A data scientist needs to load a Python-trained scikit-learn model into SAS Model Manager for deployment alongside SAS models. Which SAS capability enables this?
Select an answer to reveal the explanation.
Short Explanation
Here's the deal — you need SAS Model Manager's open-source model import capability. It lets you package a scikit-learn model as a pickle file with a score.py wrapper, then deploy it alongside SAS models.
Full Explanation
The correct capability is SAS Model Manager's open-source model import capability, which supports Python pickle files with a score.py wrapper. SAS Model Manager supports registering open-source models, including Python scikit-learn models, by packaging the model as a pickle (.pkl) file along with a score.py Python scoring script and a requirements.txt file. Model Manager's Python publishing destination executes the score.py to generate predictions. The PROC IMPORT with DBMS=PYTHON option is wrong because PROC IMPORT is for data import, not model import. The PROC HPNEURAL with IMPORT= option for Python model objects is wrong because PROC HPNEURAL has no IMPORT= option for external models. The SAS DLPy with convert_model() function to translate sklearn to SAS format is wrong because DLPy's convert_model() is for deep learning architecture conversion, not scikit-learn models.