{"id":"W3210216704","doi":"10.1109/dsaa53316.2021.9564218","title":"DaskDB: Scalable Data Science with Unified Data Analytics and In Situ Query Processing","year":2021,"lang":"en","type":"article","venue":"","topic":"Advanced Database Systems and Queries","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Python (programming language); Scalability; SQL; Relational database management system; Analytics; Database; Relational database; Benchmark (surveying); Data analysis; Usability; Data mining; Programming language; Operating system","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006324183,0.002081731,0.002072268,0.002931842,0.001768136,0.00614248,0.008246605,0.001064369,0.008697551],"category_scores_gemma":[0.01385944,0.001927867,0.0023007,0.005233571,0.002296575,0.009034997,0.01280795,0.004366707,0.006476612],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002218383,"about_ca_system_score_gemma":0.00649322,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01068711,"about_ca_topic_score_gemma":0.007963886,"domain_scores_codex":[0.9912527,0.001104639,0.0008652965,0.001553585,0.004539785,0.0006839348],"domain_scores_gemma":[0.9927699,0.001336318,0.0004101728,0.003183227,0.001302509,0.0009978389],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003168918,0.001141126,0.01480867,0.002164165,0.001093097,0.0008844189,0.001315938,0.02497029,0.03590865,0.03854289,0.5444242,0.3315777],"study_design_scores_gemma":[0.002234752,0.0005220842,0.009035778,0.0002176862,0.0002465474,0.001085665,0.0006069841,0.5332979,0.07196388,0.08404848,0.2960621,0.0006780684],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"software","genre_gemma":"methods","genre_scores_codex":[0.01488236,0.0008578861,0.4327475,0.001025654,0.0004198274,0.0009097926,0.01613551,0.5241134,0.008908153],"genre_scores_gemma":[0.1924832,0.001073758,0.6643775,0.001908523,0.0002618633,0.002048194,0.09872739,0.03017838,0.008941224],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01068711,"threshold_uncertainty_score":0.03344589,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07135703472201405,"score_gpt":0.3065453377071228,"score_spread":0.2351883029851087,"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."}}