conf_rawlog_example_baskerville.yaml

---
database:
  name: baskerville                   # the database name
  user: !ENV ${DB_USER}
  password: !ENV '${DB_PASS}'
  type: 'postgres'
  host: !ENV ${DB_HOST}
  port: !ENV ${DB_PORT}
  maintenance:                        # Optional, for data partitioning and archiving
    partition_table: 'request_sets'   # default value
    partition_by: week                # partition by week or month, default value is week
    partition_field: created_at       # which field to use for the partitioning, this is the default value, can be omitted
    strict: False                     # if False, then for the week partition the start and end date will be changed to the start and end of the respective weeks. If true, then the dates will remain unchanged. Be careful to be consistent with this.
    data_partition:                   # Optional: Define the period to create partitions for
      since: 2020-01-01               # when to start partitioning
      until: "2020-12-31 23:59:59"    # when to stop partitioning
      index_by:                       # which fields to index in the partitions that will be created (only one index is supported currently), default value, can be omitted
        - target
        - ip

engine:
  raw_log:
    paths:                    # optional, a list of logs to parse - they will be parsed subsequently
      - !ENV '${BASKERVILLE_ROOT}/data/samples/test_data_1k.json'  # sample data to run baskerville raw log pipeline with
  cache_expire_time: 604800       # sec (604800 = 1 week)
  model_id: -1                    # optional, -1 returns the latest model in the database
  extra_features:                 # useful when we need to calculate more features than the model requests or when there is no model
      - css_to_html_ratio         # feature names have the following convention: class FeatureCssToHtmlRatio --> 'css_to_html_ratio'
      - image_to_html_ratio
      - js_to_html_ratio
      - minutes_total
      - path_depth_average
      - path_depth_variance
      - payload_size_average
  data_config:
    schema: !ENV '${BASKERVILLE_ROOT}/data/samples/sample_log_schema.json'
  logpath: !ENV '${BASKERVILLE_ROOT}/baskerville.log'
  log_level: 'ERROR'

spark:
  app_name: 'Baskerville'   # the application name - can be changed for two different runs - used by the spark UI
  master: 'local'           # the ip:port of the master node, e.g. spark://someip:7077 to submit to a cluster
  parallelism: -1           # controls the number of tasks, -1 means use all cores - used for local master
  log_level: 'INFO'         # spark logs level
  storage_level: 'OFF_HEAP' # which strategy to use for storing dfs - valid values are the ones found here: https://spark.apache.org/docs/2.4.0/api/python/_modules/pyspark/storagelevel.html default: OFF_HEAP
  jars: !ENV '${BASKERVILLE_ROOT}/data/jars/postgresql-42.2.4.jar,${BASKERVILLE_ROOT}/data/spark-iforest-2.4.0.jar' # or /path/to/jars/mysql-connector-java-8.0.11.jar
  spark_driver_memory: '6G' # depends on your dataset and the available ram you have. If running locally 6 - 8 GB should be a good choice, depending on the amount of data you need to process
  metrics_conf: !ENV '${BASKERVILLE_ROOT}/data/spark.metrics'  # Optional: required only  to export spark metrics
  jar_packages: 'com.banzaicloud:spark-metrics_2.11:2.3-2.0.4,io.prometheus:simpleclient:0.3.0,io.prometheus:simpleclient_dropwizard:0.3.0,io.prometheus:simpleclient_pushgateway:0.3.0,io.dropwizard.metrics:metrics-core:3.1.2'  # required to export spark metrics
  jar_repositories: 'https://raw.github.com/banzaicloud/spark-metrics/master/maven-repo/releases' # Optional: Required only to export spark metrics
  event_log: True
  serializer: 'org.apache.spark.serializer.KryoSerializer'