apriori算法python实现实验报告_apriori算法Python实现

import numpy as np

import pandas as pd

## 方法一：

def generate_C1(data_set):

c1 = set()

for items in data_set:

for item in items:

item_set = frozenset([item])

c1.add(item_set)

return c1

#计算Ck在数据集D中的支持度，并返回支持度大于minSupport的数据集

def get_supports(data_set, ck, min_support,supports):

freq_set = set()

item_count = {}

# supports = {}

for data in data_set:

for item in ck:

if item.issubset(data):

if item not in item_count:

item_count[item] = 1

else:

item_count[item] += 1

n= float(len(data_set))

for item in item_count:

if (item_count[item] / n) >= min_support:

freq_set.add(item)

supports[item] = item_count[item] / n

return freq_set

#剪枝

def get_new_s