Classification modeling
This tool allows you to create classification models using the Spotfire Enterprise Runtime for R engine, without the need of writing any scripts yourself.
Note: Classification modeling must be authored in the installed client.
On the menu bar, select to use the tool.
See the various sections for more details.
- Creating a classification model
Use the Classification modeling tool to create classification models using the Spotfire Enterprise Runtime for R engine, without the need of writing any scripts yourself. - Logistic regression method
Logistic regression is a classification method used when the Response column is categorical with only two possible values. The probability of the possible outcomes is modeled with a logistic transformation as a weighted sum of the Predictor columns. The weights or regression coefficients are selected to maximize the likelihood of the observed data. - Classification tree method
Classification tree is a nonparametric classification method that creates a binary tree by recursively splitting the data on the predictor values. The splits are selected so that the two child nodes are purer in terms of the levels of the Response column than the parent node. Various options are used to control how deep the tree is grown. Class predictions for an observation are based on the majority class in the terminal node for the observation.
- Creating a classification model
Use the Classification modeling tool to create classification models using the Spotfire Enterprise Runtime for R engine, without the need of writing any scripts yourself. - Logistic regression method
Logistic regression is a classification method used when the Response column is categorical with only two possible values. The probability of the possible outcomes is modeled with a logistic transformation as a weighted sum of the Predictor columns. The weights or regression coefficients are selected to maximize the likelihood of the observed data. - Classification tree method
Classification tree is a nonparametric classification method that creates a binary tree by recursively splitting the data on the predictor values. The splits are selected so that the two child nodes are purer in terms of the levels of the Response column than the parent node. Various options are used to control how deep the tree is grown. Class predictions for an observation are based on the majority class in the terminal node for the observation.
Parent topic: Predictive modeling