)
end = time.time()
GTime = end - start
start = time.time()
Sfrequent = GSP.gsp(dataSet=dic_t, minsupport=2)
end = time.time()
STime = end - start
print dic
print "Apriori: time %.3fs FrequentSet: %s" % (ATime, Afrequent)
import FPGrowth
'''
rootNode = FPGrowth.treeNode('pyramid', 9, None)
rootNode.children['eye'] = FPGrowth.treeNode('eye', 13, None)
rootNode.children['phoenix'] = FPGrowth.treeNode('phoenix', 3, None)
rootNode.disp()
'''
'''
simpDat = FPGrowth.loadSimpDat()
initSet = FPGrowth.createInitSet(simpDat)
myFPtree, myHeaderTab = FPGrowth.createTree(initSet, 3)
# myFPtree.disp()
# print FPGrowth.findPrefixPath('t', myHeaderTab['t'][1])
freqItems = []
FPGrowth.mineTree(myFPtree, myHeaderTab, 3, set([]), freqItems)
print freqItems
'''
FPGrowth.kosarakTest("E:/TestDatas/MachineLearningInAction/Ch12/kosarak.dat")