Library that is intended to operate with various process mining tasks.
Project description
Documentation | Installation | Quick start
SberProcessMining (SberPM) – Process Mining Python framework
SberPM is an open-source Python library for conducting a comprehensive analysis of business processes with the use of process mining and machine learning techniques. By implementing this tool, objective and deep insights into the process on all levels can be revealed. These insights are then used to detect problems such as bottlenecks and deviations and identify potential opportunities for process improvement and optimization.
Authors: Sber Process Mining Team.
Installation
To install SberPM framework on your machine from PyPI:
pip install sberpm
To install from sources:
git clone https://github.com/SberProcessMining/Sber_Process_Mining.git
cd Sber_Process_Mining
pip install .
Additionally, you have to install graphviz executables and add the path to the executables to PATH variable:
https://graphviz.org/download/
Quick start
There are some steps for quick start for your process log analysis:
- Create a DataHolder object:
from sberpm import SuccessInputs, DurationUnits
path = "example_data.xlsx"
data_holder = DataHolder(
data=path,
col_case="id",
col_stage="action",
col_start_time="start_time",
col_end_time="end_time",
col_user="user_id",
col_text="text",
success_inputs=SuccessInputs(entries={"Подписание документов ", "Принято"}),
)
data_holder.data.head()
- Apply AutoInsights:
from sberpm.autoinsights import AutoInsights
auto_insights = AutoInsights(data_holder, successful_stage="Принято")
auto_insights.apply()
License
This project is released under the MIT License.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
File details
Details for the file sberpm-3.4.0.tar.gz
.
File metadata
- Download URL: sberpm-3.4.0.tar.gz
- Upload date:
- Size: 163.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.0.1 CPython/3.12.2
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 |
9344c7c59bf1682f04df30b50757a3cf812b1691276e710b7000095d66fc41a6
|
|
MD5 |
5377712aca1524e878faf4326bae6e27
|
|
BLAKE2b-256 |
ca5021e33aa1bc5ff3d5114da573e2a91854eb46e601e8b5c044cd1624f94f47
|