Predictor (DB)

Applies an input regression, classification, or clustering model to an input data set in order to predict a value (or the highest probability value)

Information at a Glance

Category Predict
Data source type DB
Sends output to other operators Yes
Data processing tool MapReduce

The input column names must match the column names in the data set selected for model training, except for the dependent columns.

The prediction operation outputs its prediction columns with the columns of the input data set into a user-specified prediction table.

The operator includes the following prediction columns in the user-specified output table.

  • PRED_<model_abbreviation> - the predicted value or value with highest probability
  • CONF_<model_abbreviation> - the confidence in the predicted value
  • INFO_<model_abbreviation> - a dictionary of information about the results
Model Type Model Column Abbreviation
Classification
  • Naive Bayes
  • Logistic Regression
  • SVM
  • Alpine Forest Classification
  • Decision Tree
  • NB
  • LOR
  • SVM
  • AFC
  • DT
Regression
  • Linear Regression
  • Alpine Forest Regression
  • LIR
  • AFR
Clustering K-Means KM

K-means output columns look a bit different.

The columns are:
  • PRED_KM - predicted cluster
  • DIST_KM - distance to the center of the cluster
  • INFO_KM - a dictionary of information about the results

Algorithm

The Predictor operator is used to predict the value of the dependent variable based on the model(s) generated from the input model operator(s).

Input Model What Predictor Calculates
Classification algorithms Value with the highest probability
Numeric regression algorithms Predicted value
Clustering algorithms Predicted cluster

Input

An input regression, classification, or clustering model, and an input data set against which the model is applied.

Configuration

Notes Any notes or helpful information about this operator's parameter settings. When you enter content in the Notes field, a yellow asterisk is displayed on the operator.
Output Schema The schema for the output table or view.
Output Table The table path and name where the results are output. By default, this is a unique table name based on your user ID, workflow ID, and operator.
Storage Parameters Advanced database settings for the operator output. Available only for TABLE output.

See Storage Parameters Dialog Box for more information.

Drop If Exists Specifies whether to overwrite an existing table.
  • Yes - If a table with the name exists, it is dropped before storing the results.
  • No - If a table with the name exists, the results window shows an error message.

Output

Visual Output
The data rows of the output table/view displayed (up to 2000 rows of the data).