Example: Metabolomics Regression 20260106_075713Completed

CLI Command (Copy-Paste Ready)

OMP_NUM_THREADS=1 OPENBLAS_NUM_THREADS=1 MKL_NUM_THREADS=1 VECLIB_MAXIMUM_THREADS=1 NUMEXPR_NUM_THREADS=1 /opt/ml-env/bin/python /app/scripts/ml_pipeline.py --config /app/public/ml_results/81/job_config.json

{"job_id": 81, "algorithm": "random_forest_regressor", "n_folds": 5, "holdout_used": false, "per_fold_results": [{"fold": 1, "metrics": {"r2": 0.8045535748015469, "mse": 62.75803816788853, "mae": 6.491798875000001, "rmse": 7.921997107288574, "pearson": 0.9238652862730028, "spearman": 0.9078799249530958}, "selected_features": ["metabolite_1", "metabolite_2", "metabolite_3", "metabolite_4", "metabolite_10", "metabolite_12", "metabolite_27", "metabolite_30", "metabolite_41", "metabolite_49"], "feature_importance": {"metabolite_1": 0.44552477472258983, "metabolite_2": 0.12801346336073335, "metabolite_3": 0.07373078484329189, "metabolite_4": 0.27968481279158075, "metabolite_10": 0.01095033881983243, "metabolite_12": 0.01546163173788892, "metabolite_27": 0.010720637404246391, "metabolite_30": 0.011700567915695305, "metabolite_41": 0.01483581380974126, "metabolite_49": 0.009377174594399858}, "model_file": "model_fold_1.joblib", "y_true": [90.0, 54.48, 60.74, 49.41, 39.71, 55.14, 18.0, 51.75, 45.85, 85.76, 29.99, 50.3, 72.17, 49.68, 53.21, 40.07, 35.52, 61.79, 71.96, 25.32, 66.52, 22.8, 53.38, 66.8, 29.49, 66.58, 43.39, 66.92, 38.33, 84.77, 33.38, 61.14, 29.76, 34.84, 78.3, 25.28, 53.51, 56.41, 56.27, 60.49], "y_pred": [71.9161, 52.153999999999996, 65.95526500000001, 50.685566666666645, 49.399799999999985, 58.299553333333336, 28.168600000000005, 54.73855, 42.4929, 78.11233333333335, 37.66453333333333, 52.029799999999994, 65.91299999999998, 62.35049999999998, 43.64539523809523, 43.330200000000005, 38.03312857142858, 56.19878833333335, 64.87224999999998, 32.077000000000005, 61.02114999999999, 36.339200000000005, 55.27078999999999, 70.49520000000003, 47.25229999999998, 70.44279999999999, 45.66130000000002, 51.62059999999999, 42.93613333333334, 80.66410000000003, 35.59180000000001, 59.867025000000005, 39.747466666666675, 45.757000000000005, 69.29889, 36.53122857142857, 50.0826, 53.224711904761904, 55.90781666666666, 51.984100000000005], "y_proba": null}, {"fold": 2, "metrics": {"r2": 0.8149218187203462, "mse": 64.66197848005262, "mae": 6.479434769607847, "rmse": 8.041267218545384, "pearson": 0.9044558741526231, "spearman": 0.8815610497994972}, "selected_features": ["metabolite_1", "metabolite_2", "metabolite_3", "metabolite_4", "metabolite_5", "metabolite_10", "metabolite_27", "metabolite_30", "metabolite_41", "metabolite_49"], "feature_importance": {"metabolite_1": 0.40996575260012763, "metabolite_2": 0.10235170676076008, "metabolite_3": 0.06219214653202463, "metabolite_4": 0.330358036514548, "metabolite_5": 0.020260992916529812, "metabolite_10": 0.014322231562997435, "metabolite_27": 0.01490715816895409, "metabolite_30": 0.018706305145131708, "metabolite_41": 0.013307221425805068, "metabolite_49": 0.013628448373121695}, "model_file": "model_fold_2.joblib", "y_true": [47.85, 43.34, 35.65, 42.88, 41.05, 38.85, 35.7, 18.0, 59.36, 50.23, 72.28, 58.18, 18.0, 90.0, 45.6, 28.23, 72.13, 55.1, 60.11, 75.48, 69.98, 40.5, 40.03, 49.91, 55.08, 37.71, 55.55, 79.19, 26.22, 37.88, 61.39, 77.2, 74.56, 89.84, 36.27, 79.4, 36.86, 63.71, 46.11, 76.94], "y_pred": [56.07235000000001, 44.47380000000001, 47.21373761904763, 34.68302, 34.836347619047615, 34.2756142857143, 45.23952499999999, 21.284560000000003, 60.560888725490194, 57.934185714285704, 71.6707, 53.5264, 21.85366, 