{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001036732,0.0002033393,0.0002613151,0.0001062886,0.0002982788,0.0005187726,0.002141742,0.00006780546,3.438585e-7],"category_scores_gemma":[0.0001772376,0.0002048026,0.00005127842,0.0006081271,0.00004886507,0.0004397513,0.002239486,0.0001221252,0.00000877726],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001106967,"about_ca_system_score_gemma":0.0002018745,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007003674,"about_ca_topic_score_gemma":0.000006757093,"domain_scores_codex":[0.9979699,0.00005252266,0.000448926,0.0007716049,0.0002814592,0.0004755628],"domain_scores_gemma":[0.9973832,0.0002633619,0.0002398247,0.00165059,0.0002253887,0.0002376395],"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":[0.000005244244,0.0001725707,0.0005813639,0.00004655312,0.0001142064,0.00001847718,0.001642299,0.01847068,0.00007813767,0.0006521526,0.05862522,0.9195931],"study_design_scores_gemma":[0.0005611943,0.00003569737,0.00004988499,0.00006024087,0.00002810855,0.0000443178,0.0001786821,0.9652516,0.00003403154,0.0002981326,0.03320465,0.0002534656],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002917122,0.00008794206,0.9940563,0.0006621887,0.001136005,0.0002797706,0.0006056078,0.0001900616,0.00006494976],"genre_scores_gemma":[0.02365058,0.000001233824,0.9737769,0.0003265189,0.001136952,0.000006783082,0.00104808,0.00002245437,0.00003045782],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9467809,"threshold_uncertainty_score":0.8351608,"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."}}