在 Python 中实现 Apriori 算法

17 Mar 2025 | 5 分钟阅读

Apriori 算法是一种机器学习算法，用于理解各种产品之间关系的模式。该算法最常见的用途是根据用户购物车中已有的商品来推荐商品。沃尔玛尤其利用该算法向用户推荐商品。

Python 实现算法

步骤 1：导入所需的库

import numpy as np
import pandas as pd
from mlxtend.frequent_patterns import apriori, association_rules

步骤 2：加载和探索数据

# Now, we will load the Data
data1 = pnd.read_excel('Online_Retail.xlsx')
data1.head()

输出

	InvoiceNo	StockCode	描述	数量	InvoiceDate	UnitPrice	CustomerID	国家
0	536365	85123A	WHITE HANGING HEART T-LIGHT HOLDER	6	2010-12-01 08:26:00	2.55	17850.0	英国
1	536365	71053	WHITE METAL LANTERN	6	2010-12-01 08:26:00	3.39	17850.0	英国
2	536365	84406B	CREAM CUPID HEARTS COAT HANGER	8	2010-12-01 08:26:00	2.75	17850.0	英国
3	536365	84406B	KNITTED UNION FLAG HOT WATER BOTTLE	6	2010-12-01 08:26:00	3.39	17850.0	英国
4	536365	84029E	RED WOOLLY HOTTIE WHITE HEART.	6	2010-12-01 08:26:00	3.39	17850.0	英国

输入

# here, we will explore the columns of the data
data1.columns

输出

Index(['InvoiceNo', 'StockCode', 'Description', 'Quantity', 'InvoiceDate',
       'UnitPrice', 'CustomerID', 'Country'],
      Dtype = 'object')

输入

# Now, we will explore the different regions of transactions
data1.Country.unique()

输出

array(['United Kingdom', 'France', 'Australia', 'Netherlands', 'Germany',
       'Norway', 'EIRE', 'Switzerland', 'Spain', 'Poland', 'Portugal',
       'Italy', 'Belgium', 'Lithuania', 'Japan', 'Iceland',
       'Channel Islands', 'Denmark', 'Cyprus', 'Sweden', 'Austria',
       'Israel', 'Finland', 'Bahrain', 'Greece', 'Hong Kong', 'Singapore',
       'Lebanon', 'United Arab Emirates', 'Saudi Arabia',
       'Czech Republic', 'Canada', 'Unspecified', 'Brazil', 'USA',
       'European Community', 'Malta', 'RSA'], dtype = object)

步骤 3：清理数据

# here, we will strip the extra spaces in the description
data1['Description'] = data1['Description'].str.strip()

# Now, drop the rows which does not have any invoice number
data1.dropna(axis = 0, subset = ['InvoiceNo'], inplace = True)
data1['InvoiceNo'] = data1['InvoiceNo'].astype('str')

# Now, we will drop all transactions which were done on credit
data1 = data1[~data1['InvoiceNo'].str.contains('C')]

步骤 4：根据交易地区拆分数据

# Transactions done in France
basket1_France = (data1[data1['Country'] == "France"]
		.groupby(['InvoiceNo', 'Description'])['Quantity']
		.sum().unstack().reset_index().fillna(0)
		.set_index('InvoiceNo'))

# Transactions done in the United Kingdom
basket1_UK = (data1[data1['Country'] == "United Kingdom"]
		.groupby(['InvoiceNo', 'Description'])['Quantity']
		.sum().unstack().reset_index().fillna(0)
		.set_index('InvoiceNo'))

# Transactions done in Portugal
basket1_Por = (data1[data1['Country'] == "Portugal"]
		.groupby(['InvoiceNo', 'Description'])['Quantity']
		.sum().unstack().reset_index().fillna(0)
		.set_index('InvoiceNo'))

basket1_Sweden = (data1[data1['Country'] == "Sweden"]
		.groupby(['InvoiceNo', 'Description'])['Quantity']
		.sum().unstack().reset_index().fillna(0)
		.set_index('InvoiceNo'))

