{"categories":[{"label":"Scientific/Engineering","url":"https://skillfed.io/packages/category/scientific-engineering/3"}],"enrichment":{"capability":"Implements a suite of Mann-Kendall trend tests and Sen's slope estimators for analyzing monotonic trends in time series data, including variants for seasonal, regional, and autocorrelated data.","skillfed_tags":["time-series-analysis","statistical-testing","environmental-data"],"use_cases":["Detect long-term increasing or decreasing trends in climate or environmental monitoring data with seasonal adjustments","Analyze regional hydrological trends across multiple monitoring stations using regional MK test","Estimate trend magnitude and confidence intervals in water quality or air pollution time series","Test for trends in autocorrelated economic or financial time series using variance-corrected variants","Identify monotonic patterns in multi-parameter datasets where parameters are correlated with each other"],"what_it_does":"pyMannKendall is a pure Python implementation of the Mann-Kendall family of non-parametric trend tests, designed for analyzing time series data without assuming normal distribution. It provides 11 variants of the Mann-Kendall test (original, Hamed-Rao, Yue-Wang, pre-whitening, multivariate, seasonal, regional, correlated multivariate, correlated seasonal, and partial) plus two Sen's slope estimators for quantifying trend magnitude. The package depends on numpy and scipy for numerical computation.\n\nThe tests return structured results including trend direction, p-value, test statistics, Kendall's Tau, and slope estimates. It is particularly useful when time series data violates normality assumptions or contains serial correlation, seasonal patterns, or spatial structure. Each test accepts a data vector and optional parameters like significance level and seasonal period, making it flexible for different analytical scenarios.","worth_installing":"Yes, if you need robust non-parametric trend analysis for time series data. Install friction is minimal and the package is stable and well-established. However, note that the last release was in January 2023; verify that it supports your target Python version and that no critical bugs have emerged in your use case before production deployment."},"id":"pymannkendall","links":{"html":"https://skillfed.io/packages/pymannkendall","md":"https://skillfed.io/packages/pymannkendall.md","pypi":"https://pypi.org/project/pymannkendall/"},"maintenance":{"status":"aging"},"meta":{"latest_release":"2023-01-14","license_spdx":null,"license_treatment":"permissive","name":"pymannkendall","python_support":"unspecified","summary":"A python package for non-parametric Mann-Kendall family of trend tests."},"popularity":{"monthly_downloads":633123,"position":5648,"tier":"top_15000"},"security":{"n_vulnerabilities":0},"version":"1.4.3"}