{"id":"W2782764707","doi":"10.1109/bigdata.2017.8258254","title":"Efficient incremental data analytics with apache spark","year":2017,"lang":"en","type":"article","venue":"","topic":"Smart Grid Energy Management","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"SPARK (programming language); Computer science; Speedup; Scalability; Smart meter; Analytics; Big data; Data analysis; Context (archaeology); Computation; Field (mathematics); Efficient energy use; Electricity; Real-time computing; Data science; Data mining; Database; Parallel computing; Algorithm; Engineering","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":[0.001600714,0.002016337,0.001232754,0.001338278,0.0008755733,0.002349511,0.004192934,0.000510059,0.003469083],"category_scores_gemma":[0.007295415,0.0008276394,0.001194068,0.002602105,0.0007403564,0.003536834,0.003735427,0.001990522,0.002769971],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006587906,"about_ca_system_score_gemma":0.003322958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007678858,"about_ca_topic_score_gemma":0.007804334,"domain_scores_codex":[0.9972814,0.0003043612,0.0002160779,0.0006411202,0.001241144,0.0003157147],"domain_scores_gemma":[0.9970645,0.000718292,0.0001383633,0.00113056,0.0006677036,0.0002804901],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002306892,0.0009105508,0.01162242,0.001145097,0.0005741201,0.001056225,0.001140644,0.1171505,0.03488178,0.02830027,0.2680713,0.5328403],"study_design_scores_gemma":[0.0003619388,0.0001426705,0.001942289,0.00003186379,0.00006438443,0.0003123418,0.0002788138,0.9070098,0.019358,0.0348583,0.03555225,0.00008739562],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.05106537,0.0009849932,0.7367884,0.001282918,0.0007270366,0.0007229376,0.007339407,0.1896576,0.01143134],"genre_scores_gemma":[0.4329529,0.0005317595,0.5313808,0.0005075258,0.0002662672,0.0006635975,0.02481968,0.004660884,0.004216532],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007678858,"threshold_uncertainty_score":0.01526833,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04724063593868591,"score_gpt":0.2396669557520377,"score_spread":0.1924263198133518,"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."}}