# !/usr/bin/python
# coding:utf-8
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
def createinitset(dataset):
"""產生初始資料集合"""
retdict = {}
for trans in dataset:
fset = frozenset(trans)
retdict.setdefault(fset, 0)
retdict[fset] += 1
return retdict
class treenode:
def __init__(self, namevalue, numoccur, parentnode):
self.name = namevalue
self.count = numoccur
self.nodelink = none
self.parent = parentnode
self.children = {}
def inc(self, numoccur):
self.count += numoccur
def disp(self, ind=1):
print(' ' * ind, self.name, ' ', self.count)
for child in self.children.values():
child.disp(ind + 1)
def createtree(dataset, minsup=1):
headertable = {}
#此一次遍歷資料集， 記錄每個資料項的支援度
for trans in dataset:
for item in trans:
headertable[item] = headertable.get(item, 0) + 1
#根據最小支援度過濾
lessthanminsup = list(filter(lambda k:headertable[k] < minsup, headertable.keys()))
for k in lessthanminsup:
del(headertable[k])
freqitemset = set(headertable.keys())
#如果所有資料都不滿足最小支援度，返回none, none
if len(freqitemset) == 0:
return none, none
for k in headertable:
headertable[k] = [headertable[k], none]
rettree = treenode('φ', 1, none)
#第二次遍歷資料集，構建fp-tree
for transet, count in dataset.items():
#根據最小支援度處理一條訓練樣本，key:樣本中的乙個樣例，value:該樣例的的全域性支援度
locald = {}
for item in transet:
if item in freqitemset:
locald[item] = headertable[item][0]
if len(locald) > 0:
#根據全域性頻繁項對每個事務中的資料進行排序,等價於 order by p[1] desc, p[0] desc
ordereditems = [v[0] for v in sorted(locald.items(), key=lambda p: (p[1], p[0]), reverse=true)]
updatetree(ordereditems, rettree, headertable, count)
return rettree, headertable
def updatetree(items, intree, headertable, count):
if items[0] in intree.children: # 檢查該元素是否已經存在fp樹中
intree.children[items[0]].inc(count) # 計數+1
else: # 不存在則新增到fp樹中
intree.children[items[0]] = treenode(items[0], count, intree)
if headertable[items[0]][1] == none: # 更新頭表
headertable[items[0]][1] = intree.children[items[0]]
else:
updateheader(headertable[items[0]][1], intree.children[items[0]])
if len(items) > 1: # 擷取已排序list的剩餘部分，並以當前節點作為父節點
updatetree(items[1:], intree.children[items[0]], headertable, count)
def updateheader(nodetotest, targetnode):
while (nodetotest.nodelink != none): # 找到尾節點
nodetotest = nodetotest.nodelink
nodetotest.nodelink = targetnode
def ascendtree(leafnode, prefixpath):
"""獲取當前節點的所有祖先"""
if leafnode.parent != none:
ascendtree(leafnode.parent, prefixpath)
def findprefixpath(basepat, headtable):
"""獲取當前頻繁項的所有字首路徑（條件模式基）"""
condpats = {}
treenode = headtable[basepat][1]
while treenode != none:
# 獲取當前頻繁項的所有字首路徑（條件模式基）
prefixpath =
ascendtree(treenode, prefixpath)
if len(prefixpath) > 1:
condpats[frozenset(prefixpath[1:])] = treenode.count # 該條件模式基獲得該節點所具有的置信度
treenode = treenode.nodelink
return condpats
def minetree(intree, headertable, minsup=1, prefix=set(), freqitemlist=):
bigl = [v[0] for v in sorted(headertable.items(), key=lambda p: (p[1][0], p[0]))]
for basepat in bigl:
newfreqset = prefix.copy()
newfreqset.add(basepat)
# 通過條件模式基找到的頻繁項集
condpattbases = findprefixpath(basepat, headertable)
# 建立條件fp樹
mycondtree, myhead = createtree(condpattbases, minsup)
if myhead != none:
print('condpattbases: ', basepat, condpattbases)
mycondtree.disp()
print('*' * 30)
minetree(mycondtree, myhead, minsup, newfreqset, freqitemlist)
def main():
simpdat = loadsimpdat()
dictdat = createinitset(simpdat)
myfptree, myheader = createtree(dictdat, 3)
myfptree.disp()
print('*' * 30)
# 獲取條件模式基
for key in [v[0] for v in sorted(myheader.items(), key=lambda p: (p[1][0], p[0]), reverse=true)]:
condpats = findprefixpath(key, myheader)
print(key, condpats)
print('*' * 30)
# 建立條件fp樹
minetree(myfptree, myheader, 2)
if __name__ == '__main__':
main()
python3實現CryptoJS AES加密演算法
from crypto.cipher import aes from binascii import b2a hex,a2b hex import base64 class aescrypt def init self,key self.key key.encode utf8 self.mode a...
Python3 實現選擇排序
選擇排序 selection sort 原理很簡單，就是依次在未排序資料段中選擇出乙個最小的數，然後將其排列在已排序資料段末端，直到整個資料段排序完成演算法結束。程式如下，第乙個迴圈依次縮小未排序資料段的長度，並且每次將最小值暫定為未排序中第一位索引。第二個迴圈依次將該最小值與未排序資料段作比較，選...
python3實現線性單元
理論知識見 直接上python3的 coding utf 8 import matplotlib.pyplot as plt from functools import reduce class perceptron object 初始化，輸入訓練數目，啟用函式 def init self,inpu...