81.30360000000002, 39.3529, 33.848040000000005, 63.095149999999975, 59.0433857142857, 65.05467324929974, 66.85299999999998, 68.4808, 37.3717142857143, 35.38000000000002, 42.12631428571429, 42.384834285714284, 34.842299999999994, 55.769000000000005, 80.08132500000004, 29.220893333333336, 50.58022857142859, 43.86006666666666, 80.31640000000004, 66.41099999999999, 66.45084999999999, 40.45311428571429, 71.47180000000002, 50.34259999999999, 62.63519999999998, 53.62923499999998, 82.44740000000003], "y_proba": null}, {"fold": 3, "metrics": {"r2": 0.8287649013206875, "mse": 59.35302050360908, "mae": 6.426762683150185, "rmse": 7.704091153640972, "pearson": 0.9323483437981545, "spearman": 0.9308128909344059}, "selected_features": ["metabolite_1", "metabolite_2", "metabolite_3", "metabolite_4", "metabolite_10", "metabolite_21", "metabolite_27", "metabolite_35", "metabolite_41", "metabolite_49"], "feature_importance": {"metabolite_1": 0.4602219291456864, "metabolite_2": 0.13051063115380945, "metabolite_3": 0.051821966741101615, "metabolite_4": 0.2864886290134496, "metabolite_10": 0.008442327882583062, "metabolite_21": 0.014273912809667633, "metabolite_27": 0.012690936805220978, "metabolite_35": 0.012556755449248157, "metabolite_41": 0.013994256721074447, "metabolite_49": 0.008998654278158694}, "model_file": "model_fold_3.joblib", "y_true": [68.08, 74.37, 67.97, 71.0, 77.74, 47.87, 34.11, 48.82, 18.0, 64.68, 29.21, 61.04, 58.96, 52.17, 62.39, 61.45, 25.99, 59.39, 32.42, 88.42, 66.13, 44.18, 59.06, 31.57, 55.9, 66.42, 41.74, 33.37, 18.0, 37.11, 48.23, 39.53, 37.96, 83.56, 18.39, 44.69, 79.36, 44.6, 23.72, 47.47], "y_pred": [66.50438000000001, 65.5074, 54.81097142857143, 66.8901, 60.98066666666666, 53.32114285714285, 37.23518666666667, 45.51105000000001, 31.142266666666686, 62.47786666666665, 36.80506666666667, 52.7171880952381, 51.18813333333333, 56.70489285714285, 55.19839428571427, 66.48645000000002, 27.682386666666666, 57.83913333333332, 31.568693040293034, 83.66720000000001, 60.27440000000001, 50.132142857142846, 49.6766, 43.50410256410257, 59.52040000000001, 61.71219999999998, 53.40033333333333, 46.16446666666667, 23.7142, 43.06094666666669, 51.01480000000001, 40.9092, 41.82273333333333, 67.30815333333335, 30.990746666666674, 47.83025714285714, 79.0718, 41.06660000000001, 30.928582564102577, 54.92113333333334], "y_proba": null}, {"fold": 4, "metrics": {"r2": 0.8541710410952168, "mse": 65.72891612780843, "mae": 6.305607291666663, "rmse": 8.107337178618417, "pearson": 0.9272679146738869, "spearman": 0.9122807057692014}, "selected_features": ["metabolite_1", "metabolite_2", "metabolite_3", "metabolite_4", "metabolite_5", "metabolite_9", "metabolite_26", "metabolite_27", "metabolite_41", "metabolite_49"], "feature_importance": {"metabolite_1": 0.4220710098522647, "metabolite_2": 0.1602716019495984, "metabolite_3": 0.06734011504463791, "metabolite_4": 0.2548320793233128, "metabolite_5": 0.022689103331683204, "metabolite_9": 0.011516705322121481, "metabolite_26": 0.01749196510262308, "metabolite_27": 0.014172787804444895, "metabolite_41": 0.014417132308425416, "metabolite_49": 0.015197499960888095}, "model_file": "model_fold_4.joblib", "y_true": [79.32, 33.35, 40.91, 79.94, 52.43, 59.77, 32.63, 18.0, 81.56, 46.5, 74.33, 61.03, 84.53, 75.23, 18.0, 63.38, 76.4, 65.27, 46.56, 60.97, 56.03, 72.35, 21.59, 49.34, 64.36, 23.43, 45.44, 25.78, 48.77, 90.0, 83.55, 19.11, 53.0, 25.3, 63.39, 47.87, 61.58, 57.02, 90.0, 31.44], "y_pred": [76.07180000000005, 29.20068, 52.587266666666686, 73.64158571428572, 56.388000000000005, 58.653800000000004, 30.715673333333328, 