{"id":"W2180880586","doi":"10.1007/s10586-015-0477-1","title":"A distributed frequent itemset mining algorithm using Spark for Big Data analytics","year":2015,"lang":"en","type":"article","venue":"Cluster Computing","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":85,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"National Natural Science Foundation of China","keywords":"Computer science; SPARK (programming language); Pruning; Scalability; Data mining; Association rule learning; Big data; Benchmark (surveying); GSP Algorithm; Computation; Process (computing); Algorithm; Apriori algorithm; Database","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":[0.001791132,0.001050588,0.002400257,0.002030664,0.001676835,0.001626177,0.003363443,0.0008207568,0.003159557],"category_scores_gemma":[0.00451164,0.0007699398,0.001396952,0.003858164,0.0004204265,0.001995557,0.001753311,0.001209564,0.001940976],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00052421,"about_ca_system_score_gemma":0.002159019,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002910501,"about_ca_topic_score_gemma":0.004830347,"domain_scores_codex":[0.9985098,0.0001873402,0.0001708549,0.0004260218,0.0005816038,0.0001243541],"domain_scores_gemma":[0.9976533,0.0006126609,0.0001019184,0.0006034978,0.0007906689,0.0002379656],"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":[0.002269084,0.001230543,0.006523581,0.0005221679,0.000670569,0.0007784688,0.000312561,0.07169991,0.02512808,0.008766173,0.04796354,0.8341354],"study_design_scores_gemma":[0.0004897538,0.0003033849,0.001541867,0.00001662605,0.0001389484,0.0007148299,0.0001542851,0.9588093,0.008574192,0.0179785,0.01121968,0.00005872591],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02572364,0.0003693204,0.9593866,0.0003388284,0.0002799283,0.000302282,0.0009036519,0.0114128,0.001282961],"genre_scores_gemma":[0.09833704,0.0001578708,0.8960226,0.0001227671,0.0001221025,0.0002758086,0.002561637,0.0004264781,0.001973806],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003363443,"threshold_uncertainty_score":0.01056975,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.256721916407233,"score_gpt":0.3448207135320219,"score_spread":0.08809879712478885,"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."}}