rdf-regression-example.conf

# Copyright (c) 2015, Cloudera, Inc. All Rights Reserved.
#
# Cloudera, Inc. licenses this file to you under the Apache License,
# Version 2.0 (the "License"). You may not use this file except in
# compliance with the License. You may obtain a copy of the License at
#
#     http://www.apache.org/licenses/LICENSE-2.0
#
# This software is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
# CONDITIONS OF ANY KIND, either express or implied. See the License for
# the specific language governing permissions and limitations under the
# License.

# A very basic example config file configuring only the essential elements to
# run a decision forest-based application.

# It's possible to specify reusable values:
kafka-brokers = "b03.example.com:9092,b04.example.com:9092"
zk-servers = "b01.example.com:2181,b02.example.com:2181"
hdfs-base = "hdfs:///user/example/Oryx"

oryx {
  id = "RDFRegressionExample"
  input-topic {
    broker = ${kafka-brokers}
    lock = {
      master = ${zk-servers}
    }
  }
  update-topic {
    broker = ${kafka-brokers}
    lock = {
      master = ${zk-servers}
    }
  }

  batch {
    streaming {
      generation-interval-sec = 300
      num-executors = 4
      executor-cores = 8
      executor-memory = "4g"
    }
    update-class = "com.cloudera.oryx.app.batch.mllib.rdf.RDFUpdate"
    storage {
      data-dir = ${hdfs-base}"/data/"
      model-dir = ${hdfs-base}"/model/"
    }
    ui {
      port = 4040
    }
  }
  speed {
    model-manager-class = "com.cloudera.oryx.app.speed.rdf.RDFSpeedModelManager"
    ui {
      port = 4041
    }
  }
  serving {
    model-manager-class = "com.cloudera.oryx.app.serving.rdf.model.RDFServingModelManager"
    application-resources = "com.cloudera.oryx.app.serving,com.cloudera.oryx.app.serving.classreg,com.cloudera.oryx.app.serving.rdf"
    api {
      port = 8080
    }
  }

  # This depends on the input data; example is an fictional dataset
  input-schema = {
    feature-names = ["county", "route", "start", "end", "length", "exposure", "threshold", "rate"]
    categorical-features = ["county", "route", "threshold"]
    numeric-features = ["start", "end", "length", "exposure", "rate"]
    target-feature = "rate"
    num-features = 8
  }

  # Parameters for rdf; for regression you must specify variance as the impurity measure
  rdf {
    hyperparams {
      "max-depth" = 8
      "min-node-size" = 16
      "max-split-candidates" = 100
      impurity = variance
      "min-info-gain-nats" = 0.001
    }
    "num-trees" = 20
  }

}