def test():
simpDat = fpGrowth.loadSimpDat()
initSet = fpGrowth.createInitSet(simpDat)
myFPtree, myHeaderTab = fpGrowth.createTree(initSet, 3)
myFPtree.disp()
freqItems = []
fpGrowth.mineTree(myFPtree, myHeaderTab, 3, set([]), freqItems)
import fpGrowth
rootNode = fpGrowth.treeNode('pyramid', 9, None)
rootNode.children['eye'] = fpGrowth.treeNode('eye', 13, None)
rootNode.disp()
rootNode.children['phoenix'] = fpGrowth.treeNode('phoenix', 3, None)
rootNode.disp()
from importlib import reload
reload(fpGrowth)
simpDat = fpGrowth.loadSimpDat()
simpDat
initSet = fpGrowth.createInitSet(simpDat)
initSet
# 创建FP树
myFPtree, myHeaderTab = fpGrowth.createTree(initSet, 3)
myFPtree.disp()
reload(fpGrowth)
fpGrowth.findPrefixPath('x', myHeaderTab['x'][1])
fpGrowth.findPrefixPath('z', myHeaderTab['z'][1])
fpGrowth.findPrefixPath('r', myHeaderTab['r'][1])
reload(fpGrowth)
freqItems = []
fpGrowth.mineTree(myFPtree, myHeaderTab, 3, set([]), freqItems)
freqItems
# 示例：从新闻网站点击流中挖掘
parsedDat = [line.split() for line in open('kosarak.dat').readlines()]
initSet = fpGrowth.createInitSet(parsedDat)
myFPtree, myHeaderTab = fpGrowth.createTree(initSet, 100000)
import fpGrowth
simpDat = fpGrowth.loadSimpDat()
# print simpDat
initSet = fpGrowth.createInitSet(simpDat)
# print initSet
myFpTree, myHeaderTab = fpGrowth.createTree(initSet, 3)
# print myFpTree.disp()
# print myHeaderTab
myCondPat = fpGrowth.findPrefixPath('x', myHeaderTab['x'][1])
# print myCondPat
freqItems = []
myfpGrowth = fpGrowth.mineTree(myFpTree, myHeaderTab, 3, set([]), freqItems)
# print myFpTree.disp()
# -*- coding:utf-8 -*-
import fpGrowth
#算法基本过程：
#1.创建FP树的数据结构
#2.第一次遍历数据集会获得每个元素项的出现频率。 去掉不满足支持度的元素项
#3.对每个事务（即每个记录）中的集合进行排序。排序基于元素项的绝对出现频率来进行
#4.构建FP树。从空集开始，向其中不断添加频繁项集。即在构建时，读入每个事务中的项集，并将其添加到已存在的路径中。
# 如果树中已经存在现有元素，则增加现有元素的值
# 如果该路径不存在，则创建一条新路径。
###测试FP数的数据结构
#rootNode = fpGrowth.treeNode('pyramid',9,None)
#rootNode.children['eye'] = fpGrowth.treeNode('eye',13,None)
#rootNode.children['phoenix'] = fpGrowth.treeNode('phoenix',3,None)
#rootNode.disp()
simData = fpGrowth.loadSimpDat()
initSet = fpGrowth.createInitSet(simData)
myFpTree,myHeaderTab = fpGrowth.createTree(initSet, 3)
myFpTree.disp()
myCondPats = fpGrowth.findPrefixPath('r', myHeaderTab['r'][1])
print ('myCondPats is' , myCondPats)
freqItems = []
fpGrowth.mineTree(myFpTree, myHeaderTab, 3, set ([]), freqItems)
print('频繁项集 is' , freqItems)
# -*- coding: utf-8 -*-
'''
Created on 2016年6月22日
@author: xiaoyuan
'''
import fpGrowth
