The paper introduces the powerlaw Python package, designed to facilitate the analysis of heavy-tailed distributions. Power laws are theoretically interesting probability distributions characterized by a "heavy-tail" behavior, where the tails of the distribution contain a significant portion of the probability. Accurate fitting and goodness-of-fit testing for power laws are non-trivial tasks, especially when dealing with empirical data from specific domains. The powerlaw package aims to address these challenges by providing an easy-to-use interface for fitting and analyzing various probability distributions, including power laws. Key features of the powerlaw package include: - **Ease of Use**: The package simplifies the process of fitting and analyzing distributions with minimal programming and statistical expertise. - **Comprehensive Support**: It supports a wide range of probability distributions and subtypes, making it versatile for different applications. - **Extensibility**: The source code is publicly available and easily extensible, allowing users to add new distributions and functionalities. - **Visualization**: It provides tools for plotting probability density functions (PDFs), cumulative distribution functions (CDFs), and complementary cumulative distribution functions (CCDFs) on both linear and logarithmic scales. - **Fitting Methods**: The package includes methods for identifying the optimal scaling range ($x_{min}$) and comparing the goodness of fit between different distributions using statistical tests like the Kolmogorov-Smirnov test and loglikelihood ratios. The authors also discuss the importance of considering domain-specific generative mechanisms when selecting candidate distributions and provide examples of using the package to fit power laws to real-world datasets, such as word frequencies and neuron connections. The package is available on the Python Package Index (PyPI) and can be installed using pip. The source code is maintained on GitHub and Google Code, and the authors encourage contributions from the community. Overall, the powerlaw package is a valuable tool for researchers and practitioners working with heavy-tailed data, offering a user-friendly and flexible approach to fitting and analyzing such distributions.The paper introduces the powerlaw Python package, designed to facilitate the analysis of heavy-tailed distributions. Power laws are theoretically interesting probability distributions characterized by a "heavy-tail" behavior, where the tails of the distribution contain a significant portion of the probability. Accurate fitting and goodness-of-fit testing for power laws are non-trivial tasks, especially when dealing with empirical data from specific domains. The powerlaw package aims to address these challenges by providing an easy-to-use interface for fitting and analyzing various probability distributions, including power laws. Key features of the powerlaw package include: - **Ease of Use**: The package simplifies the process of fitting and analyzing distributions with minimal programming and statistical expertise. - **Comprehensive Support**: It supports a wide range of probability distributions and subtypes, making it versatile for different applications. - **Extensibility**: The source code is publicly available and easily extensible, allowing users to add new distributions and functionalities. - **Visualization**: It provides tools for plotting probability density functions (PDFs), cumulative distribution functions (CDFs), and complementary cumulative distribution functions (CCDFs) on both linear and logarithmic scales. - **Fitting Methods**: The package includes methods for identifying the optimal scaling range ($x_{min}$) and comparing the goodness of fit between different distributions using statistical tests like the Kolmogorov-Smirnov test and loglikelihood ratios. The authors also discuss the importance of considering domain-specific generative mechanisms when selecting candidate distributions and provide examples of using the package to fit power laws to real-world datasets, such as word frequencies and neuron connections. The package is available on the Python Package Index (PyPI) and can be installed using pip. The source code is maintained on GitHub and Google Code, and the authors encourage contributions from the community. Overall, the powerlaw package is a valuable tool for researchers and practitioners working with heavy-tailed data, offering a user-friendly and flexible approach to fitting and analyzing such distributions.