python中Apriori算法实现讲解

# -*- coding: utf-8 -*-
"""
Created on Sat Dec 9 15:33:45 2017
@author: LPS
"""
import numpy as np
from itertools import combinations # 迭代工具
data = [[1,2,5], [2,4], [2,3], [1,2,4], [1,3], [2,3], [1,3], [1,2,3,5], [1,2,3]]
minsp = 2
d = []
for i in range(len(data)):
 d.extend(data[i])
new_d = list(set(d))
def satisfy(s, s_new, k): # 更新确实存在的L 
 e =[]
 ss_new =[]
 for i in range(len(s_new)):
  for j in combinations(s_new[i], k): # 迭代产生所有元素可能性组合
   e.append(list(j))
  if ([l for l in e if l not in s]) ==[] :
   ss_new.append(s_new[i])
  e = []
  return ss_new # 筛选满足条件的结果 
def count(s_new): # 返回narray格式的C
 num = 0
 C = np.copy(s_new)
 C = np.column_stack((C, np.zeros(C.shape[0])))
 for i in range(len(s_new)):
  for j in range(len(data)):
   if ([l for l in s_new[i] if l not in data[j]]) ==[] :
    num = num+1
  C[i,-1] = num
  num = 0   
 return C
def limit(L): # 删掉不满足阈值的C
 row = []
 for i in range(L.shape[0]):
  if L[i,-1] < minsp :
   row.append(i)
 L = np.delete(L, row, 0) 
 return L
def generate(L, k): # 实现由L至C的转换
 s = []
 for i in range(L.shape[0]):
  s.append(list(L[i,:-1]))
 s_new = []
# L = L.delete(L, -1, 1)
# l = L.shape[1]
 for i in range(L.shape[0]-1):
  for j in range(i+1, L.shape[0]):
   if (L[j,-2]>L[i,-2]):
    t = list(np.copy(s[i]))
    t.append(L[j,-2])
    s_new.append(t) # s_new为列表
    
 s_new = satisfy(s, s_new, k) 
 C = count(s_new)
 return C
# 初始的C与L
C = np.zeros([len(new_d), 2])
for i in range(len(new_d)):
 C[i:] = np.array([new_d[i], d.count(new_d[i])])
L = np.copy(C)
L = limit(L)
# 开始迭代
k = 1
while (np.max(L[:,-1]) > minsp):
 C = generate(L, k) # 由L产生C
 L = limit(C)  # 由C产生L
 k = k+1
# 对最终结果去重复
print((list(set([tuple(t) for t in L])))
# 结果为 [(1.0, 2.0, 3.0, 2.0), (1.0, 2.0, 5.0, 2.0)]