{ "model_name": "Simple Linear Regression", "model_key": "linear-regression", "model_type": "tabular_regression", "task": "regression", "framework": "scikit-learn", "reusable": true, "generic_implementation": "regression_model.py (GenericRegressionModel class / train_and_predict function)", "development_dataset": { "note": "Used only to develop/test this notebook -- the implementation is not restricted to it.", "path": "Tetuan City power consumption.csv", "target_column": "Zone 3 Power Consumption", "feature_columns": [ "Zone 1 Power Consumption" ], "train_size": 41932, "test_size": 10484, "training_time_seconds": 0.5309064388275146, "metrics": { "MAE": 3416.8772067095542, "MSE": 19319221.150540683, "RMSE": 4395.363597080529, "MedianAbsoluteError": 2689.506229219387, "MaxError": 18730.459806942526, "R2": 0.5569445648951383, "ExplainedVariance": 0.5569687568505464, "MAPE": 20.73611924251748, "MSLE": 0.06045518318412465, "RMSLE": 0.24587635751353698, "AdjustedR2": 0.556902296679616, "PearsonCorrelation": 0.7463196192706589, "SpearmanCorrelation": 0.7468353620156126 }, "statistical_summary": { "status": "applicable", "r_squared": 0.5652388836693387, "adjusted_r_squared": 0.5652285149329607, "f_statistic": 54513.76745069764, "f_test_p_value": 0.0, "coefficients": { "const": 17819.88174259713, "numeric__Zone 1 Power Consumption": 4982.099348300972 }, "t_statistics": { "const": 835.1135544636528, "numeric__Zone 1 Power Consumption": 233.4818353763258 }, "coefficient_p_values": { "const": 0.0, "numeric__Zone 1 Power Consumption": 0.0 }, "standard_errors": { "const": 21.338273875870513, "numeric__Zone 1 Power Consumption": 21.3382738758706 }, "confidence_intervals_95pct": { "const": [ 17778.0582870196, 17861.705198174655 ], "numeric__Zone 1 Power Consumption": [ 4940.275892723447, 5023.922803878498 ] } }, "residual_stats": { "mean_residual": 32.4788960576042, "median_residual": -287.10861204463254, "residual_std": 4395.243596417788, "min_residual": -11318.14280759007, "max_residual": 18730.459806942526 } }, "generic_dataset_validation": { "dataset": "synthetic (sklearn.datasets.make_regression, NOT uploaded to Hugging Face)", "passed": true, "metrics": { "MAE": 84.79215199992855, "MSE": 12009.073119832949, "RMSE": 109.58591661264211, "MedianAbsoluteError": 65.42436290659386, "MaxError": 313.83646524645, "R2": -0.00988629766069793, "ExplainedVariance": 0.019460440641405286, "MAPE": 2136.3863396657975, "MSLE": "Not Applicable", "RMSLE": "Not Applicable", "AdjustedR2": -0.020191259881725543, "PearsonCorrelation": 0.1540043608255103, "SpearmanCorrelation": 0.13508550855085505, "_notes": { "MSLE": "Negative values present in y_true or y_pred.", "RMSLE": "Negative values present in y_true or y_pred." } } }, "hyperparameters": { "copy_X": true, "fit_intercept": true, "n_jobs": null, "positive": false }, "python_version": "3.12.2 (tags/v3.12.2:6abddd9, Feb 6 2024, 21:26:36) [MSC v.1937 64 bit (AMD64)]", "library_versions": { "scikit-learn": "1.6.1", "pandas": "2.2.3", "numpy": "2.1.3" } }