fly6516
6e9c2a5f91
- 新增 Apriori算法挖掘关联规则的实现 - 新增 FP-Growth算法挖掘频繁项集的实现 - 添加相应的数据预处理和结果保存代码 - 优化代码结构，提高可读性和可维护性
104 lines
3.2 KiB
Python
104 lines
3.2 KiB
Python
# -*- coding: utf-8 -*-
|
||
from __future__ import print_function
|
||
import pandas as pd
|
||
from collections import defaultdict
|
||
|
||
|
||
class FPNode:
|
||
def __init__(self, item=None, count=0, parent=None):
|
||
self.item = item
|
||
self.count = count
|
||
self.parent = parent
|
||
self.children = {}
|
||
self.next = None
|
||
|
||
|
||
def build_fp_tree(data, min_support):
|
||
# 构建FP树
|
||
header_table = defaultdict(int)
|
||
for transaction in data:
|
||
for item in transaction:
|
||
header_table[item] += 1
|
||
|
||
# 移除不满足最小支持度的项
|
||
header_table = {k: v for k, v in header_table.items() if v >= min_support}
|
||
if not header_table:
|
||
return None, None
|
||
|
||
# 初始化头表
|
||
for k in header_table:
|
||
header_table[k] = [header_table[k], None]
|
||
|
||
root = FPNode()
|
||
for transaction in data:
|
||
filtered_items = [item for item in transaction if item in header_table]
|
||
if filtered_items:
|
||
filtered_items.sort(key=lambda x: header_table[x][0], reverse=True)
|
||
update_fp_tree(filtered_items, root, header_table)
|
||
return root, header_table
|
||
|
||
|
||
def update_fp_tree(items, node, header_table):
|
||
# 更新FP树
|
||
if items[0] in node.children:
|
||
node.children[items[0]].count += 1
|
||
else:
|
||
new_node = FPNode(item=items[0], count=1, parent=node)
|
||
node.children[items[0]] = new_node
|
||
update_header_table(header_table, items[0], new_node)
|
||
if len(items) > 1:
|
||
update_fp_tree(items[1:], node.children[items[0]], header_table)
|
||
|
||
|
||
def update_header_table(header_table, item, target_node):
|
||
# 更新头表指针
|
||
if header_table[item][1] is None:
|
||
header_table[item][1] = target_node
|
||
else:
|
||
current = header_table[item][1]
|
||
while current.next:
|
||
current = current.next
|
||
current.next = target_node
|
||
|
||
|
||
def mine_fp_tree(header_table, prefix, min_support, frequent_itemsets):
|
||
# 挖掘FP树中的频繁项集
|
||
sorted_items = [item[0] for item in sorted(header_table.items(), key=lambda x: x[1][0])]
|
||
for item in sorted_items:
|
||
new_prefix = prefix.copy()
|
||
new_prefix.add(item)
|
||
frequent_itemsets.append(new_prefix)
|
||
conditional_pattern_bases = find_prefix_paths(item, header_table)
|
||
conditional_fp_tree, conditional_header_table = build_fp_tree(conditional_pattern_bases, min_support)
|
||
if conditional_header_table:
|
||
mine_fp_tree(conditional_header_table, new_prefix, min_support, frequent_itemsets)
|
||
|
||
|
||
def find_prefix_paths(base_item, header_table):
|
||
# 找到条件模式基
|
||
paths = []
|
||
node = header_table[base_item][1]
|
||
while node:
|
||
path = []
|
||
ascend_tree(node, path)
|
||
if path:
|
||
paths.append(path)
|
||
node = node.next
|
||
return paths
|
||
|
||
|
||
def ascend_tree(node, path):
|
||
# 从节点向上遍历树
|
||
while node.parent and node.parent.item:
|
||
path.append(node.parent.item)
|
||
node = node.parent
|
||
|
||
|
||
def find_frequent_itemsets(data, min_support):
|
||
# 主函数：使用FP-Growth算法挖掘频繁项集
|
||
root, header_table = build_fp_tree(data, min_support)
|
||
if not root:
|
||
return []
|
||
frequent_itemsets = []
|
||
mine_fp_tree(header_table, set(), min_support, frequent_itemsets)
|
||
return frequent_itemsets |