You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: src/sasctl/pzmm/README.md
+2-2Lines changed: 2 additions & 2 deletions
Original file line number
Diff line number
Diff line change
@@ -2,15 +2,15 @@
2
2
3
3
## Overview
4
4
5
-
The goal of the PZMM (Python Zip Model Management) module is to allow users of SAS Model Manager on SAS Viya (MM) and SAS Open Model Manager (OMM) to zip through the process of importing Python models to OMM & MM. In order to facilitate model imports, the module can allow the user to complete the following tasks:
5
+
The goal of the PZMM (Python Zip Model Management) module is to enable users of SAS Model Manager on SAS Viya and SAS Open Model Manager to zip through the process of importing Python models into the common model repository. In order to facilitate model imports, the module allows the user to complete the following tasks:
6
6
7
7
* Writes JSON files to read in the model information, which includes the following files:
8
8
*`fileMetadata.json` specifies the file roles for the names of the input and output variables files, the Python score code file, and the Python pickle file
9
9
*`ModelProperties.json` is used to set the model properties that are read during the import process
10
10
*`inputVar.json` and `outputVar.json` are used to set the input and output variables of the model
11
11
*`dmcas_fitstat.json` is an optional file that provides the fit statistics that are associated with the imported model, which are either user-generated or data-generated
12
12
*`dmcas_lift.json` and `dmcas_roc.json` are optional files that provide the Lift and ROC plots that are associated with the imported model, which are data-generated
13
-
* Writes the `*score.py` file that is used for model scoring in MM & OMM
13
+
* Writes the `*score.py`model file that is used for model scoring
14
14
* Serializes a trained model into a binary pickle file
15
15
* Archives all relevant model files into a ZIP file and imports the model using REST API calls
0 commit comments