{"id":"W3143356065","doi":"10.1145/3448016.3457330","title":"DataPrep.EDA: Task-Centric Exploratory Data Analysis for Statistical Modeling in Python","year":2021,"lang":"en","type":"article","venue":"","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Mitacs; National Science Foundation","keywords":"Python (programming language); Granularity; Exploratory data analysis; Statistical model; Data modeling; Data structure; Data exploration","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004290423,0.00008988411,0.0001984428,0.0002180855,0.00005674191,0.000272604,0.001071109,0.0000329995,0.0000539015],"category_scores_gemma":[0.0003108363,0.00008728346,0.00003248264,0.001815436,0.00001257843,0.0009528502,0.0009793284,0.00005745006,0.00001757943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002775179,"about_ca_system_score_gemma":0.000197208,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002952733,"about_ca_topic_score_gemma":0.000235791,"domain_scores_codex":[0.9985036,0.00007662835,0.0003225855,0.0006524502,0.0002298071,0.0002149778],"domain_scores_gemma":[0.998081,0.0001313869,0.00004071254,0.001535465,0.0001179904,0.00009346615],"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":[0.00001297726,0.0008525687,0.005066239,0.0001047475,0.000500624,0.0001971079,0.0005738265,0.1109224,0.0001755671,0.8259358,0.03385536,0.0218028],"study_design_scores_gemma":[0.0002318072,0.000005489509,0.00004372118,0.000004122035,0.00006153609,0.000001050603,0.0001286735,0.9946547,0.00005196104,0.001065158,0.003634786,0.0001169563],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000192776,0.00007584539,0.9986352,0.0002266982,0.00007541838,0.00005986771,0.0004576077,0.00006595114,0.0002106157],"genre_scores_gemma":[0.3945287,0.0001488844,0.5925078,0.001379281,0.00006572354,0.00001221048,0.01083656,0.00001717664,0.0005037399],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8837324,"threshold_uncertainty_score":0.3559316,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1746381258153367,"score_gpt":0.3712001494054153,"score_spread":0.1965620235900786,"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."}}