Skip to main content

The tool is designed to mine behavior patterns

Project description

BehaviorTool是一个Python包,提供了CombinePattern、ContinuePattern和SequencePattern三个类的实现行为模式挖掘。

安装

你可以使用pip安装BahaviorPattern:

pip install BehaviorPattern

使用

在你的Python代码中引入类,例如:

from BehaviorPattern. import CombinePattern, ContinuePattern, SequencePattern

#--------------------------------- 组合行为模式挖掘 ---------------------------------#
use_behavior = []
del_behavior = []
# 创建实例
behavior = CombinePattern.Generate(data=data, 
                                   use_behavior=use_behavior, 
                                   del_behavior=del_behavior, 
                                   min_support=0.1, 
                                   min_confidence=0.5, 
                                   min_length=3, 
                                   max_length=7, 
                                   sep='@') 
# 运行模型,返回pattern结果和使用的行为列表
combine, combine_use_behavior = behavior.run() 
# 筛选lift符合要求的pattern
combine_result = combine[combine['lift'] > 6] 


#--------------------------------- 连续行为模式挖掘 ---------------------------------#
use_behavior = []
del_behavior = []
# 创建实例
behavior = ContinuePattern.Generate(data=data, 
                                    use_behavior=use_behavior, 
                                    del_behavior=del_behavior, 
                                    min_support=0.1, 
                                    min_length=3, 
                                    max_length=6, 
                                    sep='@') 
# 运行模型,返回pattern结果和使用的行为列表
continues, continue_use_behavior = behavior.run() 
# 筛选lift符合要求的pattern
continues_result = continues[continues['lift'] > 6] 


#--------------------------------- 序列行为模式挖掘 ---------------------------------#
use_behavior = []
del_behavior = []
# 创建实例
behavior = SequencePattern.Generate(data=data, 
                                    use_behavior=use_behavior, 
                                    del_behavior=del_behavior, 
                                    min_support=0.1,
                                    min_length=3, 
                                    max_length=7, 
                                    sep='@') 
# 运行模型,返回pattern结果和使用的行为列表
sequence, seq_use_behavior = behavior.run() 
# 筛选lift符合要求的pattern
sequence_result = sequence[sequence['lift'] > 6] 

依赖

BehaviorPattern依赖以下Python库:

  • numpy
  • pandas
  • efficient_apriori
  • tqdm
  • prefixspan

完整的依赖列表可以在setup.py中找到。

贡献

如果你发现任何bugs,请提交Issue或Pull Request进行更正

作者

BehaviorPattern由Chen Chen编写和维护。

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

BehaviorPattern-0.0.8.tar.gz (4.8 kB view details)

Uploaded Source

File details

Details for the file BehaviorPattern-0.0.8.tar.gz.

File metadata

  • Download URL: BehaviorPattern-0.0.8.tar.gz
  • Upload date:
  • Size: 4.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.2 CPython/3.7.9

File hashes

Hashes for BehaviorPattern-0.0.8.tar.gz
Algorithm Hash digest
SHA256 9091330b22c3b3366a736df2a16c761b8af4be5fcf35095b7aba04296c58dd4d
MD5 c95d2636e494e1a002b22ba533ccea64
BLAKE2b-256 62352b91dbcd8fbfe711ffdd7812986e24211429ba855d272f2fcbf23cef33a1

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page