步骤 5：对数据进行独热编码

# Here, we will define the hot encoding function 
# for making the data suitable
# for the concerned libraries
def hot_encode1(P):
	if(P<= 0):
		return 0
	if(P>= 1):
		return 1

# Here, we will encode the datasets
basket1_encoded = basket1_France.applymap(hot_encode1)
basket1_France = basket1_encoded

basket1_encoded = basket1_UK.applymap(hot_encode1)
basket1_UK = basket1_encoded

basket1_encoded = basket1_Por.applymap(hot_encode1)
basket1_Por = basket1_encoded

basket1_encoded = basket1_Sweden.applymap(hot_encode1)
basket1_Sweden = basket1_encoded

步骤 6：构建模型并分析结果

a) 法国

# Build the model
frq_items1 = AP(basket1_France, min_support = 0.05, use_colnames = True)

# Collect the inferred rules in a dataframe
rules1 = AR(frq_items1, metric = "lift", min_threshold = 1)
rules1 = rules1.sort_values(['confidence', 'lift'], ascending = [False, False])
print(rules1.head())

输出

antecedents \

45 (JUMBO BAG WOODLAND ANIMALS)

260 (PLASTERS IN TIN CIRCUS PARADE, RED TOADSTOOL ...

272 (RED TOADSTOOL LED NIGHT LIGHT, PLASTERS IN TI...

302 (SET/6 RED SPOTTY PAPER CUPS, SET/20 RED RETRO...

301 (SET/6 RED SPOTTY PAPER PLATES, SET/20 RED RET...

consequents antecedent support consequent support \

45 (POSTAGE) 0.076531 0.765306

260 (POSTAGE) 0.051020 0.765306

272 (POSTAGE) 0.053571 0.765306

302 (SET/6 RED SPOTTY PAPER PLATES) 0.102041s 0.127551

301 (SET/6 RED SPOTTY PAPER CUPS) 0.102041 0.137755

support confidence lift leverage conviction

45 0.076531 1.000 1.306667 0.017961 inf

260 0.051020 1.000 1.306667 0.011974 inf

272 0.053571 1.000 1.306667 0.012573 inf

302 0.099490 0.975 7.644000 0.086474 34.897959

301 0.099490 0.975 7.077778 0.085433 34.489796

从以上输出可以看出，纸杯、纸盘和盘子在法国一起被购买。这是因为法国人每周至少会与朋友和家人聚会一次。此外，由于法国政府禁止在该国使用塑料，人们不得不购买纸质替代品。

b) 英国

frq_items = apriori(basket_UK, min_support = 0.01, use_colnames = True)
rules = association_rules(frq_items, metric ="lift", min_threshold = 1)
rules = rules.sort_values(['confidence', 'lift'], ascending =[False, False])
print(rules.head())

Implementing Apriori Algorithm in Python

如果更详细地检查英国交易的指南，会发现英国消费者购买各种颜色的茶盘。原因可能是英国人喜爱茶，并倾向于收集不同颜色的茶盘以适应不同场合。

c) 葡萄牙

frq_items1 = AP(basket1_Sweden, min_support = 0.05, use_colnames = True)
rules1 = AR(frq_items1, metric ="lift", min_threshold = 1)
rules1 = rules1.sort_values(['confidence', 'lift'], ascending =[False, False])
print(rules1.head())

输出

antecedents consequents \

1170 (SET 12 COLOUR PENCILS DOLLY GIRL) (SET 12 COLOUR PENCILS SPACEBOY)

1171 (SET 12 COLOUR PENCILS SPACEBOY) (SET 12 COLOUR PENCILS DOLLY GIRL)

1172 (SET OF 4 KNICK KNACK TINS LONDON) (SET 12 COLOUR PENCILS DOLLY GIRL)

