commit 6e9c2a5f918aedac42c4cb138f43a99412e51ebf
Author: fly6516 <fly6516@outlook.com>
Date:   Wed Mar 12 16:31:10 2025 +0800

    feat(code): 添加 Apriori 和 FP-Growth 算法实现
    
    - 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

diff --git a/code/5-6_cal_apriori.py b/code/5-6_cal_apriori.py
new file mode 100644
index 0000000..9c01607
--- /dev/null
+++ b/code/5-6_cal_apriori.py
@@ -0,0 +1,24 @@
+#-*- coding: utf-8 -*-
+#使用Apriori算法挖掘菜品订单关联规则
+from __future__ import print_function
+import pandas as pd
+from apriori import * #导入自行编写的apriori函数
+
+inputfile = '../data/menu_orders.xls'
+outputfile = '../tmp/apriori_rules.xlsx' #结果文件，保留 .xlsx 格式
+data = pd.read_excel(inputfile, header = None)
+
+print(u'\n转换原始数据至0-1矩阵...')
+ct = lambda x : pd.Series(1, index = x[pd.notnull(x)]) #转换0-1矩阵的过渡函数
+b = map(ct, data.iloc[:,:].values) #用map方式执行
+data = pd.DataFrame(list(b)).fillna(0) #实现矩阵转换，空值用0填充
+print(u'\n转换完毕。')
+del b #删除中间变量b，节省内存
+
+support = 0.2 #最小支持度
+confidence = 0.5 #最小置信度
+ms = '---' #连接符，默认'--'，用来区分不同元素，如A--B。需要保证原始表格中不含有该字符
+
+# 提醒用户需要安装 openpyxl 库以支持 .xlsx 格式
+# 如果未安装，可以通过以下命令安装：pip install openpyxl
+find_rule(data, support, confidence, ms).to_excel(outputfile, engine='openpyxl') #保存结果，指定 engine='openpyxl'
\ No newline at end of file
diff --git a/code/5-6_cal_fpgrowth.py b/code/5-6_cal_fpgrowth.py
new file mode 100644
index 0000000..d7bb260
--- /dev/null
+++ b/code/5-6_cal_fpgrowth.py
@@ -0,0 +1,41 @@
+#-*- coding: utf-8 -*-
+# 使用FP-Growth算法挖掘菜品订单关联规则
+from __future__ import print_function
+import pandas as pd
+from fpgrowth import find_frequent_itemsets  # 导入FP-Growth函数
+
+inputfile = '../data/menu_orders.xls'
+outputfile = '../tmp/fpgrowth_rules.xlsx'  # 结果文件，保留 .xlsx 格式
+data = pd.read_excel(inputfile, header=None)
+
+print(u'\n转换原始数据至0-1矩阵...')
+ct = lambda x: pd.Series(1, index=x[pd.notnull(x)])  # 转换0-1矩阵的过渡函数
+b = map(ct, data.iloc[:, :].values)  # 用map方式执行
+data = pd.DataFrame(list(b)).fillna(0)  # 实现矩阵转换，空值用0填充
+print(u'\n转换完毕。')
+del b  # 删除中间变量b，节省内存
+
+# 将数据转换为事务列表
+transactions = []
+for _, row in data.iterrows():
+    transactions.append(list(row[row == 1].index))
+
+min_support = 0.2  # 最小支持度
+min_support_count = int(min_support * len(transactions))  # 转换为绝对支持度
+
+# 使用FP-Growth算法挖掘频繁项集
+frequent_itemsets = find_frequent_itemsets(transactions, min_support_count)
+
+# 确保 frequent_itemsets 是一个列表，其中每个元素是一个列表
+frequent_itemsets = [list(itemset) for itemset in frequent_itemsets]
+
+# 将结果保存为DataFrame
+# 修改：将频繁项集转换为DataFrame时，确保每一行对应一个频繁项集的所有元素
+result_data = []
+for itemset in frequent_itemsets:
+    result_data.append({'Frequent Itemsets': ', '.join(itemset)})  # 将每个频繁项集转换为字符串
+
+result = pd.DataFrame(result_data)
+result.to_excel(outputfile, engine='openpyxl')  # 保存结果，指定 engine='openpyxl'
+
+print(u'\nFP-Growth算法运行完毕，结果已保存至:', outputfile)
diff --git a/code/apriori.py b/code/apriori.py
new file mode 100644
index 0000000..619a426
--- /dev/null
+++ b/code/apriori.py
@@ -0,0 +1,59 @@
+# -*- coding: utf-8 -*-
+from __future__ import print_function
+import pandas as pd
+
+
+# 自定义连接函数，用于实现L_{k-1}到C_k的连接