24.0906, 66.9192, 61.068133333333314, 52.103913333333324, 60.52510000000004, 72.85874571428575, 74.35280000000003, 22.10777142857143, 68.88720666666666, 81.52060000000002, 65.51259999999999, 42.044900000000005, 46.06149999999999, 48.47321928571428, 71.07821428571428, 27.538, 38.32442, 67.13220000000001, 33.564650000000015, 51.07816, 26.101399999999998, 55.50936000000001, 74.4713457142857, 79.00920000000002, 29.139699999999998, 53.447179047619045, 24.866871428571425, 67.34936666666664, 52.44146666666666, 65.88749999999997, 66.21099999999998, 80.6776, 30.28729999999999], "y_proba": null}, {"fold": 5, "metrics": {"r2": 0.8307170644828452, "mse": 63.442483826399936, "mae": 6.786242291666667, "rmse": 7.965079021980883, "pearson": 0.9359790708650979, "spearman": 0.9140042475256864}, "selected_features": ["metabolite_1", "metabolite_2", "metabolite_3", "metabolite_4", "metabolite_10", "metabolite_13", "metabolite_27", "metabolite_32", "metabolite_41", "metabolite_49"], "feature_importance": {"metabolite_1": 0.47104785500742974, "metabolite_2": 0.1074221537726254, "metabolite_3": 0.08821808698332571, "metabolite_4": 0.2605905530735404, "metabolite_10": 0.012781961128173279, "metabolite_13": 0.011368905436013989, "metabolite_27": 0.013694721098805852, "metabolite_32": 0.0114225933644394, "metabolite_41": 0.010960099837303755, "metabolite_49": 0.012493070298342597}, "model_file": "model_fold_5.joblib", "y_true": [75.1, 20.84, 50.83, 68.44, 45.8, 48.5, 34.39, 18.0, 18.0, 34.98, 63.11, 90.0, 18.0, 70.91, 70.18, 40.38, 55.78, 61.49, 72.97, 40.05, 40.78, 90.0, 66.89, 27.73, 26.5, 57.74, 69.64, 64.79, 66.76, 77.16, 69.51, 43.66, 71.8, 32.72, 62.26, 49.52, 34.75, 52.38, 62.45, 55.37], "y_pred": [61.535599999999995, 35.8002, 47.67829166666667, 56.54773333333333, 44.547799999999995, 58.038625, 37.23480666666667, 26.51876666666666, 23.293200000000002, 40.9108, 63.772000000000006, 84.73900000000003, 28.121599999999997, 60.51406666666666, 62.4612, 47.13580833333332, 61.259399999999985, 61.1782, 64.72246666666666, 45.5422, 33.10979999999999, 82.95740000000004, 60.21072000000001, 45.5354, 35.017933333333325, 48.88806666666665, 67.04791999999999, 55.23052000000001, 58.5975, 71.39199999999997, 67.83068666666667, 42.77380000000001, 60.84259999999999, 38.910000000000004, 61.31419999999999, 42.062520000000006, 48.640750000000004, 50.329919999999994, 60.81398666666666, 49.65579999999997], "y_proba": null}], "aggregated_metrics": {"r2": {"mean": 0.8266256800841287, "std": 0.016758405708516517, "min": 0.8045535748015469, "max": 0.8541710410952168}, "mse": {"mean": 63.18888742115172, "std": 2.1718913565528224, "min": 59.35302050360908, "max": 65.72891612780843}, "mae": {"mean": 6.497969182218273, "std": 0.15846541907883288, "min": 6.305607291666663, "max": 6.786242291666667}, "rmse": {"mean": 7.9479543360148455, "std": 0.13751106782557504, "min": 7.704091153640972, "max": 8.107337178618417}, "pearson": {"mean": 0.924783297952553, "std": 0.010979940562616962, "min": 0.9044558741526231, "max": 0.9359790708650979}, "spearman": {"mean": 0.9093077637963773, "std": 0.01590776350090271, "min": 0.8815610497994972, "max": 0.9308128909344059}}, "aggregated_feature_importance": {"metabolite_1": {"mean": 0.44176626426561966, "std": 0.022853118439220554}, "metabolite_2": {"mean": 0.12571391139950533, "std": 0.020508102976349824}, "metabolite_3": {"mean": 0.06866062002887635, "std": 0.012127045907874471}, "metabolite_4": {"mean": 0.2823908221432863, "std": 0.026682219546454562}, "metabolite_10": {"mean": 0.011624214848396552, "std": 0.002190786628456188}, "metabolite_12": {"mean": 