# #testing create a tree datastructor
# rootNode = fpGrowth.treeNode('pyramid',9,None)
# rootNode.children['eye'] = fpGrowth.treeNode('eye',13,None)
# rootNode.children['phoenix'] = fpGrowth.treeNode('phoenix',3,None)
# rootNode.disp()
#
#
# simDat = fpGrowth.loadSimpDat()
# initSet = fpGrowth.createInitSet(simDat)
# myFPtree,myHeaderTab = fpGrowth.createTree(initSet,3)
# myFPtree.disp()
# condPattBases = fpGrowth.findPrefixPath('x',myHeaderTab['x'][1])
dateSet = fpGrowth.loadSimpDat()
freqItems = fpGrowth.fpGrowth(dateSet)
if __name__ == '__main__':
# takes all bacterias names from bactTaxa_Habitant that are animal or marine
bacteria_names()
category = "Lipid transport and metabolism"
# list of all cogs that belong to catagory
function_cogs_list = build_category_list(category)
# dict = {bac_name, {words_list, lable}}
dict, animal_counter, marine_counter = write_words(function_cogs_list)
min_sup = 100
output = open("output.txt", "w")
simpDat = fpGrowth.loadSimpDat(dict)
initSet = fpGrowth.createInitSet(simpDat)
myFPtree, myHeaderTab = fpGrowth.createTree(initSet, min_sup)
if not myHeaderTab:
print("header table empty")
print("--- %s seconds ---" % (time.time() - start_time))
exit(1)
freqItems = []
fpGrowth.mineTree(myFPtree, myHeaderTab, min_sup, set([]), freqItems)
class0 = marine_counter / (marine_counter + animal_counter)
class1 = animal_counter / (marine_counter + animal_counter)
Hc = entropy(class0, class1)
dict_IG_freq = {}
# claculate IG to all the frequent itemsets, returns also how many time each freq_itemset appears in lable 1 and 0
@author: xiaoyuan
'''
import fpGrowth
# #testing create a tree datastructor
# rootNode = fpGrowth.treeNode('pyramid',9,None)
# rootNode.children['eye'] = fpGrowth.treeNode('eye',13,None)
# rootNode.children['phoenix'] = fpGrowth.treeNode('phoenix',3,None)
# rootNode.disp()
#
#
# simDat = fpGrowth.loadSimpDat()
# initSet = fpGrowth.createInitSet(simDat)
# myFPtree,myHeaderTab = fpGrowth.createTree(initSet,3)
# myFPtree.disp()
# condPattBases = fpGrowth.findPrefixPath('x',myHeaderTab['x'][1])
dateSet = fpGrowth.loadSimpDat()
freqItems = fpGrowth.fpGrowth(dateSet)
# -*- coding:utf-8 -*-
import fpGrowth
#算法基本过程：
#1.创建FP树的数据结构
#2.第一次遍历数据集会获得每个元素项的出现频率。 去掉不满足支持度的元素项
#3.对每个事务（即每个记录）中的集合进行排序。排序基于元素项的绝对出现频率来进行
#4.构建FP树。从空集开始，向其中不断添加频繁项集。即在构建时，读入每个事务中的项集，并将其添加到已存在的路径中。
# 如果树中已经存在现有元素，则增加现有元素的值
# 如果该路径不存在，则创建一条新路径。
###测试FP数的数据结构
#rootNode = fpGrowth.treeNode('pyramid',9,None)
#rootNode.children['eye'] = fpGrowth.treeNode('eye',13,None)
#rootNode.children['phoenix'] = fpGrowth.treeNode('phoenix',3,None)
#rootNode.disp()
simData = fpGrowth.loadSimpDat()
initSet = fpGrowth.createInitSet(simData)
myFpTree, myHeaderTab = fpGrowth.createTree(initSet, 3)
myFpTree.disp()
myCondPats = fpGrowth.findPrefixPath('r', myHeaderTab['r'][1])
print('myCondPats is', myCondPats)
freqItems = []
fpGrowth.mineTree(myFpTree, myHeaderTab, 3, set([]), freqItems)
print('频繁项集 is', freqItems)
