Sklearn NMFInstall

Summary

Transform NMF model using fitted parameters

Inputs

• nmfData (required) — JSON string containing the fitted NMF
• transformFeatureColumns (required) — Comma-separated list of feature column names
• pythonPath — Path to Python executable with scikit-learn installed

Output shape

a list of items, each extending the input record with NMF component columns

Only the first returned item includes additional metadata such as reconstruction error; overall shape is a list of transformed records.

Examples

Example 1: Apply a previously fitted NMF model to transform new data

nmfData: '{"n_components":2,"components":[[...]],"reconstruction_err_":0.01}', transformFeatureColumns: 'feature1,feature2', pythonPath: 'python3'

Example 2: Transform existing workflow items using a stored NMF model

nmfData: '', transformFeatureColumns: 'colA,colB,colC', pythonPath: '/usr/bin/python3'