1173 (SET 12 COLOUR PENCILS DOLLY GIRL) (SET OF 4 KNICK KNACK TINS LONDON)

1174 (SET 12 COLOUR PENCILS DOLLY GIRL) (SET OF 4 KNICK KNACK TINS POPPIES)

antecedent support consequent support support confidence lift \

1170 0.051724 0.051724 0.051724 1.0 19.333333

1171 0.051724 0.051724 0.051724 1.0 19.333333

1172 0.051724 0.051724 0.051724 1.0 19.333333

1173 0.051724 0.051724 0.051724 1.0 19.333333

1174 0.051724 0.051724 0.051724 1.0 19.333333

leverage conviction

1170 0.049049 inf

1171 0.049049 inf

1172 0.049049 inf

1173 0.049049 inf

1174 0.049049 inf

在分析葡萄牙交易的关联规则时，可以发现饭盒套装（Knick Knack Tins）和彩色铅笔的使用。这两件物品通常属于小学儿童。学生们在学校需要这两样物品来携带午餐以及进行需要创造力的工作，因此将它们配对是有道理的。

d) 瑞典

frq_items1 = AP(basket1_Sweden, min_support = 0.05, use_colnames = True)
rules1 = AR(frq_items1, metric ="lift", min_threshold = 1)
rules1 = rules1.sort_values(['confidence', 'lift'], ascending =[False, False])
print(rules1.head())

输出

antecedents consequents \

0 (PACK OF 72 SKULL CAKE CASES) (12 PENCILS SMALL TUBE SKULL)

1 (12 PENCILS SMALL TUBE SKULL) (PACK OF 72 SKULL CAKE CASES)

4 (36 DOILIES DOLLY GIRL) (ASSORTED BOTTLE TOP MAGNETS)

5 (ASSORTED BOTTLE TOP MAGNETS) (36 DOILIES DOLLY GIRL)

180 (CHILDRENS CUTLERY DOLLY GIRL) (CHILDRENS CUTLERY CIRCUS PARADE)

antecedent support consequent support support confidence lift \

0 0.055556 0.055556 0.055556 1.0 18.0

1 0.055556 0.055556 0.055556 1.0 18.0

4 0.055556 0.055556 0.055556 1.0 18.0

5 0.055556 0.055556 0.055556 1.0 18.0

180 0.055556 0.055556 0.055556 1.0 18.0

leverage conviction

0 0.052469 inf

1 0.052469 inf

4 0.052469 inf

5 0.052469 inf

180 0.052469 inf

通过分析上述指南和上述规则，我们发现女孩和男孩的餐具被放在一起。这是有道理的，因为当父母为孩子购买餐具时，他们希望这些餐具是孩子喜欢的。

下一主题使用 VADER 进行情感分析

在 Python 中实现 Apriori 算法

Python 实现算法

联系信息

关注我们

教程

面试题

在线编译器

Python

Java

.Net Framework

AI, ML and Data Science

Cloud Technology

B.Tech and MCA

Web Technology

PHP

Software Testing

Technical Interview

Java Interview

Python

Web Interview

Database Interview

B.Tech / MCA

Important Interview

Software Testing Interview

Company Interviews

Online Compilers

Multiple Choice Questions

Python 问题

在 Python 中实现 Apriori 算法

Python 实现算法

相关帖子

Python 中的二叉堆是什么

在 Python 中读写列表到文件

Python Struct 模块

Python 中的 Fraction 模块

KMP 算法 - 使用 Python 实现 KMP 算法

Python 中的括号平衡

Python 中的 __file__ (特殊变量)

Python Timeit 模块

Python 中的 Web 开发是什么

PyQt5 QDoubleSpinBox - 获取最大可能值

订阅 Tpoint Tech

联系信息

关注我们

教程

面试题

在线编译器

Python 中的 file (特殊变量)