{"api_version":2,"name":"piflow_random_forest_training","version":"1.0","role":"transform","type":"sdk","description":"Train a Spark random forest model on Arrow records and emit the trained model as a ZIP byte stream.","icon":{"path":"M3 18h18M5 15l5-6 4 3 5-7"},"inputs":{"source":{"representations":["records"],"formats":[]}},"outputs":{"result":{"view":"bytes"}},"parameters":{"type":"object","properties":{"numTrees":{"type":"integer","description":"Number of decision trees from 1 to 100.","minimum":1,"maximum":100},"maxDepth":{"type":"integer","description":"Maximum tree depth from 1 to 15.","minimum":1,"maximum":15}},"required":["numTrees","maxDepth"],"additionalProperties":false},"documentation":{"inputs":{"source":"Arrow records with equally sized numeric lists in features. Training also requires numeric class labels in label."},"outputs":{"result":"Native Spark ML model packaged as ZIP bytes. Connect to the matching prediction operator."},"parameters":{"numTrees":{"description":"Number of decision trees from 1 to 100.","help":"Number of decision trees from 1 to 100.","example":8},"maxDepth":{"description":"Maximum tree depth from 1 to 15.","help":"Maximum tree depth from 1 to 15.","example":3}},"example_job":"name: PiFlow random forest training\nsteps:\n- id: read\n  operator: item_source@1.0\n  inputs: {}\n  params:\n    uri: context:/piflow/example.jsonl\n    view: records\n- id: process\n  operator: piflow_random_forest_training@1.0\n  inputs:\n    source: read\n  params:\n    numTrees: 8\n    maxDepth: 3\n- id: receive\n  operator: client_sink@1.0\n  inputs:\n    result: process\n"},"runtime":{"image":"sha256:edd926f5a144036f8fbfd7db6771067b44ef00023872fe68552d3419ab549e90","archive":{"sha256":"5b4a94b1342e29dcbdc310b0efa54739b4e221d84005420e9d54e305fdbd4546","size":425330122,"filename":"piflow-ecoflow-spark-runtime.tar.gz"}},"execution":{"executor":"jvm","entrypoint":"org.apache.spark.sql.piflow.RandomForestTraining","config":{}},"source_public":true,"provenance":{"license":"Apache-2.0","source_repository":"https://github.com/cas-bigdatalab/piflow","source_revision":"777361c4e72b2c5457479683916b7c8e635289ff","build_instructions":"Compile src/ using piflow-ecoflow-spark@1.0. See job.yaml for a workflow and fixtures/example.jsonl for example records.","source_archive":{"sha256":"8f0c693530a0b6dc08235350aef07c43146be42a25576b1f635595a85bdde884","size":11736,"filename":"piflow_random_forest_training-sources.zip"},"license_file":{"sha256":"c71d239df91726fc519c6eb72d318ec65820627232b2f796219e87dcf35d0ab4","size":11357,"filename":"LICENSE.txt"}},"artifact":{"sha256":"356160fc58f634dfc67d16e0960feb05378b4f146e6ab11a9dcb0b6cc782dbec","size":21723,"filename":"operator.jar"},"categories":["PiFlow","Machine learning"],"trust":{"score":4,"assessed_by":"administrator","reviewed_at_ms":1795079981340},"publication":{"author":"dacp-examples","submitted_at_ms":1795079921474,"approved_at_ms":1795079981340,"last_submitted_at_ms":1795079921474,"last_approved_at_ms":1795079981340},"download_count":4}