What it is:
A new library to analyze time series data. Kats is a lightweight, easy-to-use, and generalizable framework for generic time series analysis, including forecasting, anomaly detection, multivariate analysis, and feature extraction/embedding. To the best of our knowledge, Kats is the first comprehensive Python library for generic time series analysis, which provides both classical and advanced techniques to model time series data.
What it does:
Kats provides a set of algorithms and models for four domains in time series analysis: forecasting, detection, feature extraction and embedding, and multivariate analysis.
Forecasting: Kats provides a full set of tools for forecasting that includes 10+ individual forecasting models, ensembling, a self-supervised learning (meta-learning) model, backtesting, hyperparameter tuning, and empirical prediction intervals.
Detection: Kats supports functionalities to detect various patterns on time series data, including seasonalities, outlier, change point, and slow trend changes.
Feature extraction and embedding: The time series feature (TSFeature) extraction module in Kats can produce 65 features with clear statistical definitions, which can be incorporated in most machine learning (ML) models, such as classification and regression.
Useful utilities: Kats also provides a set of useful utilities, such as time series simulators.
Why it matters:
Time series analysis is a fundamental domain in data science and machine learning, with massive applications in various sectors such as e-commerce, finance, capacity planning, supply chain management, medicine, weather, energy, astronomy, and many others. Kats is the first comprehensive Python library to develop the standards and connect various domains in time series analysis, where the users can explore the basic characteristics of their time series data, predict the future values, monitor the anomalies, and incorporate them into their ML models and pipelines.
Get it on GitHub:
The post Meet Kats — a one-stop shop for time series analysis appeared first on Facebook Engineering.