|
countField
Event Count Field Name
required
|
Field containing the number of times an event (e.g. click) occurs for a particular query; count_i in the raw signal collection or aggr_count_i in the aggregated signal collection.
type: string
default value: 'count_i'
minLength: 1
|
|
dataFormat
Data format
required
|
Spark-compatible format that contains training data (like 'solr', 'parquet', 'orc' etc)
type: string
default value: 'solr'
minLength: 1
|
|
dataOutputFormat
Data output format
|
Spark-compatible output format (like 'solr', 'parquet', etc)
type: string
default value: 'solr'
minLength: 1
|
|
docIdField
Document ID field
required
|
Enter document id field (default is doc_id)
type: string
default value: 'doc_id'
|
|
fieldToVectorize
Solr Fields to Read
|
Fields to extract from Solr (not used for other formats)
type: string
minLength: 1
|
|
id
Spark Job ID
required
|
The ID for this Spark job. Used in the API to reference this job. Allowed characters: a-z, A-Z, dash (-) and underscore (_). Maximum length: 63 characters.
type: string
maxLength: 63
pattern: [a-zA-Z][_\-a-zA-Z0-9]*[a-zA-Z0-9]?
|
|
numWeeksRef
Num Weeks Reference
|
If using filter queries for reference and target time ranges, enter the value of (reference days / target days) here (if not using filter queries, this will be calculated automatically)
type: number
|
|
outputCollection
Output Collection
|
Solr Collection to store model-labeled data to
type: string
|
|
overwriteOutput
Overwrite Output
|
Overwrite output collection
type: boolean
default value: 'true'
|
|
partitionCols
Partition fields
|
If writing to non-Solr sources, this field will accept a comma-delimited list of column names for partitioning the dataframe before writing to the external output
type: string
|
|
randomSeed
Random seed
|
For any deterministic pseudorandom number generation
type: integer
default value: '1234'
|
|
readOptions
Read Options
|
Options used when reading input from Solr or other sources.
type: array of object
object attributes: {
key
(required)
: {
display name: Parameter Name
type: string
}
value
: {
display name: Parameter Value
type: string
}
}
|
|
recsCount
Recommendation Count
required
|
Maximum number of recs to generate (or -1 for no limit)
type: integer
default value: '500'
|
|
refTimeRange
Reference Time Days
required
|
Number of reference days: number of days to use as baseline to find trends (calculated from today)
type: integer
|
|
referenceTimeFilterQuery
Reference Filter Time Query
|
Add a Spark SQL filter query here for greater control of time filtering
type: string
|
|
sourceFields
Fields to Load
|
Solr fields to load (comma-delimited). Leave empty to allow the job to select the required fields to load at runtime.
type: string
|
|
sparkConfig
Spark Settings
|
Spark configuration settings.
type: array of object
object attributes: {
key
(required)
: {
display name: Parameter Name
type: string
}
value
: {
display name: Parameter Value
type: string
}
}
|
|
sparkPartitions
Set minimum Spark partitions for input
|
Spark will re-partition the input to have this number of partitions. Increase for greater parallelism
type: integer
default value: '200'
|
|
sparkSQL
Spark SQL filter query
|
Use this field to create a Spark SQL query for filtering your input data. The input data will be registered as spark_input
type: string
default value: 'SELECT * from spark_input'
|
|
targetFilterTimeQuery
Target Filter Time Query
|
Add a Spark SQL filter query here for greater control of time filtering
type: string
|
|
targetTimeRange
Target Time Days
required
|
Number of target days: number of days to use as target to find trends (calculated from today)
type: integer
|
|
timeField
Time field
required
|
Enter time field (default is timestamp_tdt)
type: string
default value: 'timestamp_tdt'
|
|
trainingCollection
Training Collection
required
|
Solr Collection containing labeled training data
type: string
minLength: 1
|
|
trainingDataFilterQuery
Training data filter query
|
Solr query to use when loading training data if using Solr
type: string
default value: '*:*'
|
|
trainingDataFrameConfigOptions
Dataframe Config Options
|
Additional spark dataframe loading configuration options
type: object
object attributes: {
}
object attributes: {
}
|
|
trainingDataSamplingFraction
Training data sampling fraction
|
Fraction of the training data to use
type: number
default value: '1.0'
exclusiveMaximum: false
maximum: 1.0
|
|
type
Spark Job Type
required
|
type: string
default value: 'trending-recommender'
enum: {
trending-recommender
}
|
|
typeField
Type field
required
|
Enter type field (default is type)
type: string
default value: 'type'
|
|
types
Event types
required
|
Enter a comma-separated list of event types to filter on
type: string
default value: 'click,add'
|
|
writeOptions
Write Options
|
Options used when writing output to Solr or other sources
type: array of object
object attributes: {
key
(required)
: {
display name: Parameter Name
type: string
}
value
: {
display name: Parameter Value
type: string
}
}
|