{"library":"scoringrules","title":"Scoring Rules","description":"Scoringrules is a Python library for evaluating probabilistic forecasts using various scoring rules. It provides implementations of Continuous Ranked Probability Score (CRPS), Log Score, Brier Score, Dawid-Sebastiani Score, and more for various distributions and ensembles. The current version is 0.9.0, and the library maintains an active development pace with frequent minor releases and occasional breaking changes.","language":"python","status":"active","last_verified":"Fri Apr 17","install":{"commands":["pip install scoringrules","pip install scoringrules[torch]","pip install scoringrules[jax]"],"cli":null},"imports":["import scoringrules as sr","import scoringrules.crps as sr_crps","sr.crps.gaussian(observations, mean, std)"],"auth":{"required":false,"env_vars":[]},"quickstart":{"code":"import numpy as np\nimport scoringrules as sr\n\n# Generate some synthetic data\nforecast_mean = np.array([0.1, 0.2, 0.3, 0.4])\nforecast_std = np.array([0.5, 0.5, 0.5, 0.5])\nobservations = np.array([0.1, 0.1, 0.3, 0.5])\n\n# Calculate CRPS for a Gaussian distribution\n# Observations must be the first argument since v0.5.0\ncrps_scores = sr.crps.gaussian(observations, forecast_mean, forecast_std)\nprint(f\"CRPS scores: {crps_scores}\")\nprint(f\"Mean CRPS: {np.mean(crps_scores)}\")\n","lang":"python","description":"This quickstart calculates the Continuous Ranked Probability Score (CRPS) for a set of Gaussian probabilistic forecasts against corresponding observations. It demonstrates the basic usage pattern with `numpy` arrays and the `crps.gaussian` function, highlighting the argument order requirement.","tag":null,"tag_description":null,"last_tested":null,"results":[]},"compatibility":null}