0.01546163173788892, "std": 0.0}, "metabolite_27": {"mean": 0.013237248256334443, "std": 0.001449475846394688}, "metabolite_30": {"mean": 0.015203436530413506, "std": 0.003502868614718202}, "metabolite_41": {"mean": 0.01350290482046999, "std": 0.0013680668212484128}, "metabolite_49": {"mean": 0.011938969500982187, "std": 0.0024078053934707662}, "metabolite_5": {"mean": 0.021475048124106506, "std": 0.0012140552075766958}, "metabolite_21": {"mean": 0.014273912809667633, "std": 0.0}, "metabolite_35": {"mean": 0.012556755449248157, "std": 0.0}, "metabolite_9": {"mean": 0.011516705322121481, "std": 0.0}, "metabolite_26": {"mean": 0.01749196510262308, "std": 0.0}, "metabolite_13": {"mean": 0.011368905436013989, "std": 0.0}, "metabolite_32": {"mean": 0.0114225933644394, "std": 0.0}}, "feature_selection_stats": [{"feature": "metabolite_4", "count": 5, "frequency": 1.0}, {"feature": "metabolite_41", "count": 5, "frequency": 1.0}, {"feature": "metabolite_2", "count": 5, "frequency": 1.0}, {"feature": "metabolite_49", "count": 5, "frequency": 1.0}, {"feature": "metabolite_1", "count": 5, "frequency": 1.0}, {"feature": "metabolite_27", "count": 5, "frequency": 1.0}, {"feature": "metabolite_3", "count": 5, "frequency": 1.0}, {"feature": "metabolite_10", "count": 4, "frequency": 0.8}, {"feature": "metabolite_5", "count": 2, "frequency": 0.4}, {"feature": "metabolite_30", "count": 2, "frequency": 0.4}, {"feature": "metabolite_13", "count": 1, "frequency": 0.2}, {"feature": "metabolite_9", "count": 1, "frequency": 0.2}, {"feature": "metabolite_12", "count": 1, "frequency": 0.2}, {"feature": "metabolite_26", "count": 1, "frequency": 0.2}, {"feature": "metabolite_32", "count": 1, "frequency": 0.2}, {"feature": "metabolite_35", "count": 1, "frequency": 0.2}, {"feature": "metabolite_21", "count": 1, "frequency": 0.2}], "feature_importance": {"metabolite_1": {"mean": 0.44176626426561966, "std": 0.022853118439220554}, "metabolite_2": {"mean": 0.12571391139950533, "std": 0.020508102976349824}, "metabolite_3": {"mean": 0.06866062002887635, "std": 0.012127045907874471}, "metabolite_4": {"mean": 0.2823908221432863, "std": 0.026682219546454562}, "metabolite_10": {"mean": 0.011624214848396552, "std": 0.002190786628456188}, "metabolite_12": {"mean": 0.01546163173788892, "std": 0.0}, "metabolite_27": {"mean": 0.013237248256334443, "std": 0.001449475846394688}, "metabolite_30": {"mean": 0.015203436530413506, "std": 0.003502868614718202}, "metabolite_41": {"mean": 0.01350290482046999, "std": 0.0013680668212484128}, "metabolite_49": {"mean": 0.011938969500982187, "std": 0.0024078053934707662}, "metabolite_5": {"mean": 0.021475048124106506, "std": 0.0012140552075766958}, "metabolite_21": {"mean": 0.014273912809667633, "std": 0.0}, "metabolite_35": {"mean": 0.012556755449248157, "std": 0.0}, "metabolite_9": {"mean": 0.011516705322121481, "std": 0.0}, "metabolite_26": {"mean": 0.01749196510262308, "std": 0.0}, "metabolite_13": {"mean": 0.011368905436013989, "std": 0.0}, "metabolite_32": {"mean": 0.0114225933644394, "std": 0.0}}, "charts": {"feature_importance": "feature_selection_frequency.png", "scatter_plot": "prediction_scatter.png"}, "reports": ["report_81.md"]}

Starting pipeline execution for Job: 81
Loaded data: (200, 50) features, (200,) targets.
Running nested cross-validation...
Generating visualizations...
Generating reports...
Warning: weasyprint not installed. PDF report skipped.
Warning: python-docx not installed. DOCX report skipped.
Warning: excel writer dependency missing. Excel report skipped.
Analysis complete. Results saved to /app/public/ml_results/81