Python市场购物篮分析未返回结果

Question

我正在玩一个样本数据集，其中的数据集看起来像这样

现在我使用以下内容成功转换了数据

import pandas as pd
import numpy as np 
import seaborn as sns
import matplotlib.pyplot as plt
from mlxtend.frequent_patterns import apriori
from mlxtend.frequent_patterns import association_rules
import mlxtend as ml

retail_data = pd.read_excel('Copy of FastFood_Transactions.xlsx')

sns.countplot(x = 'Product', data = retail_data, order = retail_data['Product'].value_counts().iloc[:10].index)
plt.xticks(rotation=90)

retail_data = retail_data.groupby(['Transaction ID','Product']).size().reset_index(name='count')
basket = (retail_data.groupby(['Transaction ID', 'Product'])['count']
          .sum().unstack().reset_index().fillna(0)
          .set_index('Transaction ID'))

#The encoding function
def encode_units(x):
    if x <= 0:
        return 0
    if x >= 1:
        return 1

basket_sets = basket.applymap(encode_units)

我验证了我的设置，看起来还不错。

但是，当我尝试如下应用关联规则和先验

frequent_itemsets = apriori(basket_sets, min_support=0.07, use_colnames=True)
rules = association_rules(frequent_itemsets, metric="lift", min_threshold=1)
rules.head()

规则为空白。

我尝试在应用apriori的地方检查支持和项集：

    support itemsets
0   0.084238    (3 Crispy Strips (incl. dip))
1   0.080320    (9 Hot Wings)
2   0.061100    (9 Hot Wings)
3   0.058294    (10 Filet Bites)
4   0.080214    (Chicken Original 1 stuk)

我注意到支持率非常低。可能是因为数据集稀疏吗？