{"id":"W4311557029","doi":"10.1371/journal.pcbi.1010718","title":"Eleven quick tips for data cleaning and feature engineering","year":2022,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Feature engineering; Computer science; Feature (linguistics); Data science; Field (mathematics); Component (thermodynamics); Informatics; Preprocessor; Data pre-processing; Data mining; Key (lock); Health informatics; Artificial intelligence; Machine learning; Engineering; Health care; Deep learning","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000283715,0.00009007188,0.0001189912,0.00009261517,0.0002761034,0.00004988659,0.0008644774,0.00003333791,0.00001252753],"category_scores_gemma":[0.00014642,0.00009734825,0.00001863298,0.0001925686,0.00002653305,0.0002173479,0.001063608,0.0001469436,0.000008142855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003822492,"about_ca_system_score_gemma":0.00006171525,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001000005,"about_ca_topic_score_gemma":0.000002925836,"domain_scores_codex":[0.9990373,0.0000558639,0.0001449802,0.0004278854,0.0001102454,0.0002237696],"domain_scores_gemma":[0.9989551,0.000592796,0.00005869678,0.0002834326,0.00006348417,0.00004650069],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003063375,0.0001067945,0.001040734,0.00003960505,0.00009031603,0.00001191518,0.0008494047,0.1357107,0.004531209,0.8248044,0.005912159,0.02687212],"study_design_scores_gemma":[0.00008539841,0.0001238174,0.0001872638,0.000002999438,0.000003740805,0.00003297026,0.00004720028,0.9548575,0.0002467565,0.02721547,0.01708088,0.0001159804],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02266412,0.0002286187,0.97299,0.003365321,0.0002635382,0.0002281891,0.00007680138,0.000129581,0.00005377746],"genre_scores_gemma":[0.7478039,0.000003088984,0.2510143,0.0006371521,0.0001035684,0.00005893689,0.0003187418,0.00001128242,0.00004905436],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8191469,"threshold_uncertainty_score":0.3969746,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06451839150280238,"score_gpt":0.2890776891224214,"score_spread":0.2245592976196191,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}