{"library":"opendsm","title":"OpenDSM","description":"OpenDSM provides standard methods for predicting building energy usage, supporting hourly, daily, and billing models with clustering and baseline metrics. Current version 1.2.7, requires Python >=3.10, and is actively maintained on GitHub.","language":"python","status":"active","last_verified":"Fri May 01","install":{"commands":["pip install opendsm"],"cli":null},"imports":["from opendsm import OpenDSM","from opendsm.hourly import HourlyModel","from opendsm.daily import DailyModel","from opendsm.billing import BillingModel","from opendsm.metrics import BaselineMetrics"],"auth":{"required":false,"env_vars":[]},"quickstart":{"code":"from opendsm import OpenDSM\nfrom opendsm.hourly import HourlyModel\nimport pandas as pd\n\n# Create sample hourly energy usage data\nimport numpy as np\ndates = pd.date_range('2023-01-01', periods=8760, freq='H')\nenergy = np.random.rand(8760) * 100\ntemp = np.random.rand(8760) * 35\ndf = pd.DataFrame({'energy': energy, 'temperature': temp}, index=dates)\n\n# Initialize OpenDSM with a project name\nproject = OpenDSM('my_project')\n\n# Add data\nproject.add_data(df, energy_column='energy', temperature_column='temperature')\n\n# Run hourly model\nmodel = HourlyModel(project)\nmodel.fit()\nprint(model.results())","lang":"python","description":"Quickstart example loading hourly data and fitting an hourly model.","tag":null,"tag_description":null,"last_tested":null,"results":[]},"compatibility":null}