Existing Model Utilization

This function treats or transforms the input data according to the parameters of an existing model (typically a normalization, a regression, a classification, a clustering model or an applicability domain model). The applied mathematical transformation is applied to all columns in the input data that are contained in the existing model. This model is either generated within the project or imported from the user’s Isalos models library.

Table of contents

  1. Tips
  2. See also
  3. Version History

Use the Existing Model Utilization function by browsing in the top ribbon:

Analytics \(\rightarrow\) Existing Model Utilization

Input

Data matrix with arbitrary data.

Configuration

Model Select the model to be applied to the input data from the dropdown list. If the model is developed within the same project, the name of the corresponding tab will be displayed as: (from Tab:) Name of the tab.
Type (Automatically detected) The type of model.
Description (Automatically detected) The model description provided by the user when saving a model using the Import Model from function.
Model Input (Automatically detected) The list of columns to which the model will be applied.

Output

Data matrix with processed data according to the applied model parameters.

Example

Input

In the left-hand spreadsheet of the tab insert the data matrix to be transformed. In this case, the test set data is going to be normalized according to a normalization model developed under the same project.

Existing Model input
Configuration
  1. Select Analytics \(\rightarrow\) Existing Model Utilization.
  2. Select from the dropdown list [1] the Model of interest.
Existing Model configuration
  1. The model details will be presented automatically in Type [2], Description [3] and Model Input [4] fields.
  2. Click on the Execute button [5] to apply the selected model on the input data.
Existing Model configuration
Output

In the right-hand spreadsheet of the tab the output data matrix with the normalized columns is presented.

Existing Model output

Tips

The Existing Model Utilization function is useful in cases when test/external data shall be transformed the same as way as training data has been processed, or when predictions shall be generated for a dataset using an already developed machine learning model.

See also

Different types of models can be applied on data including Normalizers, Regression, Classification and Clustering models, and the applicability Domain – APD limits.

For model import from a library of existing models refer to Import Model from and Export Model from options.

Workflows

Bodyfat prediction case study

House pricing case study

Insurance charges case study

MA score case study

Salary prediction case study

Breast cancer case study

Credit card case study

Parkinson’s disease case study

Students’ performance case study

Version History

Introduced in Isalos Analytics Platform v0.1.18

Instructions last updated on May 2024