+def connect_string(x, ms):
+    x = list(map(lambda i: sorted(i.split(ms)), x))
+    l = len(x[0])
+    r = []
+    for i in range(len(x)):
+        for j in range(i, len(x)):
+            if x[i][:l - 1] == x[j][:l - 1] and x[i][l - 1] != x[j][l - 1]:
+                r.append(x[i][:l - 1] + sorted([x[j][l - 1], x[i][l - 1]]))
+    return r
+
+
+# 寻找关联规则的函数
+def find_rule(d, support, confidence, ms=u'--'):
+    result = pd.DataFrame(index=['support', 'confidence'])  # 定义输出结果
+
+    support_series = 1.0 * d.sum() / len(d)  # 支持度序列
+    column = list(support_series[support_series > support].index)  # 初步根据支持度筛选
+    k = 0
+
+    while len(column) > 1:
+        k = k + 1
+        print(u'\n正在进行第%s次搜索...' % k)
+        column = connect_string(column, ms)
+        print(u'数目：%s...' % len(column))
+        sf = lambda i: d[i].prod(axis=1, numeric_only=True)  # 新一批支持度的计算函数
+
+        # 创建连接数据，这一步耗时、耗内存最严重。当数据集较大时，可以考虑并行运算优化。
+        d_2 = pd.DataFrame(list(map(sf, column)), index=[ms.join(i) for i in column]).T
+
+        support_series_2 = 1.0 * d_2[[ms.join(i) for i in column]].sum() / len(d)  # 计算连接后的支持度
+        column = list(support_series_2[support_series_2 > support].index)  # 新一轮支持度筛选
+        support_series = pd.concat([support_series, support_series_2])
+        column2 = []
+
+        for i in column:  # 遍历可能的推理，如{A,B,C}究竟是A+B-->C还是B+C-->A还是C+A-->B？
+            i = i.split(ms)
+            for j in range(len(i)):
+                column2.append(i[:j] + i[j + 1:] + i[j:j + 1])
+
+        cofidence_series = pd.Series(index=[ms.join(i) for i in column2])  # 定义置信度序列
+
+        for i in column2:  # 计算置信度序列
+            cofidence_series[ms.join(i)] = support_series[ms.join(sorted(i))] / support_series[ms.join(i[:len(i) - 1])]
+
+        for i in cofidence_series[cofidence_series > confidence].index:  # 置信度筛选
+            result.loc[i, 'confidence'] = cofidence_series[i]  # 使用 .loc 更新置信度
+            result.loc[i, 'support'] = support_series[ms.join(sorted(i.split(ms)))]  # 使用 .loc 更新支持度
+
+    result = result.T.sort_values(['confidence', 'support'], ascending=False)  # 结果整理，输出
+    print(u'\n结果为：')
+    print(result)
+
+    return result
\ No newline at end of file
diff --git a/code/fpgrowth.py b/code/fpgrowth.py
new file mode 100644
index 0000000..29fd4ee
--- /dev/null
+++ b/code/fpgrowth.py
@@ -0,0 +1,104 @@
+# -*- 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
\ No newline at end of file
diff --git a/data/menu_orders.xls b/data/menu_orders.xls
new file mode 100644
index 0000000..0d056e2
Binary files /dev/null and b/data/menu_orders.xls differ
diff --git a/tmp/apriori_rules.xls b/tmp/apriori_rules.xls
new file mode 100644
index 0000000..32001fe
Binary files /dev/null and b/tmp/apriori_rules.xls differ
diff --git a/tmp/apriori_rules.xlsx b/tmp/apriori_rules.xlsx
new file mode 100644
index 0000000..5616c71
Binary files /dev/null and b/tmp/apriori_rules.xlsx differ
diff --git a/tmp/fpgrowth_rules.xlsx b/tmp/fpgrowth_rules.xlsx
new file mode 100644
index 0000000..1f99d78
Binary files /dev/null and b/tmp/fpgrowth_rules.xlsx differ