Over the last few years, with the growth of time-series collecting and storing, there has been a great demand for tools and software for temporal data engineering and modeling. This paper presents a generic workflow for time series data research, including temporal data importing, preprocessing, and feature extraction. This framework is developed and built as a robust and easy-to-use Python package, called CMDA, with a modular structure that offers tools to prepare raw data, allowing both scientists and non-experts to analyze various temporal data structures.

翻译：近年来，随着时序数据采集与存储规模的增长，对时间数据工程与建模工具及软件的需求日益迫切。本文提出一种通用的时序数据研究流程，涵盖时间数据导入、预处理及特征提取等环节。该框架以名为CMDA的模块化Python工具包形式开发构建，具备稳健易用的特性，通过提供原始数据准备工具，使科研人员与非专业用户均可分析多种时间数据结构。