{"library":"pydlm","title":"PyDLM","description":"A Python library for Bayesian dynamic linear models (DLMs) for time series analysis. Current version 0.1.1.13, released 2024-07. Supports modeling, filtering, smoothing, and forecasting. Low release cadence, maintenance mode.","language":"python","status":"maintenance","last_verified":"Fri May 01","install":{"commands":["pip install pydlm"],"cli":null},"imports":["from pydlm import dlm","from pydlm import dlm"],"auth":{"required":false,"env_vars":[]},"quickstart":{"code":"from pydlm import dlm\nimport numpy as np\n\n# Generate sample time series\ndata = [2.0, 2.5, 3.0, 3.5, 4.0]\n\n# Create DLM with polynomial trend of order 1 and seasonal component 4\nmy_dlm = dlm(data) + dlm.trend(1) + dlm.seasonal(4)\n\n# Fit the model\nmy_dlm.fit()\n\n# One-step ahead predictions\npredictions = my_dlm.predictN(N=1)\nprint(predictions)\n\n# Access filtered states\nfiltered_states = my_dlm.getFilteredObs()\nprint(filtered_states)","lang":"python","description":"Basic usage: create a DLM, add components, fit, and forecast.","tag":null,"tag_description":null,"last_tested":null,"results":[]},"compatibility":null}